Add GL_EXT_shader_subgroup_extended_types support

SPIRV/GlslangToSpv.cpp

@@ -6837,8 +6837,9 @@ spv::Id TGlslangToSpvTraverser::createSubgroupOperation(glslang::TOperator op, s
     default: assert(0 && "Unhandled subgroup operation!");
     }
 
-    const bool isUnsigned = typeProxy == glslang::EbtUint || typeProxy == glslang::EbtUint64;
+
-    const bool isFloat = typeProxy == glslang::EbtFloat || typeProxy == glslang::EbtDouble;
+    const bool isUnsigned = isTypeUnsignedInt(typeProxy);
+    const bool isFloat = isTypeFloat(typeProxy);
     const bool isBool = typeProxy == glslang::EbtBool;
 
     spv::Op opCode = spv::OpNop;

Test/baseResults/spv.specConstant.vert.out

@@ -11,7 +11,7 @@ spv.specConstant.vert
                               Source GLSL 400
                               Name 4  "main"
                               Name 9  "arraySize"
-                              Name 14  "foo(vf4[s2769];"
+                              Name 14  "foo(vf4[s4393];"
                               Name 13  "p"
                               Name 17  "builtin_spec_constant("
                               Name 20  "color"
@@ -102,10 +102,10 @@ spv.specConstant.vert
                               Store 20(color) 46
               48:          10 Load 22(ucol)
                               Store 47(param) 48
-              49:           2 FunctionCall 14(foo(vf4[s2769];) 47(param)
+              49:           2 FunctionCall 14(foo(vf4[s4393];) 47(param)
                               Return
                               FunctionEnd
-14(foo(vf4[s2769];):           2 Function None 12
+14(foo(vf4[s4393];):           2 Function None 12
            13(p):     11(ptr) FunctionParameter
               15:             Label
               54:     24(ptr) AccessChain 53(dupUcol) 23

Test/baseResults/spv.subgroupExtendedTypesArithmeticNeg.comp.out

@@ -0,0 +1,557 @@
+spv.subgroupExtendedTypesArithmeticNeg.comp
+ERROR: 0:26: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:27: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:28: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:29: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:31: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:33: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:34: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:36: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:38: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:39: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:41: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:42: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:43: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:44: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:46: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:47: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:48: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:49: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:51: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:52: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:53: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:54: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:56: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:57: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:58: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:59: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:61: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:62: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:63: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:64: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:66: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:67: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:68: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:69: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:71: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:72: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:73: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:74: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:76: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:77: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:78: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:79: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:81: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:82: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:83: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:84: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:86: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:87: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:88: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:89: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:91: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:92: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:93: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:94: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:96: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:97: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:98: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:99: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:101: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:102: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:103: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:104: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:106: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:107: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:108: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:109: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:111: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:112: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:113: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:114: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:116: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:117: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:118: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:119: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:121: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:122: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:123: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:124: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:126: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:127: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:128: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:129: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:131: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:132: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:133: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:134: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:136: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:137: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:138: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:139: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:141: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:142: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:143: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:144: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:146: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:147: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:148: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:149: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:151: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:152: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:153: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:154: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:156: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:157: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:158: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:159: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:161: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:162: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:163: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:164: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:166: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:167: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:168: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:169: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:171: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:172: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:173: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:174: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:176: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:177: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:178: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:179: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:181: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:182: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:183: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:184: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:186: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:187: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:188: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:189: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:191: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:192: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:193: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:194: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:196: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:197: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:198: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:199: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:201: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:202: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:203: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:204: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:206: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:207: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:208: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:209: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:211: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:212: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:213: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:214: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:216: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:217: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:218: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:219: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:221: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:222: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:223: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:224: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:226: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:227: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:228: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:229: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:231: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:232: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:233: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:234: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:236: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:237: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:238: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:239: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:241: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:242: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:243: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:244: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:246: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:247: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:248: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:249: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:251: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:252: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:253: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:254: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:256: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:257: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:258: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:259: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:261: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:262: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:263: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:264: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:266: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:267: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:268: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:269: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:271: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:272: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:273: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:274: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:276: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:277: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:278: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:279: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:281: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:282: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:283: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:284: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:286: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:287: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:288: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:289: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:291: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:292: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:293: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:294: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:296: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:297: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:298: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:299: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:301: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:302: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:303: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:304: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:306: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:307: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:308: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:309: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:311: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:312: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:313: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:314: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:316: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:317: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:318: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:319: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:321: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:322: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:323: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:324: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:326: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:327: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:328: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:329: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:331: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:332: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:333: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:334: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:336: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:337: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:338: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:339: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:341: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:342: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:343: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:344: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:346: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:347: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:348: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:349: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:351: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:352: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:353: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:354: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:356: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:357: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:358: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:359: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:361: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:362: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:363: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:364: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:366: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:367: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:368: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:369: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:371: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:372: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:373: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:374: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:376: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:377: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:378: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:379: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:381: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:382: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:383: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:384: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:386: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:387: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:388: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:389: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:391: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:392: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:393: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:394: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:396: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:397: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:398: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:399: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:401: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:402: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:403: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:404: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:406: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:407: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:408: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:409: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:411: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:412: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:413: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:414: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:416: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:417: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:418: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:419: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:421: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:422: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:423: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:424: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:426: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:427: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:428: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:429: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:431: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:432: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:433: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:434: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:436: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:437: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:438: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:439: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:441: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:442: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:443: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:444: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:446: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:447: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:448: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:449: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:451: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:452: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:453: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:454: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:456: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:457: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:458: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:459: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:461: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:462: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:463: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:464: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:466: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:467: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:468: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:469: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:471: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:472: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:473: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:474: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:476: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:477: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:478: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:479: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:481: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:482: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:483: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:484: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:486: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:487: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:488: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:489: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:491: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:492: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:493: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:494: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:496: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:497: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:498: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:499: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:501: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:502: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:503: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:504: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:506: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:507: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:508: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:509: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:511: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:512: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:513: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:514: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:516: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:517: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:518: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:519: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:521: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:522: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:523: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:524: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:526: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:527: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:528: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:529: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:531: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:532: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:533: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:534: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:536: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:537: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:538: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:539: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:541: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:542: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:543: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:544: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:546: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:547: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:548: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:549: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:551: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:552: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:553: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:554: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:556: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:557: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:558: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:559: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:561: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:562: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:563: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:564: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:566: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:567: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:568: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:569: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:571: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:572: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:573: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:574: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:576: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:577: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:578: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:579: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:581: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:582: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:583: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:584: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:586: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:587: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:588: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:589: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:591: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:592: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:593: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:594: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:596: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:597: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:598: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:599: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:601: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:602: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:603: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:604: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:606: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:607: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:608: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:609: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:611: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:612: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:613: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:614: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:616: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:617: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:618: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:619: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:621: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:622: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:623: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:624: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:626: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:627: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:628: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:629: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:631: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:632: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:633: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:634: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:636: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:637: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:638: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:639: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:641: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:642: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:643: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:644: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:646: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:647: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:648: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:649: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:651: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:652: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:653: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:654: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:656: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:657: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:658: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:659: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:661: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:662: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:663: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:664: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:666: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:667: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:668: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:669: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:671: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:672: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:673: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:674: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:676: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:677: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:678: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:679: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:681: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:682: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:683: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:684: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:686: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:687: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:688: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:689: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:691: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:692: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:693: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:694: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:696: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:697: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:698: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:699: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:701: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:702: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:703: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:704: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:706: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:707: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:708: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:709: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:711: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:712: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:713: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:714: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 552 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesBallot.comp.out

@@ -0,0 +1,560 @@
+spv.subgroupExtendedTypesBallot.comp
+// Module Version 10300
+// Generated by (magic number): 80007
+// Id's are bound by 441
+
+                              Capability Shader
+                              Capability Float16
+                              Capability Int64
+                              Capability Int16
+                              Capability Int8
+                              Capability GroupNonUniform
+                              Capability GroupNonUniformBallot
+                              Capability StorageUniformBufferBlock16
+                              Capability StorageBuffer8BitAccess
+                              Extension  "SPV_KHR_8bit_storage"
+               1:             ExtInstImport  "GLSL.std.450"
+                              MemoryModel Logical GLSL450
+                              EntryPoint GLCompute 4  "main" 10 12
+                              ExecutionMode 4 LocalSize 8 1 1
+                              Source GLSL 450
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_float16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int64"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int8"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_float16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int64"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int8"
+                              SourceExtension  "GL_KHR_shader_subgroup_ballot"
+                              SourceExtension  "GL_KHR_shader_subgroup_basic"
+                              Name 4  "main"
+                              Name 8  "invocation"
+                              Name 10  "gl_SubgroupInvocationID"
+                              Name 12  "gl_SubgroupSize"
+                              Name 31  "Buffers"
+                              MemberName 31(Buffers) 0  "i8"
+                              MemberName 31(Buffers) 1  "u8"
+                              MemberName 31(Buffers) 2  "i16"
+                              MemberName 31(Buffers) 3  "u16"
+                              MemberName 31(Buffers) 4  "i64"
+                              MemberName 31(Buffers) 5  "u64"
+                              MemberName 31(Buffers) 6  "f16"
+                              Name 34  "data"
+                              Decorate 10(gl_SubgroupInvocationID) RelaxedPrecision
+                              Decorate 10(gl_SubgroupInvocationID) BuiltIn SubgroupLocalInvocationId
+                              Decorate 11 RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) BuiltIn SubgroupSize
+                              Decorate 13 RelaxedPrecision
+                              Decorate 14 RelaxedPrecision
+                              Decorate 16 RelaxedPrecision
+                              MemberDecorate 31(Buffers) 0 Offset 0
+                              MemberDecorate 31(Buffers) 1 Offset 4
+                              MemberDecorate 31(Buffers) 2 Offset 8
+                              MemberDecorate 31(Buffers) 3 Offset 16
+                              MemberDecorate 31(Buffers) 4 Offset 32
+                              MemberDecorate 31(Buffers) 5 Offset 64
+                              MemberDecorate 31(Buffers) 6 Offset 96
+                              Decorate 31(Buffers) Block
+                              Decorate 34(data) DescriptorSet 0
+                              Decorate 34(data) Binding 0
+                              Decorate 440 BuiltIn WorkgroupSize
+               2:             TypeVoid
+               3:             TypeFunction 2
+               6:             TypeInt 32 0
+               7:             TypePointer Function 6(int)
+               9:             TypePointer Input 6(int)
+10(gl_SubgroupInvocationID):      9(ptr) Variable Input
+12(gl_SubgroupSize):      9(ptr) Variable Input
+              15:      6(int) Constant 4
+              17:             TypeInt 8 1
+              18:             TypeVector 17(int8_t) 4
+              19:             TypeInt 8 0
+              20:             TypeVector 19(int8_t) 4
+              21:             TypeInt 16 1
+              22:             TypeVector 21(int16_t) 4
+              23:             TypeInt 16 0
+              24:             TypeVector 23(int16_t) 4
+              25:             TypeInt 64 1
+              26:             TypeVector 25(int64_t) 4
+              27:             TypeInt 64 0
+              28:             TypeVector 27(int64_t) 4
+              29:             TypeFloat 16
+              30:             TypeVector 29(float16_t) 4
+     31(Buffers):             TypeStruct 18(i8vec4) 20(i8vec4) 22(i16vec4) 24(i16vec4) 26(i64vec4) 28(i64vec4) 30(f16vec4)
+              32:             TypeArray 31(Buffers) 15
+              33:             TypePointer StorageBuffer 32
+        34(data):     33(ptr) Variable StorageBuffer
+              36:             TypeInt 32 1
+              37:     36(int) Constant 0
+              38:      6(int) Constant 0
+              39:             TypePointer StorageBuffer 17(int8_t)
+              42:      6(int) Constant 3
+              46:     36(int) Constant 1
+              47:             TypeVector 17(int8_t) 2
+              48:             TypePointer StorageBuffer 18(i8vec4)
+              57:     36(int) Constant 2
+              58:             TypeVector 17(int8_t) 3
+              67:     36(int) Constant 3
+              99:             TypePointer StorageBuffer 19(int8_t)
+             105:             TypeVector 19(int8_t) 2
+             106:             TypePointer StorageBuffer 20(i8vec4)
+             115:             TypeVector 19(int8_t) 3
+             155:             TypePointer StorageBuffer 21(int16_t)
+             161:             TypeVector 21(int16_t) 2
+             162:             TypePointer StorageBuffer 22(i16vec4)
+             171:             TypeVector 21(int16_t) 3
+             211:             TypePointer StorageBuffer 23(int16_t)
+             217:             TypeVector 23(int16_t) 2
+             218:             TypePointer StorageBuffer 24(i16vec4)
+             227:             TypeVector 23(int16_t) 3
+             267:     36(int) Constant 4
+             268:             TypePointer StorageBuffer 25(int64_t)
+             274:             TypeVector 25(int64_t) 2
+             275:             TypePointer StorageBuffer 26(i64vec4)
+             284:             TypeVector 25(int64_t) 3
+             324:     36(int) Constant 5
+             325:             TypePointer StorageBuffer 27(int64_t)
+             331:             TypeVector 27(int64_t) 2
+             332:             TypePointer StorageBuffer 28(i64vec4)
+             341:             TypeVector 27(int64_t) 3
+             381:     36(int) Constant 6
+             382:             TypePointer StorageBuffer 29(float16_t)
+             388:             TypeVector 29(float16_t) 2
+             389:             TypePointer StorageBuffer 30(f16vec4)
+             398:             TypeVector 29(float16_t) 3
+             437:             TypeVector 6(int) 3
+             438:      6(int) Constant 8
+             439:      6(int) Constant 1
+             440:  437(ivec3) ConstantComposite 438 439 439
+         4(main):           2 Function None 3
+               5:             Label
+   8(invocation):      7(ptr) Variable Function
+              11:      6(int) Load 10(gl_SubgroupInvocationID)
+              13:      6(int) Load 12(gl_SubgroupSize)
+              14:      6(int) IAdd 11 13
+              16:      6(int) UMod 14 15
+                              Store 8(invocation) 16
+              35:      6(int) Load 8(invocation)
+              40:     39(ptr) AccessChain 34(data) 37 37 38
+              41:  17(int8_t) Load 40
+              43:  17(int8_t) GroupNonUniformBroadcast 42 41 42
+              44:     39(ptr) AccessChain 34(data) 35 37 38
+                              Store 44 43
+              45:      6(int) Load 8(invocation)
+              49:     48(ptr) AccessChain 34(data) 46 37
+              50:  18(i8vec4) Load 49
+              51:  47(i8vec2) VectorShuffle 50 50 0 1
+              52:  47(i8vec2) GroupNonUniformBroadcast 42 51 42
+              53:     48(ptr) AccessChain 34(data) 45 37
+              54:  18(i8vec4) Load 53
+              55:  18(i8vec4) VectorShuffle 54 52 4 5 2 3
+                              Store 53 55
+              56:      6(int) Load 8(invocation)
+              59:     48(ptr) AccessChain 34(data) 57 37
+              60:  18(i8vec4) Load 59
+              61:  58(i8vec3) VectorShuffle 60 60 0 1 2
+              62:  58(i8vec3) GroupNonUniformBroadcast 42 61 42
+              63:     48(ptr) AccessChain 34(data) 56 37
+              64:  18(i8vec4) Load 63
+              65:  18(i8vec4) VectorShuffle 64 62 4 5 6 3
+                              Store 63 65
+              66:      6(int) Load 8(invocation)
+              68:     48(ptr) AccessChain 34(data) 67 37
+              69:  18(i8vec4) Load 68
+              70:  18(i8vec4) GroupNonUniformBroadcast 42 69 42
+              71:     48(ptr) AccessChain 34(data) 66 37
+                              Store 71 70
+              72:      6(int) Load 8(invocation)
+              73:     39(ptr) AccessChain 34(data) 37 37 38
+              74:  17(int8_t) Load 73
+              75:  17(int8_t) GroupNonUniformBroadcastFirst 42 74
+              76:     39(ptr) AccessChain 34(data) 72 37 38
+                              Store 76 75
+              77:      6(int) Load 8(invocation)
+              78:     48(ptr) AccessChain 34(data) 46 37
+              79:  18(i8vec4) Load 78
+              80:  47(i8vec2) VectorShuffle 79 79 0 1
+              81:  47(i8vec2) GroupNonUniformBroadcastFirst 42 80
+              82:     48(ptr) AccessChain 34(data) 77 37
+              83:  18(i8vec4) Load 82
+              84:  18(i8vec4) VectorShuffle 83 81 4 5 2 3
+                              Store 82 84
+              85:      6(int) Load 8(invocation)
+              86:     48(ptr) AccessChain 34(data) 57 37
+              87:  18(i8vec4) Load 86
+              88:  58(i8vec3) VectorShuffle 87 87 0 1 2
+              89:  58(i8vec3) GroupNonUniformBroadcastFirst 42 88
+              90:     48(ptr) AccessChain 34(data) 85 37
+              91:  18(i8vec4) Load 90
+              92:  18(i8vec4) VectorShuffle 91 89 4 5 6 3
+                              Store 90 92
+              93:      6(int) Load 8(invocation)
+              94:     48(ptr) AccessChain 34(data) 67 37
+              95:  18(i8vec4) Load 94
+              96:  18(i8vec4) GroupNonUniformBroadcastFirst 42 95
+              97:     48(ptr) AccessChain 34(data) 93 37
+                              Store 97 96
+              98:      6(int) Load 8(invocation)
+             100:     99(ptr) AccessChain 34(data) 37 46 38
+             101:  19(int8_t) Load 100
+             102:  19(int8_t) GroupNonUniformBroadcast 42 101 42
+             103:     99(ptr) AccessChain 34(data) 98 46 38
+                              Store 103 102
+             104:      6(int) Load 8(invocation)
+             107:    106(ptr) AccessChain 34(data) 46 46
+             108:  20(i8vec4) Load 107
+             109: 105(i8vec2) VectorShuffle 108 108 0 1
+             110: 105(i8vec2) GroupNonUniformBroadcast 42 109 42
+             111:    106(ptr) AccessChain 34(data) 104 46
+             112:  20(i8vec4) Load 111
+             113:  20(i8vec4) VectorShuffle 112 110 4 5 2 3
+                              Store 111 113
+             114:      6(int) Load 8(invocation)
+             116:    106(ptr) AccessChain 34(data) 57 46
+             117:  20(i8vec4) Load 116
+             118: 115(i8vec3) VectorShuffle 117 117 0 1 2
+             119: 115(i8vec3) GroupNonUniformBroadcast 42 118 42
+             120:    106(ptr) AccessChain 34(data) 114 46
+             121:  20(i8vec4) Load 120
+             122:  20(i8vec4) VectorShuffle 121 119 4 5 6 3
+                              Store 120 122
+             123:      6(int) Load 8(invocation)
+             124:    106(ptr) AccessChain 34(data) 67 46
+             125:  20(i8vec4) Load 124
+             126:  20(i8vec4) GroupNonUniformBroadcast 42 125 42
+             127:    106(ptr) AccessChain 34(data) 123 46
+                              Store 127 126
+             128:      6(int) Load 8(invocation)
+             129:     99(ptr) AccessChain 34(data) 37 46 38
+             130:  19(int8_t) Load 129
+             131:  19(int8_t) GroupNonUniformBroadcastFirst 42 130
+             132:     99(ptr) AccessChain 34(data) 128 46 38
+                              Store 132 131
+             133:      6(int) Load 8(invocation)
+             134:    106(ptr) AccessChain 34(data) 46 46
+             135:  20(i8vec4) Load 134
+             136: 105(i8vec2) VectorShuffle 135 135 0 1
+             137: 105(i8vec2) GroupNonUniformBroadcastFirst 42 136
+             138:    106(ptr) AccessChain 34(data) 133 46
+             139:  20(i8vec4) Load 138
+             140:  20(i8vec4) VectorShuffle 139 137 4 5 2 3
+                              Store 138 140
+             141:      6(int) Load 8(invocation)
+             142:    106(ptr) AccessChain 34(data) 57 46
+             143:  20(i8vec4) Load 142
+             144: 115(i8vec3) VectorShuffle 143 143 0 1 2
+             145: 115(i8vec3) GroupNonUniformBroadcastFirst 42 144
+             146:    106(ptr) AccessChain 34(data) 141 46
+             147:  20(i8vec4) Load 146
+             148:  20(i8vec4) VectorShuffle 147 145 4 5 6 3
+                              Store 146 148
+             149:      6(int) Load 8(invocation)
+             150:    106(ptr) AccessChain 34(data) 67 46
+             151:  20(i8vec4) Load 150
+             152:  20(i8vec4) GroupNonUniformBroadcastFirst 42 151
+             153:    106(ptr) AccessChain 34(data) 149 46
+                              Store 153 152
+             154:      6(int) Load 8(invocation)
+             156:    155(ptr) AccessChain 34(data) 37 57 38
+             157: 21(int16_t) Load 156
+             158: 21(int16_t) GroupNonUniformBroadcast 42 157 42
+             159:    155(ptr) AccessChain 34(data) 154 57 38
+                              Store 159 158
+             160:      6(int) Load 8(invocation)
+             163:    162(ptr) AccessChain 34(data) 46 57
+             164: 22(i16vec4) Load 163
+             165:161(i16vec2) VectorShuffle 164 164 0 1
+             166:161(i16vec2) GroupNonUniformBroadcast 42 165 42
+             167:    162(ptr) AccessChain 34(data) 160 57
+             168: 22(i16vec4) Load 167
+             169: 22(i16vec4) VectorShuffle 168 166 4 5 2 3
+                              Store 167 169
+             170:      6(int) Load 8(invocation)
+             172:    162(ptr) AccessChain 34(data) 57 57
+             173: 22(i16vec4) Load 172
+             174:171(i16vec3) VectorShuffle 173 173 0 1 2
+             175:171(i16vec3) GroupNonUniformBroadcast 42 174 42
+             176:    162(ptr) AccessChain 34(data) 170 57
+             177: 22(i16vec4) Load 176
+             178: 22(i16vec4) VectorShuffle 177 175 4 5 6 3
+                              Store 176 178
+             179:      6(int) Load 8(invocation)
+             180:    162(ptr) AccessChain 34(data) 67 57
+             181: 22(i16vec4) Load 180
+             182: 22(i16vec4) GroupNonUniformBroadcast 42 181 42
+             183:    162(ptr) AccessChain 34(data) 179 57
+                              Store 183 182
+             184:      6(int) Load 8(invocation)
+             185:    155(ptr) AccessChain 34(data) 37 57 38
+             186: 21(int16_t) Load 185
+             187: 21(int16_t) GroupNonUniformBroadcastFirst 42 186
+             188:    155(ptr) AccessChain 34(data) 184 57 38
+                              Store 188 187
+             189:      6(int) Load 8(invocation)
+             190:    162(ptr) AccessChain 34(data) 46 57
+             191: 22(i16vec4) Load 190
+             192:161(i16vec2) VectorShuffle 191 191 0 1
+             193:161(i16vec2) GroupNonUniformBroadcastFirst 42 192
+             194:    162(ptr) AccessChain 34(data) 189 57
+             195: 22(i16vec4) Load 194
+             196: 22(i16vec4) VectorShuffle 195 193 4 5 2 3
+                              Store 194 196
+             197:      6(int) Load 8(invocation)
+             198:    162(ptr) AccessChain 34(data) 57 57
+             199: 22(i16vec4) Load 198
+             200:171(i16vec3) VectorShuffle 199 199 0 1 2
+             201:171(i16vec3) GroupNonUniformBroadcastFirst 42 200
+             202:    162(ptr) AccessChain 34(data) 197 57
+             203: 22(i16vec4) Load 202
+             204: 22(i16vec4) VectorShuffle 203 201 4 5 6 3
+                              Store 202 204
+             205:      6(int) Load 8(invocation)
+             206:    162(ptr) AccessChain 34(data) 67 57
+             207: 22(i16vec4) Load 206
+             208: 22(i16vec4) GroupNonUniformBroadcastFirst 42 207
+             209:    162(ptr) AccessChain 34(data) 205 57
+                              Store 209 208
+             210:      6(int) Load 8(invocation)
+             212:    211(ptr) AccessChain 34(data) 37 67 38
+             213: 23(int16_t) Load 212
+             214: 23(int16_t) GroupNonUniformBroadcast 42 213 42
+             215:    211(ptr) AccessChain 34(data) 210 67 38
+                              Store 215 214
+             216:      6(int) Load 8(invocation)
+             219:    218(ptr) AccessChain 34(data) 46 67
+             220: 24(i16vec4) Load 219
+             221:217(i16vec2) VectorShuffle 220 220 0 1
+             222:217(i16vec2) GroupNonUniformBroadcast 42 221 42
+             223:    218(ptr) AccessChain 34(data) 216 67
+             224: 24(i16vec4) Load 223
+             225: 24(i16vec4) VectorShuffle 224 222 4 5 2 3
+                              Store 223 225
+             226:      6(int) Load 8(invocation)
+             228:    218(ptr) AccessChain 34(data) 57 67
+             229: 24(i16vec4) Load 228
+             230:227(i16vec3) VectorShuffle 229 229 0 1 2
+             231:227(i16vec3) GroupNonUniformBroadcast 42 230 42
+             232:    218(ptr) AccessChain 34(data) 226 67
+             233: 24(i16vec4) Load 232
+             234: 24(i16vec4) VectorShuffle 233 231 4 5 6 3
+                              Store 232 234
+             235:      6(int) Load 8(invocation)
+             236:    218(ptr) AccessChain 34(data) 67 67
+             237: 24(i16vec4) Load 236
+             238: 24(i16vec4) GroupNonUniformBroadcast 42 237 42
+             239:    218(ptr) AccessChain 34(data) 235 67
+                              Store 239 238
+             240:      6(int) Load 8(invocation)
+             241:    211(ptr) AccessChain 34(data) 37 67 38
+             242: 23(int16_t) Load 241
+             243: 23(int16_t) GroupNonUniformBroadcastFirst 42 242
+             244:    211(ptr) AccessChain 34(data) 240 67 38
+                              Store 244 243
+             245:      6(int) Load 8(invocation)
+             246:    218(ptr) AccessChain 34(data) 46 67
+             247: 24(i16vec4) Load 246
+             248:217(i16vec2) VectorShuffle 247 247 0 1
+             249:217(i16vec2) GroupNonUniformBroadcastFirst 42 248
+             250:    218(ptr) AccessChain 34(data) 245 67
+             251: 24(i16vec4) Load 250
+             252: 24(i16vec4) VectorShuffle 251 249 4 5 2 3
+                              Store 250 252
+             253:      6(int) Load 8(invocation)
+             254:    218(ptr) AccessChain 34(data) 57 67
+             255: 24(i16vec4) Load 254
+             256:227(i16vec3) VectorShuffle 255 255 0 1 2
+             257:227(i16vec3) GroupNonUniformBroadcastFirst 42 256
+             258:    218(ptr) AccessChain 34(data) 253 67
+             259: 24(i16vec4) Load 258
+             260: 24(i16vec4) VectorShuffle 259 257 4 5 6 3
+                              Store 258 260
+             261:      6(int) Load 8(invocation)
+             262:    218(ptr) AccessChain 34(data) 67 67
+             263: 24(i16vec4) Load 262
+             264: 24(i16vec4) GroupNonUniformBroadcastFirst 42 263
+             265:    218(ptr) AccessChain 34(data) 261 67
+                              Store 265 264
+             266:      6(int) Load 8(invocation)
+             269:    268(ptr) AccessChain 34(data) 37 267 38
+             270: 25(int64_t) Load 269
+             271: 25(int64_t) GroupNonUniformBroadcast 42 270 42
+             272:    268(ptr) AccessChain 34(data) 266 267 38
+                              Store 272 271
+             273:      6(int) Load 8(invocation)
+             276:    275(ptr) AccessChain 34(data) 46 267
+             277: 26(i64vec4) Load 276
+             278:274(i64vec2) VectorShuffle 277 277 0 1
+             279:274(i64vec2) GroupNonUniformBroadcast 42 278 42
+             280:    275(ptr) AccessChain 34(data) 273 267
+             281: 26(i64vec4) Load 280
+             282: 26(i64vec4) VectorShuffle 281 279 4 5 2 3
+                              Store 280 282
+             283:      6(int) Load 8(invocation)
+             285:    275(ptr) AccessChain 34(data) 57 267
+             286: 26(i64vec4) Load 285
+             287:284(i64vec3) VectorShuffle 286 286 0 1 2
+             288:284(i64vec3) GroupNonUniformBroadcast 42 287 42
+             289:    275(ptr) AccessChain 34(data) 283 267
+             290: 26(i64vec4) Load 289
+             291: 26(i64vec4) VectorShuffle 290 288 4 5 6 3
+                              Store 289 291
+             292:      6(int) Load 8(invocation)
+             293:    275(ptr) AccessChain 34(data) 67 267
+             294: 26(i64vec4) Load 293
+             295: 26(i64vec4) GroupNonUniformBroadcast 42 294 42
+             296:    275(ptr) AccessChain 34(data) 292 267
+                              Store 296 295
+             297:      6(int) Load 8(invocation)
+             298:    268(ptr) AccessChain 34(data) 37 267 38
+             299: 25(int64_t) Load 298
+             300: 25(int64_t) GroupNonUniformBroadcastFirst 42 299
+             301:    268(ptr) AccessChain 34(data) 297 267 38
+                              Store 301 300
+             302:      6(int) Load 8(invocation)
+             303:    275(ptr) AccessChain 34(data) 46 267
+             304: 26(i64vec4) Load 303
+             305:274(i64vec2) VectorShuffle 304 304 0 1
+             306:274(i64vec2) GroupNonUniformBroadcastFirst 42 305
+             307:    275(ptr) AccessChain 34(data) 302 267
+             308: 26(i64vec4) Load 307
+             309: 26(i64vec4) VectorShuffle 308 306 4 5 2 3
+                              Store 307 309
+             310:      6(int) Load 8(invocation)
+             311:    275(ptr) AccessChain 34(data) 57 267
+             312: 26(i64vec4) Load 311
+             313:284(i64vec3) VectorShuffle 312 312 0 1 2
+             314:284(i64vec3) GroupNonUniformBroadcastFirst 42 313
+             315:    275(ptr) AccessChain 34(data) 310 267
+             316: 26(i64vec4) Load 315
+             317: 26(i64vec4) VectorShuffle 316 314 4 5 6 3
+                              Store 315 317
+             318:      6(int) Load 8(invocation)
+             319:    275(ptr) AccessChain 34(data) 67 267
+             320: 26(i64vec4) Load 319
+             321: 26(i64vec4) GroupNonUniformBroadcastFirst 42 320
+             322:    275(ptr) AccessChain 34(data) 318 267
+                              Store 322 321
+             323:      6(int) Load 8(invocation)
+             326:    325(ptr) AccessChain 34(data) 37 324 38
+             327: 27(int64_t) Load 326
+             328: 27(int64_t) GroupNonUniformBroadcast 42 327 42
+             329:    325(ptr) AccessChain 34(data) 323 324 38
+                              Store 329 328
+             330:      6(int) Load 8(invocation)
+             333:    332(ptr) AccessChain 34(data) 46 324
+             334: 28(i64vec4) Load 333
+             335:331(i64vec2) VectorShuffle 334 334 0 1
+             336:331(i64vec2) GroupNonUniformBroadcast 42 335 42
+             337:    332(ptr) AccessChain 34(data) 330 324
+             338: 28(i64vec4) Load 337
+             339: 28(i64vec4) VectorShuffle 338 336 4 5 2 3
+                              Store 337 339
+             340:      6(int) Load 8(invocation)
+             342:    332(ptr) AccessChain 34(data) 57 324
+             343: 28(i64vec4) Load 342
+             344:341(i64vec3) VectorShuffle 343 343 0 1 2
+             345:341(i64vec3) GroupNonUniformBroadcast 42 344 42
+             346:    332(ptr) AccessChain 34(data) 340 324
+             347: 28(i64vec4) Load 346
+             348: 28(i64vec4) VectorShuffle 347 345 4 5 6 3
+                              Store 346 348
+             349:      6(int) Load 8(invocation)
+             350:    332(ptr) AccessChain 34(data) 67 324
+             351: 28(i64vec4) Load 350
+             352: 28(i64vec4) GroupNonUniformBroadcast 42 351 42
+             353:    332(ptr) AccessChain 34(data) 349 324
+                              Store 353 352
+             354:      6(int) Load 8(invocation)
+             355:    325(ptr) AccessChain 34(data) 37 324 38
+             356: 27(int64_t) Load 355
+             357: 27(int64_t) GroupNonUniformBroadcastFirst 42 356
+             358:    325(ptr) AccessChain 34(data) 354 324 38
+                              Store 358 357
+             359:      6(int) Load 8(invocation)
+             360:    332(ptr) AccessChain 34(data) 46 324
+             361: 28(i64vec4) Load 360
+             362:331(i64vec2) VectorShuffle 361 361 0 1
+             363:331(i64vec2) GroupNonUniformBroadcastFirst 42 362
+             364:    332(ptr) AccessChain 34(data) 359 324
+             365: 28(i64vec4) Load 364
+             366: 28(i64vec4) VectorShuffle 365 363 4 5 2 3
+                              Store 364 366
+             367:      6(int) Load 8(invocation)
+             368:    332(ptr) AccessChain 34(data) 57 324
+             369: 28(i64vec4) Load 368
+             370:341(i64vec3) VectorShuffle 369 369 0 1 2
+             371:341(i64vec3) GroupNonUniformBroadcastFirst 42 370
+             372:    332(ptr) AccessChain 34(data) 367 324
+             373: 28(i64vec4) Load 372
+             374: 28(i64vec4) VectorShuffle 373 371 4 5 6 3
+                              Store 372 374
+             375:      6(int) Load 8(invocation)
+             376:    332(ptr) AccessChain 34(data) 67 324
+             377: 28(i64vec4) Load 376
+             378: 28(i64vec4) GroupNonUniformBroadcastFirst 42 377
+             379:    332(ptr) AccessChain 34(data) 375 324
+                              Store 379 378
+             380:      6(int) Load 8(invocation)
+             383:    382(ptr) AccessChain 34(data) 37 381 38
+             384:29(float16_t) Load 383
+             385:29(float16_t) GroupNonUniformBroadcast 42 384 42
+             386:    382(ptr) AccessChain 34(data) 380 381 38
+                              Store 386 385
+             387:      6(int) Load 8(invocation)
+             390:    389(ptr) AccessChain 34(data) 46 381
+             391: 30(f16vec4) Load 390
+             392:388(f16vec2) VectorShuffle 391 391 0 1
+             393:388(f16vec2) GroupNonUniformBroadcast 42 392 42
+             394:    389(ptr) AccessChain 34(data) 387 381
+             395: 30(f16vec4) Load 394
+             396: 30(f16vec4) VectorShuffle 395 393 4 5 2 3
+                              Store 394 396
+             397:      6(int) Load 8(invocation)
+             399:    389(ptr) AccessChain 34(data) 57 381
+             400: 30(f16vec4) Load 399
+             401:398(f16vec3) VectorShuffle 400 400 0 1 2
+             402:398(f16vec3) GroupNonUniformBroadcast 42 401 42
+             403:    389(ptr) AccessChain 34(data) 397 381
+             404: 30(f16vec4) Load 403
+             405: 30(f16vec4) VectorShuffle 404 402 4 5 6 3
+                              Store 403 405
+             406:      6(int) Load 8(invocation)
+             407:    389(ptr) AccessChain 34(data) 67 381
+             408: 30(f16vec4) Load 407
+             409: 30(f16vec4) GroupNonUniformBroadcast 42 408 42
+             410:    389(ptr) AccessChain 34(data) 406 381
+                              Store 410 409
+             411:      6(int) Load 8(invocation)
+             412:    382(ptr) AccessChain 34(data) 37 381 38
+             413:29(float16_t) Load 412
+             414:29(float16_t) GroupNonUniformBroadcastFirst 42 413
+             415:    382(ptr) AccessChain 34(data) 411 381 38
+                              Store 415 414
+             416:      6(int) Load 8(invocation)
+             417:    389(ptr) AccessChain 34(data) 46 381
+             418: 30(f16vec4) Load 417
+             419:388(f16vec2) VectorShuffle 418 418 0 1
+             420:388(f16vec2) GroupNonUniformBroadcastFirst 42 419
+             421:    389(ptr) AccessChain 34(data) 416 381
+             422: 30(f16vec4) Load 421
+             423: 30(f16vec4) VectorShuffle 422 420 4 5 2 3
+                              Store 421 423
+             424:      6(int) Load 8(invocation)
+             425:    389(ptr) AccessChain 34(data) 57 381
+             426: 30(f16vec4) Load 425
+             427:398(f16vec3) VectorShuffle 426 426 0 1 2
+             428:398(f16vec3) GroupNonUniformBroadcastFirst 42 427
+             429:    389(ptr) AccessChain 34(data) 424 381
+             430: 30(f16vec4) Load 429
+             431: 30(f16vec4) VectorShuffle 430 428 4 5 6 3
+                              Store 429 431
+             432:      6(int) Load 8(invocation)
+             433:    389(ptr) AccessChain 34(data) 67 381
+             434: 30(f16vec4) Load 433
+             435: 30(f16vec4) GroupNonUniformBroadcastFirst 42 434
+             436:    389(ptr) AccessChain 34(data) 432 381
+                              Store 436 435
+                              Return
+                              FunctionEnd

Test/baseResults/spv.subgroupExtendedTypesBallotNeg.comp.out

@@ -0,0 +1,61 @@
+spv.subgroupExtendedTypesBallotNeg.comp
+ERROR: 0:26: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:27: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:28: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:29: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:30: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:31: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:33: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:35: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:36: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:38: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:39: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:40: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:41: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:42: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:44: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:45: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:46: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:47: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:48: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:49: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:50: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:51: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:53: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:54: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:55: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:56: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:57: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:58: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:59: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:60: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:62: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:63: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:64: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:65: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:66: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:67: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:68: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:69: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:71: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:72: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:73: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:74: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:75: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:76: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:77: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:78: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:80: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:81: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:82: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:83: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:84: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:85: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:86: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:87: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 56 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesBasic.comp.out

@@ -0,0 +1,9 @@
+spv.subgroupExtendedTypesBasic.comp
+ERROR: #version: compute shaders require es profile with version 310 or above, or non-es profile with version 420 or above
+ERROR: #version: statement must appear first in es-profile shader; before comments or newlines
+ERROR: 1 compilation errors.  No code generated.
+
+
+ERROR: Linking compute stage: Missing entry point: Each stage requires one entry point
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesClusteredNeg.comp.out

@@ -0,0 +1,189 @@
+spv.subgroupExtendedTypesClusteredNeg.comp
+ERROR: 0:26: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:27: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:28: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:29: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:31: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:33: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:34: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:36: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:38: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:39: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:41: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:42: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:43: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:44: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:46: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:47: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:48: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:49: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:51: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:52: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:53: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:54: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:56: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:57: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:58: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:59: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:61: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:62: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:63: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:64: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:66: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:67: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:68: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:69: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:71: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:72: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:73: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:74: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:76: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:77: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:78: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:79: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:81: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:82: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:83: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:84: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:86: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:87: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:88: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:89: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:91: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:92: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:93: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:94: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:96: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:97: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:98: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:99: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:101: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:102: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:103: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:104: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:106: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:107: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:108: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:109: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:111: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:112: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:113: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:114: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:116: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:117: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:118: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:119: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:121: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:122: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:123: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:124: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:126: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:127: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:128: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:129: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:131: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:132: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:133: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:134: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:136: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:137: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:138: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:139: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:141: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:142: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:143: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:144: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:146: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:147: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:148: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:149: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:151: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:152: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:153: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:154: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:156: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:157: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:158: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:159: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:161: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:162: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:163: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:164: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:166: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:167: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:168: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:169: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:171: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:172: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:173: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:174: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:176: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:177: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:178: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:179: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:181: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:182: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:183: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:184: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:186: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:187: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:188: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:189: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:191: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:192: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:193: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:194: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:196: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:197: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:198: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:199: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:201: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:202: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:203: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:204: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:206: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:207: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:208: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:209: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:211: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:212: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:213: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:214: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:216: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:217: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:218: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:219: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:221: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:222: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:223: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:224: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:226: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:227: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:228: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:229: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:231: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:232: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:233: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:234: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:236: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:237: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:238: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:239: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:241: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:242: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:243: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:244: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:246: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:247: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:248: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:249: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:251: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:252: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:253: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:254: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 184 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesPartitionedNeg.comp.out

@@ -0,0 +1,217 @@
+spv.subgroupExtendedTypesPartitionedNeg.comp
+ERROR: 0:27: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:28: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:29: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:30: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:33: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:34: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:35: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:38: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:39: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:40: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:42: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:43: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:44: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:45: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:47: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:48: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:49: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:50: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:52: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:53: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:54: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:55: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:57: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:58: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:59: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:60: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:62: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:63: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:64: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:65: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:67: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:68: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:69: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:70: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:72: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:73: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:74: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:75: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:77: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:78: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:79: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:80: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:82: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:83: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:84: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:85: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:87: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:88: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:89: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:90: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:92: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:93: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:94: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:95: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:97: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:98: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:99: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:100: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:102: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:103: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:104: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:105: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:107: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:108: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:109: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:110: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:112: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:113: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:114: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:115: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:117: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:118: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:119: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:120: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:122: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:123: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:124: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:125: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:127: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:128: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:129: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:130: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:132: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:133: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:134: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:135: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:137: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:138: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:139: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:140: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:142: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:143: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:144: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:145: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:147: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:148: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:149: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:150: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:152: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:153: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:154: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:155: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:157: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:158: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:159: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:160: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:162: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:163: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:164: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:165: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:167: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:168: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:169: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:170: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:172: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:173: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:174: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:175: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:177: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:178: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:179: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:180: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:182: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:183: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:184: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:185: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:187: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:188: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:189: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:190: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:192: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:193: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:194: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:195: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:197: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:198: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:199: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:200: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:202: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:203: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:204: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:205: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:207: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:208: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:209: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:210: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:212: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:213: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:214: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:215: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:217: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:218: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:219: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:220: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:222: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:223: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:224: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:225: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:227: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:228: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:229: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:230: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:232: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:233: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:234: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:235: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:237: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:238: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:239: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:240: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:242: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:243: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:244: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:245: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:247: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:248: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:249: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:250: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:252: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:253: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:254: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:255: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:257: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:258: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:259: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:260: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:262: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:263: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:264: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:265: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:267: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:268: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:269: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:270: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:272: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:273: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:274: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:275: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:277: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:278: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:279: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:280: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:282: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:283: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:284: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:285: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:287: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:288: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:289: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:290: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 212 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesQuad.comp.out

@@ -0,0 +1,981 @@
+spv.subgroupExtendedTypesQuad.comp
+// Module Version 10300
+// Generated by (magic number): 80007
+// Id's are bound by 806
+
+                              Capability Shader
+                              Capability Float16
+                              Capability Int64
+                              Capability Int16
+                              Capability Int8
+                              Capability GroupNonUniform
+                              Capability GroupNonUniformQuad
+                              Capability StorageUniformBufferBlock16
+                              Capability StorageBuffer8BitAccess
+                              Extension  "SPV_KHR_8bit_storage"
+               1:             ExtInstImport  "GLSL.std.450"
+                              MemoryModel Logical GLSL450
+                              EntryPoint GLCompute 4  "main" 10 12
+                              ExecutionMode 4 LocalSize 8 1 1
+                              Source GLSL 450
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_float16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int64"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int8"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_float16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int64"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int8"
+                              SourceExtension  "GL_KHR_shader_subgroup_basic"
+                              SourceExtension  "GL_KHR_shader_subgroup_quad"
+                              Name 4  "main"
+                              Name 8  "invocation"
+                              Name 10  "gl_SubgroupInvocationID"
+                              Name 12  "gl_SubgroupSize"
+                              Name 31  "Buffers"
+                              MemberName 31(Buffers) 0  "i8"
+                              MemberName 31(Buffers) 1  "u8"
+                              MemberName 31(Buffers) 2  "i16"
+                              MemberName 31(Buffers) 3  "u16"
+                              MemberName 31(Buffers) 4  "i64"
+                              MemberName 31(Buffers) 5  "u64"
+                              MemberName 31(Buffers) 6  "f16"
+                              Name 34  "data"
+                              Decorate 10(gl_SubgroupInvocationID) RelaxedPrecision
+                              Decorate 10(gl_SubgroupInvocationID) BuiltIn SubgroupLocalInvocationId
+                              Decorate 11 RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) BuiltIn SubgroupSize
+                              Decorate 13 RelaxedPrecision
+                              Decorate 14 RelaxedPrecision
+                              Decorate 16 RelaxedPrecision
+                              MemberDecorate 31(Buffers) 0 Offset 0
+                              MemberDecorate 31(Buffers) 1 Offset 4
+                              MemberDecorate 31(Buffers) 2 Offset 8
+                              MemberDecorate 31(Buffers) 3 Offset 16
+                              MemberDecorate 31(Buffers) 4 Offset 32
+                              MemberDecorate 31(Buffers) 5 Offset 64
+                              MemberDecorate 31(Buffers) 6 Offset 96
+                              Decorate 31(Buffers) Block
+                              Decorate 34(data) DescriptorSet 0
+                              Decorate 34(data) Binding 0
+                              Decorate 805 BuiltIn WorkgroupSize
+               2:             TypeVoid
+               3:             TypeFunction 2
+               6:             TypeInt 32 0
+               7:             TypePointer Function 6(int)
+               9:             TypePointer Input 6(int)
+10(gl_SubgroupInvocationID):      9(ptr) Variable Input
+12(gl_SubgroupSize):      9(ptr) Variable Input
+              15:      6(int) Constant 4
+              17:             TypeInt 8 1
+              18:             TypeVector 17(int8_t) 4
+              19:             TypeInt 8 0
+              20:             TypeVector 19(int8_t) 4
+              21:             TypeInt 16 1
+              22:             TypeVector 21(int16_t) 4
+              23:             TypeInt 16 0
+              24:             TypeVector 23(int16_t) 4
+              25:             TypeInt 64 1
+              26:             TypeVector 25(int64_t) 4
+              27:             TypeInt 64 0
+              28:             TypeVector 27(int64_t) 4
+              29:             TypeFloat 16
+              30:             TypeVector 29(float16_t) 4
+     31(Buffers):             TypeStruct 18(i8vec4) 20(i8vec4) 22(i16vec4) 24(i16vec4) 26(i64vec4) 28(i64vec4) 30(f16vec4)
+              32:             TypeArray 31(Buffers) 15
+              33:             TypePointer StorageBuffer 32
+        34(data):     33(ptr) Variable StorageBuffer
+              36:             TypeInt 32 1
+              37:     36(int) Constant 0
+              38:      6(int) Constant 0
+              39:             TypePointer StorageBuffer 17(int8_t)
+              42:      6(int) Constant 1
+              43:      6(int) Constant 3
+              47:     36(int) Constant 1
+              48:             TypeVector 17(int8_t) 2
+              49:             TypePointer StorageBuffer 18(i8vec4)
+              58:     36(int) Constant 2
+              59:             TypeVector 17(int8_t) 3
+              68:     36(int) Constant 3
+             128:      6(int) Constant 2
+             153:             TypePointer StorageBuffer 19(int8_t)
+             159:             TypeVector 19(int8_t) 2
+             160:             TypePointer StorageBuffer 20(i8vec4)
+             169:             TypeVector 19(int8_t) 3
+             261:             TypePointer StorageBuffer 21(int16_t)
+             267:             TypeVector 21(int16_t) 2
+             268:             TypePointer StorageBuffer 22(i16vec4)
+             277:             TypeVector 21(int16_t) 3
+             369:             TypePointer StorageBuffer 23(int16_t)
+             375:             TypeVector 23(int16_t) 2
+             376:             TypePointer StorageBuffer 24(i16vec4)
+             385:             TypeVector 23(int16_t) 3
+             477:     36(int) Constant 4
+             478:             TypePointer StorageBuffer 25(int64_t)
+             484:             TypeVector 25(int64_t) 2
+             485:             TypePointer StorageBuffer 26(i64vec4)
+             494:             TypeVector 25(int64_t) 3
+             586:     36(int) Constant 5
+             587:             TypePointer StorageBuffer 27(int64_t)
+             593:             TypeVector 27(int64_t) 2
+             594:             TypePointer StorageBuffer 28(i64vec4)
+             603:             TypeVector 27(int64_t) 3
+             695:     36(int) Constant 6
+             696:             TypePointer StorageBuffer 29(float16_t)
+             702:             TypeVector 29(float16_t) 2
+             703:             TypePointer StorageBuffer 30(f16vec4)
+             712:             TypeVector 29(float16_t) 3
+             803:             TypeVector 6(int) 3
+             804:      6(int) Constant 8
+             805:  803(ivec3) ConstantComposite 804 42 42
+         4(main):           2 Function None 3
+               5:             Label
+   8(invocation):      7(ptr) Variable Function
+              11:      6(int) Load 10(gl_SubgroupInvocationID)
+              13:      6(int) Load 12(gl_SubgroupSize)
+              14:      6(int) IAdd 11 13
+              16:      6(int) UMod 14 15
+                              Store 8(invocation) 16
+              35:      6(int) Load 8(invocation)
+              40:     39(ptr) AccessChain 34(data) 37 37 38
+              41:  17(int8_t) Load 40
+              44:  17(int8_t) GroupNonUniformQuadBroadcast 43 41 42
+              45:     39(ptr) AccessChain 34(data) 35 37 38
+                              Store 45 44
+              46:      6(int) Load 8(invocation)
+              50:     49(ptr) AccessChain 34(data) 47 37
+              51:  18(i8vec4) Load 50
+              52:  48(i8vec2) VectorShuffle 51 51 0 1
+              53:  48(i8vec2) GroupNonUniformQuadBroadcast 43 52 42
+              54:     49(ptr) AccessChain 34(data) 46 37
+              55:  18(i8vec4) Load 54
+              56:  18(i8vec4) VectorShuffle 55 53 4 5 2 3
+                              Store 54 56
+              57:      6(int) Load 8(invocation)
+              60:     49(ptr) AccessChain 34(data) 58 37
+              61:  18(i8vec4) Load 60
+              62:  59(i8vec3) VectorShuffle 61 61 0 1 2
+              63:  59(i8vec3) GroupNonUniformQuadBroadcast 43 62 42
+              64:     49(ptr) AccessChain 34(data) 57 37
+              65:  18(i8vec4) Load 64
+              66:  18(i8vec4) VectorShuffle 65 63 4 5 6 3
+                              Store 64 66
+              67:      6(int) Load 8(invocation)
+              69:     49(ptr) AccessChain 34(data) 68 37
+              70:  18(i8vec4) Load 69
+              71:  18(i8vec4) GroupNonUniformQuadBroadcast 43 70 42
+              72:     49(ptr) AccessChain 34(data) 67 37
+                              Store 72 71
+              73:      6(int) Load 8(invocation)
+              74:     39(ptr) AccessChain 34(data) 37 37 38
+              75:  17(int8_t) Load 74
+              76:  17(int8_t) GroupNonUniformQuadSwap 43 75 38
+              77:     39(ptr) AccessChain 34(data) 73 37 38
+                              Store 77 76
+              78:      6(int) Load 8(invocation)
+              79:     49(ptr) AccessChain 34(data) 47 37
+              80:  18(i8vec4) Load 79
+              81:  48(i8vec2) VectorShuffle 80 80 0 1
+              82:  48(i8vec2) GroupNonUniformQuadSwap 43 81 38
+              83:     49(ptr) AccessChain 34(data) 78 37
+              84:  18(i8vec4) Load 83
+              85:  18(i8vec4) VectorShuffle 84 82 4 5 2 3
+                              Store 83 85
+              86:      6(int) Load 8(invocation)
+              87:     49(ptr) AccessChain 34(data) 58 37
+              88:  18(i8vec4) Load 87
+              89:  59(i8vec3) VectorShuffle 88 88 0 1 2
+              90:  59(i8vec3) GroupNonUniformQuadSwap 43 89 38
+              91:     49(ptr) AccessChain 34(data) 86 37
+              92:  18(i8vec4) Load 91
+              93:  18(i8vec4) VectorShuffle 92 90 4 5 6 3
+                              Store 91 93
+              94:      6(int) Load 8(invocation)
+              95:     49(ptr) AccessChain 34(data) 68 37
+              96:  18(i8vec4) Load 95
+              97:  18(i8vec4) GroupNonUniformQuadSwap 43 96 38
+              98:     49(ptr) AccessChain 34(data) 94 37
+                              Store 98 97
+              99:      6(int) Load 8(invocation)
+             100:     39(ptr) AccessChain 34(data) 37 37 38
+             101:  17(int8_t) Load 100
+             102:  17(int8_t) GroupNonUniformQuadSwap 43 101 42
+             103:     39(ptr) AccessChain 34(data) 99 37 38
+                              Store 103 102
+             104:      6(int) Load 8(invocation)
+             105:     49(ptr) AccessChain 34(data) 47 37
+             106:  18(i8vec4) Load 105
+             107:  48(i8vec2) VectorShuffle 106 106 0 1
+             108:  48(i8vec2) GroupNonUniformQuadSwap 43 107 42
+             109:     49(ptr) AccessChain 34(data) 104 37
+             110:  18(i8vec4) Load 109
+             111:  18(i8vec4) VectorShuffle 110 108 4 5 2 3
+                              Store 109 111
+             112:      6(int) Load 8(invocation)
+             113:     49(ptr) AccessChain 34(data) 58 37
+             114:  18(i8vec4) Load 113
+             115:  59(i8vec3) VectorShuffle 114 114 0 1 2
+             116:  59(i8vec3) GroupNonUniformQuadSwap 43 115 42
+             117:     49(ptr) AccessChain 34(data) 112 37
+             118:  18(i8vec4) Load 117
+             119:  18(i8vec4) VectorShuffle 118 116 4 5 6 3
+                              Store 117 119
+             120:      6(int) Load 8(invocation)
+             121:     49(ptr) AccessChain 34(data) 68 37
+             122:  18(i8vec4) Load 121
+             123:  18(i8vec4) GroupNonUniformQuadSwap 43 122 42
+             124:     49(ptr) AccessChain 34(data) 120 37
+                              Store 124 123
+             125:      6(int) Load 8(invocation)
+             126:     39(ptr) AccessChain 34(data) 37 37 38
+             127:  17(int8_t) Load 126
+             129:  17(int8_t) GroupNonUniformQuadSwap 43 127 128
+             130:     39(ptr) AccessChain 34(data) 125 37 38
+                              Store 130 129
+             131:      6(int) Load 8(invocation)
+             132:     49(ptr) AccessChain 34(data) 47 37
+             133:  18(i8vec4) Load 132
+             134:  48(i8vec2) VectorShuffle 133 133 0 1
+             135:  48(i8vec2) GroupNonUniformQuadSwap 43 134 128
+             136:     49(ptr) AccessChain 34(data) 131 37
+             137:  18(i8vec4) Load 136
+             138:  18(i8vec4) VectorShuffle 137 135 4 5 2 3
+                              Store 136 138
+             139:      6(int) Load 8(invocation)
+             140:     49(ptr) AccessChain 34(data) 58 37
+             141:  18(i8vec4) Load 140
+             142:  59(i8vec3) VectorShuffle 141 141 0 1 2
+             143:  59(i8vec3) GroupNonUniformQuadSwap 43 142 128
+             144:     49(ptr) AccessChain 34(data) 139 37
+             145:  18(i8vec4) Load 144
+             146:  18(i8vec4) VectorShuffle 145 143 4 5 6 3
+                              Store 144 146
+             147:      6(int) Load 8(invocation)
+             148:     49(ptr) AccessChain 34(data) 68 37
+             149:  18(i8vec4) Load 148
+             150:  18(i8vec4) GroupNonUniformQuadSwap 43 149 128
+             151:     49(ptr) AccessChain 34(data) 147 37
+                              Store 151 150
+             152:      6(int) Load 8(invocation)
+             154:    153(ptr) AccessChain 34(data) 37 47 38
+             155:  19(int8_t) Load 154
+             156:  19(int8_t) GroupNonUniformQuadBroadcast 43 155 42
+             157:    153(ptr) AccessChain 34(data) 152 47 38
+                              Store 157 156
+             158:      6(int) Load 8(invocation)
+             161:    160(ptr) AccessChain 34(data) 47 47
+             162:  20(i8vec4) Load 161
+             163: 159(i8vec2) VectorShuffle 162 162 0 1
+             164: 159(i8vec2) GroupNonUniformQuadBroadcast 43 163 42
+             165:    160(ptr) AccessChain 34(data) 158 47
+             166:  20(i8vec4) Load 165
+             167:  20(i8vec4) VectorShuffle 166 164 4 5 2 3
+                              Store 165 167
+             168:      6(int) Load 8(invocation)
+             170:    160(ptr) AccessChain 34(data) 58 47
+             171:  20(i8vec4) Load 170
+             172: 169(i8vec3) VectorShuffle 171 171 0 1 2
+             173: 169(i8vec3) GroupNonUniformQuadBroadcast 43 172 42
+             174:    160(ptr) AccessChain 34(data) 168 47
+             175:  20(i8vec4) Load 174
+             176:  20(i8vec4) VectorShuffle 175 173 4 5 6 3
+                              Store 174 176
+             177:      6(int) Load 8(invocation)
+             178:    160(ptr) AccessChain 34(data) 68 47
+             179:  20(i8vec4) Load 178
+             180:  20(i8vec4) GroupNonUniformQuadBroadcast 43 179 42
+             181:    160(ptr) AccessChain 34(data) 177 47
+                              Store 181 180
+             182:      6(int) Load 8(invocation)
+             183:    153(ptr) AccessChain 34(data) 37 47 38
+             184:  19(int8_t) Load 183
+             185:  19(int8_t) GroupNonUniformQuadSwap 43 184 38
+             186:    153(ptr) AccessChain 34(data) 182 47 38
+                              Store 186 185
+             187:      6(int) Load 8(invocation)
+             188:    160(ptr) AccessChain 34(data) 47 47
+             189:  20(i8vec4) Load 188
+             190: 159(i8vec2) VectorShuffle 189 189 0 1
+             191: 159(i8vec2) GroupNonUniformQuadSwap 43 190 38
+             192:    160(ptr) AccessChain 34(data) 187 47
+             193:  20(i8vec4) Load 192
+             194:  20(i8vec4) VectorShuffle 193 191 4 5 2 3
+                              Store 192 194
+             195:      6(int) Load 8(invocation)
+             196:    160(ptr) AccessChain 34(data) 58 47
+             197:  20(i8vec4) Load 196
+             198: 169(i8vec3) VectorShuffle 197 197 0 1 2
+             199: 169(i8vec3) GroupNonUniformQuadSwap 43 198 38
+             200:    160(ptr) AccessChain 34(data) 195 47
+             201:  20(i8vec4) Load 200
+             202:  20(i8vec4) VectorShuffle 201 199 4 5 6 3
+                              Store 200 202
+             203:      6(int) Load 8(invocation)
+             204:    160(ptr) AccessChain 34(data) 68 47
+             205:  20(i8vec4) Load 204
+             206:  20(i8vec4) GroupNonUniformQuadSwap 43 205 38
+             207:    160(ptr) AccessChain 34(data) 203 47
+                              Store 207 206
+             208:      6(int) Load 8(invocation)
+             209:    153(ptr) AccessChain 34(data) 37 47 38
+             210:  19(int8_t) Load 209
+             211:  19(int8_t) GroupNonUniformQuadSwap 43 210 42
+             212:    153(ptr) AccessChain 34(data) 208 47 38
+                              Store 212 211
+             213:      6(int) Load 8(invocation)
+             214:    160(ptr) AccessChain 34(data) 47 47
+             215:  20(i8vec4) Load 214
+             216: 159(i8vec2) VectorShuffle 215 215 0 1
+             217: 159(i8vec2) GroupNonUniformQuadSwap 43 216 42
+             218:    160(ptr) AccessChain 34(data) 213 47
+             219:  20(i8vec4) Load 218
+             220:  20(i8vec4) VectorShuffle 219 217 4 5 2 3
+                              Store 218 220
+             221:      6(int) Load 8(invocation)
+             222:    160(ptr) AccessChain 34(data) 58 47
+             223:  20(i8vec4) Load 222
+             224: 169(i8vec3) VectorShuffle 223 223 0 1 2
+             225: 169(i8vec3) GroupNonUniformQuadSwap 43 224 42
+             226:    160(ptr) AccessChain 34(data) 221 47
+             227:  20(i8vec4) Load 226
+             228:  20(i8vec4) VectorShuffle 227 225 4 5 6 3
+                              Store 226 228
+             229:      6(int) Load 8(invocation)
+             230:    160(ptr) AccessChain 34(data) 68 47
+             231:  20(i8vec4) Load 230
+             232:  20(i8vec4) GroupNonUniformQuadSwap 43 231 42
+             233:    160(ptr) AccessChain 34(data) 229 47
+                              Store 233 232
+             234:      6(int) Load 8(invocation)
+             235:    153(ptr) AccessChain 34(data) 37 47 38
+             236:  19(int8_t) Load 235
+             237:  19(int8_t) GroupNonUniformQuadSwap 43 236 128
+             238:    153(ptr) AccessChain 34(data) 234 47 38
+                              Store 238 237
+             239:      6(int) Load 8(invocation)
+             240:    160(ptr) AccessChain 34(data) 47 47
+             241:  20(i8vec4) Load 240
+             242: 159(i8vec2) VectorShuffle 241 241 0 1
+             243: 159(i8vec2) GroupNonUniformQuadSwap 43 242 128
+             244:    160(ptr) AccessChain 34(data) 239 47
+             245:  20(i8vec4) Load 244
+             246:  20(i8vec4) VectorShuffle 245 243 4 5 2 3
+                              Store 244 246
+             247:      6(int) Load 8(invocation)
+             248:    160(ptr) AccessChain 34(data) 58 47
+             249:  20(i8vec4) Load 248
+             250: 169(i8vec3) VectorShuffle 249 249 0 1 2
+             251: 169(i8vec3) GroupNonUniformQuadSwap 43 250 128
+             252:    160(ptr) AccessChain 34(data) 247 47
+             253:  20(i8vec4) Load 252
+             254:  20(i8vec4) VectorShuffle 253 251 4 5 6 3
+                              Store 252 254
+             255:      6(int) Load 8(invocation)
+             256:    160(ptr) AccessChain 34(data) 68 47
+             257:  20(i8vec4) Load 256
+             258:  20(i8vec4) GroupNonUniformQuadSwap 43 257 128
+             259:    160(ptr) AccessChain 34(data) 255 47
+                              Store 259 258
+             260:      6(int) Load 8(invocation)
+             262:    261(ptr) AccessChain 34(data) 37 58 38
+             263: 21(int16_t) Load 262
+             264: 21(int16_t) GroupNonUniformQuadBroadcast 43 263 42
+             265:    261(ptr) AccessChain 34(data) 260 58 38
+                              Store 265 264
+             266:      6(int) Load 8(invocation)
+             269:    268(ptr) AccessChain 34(data) 47 58
+             270: 22(i16vec4) Load 269
+             271:267(i16vec2) VectorShuffle 270 270 0 1
+             272:267(i16vec2) GroupNonUniformQuadBroadcast 43 271 42
+             273:    268(ptr) AccessChain 34(data) 266 58
+             274: 22(i16vec4) Load 273
+             275: 22(i16vec4) VectorShuffle 274 272 4 5 2 3
+                              Store 273 275
+             276:      6(int) Load 8(invocation)
+             278:    268(ptr) AccessChain 34(data) 58 58
+             279: 22(i16vec4) Load 278
+             280:277(i16vec3) VectorShuffle 279 279 0 1 2
+             281:277(i16vec3) GroupNonUniformQuadBroadcast 43 280 42
+             282:    268(ptr) AccessChain 34(data) 276 58
+             283: 22(i16vec4) Load 282
+             284: 22(i16vec4) VectorShuffle 283 281 4 5 6 3
+                              Store 282 284
+             285:      6(int) Load 8(invocation)
+             286:    268(ptr) AccessChain 34(data) 68 58
+             287: 22(i16vec4) Load 286
+             288: 22(i16vec4) GroupNonUniformQuadBroadcast 43 287 42
+             289:    268(ptr) AccessChain 34(data) 285 58
+                              Store 289 288
+             290:      6(int) Load 8(invocation)
+             291:    261(ptr) AccessChain 34(data) 37 58 38
+             292: 21(int16_t) Load 291
+             293: 21(int16_t) GroupNonUniformQuadSwap 43 292 38
+             294:    261(ptr) AccessChain 34(data) 290 58 38
+                              Store 294 293
+             295:      6(int) Load 8(invocation)
+             296:    268(ptr) AccessChain 34(data) 47 58
+             297: 22(i16vec4) Load 296
+             298:267(i16vec2) VectorShuffle 297 297 0 1
+             299:267(i16vec2) GroupNonUniformQuadSwap 43 298 38
+             300:    268(ptr) AccessChain 34(data) 295 58
+             301: 22(i16vec4) Load 300
+             302: 22(i16vec4) VectorShuffle 301 299 4 5 2 3
+                              Store 300 302
+             303:      6(int) Load 8(invocation)
+             304:    268(ptr) AccessChain 34(data) 58 58
+             305: 22(i16vec4) Load 304
+             306:277(i16vec3) VectorShuffle 305 305 0 1 2
+             307:277(i16vec3) GroupNonUniformQuadSwap 43 306 38
+             308:    268(ptr) AccessChain 34(data) 303 58
+             309: 22(i16vec4) Load 308
+             310: 22(i16vec4) VectorShuffle 309 307 4 5 6 3
+                              Store 308 310
+             311:      6(int) Load 8(invocation)
+             312:    268(ptr) AccessChain 34(data) 68 58
+             313: 22(i16vec4) Load 312
+             314: 22(i16vec4) GroupNonUniformQuadSwap 43 313 38
+             315:    268(ptr) AccessChain 34(data) 311 58
+                              Store 315 314
+             316:      6(int) Load 8(invocation)
+             317:    261(ptr) AccessChain 34(data) 37 58 38
+             318: 21(int16_t) Load 317
+             319: 21(int16_t) GroupNonUniformQuadSwap 43 318 42
+             320:    261(ptr) AccessChain 34(data) 316 58 38
+                              Store 320 319
+             321:      6(int) Load 8(invocation)
+             322:    268(ptr) AccessChain 34(data) 47 58
+             323: 22(i16vec4) Load 322
+             324:267(i16vec2) VectorShuffle 323 323 0 1
+             325:267(i16vec2) GroupNonUniformQuadSwap 43 324 42
+             326:    268(ptr) AccessChain 34(data) 321 58
+             327: 22(i16vec4) Load 326
+             328: 22(i16vec4) VectorShuffle 327 325 4 5 2 3
+                              Store 326 328
+             329:      6(int) Load 8(invocation)
+             330:    268(ptr) AccessChain 34(data) 58 58
+             331: 22(i16vec4) Load 330
+             332:277(i16vec3) VectorShuffle 331 331 0 1 2
+             333:277(i16vec3) GroupNonUniformQuadSwap 43 332 42
+             334:    268(ptr) AccessChain 34(data) 329 58
+             335: 22(i16vec4) Load 334
+             336: 22(i16vec4) VectorShuffle 335 333 4 5 6 3
+                              Store 334 336
+             337:      6(int) Load 8(invocation)
+             338:    268(ptr) AccessChain 34(data) 68 58
+             339: 22(i16vec4) Load 338
+             340: 22(i16vec4) GroupNonUniformQuadSwap 43 339 42
+             341:    268(ptr) AccessChain 34(data) 337 58
+                              Store 341 340
+             342:      6(int) Load 8(invocation)
+             343:    261(ptr) AccessChain 34(data) 37 58 38
+             344: 21(int16_t) Load 343
+             345: 21(int16_t) GroupNonUniformQuadSwap 43 344 128
+             346:    261(ptr) AccessChain 34(data) 342 58 38
+                              Store 346 345
+             347:      6(int) Load 8(invocation)
+             348:    268(ptr) AccessChain 34(data) 47 58
+             349: 22(i16vec4) Load 348
+             350:267(i16vec2) VectorShuffle 349 349 0 1
+             351:267(i16vec2) GroupNonUniformQuadSwap 43 350 128
+             352:    268(ptr) AccessChain 34(data) 347 58
+             353: 22(i16vec4) Load 352
+             354: 22(i16vec4) VectorShuffle 353 351 4 5 2 3
+                              Store 352 354
+             355:      6(int) Load 8(invocation)
+             356:    268(ptr) AccessChain 34(data) 58 58
+             357: 22(i16vec4) Load 356
+             358:277(i16vec3) VectorShuffle 357 357 0 1 2
+             359:277(i16vec3) GroupNonUniformQuadSwap 43 358 128
+             360:    268(ptr) AccessChain 34(data) 355 58
+             361: 22(i16vec4) Load 360
+             362: 22(i16vec4) VectorShuffle 361 359 4 5 6 3
+                              Store 360 362
+             363:      6(int) Load 8(invocation)
+             364:    268(ptr) AccessChain 34(data) 68 58
+             365: 22(i16vec4) Load 364
+             366: 22(i16vec4) GroupNonUniformQuadSwap 43 365 128
+             367:    268(ptr) AccessChain 34(data) 363 58
+                              Store 367 366
+             368:      6(int) Load 8(invocation)
+             370:    369(ptr) AccessChain 34(data) 37 68 38
+             371: 23(int16_t) Load 370
+             372: 23(int16_t) GroupNonUniformQuadBroadcast 43 371 42
+             373:    369(ptr) AccessChain 34(data) 368 68 38
+                              Store 373 372
+             374:      6(int) Load 8(invocation)
+             377:    376(ptr) AccessChain 34(data) 47 68
+             378: 24(i16vec4) Load 377
+             379:375(i16vec2) VectorShuffle 378 378 0 1
+             380:375(i16vec2) GroupNonUniformQuadBroadcast 43 379 42
+             381:    376(ptr) AccessChain 34(data) 374 68
+             382: 24(i16vec4) Load 381
+             383: 24(i16vec4) VectorShuffle 382 380 4 5 2 3
+                              Store 381 383
+             384:      6(int) Load 8(invocation)
+             386:    376(ptr) AccessChain 34(data) 58 68
+             387: 24(i16vec4) Load 386
+             388:385(i16vec3) VectorShuffle 387 387 0 1 2
+             389:385(i16vec3) GroupNonUniformQuadBroadcast 43 388 42
+             390:    376(ptr) AccessChain 34(data) 384 68
+             391: 24(i16vec4) Load 390
+             392: 24(i16vec4) VectorShuffle 391 389 4 5 6 3
+                              Store 390 392
+             393:      6(int) Load 8(invocation)
+             394:    376(ptr) AccessChain 34(data) 68 68
+             395: 24(i16vec4) Load 394
+             396: 24(i16vec4) GroupNonUniformQuadBroadcast 43 395 42
+             397:    376(ptr) AccessChain 34(data) 393 68
+                              Store 397 396
+             398:      6(int) Load 8(invocation)
+             399:    369(ptr) AccessChain 34(data) 37 68 38
+             400: 23(int16_t) Load 399
+             401: 23(int16_t) GroupNonUniformQuadSwap 43 400 38
+             402:    369(ptr) AccessChain 34(data) 398 68 38
+                              Store 402 401
+             403:      6(int) Load 8(invocation)
+             404:    376(ptr) AccessChain 34(data) 47 68
+             405: 24(i16vec4) Load 404
+             406:375(i16vec2) VectorShuffle 405 405 0 1
+             407:375(i16vec2) GroupNonUniformQuadSwap 43 406 38
+             408:    376(ptr) AccessChain 34(data) 403 68
+             409: 24(i16vec4) Load 408
+             410: 24(i16vec4) VectorShuffle 409 407 4 5 2 3
+                              Store 408 410
+             411:      6(int) Load 8(invocation)
+             412:    376(ptr) AccessChain 34(data) 58 68
+             413: 24(i16vec4) Load 412
+             414:385(i16vec3) VectorShuffle 413 413 0 1 2
+             415:385(i16vec3) GroupNonUniformQuadSwap 43 414 38
+             416:    376(ptr) AccessChain 34(data) 411 68
+             417: 24(i16vec4) Load 416
+             418: 24(i16vec4) VectorShuffle 417 415 4 5 6 3
+                              Store 416 418
+             419:      6(int) Load 8(invocation)
+             420:    376(ptr) AccessChain 34(data) 68 68
+             421: 24(i16vec4) Load 420
+             422: 24(i16vec4) GroupNonUniformQuadSwap 43 421 38
+             423:    376(ptr) AccessChain 34(data) 419 68
+                              Store 423 422
+             424:      6(int) Load 8(invocation)
+             425:    369(ptr) AccessChain 34(data) 37 68 38
+             426: 23(int16_t) Load 425
+             427: 23(int16_t) GroupNonUniformQuadSwap 43 426 42
+             428:    369(ptr) AccessChain 34(data) 424 68 38
+                              Store 428 427
+             429:      6(int) Load 8(invocation)
+             430:    376(ptr) AccessChain 34(data) 47 68
+             431: 24(i16vec4) Load 430
+             432:375(i16vec2) VectorShuffle 431 431 0 1
+             433:375(i16vec2) GroupNonUniformQuadSwap 43 432 42
+             434:    376(ptr) AccessChain 34(data) 429 68
+             435: 24(i16vec4) Load 434
+             436: 24(i16vec4) VectorShuffle 435 433 4 5 2 3
+                              Store 434 436
+             437:      6(int) Load 8(invocation)
+             438:    376(ptr) AccessChain 34(data) 58 68
+             439: 24(i16vec4) Load 438
+             440:385(i16vec3) VectorShuffle 439 439 0 1 2
+             441:385(i16vec3) GroupNonUniformQuadSwap 43 440 42
+             442:    376(ptr) AccessChain 34(data) 437 68
+             443: 24(i16vec4) Load 442
+             444: 24(i16vec4) VectorShuffle 443 441 4 5 6 3
+                              Store 442 444
+             445:      6(int) Load 8(invocation)
+             446:    376(ptr) AccessChain 34(data) 68 68
+             447: 24(i16vec4) Load 446
+             448: 24(i16vec4) GroupNonUniformQuadSwap 43 447 42
+             449:    376(ptr) AccessChain 34(data) 445 68
+                              Store 449 448
+             450:      6(int) Load 8(invocation)
+             451:    369(ptr) AccessChain 34(data) 37 68 38
+             452: 23(int16_t) Load 451
+             453: 23(int16_t) GroupNonUniformQuadSwap 43 452 128
+             454:    369(ptr) AccessChain 34(data) 450 68 38
+                              Store 454 453
+             455:      6(int) Load 8(invocation)
+             456:    376(ptr) AccessChain 34(data) 47 68
+             457: 24(i16vec4) Load 456
+             458:375(i16vec2) VectorShuffle 457 457 0 1
+             459:375(i16vec2) GroupNonUniformQuadSwap 43 458 128
+             460:    376(ptr) AccessChain 34(data) 455 68
+             461: 24(i16vec4) Load 460
+             462: 24(i16vec4) VectorShuffle 461 459 4 5 2 3
+                              Store 460 462
+             463:      6(int) Load 8(invocation)
+             464:    376(ptr) AccessChain 34(data) 58 68
+             465: 24(i16vec4) Load 464
+             466:385(i16vec3) VectorShuffle 465 465 0 1 2
+             467:385(i16vec3) GroupNonUniformQuadSwap 43 466 128
+             468:    376(ptr) AccessChain 34(data) 463 68
+             469: 24(i16vec4) Load 468
+             470: 24(i16vec4) VectorShuffle 469 467 4 5 6 3
+                              Store 468 470
+             471:      6(int) Load 8(invocation)
+             472:    376(ptr) AccessChain 34(data) 68 68
+             473: 24(i16vec4) Load 472
+             474: 24(i16vec4) GroupNonUniformQuadSwap 43 473 128
+             475:    376(ptr) AccessChain 34(data) 471 68
+                              Store 475 474
+             476:      6(int) Load 8(invocation)
+             479:    478(ptr) AccessChain 34(data) 37 477 38
+             480: 25(int64_t) Load 479
+             481: 25(int64_t) GroupNonUniformQuadBroadcast 43 480 42
+             482:    478(ptr) AccessChain 34(data) 476 477 38
+                              Store 482 481
+             483:      6(int) Load 8(invocation)
+             486:    485(ptr) AccessChain 34(data) 47 477
+             487: 26(i64vec4) Load 486
+             488:484(i64vec2) VectorShuffle 487 487 0 1
+             489:484(i64vec2) GroupNonUniformQuadBroadcast 43 488 42
+             490:    485(ptr) AccessChain 34(data) 483 477
+             491: 26(i64vec4) Load 490
+             492: 26(i64vec4) VectorShuffle 491 489 4 5 2 3
+                              Store 490 492
+             493:      6(int) Load 8(invocation)
+             495:    485(ptr) AccessChain 34(data) 58 477
+             496: 26(i64vec4) Load 495
+             497:494(i64vec3) VectorShuffle 496 496 0 1 2
+             498:494(i64vec3) GroupNonUniformQuadBroadcast 43 497 42
+             499:    485(ptr) AccessChain 34(data) 493 477
+             500: 26(i64vec4) Load 499
+             501: 26(i64vec4) VectorShuffle 500 498 4 5 6 3
+                              Store 499 501
+             502:      6(int) Load 8(invocation)
+             503:    485(ptr) AccessChain 34(data) 68 477
+             504: 26(i64vec4) Load 503
+             505: 26(i64vec4) GroupNonUniformQuadBroadcast 43 504 42
+             506:    485(ptr) AccessChain 34(data) 502 477
+                              Store 506 505
+             507:      6(int) Load 8(invocation)
+             508:    478(ptr) AccessChain 34(data) 37 477 38
+             509: 25(int64_t) Load 508
+             510: 25(int64_t) GroupNonUniformQuadSwap 43 509 38
+             511:    478(ptr) AccessChain 34(data) 507 477 38
+                              Store 511 510
+             512:      6(int) Load 8(invocation)
+             513:    485(ptr) AccessChain 34(data) 47 477
+             514: 26(i64vec4) Load 513
+             515:484(i64vec2) VectorShuffle 514 514 0 1
+             516:484(i64vec2) GroupNonUniformQuadSwap 43 515 38
+             517:    485(ptr) AccessChain 34(data) 512 477
+             518: 26(i64vec4) Load 517
+             519: 26(i64vec4) VectorShuffle 518 516 4 5 2 3
+                              Store 517 519
+             520:      6(int) Load 8(invocation)
+             521:    485(ptr) AccessChain 34(data) 58 477
+             522: 26(i64vec4) Load 521
+             523:494(i64vec3) VectorShuffle 522 522 0 1 2
+             524:494(i64vec3) GroupNonUniformQuadSwap 43 523 38
+             525:    485(ptr) AccessChain 34(data) 520 477
+             526: 26(i64vec4) Load 525
+             527: 26(i64vec4) VectorShuffle 526 524 4 5 6 3
+                              Store 525 527
+             528:      6(int) Load 8(invocation)
+             529:    485(ptr) AccessChain 34(data) 68 477
+             530: 26(i64vec4) Load 529
+             531: 26(i64vec4) GroupNonUniformQuadSwap 43 530 38
+             532:    485(ptr) AccessChain 34(data) 528 477
+                              Store 532 531
+             533:      6(int) Load 8(invocation)
+             534:    478(ptr) AccessChain 34(data) 37 477 38
+             535: 25(int64_t) Load 534
+             536: 25(int64_t) GroupNonUniformQuadSwap 43 535 42
+             537:    478(ptr) AccessChain 34(data) 533 477 38
+                              Store 537 536
+             538:      6(int) Load 8(invocation)
+             539:    485(ptr) AccessChain 34(data) 47 477
+             540: 26(i64vec4) Load 539
+             541:484(i64vec2) VectorShuffle 540 540 0 1
+             542:484(i64vec2) GroupNonUniformQuadSwap 43 541 42
+             543:    485(ptr) AccessChain 34(data) 538 477
+             544: 26(i64vec4) Load 543
+             545: 26(i64vec4) VectorShuffle 544 542 4 5 2 3
+                              Store 543 545
+             546:      6(int) Load 8(invocation)
+             547:    485(ptr) AccessChain 34(data) 58 477
+             548: 26(i64vec4) Load 547
+             549:494(i64vec3) VectorShuffle 548 548 0 1 2
+             550:494(i64vec3) GroupNonUniformQuadSwap 43 549 42
+             551:    485(ptr) AccessChain 34(data) 546 477
+             552: 26(i64vec4) Load 551
+             553: 26(i64vec4) VectorShuffle 552 550 4 5 6 3
+                              Store 551 553
+             554:      6(int) Load 8(invocation)
+             555:    485(ptr) AccessChain 34(data) 68 477
+             556: 26(i64vec4) Load 555
+             557: 26(i64vec4) GroupNonUniformQuadSwap 43 556 42
+             558:    485(ptr) AccessChain 34(data) 554 477
+                              Store 558 557
+             559:      6(int) Load 8(invocation)
+             560:    478(ptr) AccessChain 34(data) 37 477 38
+             561: 25(int64_t) Load 560
+             562: 25(int64_t) GroupNonUniformQuadSwap 43 561 128
+             563:    478(ptr) AccessChain 34(data) 559 477 38
+                              Store 563 562
+             564:      6(int) Load 8(invocation)
+             565:    485(ptr) AccessChain 34(data) 47 477
+             566: 26(i64vec4) Load 565
+             567:484(i64vec2) VectorShuffle 566 566 0 1
+             568:484(i64vec2) GroupNonUniformQuadSwap 43 567 128
+             569:    485(ptr) AccessChain 34(data) 564 477
+             570: 26(i64vec4) Load 569
+             571: 26(i64vec4) VectorShuffle 570 568 4 5 2 3
+                              Store 569 571
+             572:      6(int) Load 8(invocation)
+             573:    485(ptr) AccessChain 34(data) 58 477
+             574: 26(i64vec4) Load 573
+             575:494(i64vec3) VectorShuffle 574 574 0 1 2
+             576:494(i64vec3) GroupNonUniformQuadSwap 43 575 128
+             577:    485(ptr) AccessChain 34(data) 572 477
+             578: 26(i64vec4) Load 577
+             579: 26(i64vec4) VectorShuffle 578 576 4 5 6 3
+                              Store 577 579
+             580:      6(int) Load 8(invocation)
+             581:    485(ptr) AccessChain 34(data) 68 477
+             582: 26(i64vec4) Load 581
+             583: 26(i64vec4) GroupNonUniformQuadSwap 43 582 128
+             584:    485(ptr) AccessChain 34(data) 580 477
+                              Store 584 583
+             585:      6(int) Load 8(invocation)
+             588:    587(ptr) AccessChain 34(data) 37 586 38
+             589: 27(int64_t) Load 588
+             590: 27(int64_t) GroupNonUniformQuadBroadcast 43 589 42
+             591:    587(ptr) AccessChain 34(data) 585 586 38
+                              Store 591 590
+             592:      6(int) Load 8(invocation)
+             595:    594(ptr) AccessChain 34(data) 47 586
+             596: 28(i64vec4) Load 595
+             597:593(i64vec2) VectorShuffle 596 596 0 1
+             598:593(i64vec2) GroupNonUniformQuadBroadcast 43 597 42
+             599:    594(ptr) AccessChain 34(data) 592 586
+             600: 28(i64vec4) Load 599
+             601: 28(i64vec4) VectorShuffle 600 598 4 5 2 3
+                              Store 599 601
+             602:      6(int) Load 8(invocation)
+             604:    594(ptr) AccessChain 34(data) 58 586
+             605: 28(i64vec4) Load 604
+             606:603(i64vec3) VectorShuffle 605 605 0 1 2
+             607:603(i64vec3) GroupNonUniformQuadBroadcast 43 606 42
+             608:    594(ptr) AccessChain 34(data) 602 586
+             609: 28(i64vec4) Load 608
+             610: 28(i64vec4) VectorShuffle 609 607 4 5 6 3
+                              Store 608 610
+             611:      6(int) Load 8(invocation)
+             612:    594(ptr) AccessChain 34(data) 68 586
+             613: 28(i64vec4) Load 612
+             614: 28(i64vec4) GroupNonUniformQuadBroadcast 43 613 42
+             615:    594(ptr) AccessChain 34(data) 611 586
+                              Store 615 614
+             616:      6(int) Load 8(invocation)
+             617:    587(ptr) AccessChain 34(data) 37 586 38
+             618: 27(int64_t) Load 617
+             619: 27(int64_t) GroupNonUniformQuadSwap 43 618 38
+             620:    587(ptr) AccessChain 34(data) 616 586 38
+                              Store 620 619
+             621:      6(int) Load 8(invocation)
+             622:    594(ptr) AccessChain 34(data) 47 586
+             623: 28(i64vec4) Load 622
+             624:593(i64vec2) VectorShuffle 623 623 0 1
+             625:593(i64vec2) GroupNonUniformQuadSwap 43 624 38
+             626:    594(ptr) AccessChain 34(data) 621 586
+             627: 28(i64vec4) Load 626
+             628: 28(i64vec4) VectorShuffle 627 625 4 5 2 3
+                              Store 626 628
+             629:      6(int) Load 8(invocation)
+             630:    594(ptr) AccessChain 34(data) 58 586
+             631: 28(i64vec4) Load 630
+             632:603(i64vec3) VectorShuffle 631 631 0 1 2
+             633:603(i64vec3) GroupNonUniformQuadSwap 43 632 38
+             634:    594(ptr) AccessChain 34(data) 629 586
+             635: 28(i64vec4) Load 634
+             636: 28(i64vec4) VectorShuffle 635 633 4 5 6 3
+                              Store 634 636
+             637:      6(int) Load 8(invocation)
+             638:    594(ptr) AccessChain 34(data) 68 586
+             639: 28(i64vec4) Load 638
+             640: 28(i64vec4) GroupNonUniformQuadSwap 43 639 38
+             641:    594(ptr) AccessChain 34(data) 637 586
+                              Store 641 640
+             642:      6(int) Load 8(invocation)
+             643:    587(ptr) AccessChain 34(data) 37 586 38
+             644: 27(int64_t) Load 643
+             645: 27(int64_t) GroupNonUniformQuadSwap 43 644 42
+             646:    587(ptr) AccessChain 34(data) 642 586 38
+                              Store 646 645
+             647:      6(int) Load 8(invocation)
+             648:    594(ptr) AccessChain 34(data) 47 586
+             649: 28(i64vec4) Load 648
+             650:593(i64vec2) VectorShuffle 649 649 0 1
+             651:593(i64vec2) GroupNonUniformQuadSwap 43 650 42
+             652:    594(ptr) AccessChain 34(data) 647 586
+             653: 28(i64vec4) Load 652
+             654: 28(i64vec4) VectorShuffle 653 651 4 5 2 3
+                              Store 652 654
+             655:      6(int) Load 8(invocation)
+             656:    594(ptr) AccessChain 34(data) 58 586
+             657: 28(i64vec4) Load 656
+             658:603(i64vec3) VectorShuffle 657 657 0 1 2
+             659:603(i64vec3) GroupNonUniformQuadSwap 43 658 42
+             660:    594(ptr) AccessChain 34(data) 655 586
+             661: 28(i64vec4) Load 660
+             662: 28(i64vec4) VectorShuffle 661 659 4 5 6 3
+                              Store 660 662
+             663:      6(int) Load 8(invocation)
+             664:    594(ptr) AccessChain 34(data) 68 586
+             665: 28(i64vec4) Load 664
+             666: 28(i64vec4) GroupNonUniformQuadSwap 43 665 42
+             667:    594(ptr) AccessChain 34(data) 663 586
+                              Store 667 666
+             668:      6(int) Load 8(invocation)
+             669:    587(ptr) AccessChain 34(data) 37 586 38
+             670: 27(int64_t) Load 669
+             671: 27(int64_t) GroupNonUniformQuadSwap 43 670 128
+             672:    587(ptr) AccessChain 34(data) 668 586 38
+                              Store 672 671
+             673:      6(int) Load 8(invocation)
+             674:    594(ptr) AccessChain 34(data) 47 586
+             675: 28(i64vec4) Load 674
+             676:593(i64vec2) VectorShuffle 675 675 0 1
+             677:593(i64vec2) GroupNonUniformQuadSwap 43 676 128
+             678:    594(ptr) AccessChain 34(data) 673 586
+             679: 28(i64vec4) Load 678
+             680: 28(i64vec4) VectorShuffle 679 677 4 5 2 3
+                              Store 678 680
+             681:      6(int) Load 8(invocation)
+             682:    594(ptr) AccessChain 34(data) 58 586
+             683: 28(i64vec4) Load 682
+             684:603(i64vec3) VectorShuffle 683 683 0 1 2
+             685:603(i64vec3) GroupNonUniformQuadSwap 43 684 128
+             686:    594(ptr) AccessChain 34(data) 681 586
+             687: 28(i64vec4) Load 686
+             688: 28(i64vec4) VectorShuffle 687 685 4 5 6 3
+                              Store 686 688
+             689:      6(int) Load 8(invocation)
+             690:    594(ptr) AccessChain 34(data) 68 586
+             691: 28(i64vec4) Load 690
+             692: 28(i64vec4) GroupNonUniformQuadSwap 43 691 128
+             693:    594(ptr) AccessChain 34(data) 689 586
+                              Store 693 692
+             694:      6(int) Load 8(invocation)
+             697:    696(ptr) AccessChain 34(data) 37 695 38
+             698:29(float16_t) Load 697
+             699:29(float16_t) GroupNonUniformQuadBroadcast 43 698 42
+             700:    696(ptr) AccessChain 34(data) 694 695 38
+                              Store 700 699
+             701:      6(int) Load 8(invocation)
+             704:    703(ptr) AccessChain 34(data) 47 695
+             705: 30(f16vec4) Load 704
+             706:702(f16vec2) VectorShuffle 705 705 0 1
+             707:702(f16vec2) GroupNonUniformQuadBroadcast 43 706 42
+             708:    703(ptr) AccessChain 34(data) 701 695
+             709: 30(f16vec4) Load 708
+             710: 30(f16vec4) VectorShuffle 709 707 4 5 2 3
+                              Store 708 710
+             711:      6(int) Load 8(invocation)
+             713:    703(ptr) AccessChain 34(data) 58 695
+             714: 30(f16vec4) Load 713
+             715:712(f16vec3) VectorShuffle 714 714 0 1 2
+             716:712(f16vec3) GroupNonUniformQuadBroadcast 43 715 42
+             717:    703(ptr) AccessChain 34(data) 711 695
+             718: 30(f16vec4) Load 717
+             719: 30(f16vec4) VectorShuffle 718 716 4 5 6 3
+                              Store 717 719
+             720:      6(int) Load 8(invocation)
+             721:    703(ptr) AccessChain 34(data) 68 695
+             722: 30(f16vec4) Load 721
+             723: 30(f16vec4) GroupNonUniformQuadBroadcast 43 722 42
+             724:    703(ptr) AccessChain 34(data) 720 695
+                              Store 724 723
+             725:      6(int) Load 8(invocation)
+             726:    696(ptr) AccessChain 34(data) 37 695 38
+             727:29(float16_t) Load 726
+             728:29(float16_t) GroupNonUniformQuadSwap 43 727 38
+             729:    696(ptr) AccessChain 34(data) 725 695 38
+                              Store 729 728
+             730:      6(int) Load 8(invocation)
+             731:    703(ptr) AccessChain 34(data) 47 695
+             732: 30(f16vec4) Load 731
+             733:702(f16vec2) VectorShuffle 732 732 0 1
+             734:702(f16vec2) GroupNonUniformQuadSwap 43 733 38
+             735:    703(ptr) AccessChain 34(data) 730 695
+             736: 30(f16vec4) Load 735
+             737: 30(f16vec4) VectorShuffle 736 734 4 5 2 3
+                              Store 735 737
+             738:      6(int) Load 8(invocation)
+             739:    703(ptr) AccessChain 34(data) 58 695
+             740: 30(f16vec4) Load 739
+             741:712(f16vec3) VectorShuffle 740 740 0 1 2
+             742:712(f16vec3) GroupNonUniformQuadSwap 43 741 38
+             743:    703(ptr) AccessChain 34(data) 738 695
+             744: 30(f16vec4) Load 743
+             745: 30(f16vec4) VectorShuffle 744 742 4 5 6 3
+                              Store 743 745
+             746:      6(int) Load 8(invocation)
+             747:    703(ptr) AccessChain 34(data) 68 695
+             748: 30(f16vec4) Load 747
+             749: 30(f16vec4) GroupNonUniformQuadSwap 43 748 38
+             750:    703(ptr) AccessChain 34(data) 746 695
+                              Store 750 749
+             751:      6(int) Load 8(invocation)
+             752:    696(ptr) AccessChain 34(data) 37 695 38
+             753:29(float16_t) Load 752
+             754:29(float16_t) GroupNonUniformQuadSwap 43 753 42
+             755:    696(ptr) AccessChain 34(data) 751 695 38
+                              Store 755 754
+             756:      6(int) Load 8(invocation)
+             757:    703(ptr) AccessChain 34(data) 47 695
+             758: 30(f16vec4) Load 757
+             759:702(f16vec2) VectorShuffle 758 758 0 1
+             760:702(f16vec2) GroupNonUniformQuadSwap 43 759 42
+             761:    703(ptr) AccessChain 34(data) 756 695
+             762: 30(f16vec4) Load 761
+             763: 30(f16vec4) VectorShuffle 762 760 4 5 2 3
+                              Store 761 763
+             764:      6(int) Load 8(invocation)
+             765:    703(ptr) AccessChain 34(data) 58 695
+             766: 30(f16vec4) Load 765
+             767:712(f16vec3) VectorShuffle 766 766 0 1 2
+             768:712(f16vec3) GroupNonUniformQuadSwap 43 767 42
+             769:    703(ptr) AccessChain 34(data) 764 695
+             770: 30(f16vec4) Load 769
+             771: 30(f16vec4) VectorShuffle 770 768 4 5 6 3
+                              Store 769 771
+             772:      6(int) Load 8(invocation)
+             773:    703(ptr) AccessChain 34(data) 68 695
+             774: 30(f16vec4) Load 773
+             775: 30(f16vec4) GroupNonUniformQuadSwap 43 774 42
+             776:    703(ptr) AccessChain 34(data) 772 695
+                              Store 776 775
+             777:      6(int) Load 8(invocation)
+             778:    696(ptr) AccessChain 34(data) 37 695 38
+             779:29(float16_t) Load 778
+             780:29(float16_t) GroupNonUniformQuadSwap 43 779 128
+             781:    696(ptr) AccessChain 34(data) 777 695 38
+                              Store 781 780
+             782:      6(int) Load 8(invocation)
+             783:    703(ptr) AccessChain 34(data) 47 695
+             784: 30(f16vec4) Load 783
+             785:702(f16vec2) VectorShuffle 784 784 0 1
+             786:702(f16vec2) GroupNonUniformQuadSwap 43 785 128
+             787:    703(ptr) AccessChain 34(data) 782 695
+             788: 30(f16vec4) Load 787
+             789: 30(f16vec4) VectorShuffle 788 786 4 5 2 3
+                              Store 787 789
+             790:      6(int) Load 8(invocation)
+             791:    703(ptr) AccessChain 34(data) 58 695
+             792: 30(f16vec4) Load 791
+             793:712(f16vec3) VectorShuffle 792 792 0 1 2
+             794:712(f16vec3) GroupNonUniformQuadSwap 43 793 128
+             795:    703(ptr) AccessChain 34(data) 790 695
+             796: 30(f16vec4) Load 795
+             797: 30(f16vec4) VectorShuffle 796 794 4 5 6 3
+                              Store 795 797
+             798:      6(int) Load 8(invocation)
+             799:    703(ptr) AccessChain 34(data) 68 695
+             800: 30(f16vec4) Load 799
+             801: 30(f16vec4) GroupNonUniformQuadSwap 43 800 128
+             802:    703(ptr) AccessChain 34(data) 798 695
+                              Store 802 801
+                              Return
+                              FunctionEnd

Test/baseResults/spv.subgroupExtendedTypesQuadNeg.comp.out

@@ -0,0 +1,117 @@
+spv.subgroupExtendedTypesQuadNeg.comp
+ERROR: 0:26: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:27: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:28: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:29: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:31: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:33: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:34: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:36: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:38: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:39: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:41: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:42: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:43: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:44: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:46: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:47: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:48: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:49: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:51: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:52: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:53: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:54: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:56: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:57: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:58: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:59: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:61: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:62: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:63: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:64: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:66: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:67: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:68: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:69: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:71: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:72: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:73: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:74: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:76: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:77: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:78: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:79: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:81: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:82: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:83: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:84: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:86: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:87: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:88: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:89: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:91: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:92: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:93: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:94: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:96: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:97: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:98: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:99: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:101: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:102: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:103: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:104: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:106: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:107: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:108: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:109: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:111: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:112: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:113: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:114: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:116: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:117: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:118: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:119: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:121: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:122: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:123: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:124: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:126: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:127: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:128: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:129: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:131: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:132: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:133: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:134: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:136: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:137: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:138: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:139: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:141: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:142: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:143: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:144: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:146: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:147: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:148: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:149: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:151: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:152: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:153: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:154: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:156: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:157: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:158: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:159: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:161: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:162: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:163: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:164: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 112 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesShuffle.comp.out

@@ -0,0 +1,616 @@
+spv.subgroupExtendedTypesShuffle.comp
+// Module Version 10300
+// Generated by (magic number): 80007
+// Id's are bound by 497
+
+                              Capability Shader
+                              Capability Float16
+                              Capability Int64
+                              Capability Int16
+                              Capability Int8
+                              Capability GroupNonUniform
+                              Capability GroupNonUniformShuffle
+                              Capability StorageUniformBufferBlock16
+                              Capability StorageBuffer8BitAccess
+                              Extension  "SPV_KHR_8bit_storage"
+               1:             ExtInstImport  "GLSL.std.450"
+                              MemoryModel Logical GLSL450
+                              EntryPoint GLCompute 4  "main" 10 12
+                              ExecutionMode 4 LocalSize 8 1 1
+                              Source GLSL 450
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_float16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int64"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int8"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_float16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int64"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int8"
+                              SourceExtension  "GL_KHR_shader_subgroup_basic"
+                              SourceExtension  "GL_KHR_shader_subgroup_shuffle"
+                              Name 4  "main"
+                              Name 8  "invocation"
+                              Name 10  "gl_SubgroupInvocationID"
+                              Name 12  "gl_SubgroupSize"
+                              Name 31  "Buffers"
+                              MemberName 31(Buffers) 0  "i8"
+                              MemberName 31(Buffers) 1  "u8"
+                              MemberName 31(Buffers) 2  "i16"
+                              MemberName 31(Buffers) 3  "u16"
+                              MemberName 31(Buffers) 4  "i64"
+                              MemberName 31(Buffers) 5  "u64"
+                              MemberName 31(Buffers) 6  "f16"
+                              Name 34  "data"
+                              Decorate 10(gl_SubgroupInvocationID) RelaxedPrecision
+                              Decorate 10(gl_SubgroupInvocationID) BuiltIn SubgroupLocalInvocationId
+                              Decorate 11 RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) BuiltIn SubgroupSize
+                              Decorate 13 RelaxedPrecision
+                              Decorate 14 RelaxedPrecision
+                              Decorate 16 RelaxedPrecision
+                              MemberDecorate 31(Buffers) 0 Offset 0
+                              MemberDecorate 31(Buffers) 1 Offset 4
+                              MemberDecorate 31(Buffers) 2 Offset 8
+                              MemberDecorate 31(Buffers) 3 Offset 16
+                              MemberDecorate 31(Buffers) 4 Offset 32
+                              MemberDecorate 31(Buffers) 5 Offset 64
+                              MemberDecorate 31(Buffers) 6 Offset 96
+                              Decorate 31(Buffers) Block
+                              Decorate 34(data) DescriptorSet 0
+                              Decorate 34(data) Binding 0
+                              Decorate 496 BuiltIn WorkgroupSize
+               2:             TypeVoid
+               3:             TypeFunction 2
+               6:             TypeInt 32 0
+               7:             TypePointer Function 6(int)
+               9:             TypePointer Input 6(int)
+10(gl_SubgroupInvocationID):      9(ptr) Variable Input
+12(gl_SubgroupSize):      9(ptr) Variable Input
+              15:      6(int) Constant 4
+              17:             TypeInt 8 1
+              18:             TypeVector 17(int8_t) 4
+              19:             TypeInt 8 0
+              20:             TypeVector 19(int8_t) 4
+              21:             TypeInt 16 1
+              22:             TypeVector 21(int16_t) 4
+              23:             TypeInt 16 0
+              24:             TypeVector 23(int16_t) 4
+              25:             TypeInt 64 1
+              26:             TypeVector 25(int64_t) 4
+              27:             TypeInt 64 0
+              28:             TypeVector 27(int64_t) 4
+              29:             TypeFloat 16
+              30:             TypeVector 29(float16_t) 4
+     31(Buffers):             TypeStruct 18(i8vec4) 20(i8vec4) 22(i16vec4) 24(i16vec4) 26(i64vec4) 28(i64vec4) 30(f16vec4)
+              32:             TypeArray 31(Buffers) 15
+              33:             TypePointer StorageBuffer 32
+        34(data):     33(ptr) Variable StorageBuffer
+              36:             TypeInt 32 1
+              37:     36(int) Constant 0
+              38:      6(int) Constant 0
+              39:             TypePointer StorageBuffer 17(int8_t)
+              43:      6(int) Constant 3
+              47:     36(int) Constant 1
+              48:             TypeVector 17(int8_t) 2
+              49:             TypePointer StorageBuffer 18(i8vec4)
+              59:     36(int) Constant 2
+              60:             TypeVector 17(int8_t) 3
+              70:     36(int) Constant 3
+             107:             TypePointer StorageBuffer 19(int8_t)
+             114:             TypeVector 19(int8_t) 2
+             115:             TypePointer StorageBuffer 20(i8vec4)
+             125:             TypeVector 19(int8_t) 3
+             171:             TypePointer StorageBuffer 21(int16_t)
+             178:             TypeVector 21(int16_t) 2
+             179:             TypePointer StorageBuffer 22(i16vec4)
+             189:             TypeVector 21(int16_t) 3
+             235:             TypePointer StorageBuffer 23(int16_t)
+             242:             TypeVector 23(int16_t) 2
+             243:             TypePointer StorageBuffer 24(i16vec4)
+             253:             TypeVector 23(int16_t) 3
+             299:     36(int) Constant 4
+             300:             TypePointer StorageBuffer 25(int64_t)
+             307:             TypeVector 25(int64_t) 2
+             308:             TypePointer StorageBuffer 26(i64vec4)
+             318:             TypeVector 25(int64_t) 3
+             364:     36(int) Constant 5
+             365:             TypePointer StorageBuffer 27(int64_t)
+             372:             TypeVector 27(int64_t) 2
+             373:             TypePointer StorageBuffer 28(i64vec4)
+             383:             TypeVector 27(int64_t) 3
+             429:     36(int) Constant 6
+             430:             TypePointer StorageBuffer 29(float16_t)
+             437:             TypeVector 29(float16_t) 2
+             438:             TypePointer StorageBuffer 30(f16vec4)
+             448:             TypeVector 29(float16_t) 3
+             493:             TypeVector 6(int) 3
+             494:      6(int) Constant 8
+             495:      6(int) Constant 1
+             496:  493(ivec3) ConstantComposite 494 495 495
+         4(main):           2 Function None 3
+               5:             Label
+   8(invocation):      7(ptr) Variable Function
+              11:      6(int) Load 10(gl_SubgroupInvocationID)
+              13:      6(int) Load 12(gl_SubgroupSize)
+              14:      6(int) IAdd 11 13
+              16:      6(int) UMod 14 15
+                              Store 8(invocation) 16
+              35:      6(int) Load 8(invocation)
+              40:     39(ptr) AccessChain 34(data) 37 37 38
+              41:  17(int8_t) Load 40
+              42:      6(int) Load 8(invocation)
+              44:  17(int8_t) GroupNonUniformShuffle 43 41 42
+              45:     39(ptr) AccessChain 34(data) 35 37 38
+                              Store 45 44
+              46:      6(int) Load 8(invocation)
+              50:     49(ptr) AccessChain 34(data) 47 37
+              51:  18(i8vec4) Load 50
+              52:  48(i8vec2) VectorShuffle 51 51 0 1
+              53:      6(int) Load 8(invocation)
+              54:  48(i8vec2) GroupNonUniformShuffle 43 52 53
+              55:     49(ptr) AccessChain 34(data) 46 37
+              56:  18(i8vec4) Load 55
+              57:  18(i8vec4) VectorShuffle 56 54 4 5 2 3
+                              Store 55 57
+              58:      6(int) Load 8(invocation)
+              61:     49(ptr) AccessChain 34(data) 59 37
+              62:  18(i8vec4) Load 61
+              63:  60(i8vec3) VectorShuffle 62 62 0 1 2
+              64:      6(int) Load 8(invocation)
+              65:  60(i8vec3) GroupNonUniformShuffle 43 63 64
+              66:     49(ptr) AccessChain 34(data) 58 37
+              67:  18(i8vec4) Load 66
+              68:  18(i8vec4) VectorShuffle 67 65 4 5 6 3
+                              Store 66 68
+              69:      6(int) Load 8(invocation)
+              71:     49(ptr) AccessChain 34(data) 70 37
+              72:  18(i8vec4) Load 71
+              73:      6(int) Load 8(invocation)
+              74:  18(i8vec4) GroupNonUniformShuffle 43 72 73
+              75:     49(ptr) AccessChain 34(data) 69 37
+                              Store 75 74
+              76:      6(int) Load 8(invocation)
+              77:     39(ptr) AccessChain 34(data) 37 37 38
+              78:  17(int8_t) Load 77
+              79:      6(int) Load 8(invocation)
+              80:  17(int8_t) GroupNonUniformShuffleXor 43 78 79
+              81:     39(ptr) AccessChain 34(data) 76 37 38
+                              Store 81 80
+              82:      6(int) Load 8(invocation)
+              83:     49(ptr) AccessChain 34(data) 47 37
+              84:  18(i8vec4) Load 83
+              85:  48(i8vec2) VectorShuffle 84 84 0 1
+              86:      6(int) Load 8(invocation)
+              87:  48(i8vec2) GroupNonUniformShuffleXor 43 85 86
+              88:     49(ptr) AccessChain 34(data) 82 37
+              89:  18(i8vec4) Load 88
+              90:  18(i8vec4) VectorShuffle 89 87 4 5 2 3
+                              Store 88 90
+              91:      6(int) Load 8(invocation)
+              92:     49(ptr) AccessChain 34(data) 59 37
+              93:  18(i8vec4) Load 92
+              94:  60(i8vec3) VectorShuffle 93 93 0 1 2
+              95:      6(int) Load 8(invocation)
+              96:  60(i8vec3) GroupNonUniformShuffleXor 43 94 95
+              97:     49(ptr) AccessChain 34(data) 91 37
+              98:  18(i8vec4) Load 97
+              99:  18(i8vec4) VectorShuffle 98 96 4 5 6 3
+                              Store 97 99
+             100:      6(int) Load 8(invocation)
+             101:     49(ptr) AccessChain 34(data) 70 37
+             102:  18(i8vec4) Load 101
+             103:      6(int) Load 8(invocation)
+             104:  18(i8vec4) GroupNonUniformShuffleXor 43 102 103
+             105:     49(ptr) AccessChain 34(data) 100 37
+                              Store 105 104
+             106:      6(int) Load 8(invocation)
+             108:    107(ptr) AccessChain 34(data) 37 47 38
+             109:  19(int8_t) Load 108
+             110:      6(int) Load 8(invocation)
+             111:  19(int8_t) GroupNonUniformShuffle 43 109 110
+             112:    107(ptr) AccessChain 34(data) 106 47 38
+                              Store 112 111
+             113:      6(int) Load 8(invocation)
+             116:    115(ptr) AccessChain 34(data) 47 47
+             117:  20(i8vec4) Load 116
+             118: 114(i8vec2) VectorShuffle 117 117 0 1
+             119:      6(int) Load 8(invocation)
+             120: 114(i8vec2) GroupNonUniformShuffle 43 118 119
+             121:    115(ptr) AccessChain 34(data) 113 47
+             122:  20(i8vec4) Load 121
+             123:  20(i8vec4) VectorShuffle 122 120 4 5 2 3
+                              Store 121 123
+             124:      6(int) Load 8(invocation)
+             126:    115(ptr) AccessChain 34(data) 59 47
+             127:  20(i8vec4) Load 126
+             128: 125(i8vec3) VectorShuffle 127 127 0 1 2
+             129:      6(int) Load 8(invocation)
+             130: 125(i8vec3) GroupNonUniformShuffle 43 128 129
+             131:    115(ptr) AccessChain 34(data) 124 47
+             132:  20(i8vec4) Load 131
+             133:  20(i8vec4) VectorShuffle 132 130 4 5 6 3
+                              Store 131 133
+             134:      6(int) Load 8(invocation)
+             135:    115(ptr) AccessChain 34(data) 70 47
+             136:  20(i8vec4) Load 135
+             137:      6(int) Load 8(invocation)
+             138:  20(i8vec4) GroupNonUniformShuffle 43 136 137
+             139:    115(ptr) AccessChain 34(data) 134 47
+                              Store 139 138
+             140:      6(int) Load 8(invocation)
+             141:    107(ptr) AccessChain 34(data) 37 47 38
+             142:  19(int8_t) Load 141
+             143:      6(int) Load 8(invocation)
+             144:  19(int8_t) GroupNonUniformShuffleXor 43 142 143
+             145:    107(ptr) AccessChain 34(data) 140 47 38
+                              Store 145 144
+             146:      6(int) Load 8(invocation)
+             147:    115(ptr) AccessChain 34(data) 47 47
+             148:  20(i8vec4) Load 147
+             149: 114(i8vec2) VectorShuffle 148 148 0 1
+             150:      6(int) Load 8(invocation)
+             151: 114(i8vec2) GroupNonUniformShuffleXor 43 149 150
+             152:    115(ptr) AccessChain 34(data) 146 47
+             153:  20(i8vec4) Load 152
+             154:  20(i8vec4) VectorShuffle 153 151 4 5 2 3
+                              Store 152 154
+             155:      6(int) Load 8(invocation)
+             156:    115(ptr) AccessChain 34(data) 59 47
+             157:  20(i8vec4) Load 156
+             158: 125(i8vec3) VectorShuffle 157 157 0 1 2
+             159:      6(int) Load 8(invocation)
+             160: 125(i8vec3) GroupNonUniformShuffleXor 43 158 159
+             161:    115(ptr) AccessChain 34(data) 155 47
+             162:  20(i8vec4) Load 161
+             163:  20(i8vec4) VectorShuffle 162 160 4 5 6 3
+                              Store 161 163
+             164:      6(int) Load 8(invocation)
+             165:    115(ptr) AccessChain 34(data) 70 47
+             166:  20(i8vec4) Load 165
+             167:      6(int) Load 8(invocation)
+             168:  20(i8vec4) GroupNonUniformShuffleXor 43 166 167
+             169:    115(ptr) AccessChain 34(data) 164 47
+                              Store 169 168
+             170:      6(int) Load 8(invocation)
+             172:    171(ptr) AccessChain 34(data) 37 59 38
+             173: 21(int16_t) Load 172
+             174:      6(int) Load 8(invocation)
+             175: 21(int16_t) GroupNonUniformShuffle 43 173 174
+             176:    171(ptr) AccessChain 34(data) 170 59 38
+                              Store 176 175
+             177:      6(int) Load 8(invocation)
+             180:    179(ptr) AccessChain 34(data) 47 59
+             181: 22(i16vec4) Load 180
+             182:178(i16vec2) VectorShuffle 181 181 0 1
+             183:      6(int) Load 8(invocation)
+             184:178(i16vec2) GroupNonUniformShuffle 43 182 183
+             185:    179(ptr) AccessChain 34(data) 177 59
+             186: 22(i16vec4) Load 185
+             187: 22(i16vec4) VectorShuffle 186 184 4 5 2 3
+                              Store 185 187
+             188:      6(int) Load 8(invocation)
+             190:    179(ptr) AccessChain 34(data) 59 59
+             191: 22(i16vec4) Load 190
+             192:189(i16vec3) VectorShuffle 191 191 0 1 2
+             193:      6(int) Load 8(invocation)
+             194:189(i16vec3) GroupNonUniformShuffle 43 192 193
+             195:    179(ptr) AccessChain 34(data) 188 59
+             196: 22(i16vec4) Load 195
+             197: 22(i16vec4) VectorShuffle 196 194 4 5 6 3
+                              Store 195 197
+             198:      6(int) Load 8(invocation)
+             199:    179(ptr) AccessChain 34(data) 70 59
+             200: 22(i16vec4) Load 199
+             201:      6(int) Load 8(invocation)
+             202: 22(i16vec4) GroupNonUniformShuffle 43 200 201
+             203:    179(ptr) AccessChain 34(data) 198 59
+                              Store 203 202
+             204:      6(int) Load 8(invocation)
+             205:    171(ptr) AccessChain 34(data) 37 59 38
+             206: 21(int16_t) Load 205
+             207:      6(int) Load 8(invocation)
+             208: 21(int16_t) GroupNonUniformShuffleXor 43 206 207
+             209:    171(ptr) AccessChain 34(data) 204 59 38
+                              Store 209 208
+             210:      6(int) Load 8(invocation)
+             211:    179(ptr) AccessChain 34(data) 47 59
+             212: 22(i16vec4) Load 211
+             213:178(i16vec2) VectorShuffle 212 212 0 1
+             214:      6(int) Load 8(invocation)
+             215:178(i16vec2) GroupNonUniformShuffleXor 43 213 214
+             216:    179(ptr) AccessChain 34(data) 210 59
+             217: 22(i16vec4) Load 216
+             218: 22(i16vec4) VectorShuffle 217 215 4 5 2 3
+                              Store 216 218
+             219:      6(int) Load 8(invocation)
+             220:    179(ptr) AccessChain 34(data) 59 59
+             221: 22(i16vec4) Load 220
+             222:189(i16vec3) VectorShuffle 221 221 0 1 2
+             223:      6(int) Load 8(invocation)
+             224:189(i16vec3) GroupNonUniformShuffleXor 43 222 223
+             225:    179(ptr) AccessChain 34(data) 219 59
+             226: 22(i16vec4) Load 225
+             227: 22(i16vec4) VectorShuffle 226 224 4 5 6 3
+                              Store 225 227
+             228:      6(int) Load 8(invocation)
+             229:    179(ptr) AccessChain 34(data) 70 59
+             230: 22(i16vec4) Load 229
+             231:      6(int) Load 8(invocation)
+             232: 22(i16vec4) GroupNonUniformShuffleXor 43 230 231
+             233:    179(ptr) AccessChain 34(data) 228 59
+                              Store 233 232
+             234:      6(int) Load 8(invocation)
+             236:    235(ptr) AccessChain 34(data) 37 70 38
+             237: 23(int16_t) Load 236
+             238:      6(int) Load 8(invocation)
+             239: 23(int16_t) GroupNonUniformShuffle 43 237 238
+             240:    235(ptr) AccessChain 34(data) 234 70 38
+                              Store 240 239
+             241:      6(int) Load 8(invocation)
+             244:    243(ptr) AccessChain 34(data) 47 70
+             245: 24(i16vec4) Load 244
+             246:242(i16vec2) VectorShuffle 245 245 0 1
+             247:      6(int) Load 8(invocation)
+             248:242(i16vec2) GroupNonUniformShuffle 43 246 247
+             249:    243(ptr) AccessChain 34(data) 241 70
+             250: 24(i16vec4) Load 249
+             251: 24(i16vec4) VectorShuffle 250 248 4 5 2 3
+                              Store 249 251
+             252:      6(int) Load 8(invocation)
+             254:    243(ptr) AccessChain 34(data) 59 70
+             255: 24(i16vec4) Load 254
+             256:253(i16vec3) VectorShuffle 255 255 0 1 2
+             257:      6(int) Load 8(invocation)
+             258:253(i16vec3) GroupNonUniformShuffle 43 256 257
+             259:    243(ptr) AccessChain 34(data) 252 70
+             260: 24(i16vec4) Load 259
+             261: 24(i16vec4) VectorShuffle 260 258 4 5 6 3
+                              Store 259 261
+             262:      6(int) Load 8(invocation)
+             263:    243(ptr) AccessChain 34(data) 70 70
+             264: 24(i16vec4) Load 263
+             265:      6(int) Load 8(invocation)
+             266: 24(i16vec4) GroupNonUniformShuffle 43 264 265
+             267:    243(ptr) AccessChain 34(data) 262 70
+                              Store 267 266
+             268:      6(int) Load 8(invocation)
+             269:    235(ptr) AccessChain 34(data) 37 70 38
+             270: 23(int16_t) Load 269
+             271:      6(int) Load 8(invocation)
+             272: 23(int16_t) GroupNonUniformShuffleXor 43 270 271
+             273:    235(ptr) AccessChain 34(data) 268 70 38
+                              Store 273 272
+             274:      6(int) Load 8(invocation)
+             275:    243(ptr) AccessChain 34(data) 47 70
+             276: 24(i16vec4) Load 275
+             277:242(i16vec2) VectorShuffle 276 276 0 1
+             278:      6(int) Load 8(invocation)
+             279:242(i16vec2) GroupNonUniformShuffleXor 43 277 278
+             280:    243(ptr) AccessChain 34(data) 274 70
+             281: 24(i16vec4) Load 280
+             282: 24(i16vec4) VectorShuffle 281 279 4 5 2 3
+                              Store 280 282
+             283:      6(int) Load 8(invocation)
+             284:    243(ptr) AccessChain 34(data) 59 70
+             285: 24(i16vec4) Load 284
+             286:253(i16vec3) VectorShuffle 285 285 0 1 2
+             287:      6(int) Load 8(invocation)
+             288:253(i16vec3) GroupNonUniformShuffleXor 43 286 287
+             289:    243(ptr) AccessChain 34(data) 283 70
+             290: 24(i16vec4) Load 289
+             291: 24(i16vec4) VectorShuffle 290 288 4 5 6 3
+                              Store 289 291
+             292:      6(int) Load 8(invocation)
+             293:    243(ptr) AccessChain 34(data) 70 70
+             294: 24(i16vec4) Load 293
+             295:      6(int) Load 8(invocation)
+             296: 24(i16vec4) GroupNonUniformShuffleXor 43 294 295
+             297:    243(ptr) AccessChain 34(data) 292 70
+                              Store 297 296
+             298:      6(int) Load 8(invocation)
+             301:    300(ptr) AccessChain 34(data) 37 299 38
+             302: 25(int64_t) Load 301
+             303:      6(int) Load 8(invocation)
+             304: 25(int64_t) GroupNonUniformShuffle 43 302 303
+             305:    300(ptr) AccessChain 34(data) 298 299 38
+                              Store 305 304
+             306:      6(int) Load 8(invocation)
+             309:    308(ptr) AccessChain 34(data) 47 299
+             310: 26(i64vec4) Load 309
+             311:307(i64vec2) VectorShuffle 310 310 0 1
+             312:      6(int) Load 8(invocation)
+             313:307(i64vec2) GroupNonUniformShuffle 43 311 312
+             314:    308(ptr) AccessChain 34(data) 306 299
+             315: 26(i64vec4) Load 314
+             316: 26(i64vec4) VectorShuffle 315 313 4 5 2 3
+                              Store 314 316
+             317:      6(int) Load 8(invocation)
+             319:    308(ptr) AccessChain 34(data) 59 299
+             320: 26(i64vec4) Load 319
+             321:318(i64vec3) VectorShuffle 320 320 0 1 2
+             322:      6(int) Load 8(invocation)
+             323:318(i64vec3) GroupNonUniformShuffle 43 321 322
+             324:    308(ptr) AccessChain 34(data) 317 299
+             325: 26(i64vec4) Load 324
+             326: 26(i64vec4) VectorShuffle 325 323 4 5 6 3
+                              Store 324 326
+             327:      6(int) Load 8(invocation)
+             328:    308(ptr) AccessChain 34(data) 70 299
+             329: 26(i64vec4) Load 328
+             330:      6(int) Load 8(invocation)
+             331: 26(i64vec4) GroupNonUniformShuffle 43 329 330
+             332:    308(ptr) AccessChain 34(data) 327 299
+                              Store 332 331
+             333:      6(int) Load 8(invocation)
+             334:    300(ptr) AccessChain 34(data) 37 299 38
+             335: 25(int64_t) Load 334
+             336:      6(int) Load 8(invocation)
+             337: 25(int64_t) GroupNonUniformShuffleXor 43 335 336
+             338:    300(ptr) AccessChain 34(data) 333 299 38
+                              Store 338 337
+             339:      6(int) Load 8(invocation)
+             340:    308(ptr) AccessChain 34(data) 47 299
+             341: 26(i64vec4) Load 340
+             342:307(i64vec2) VectorShuffle 341 341 0 1
+             343:      6(int) Load 8(invocation)
+             344:307(i64vec2) GroupNonUniformShuffleXor 43 342 343
+             345:    308(ptr) AccessChain 34(data) 339 299
+             346: 26(i64vec4) Load 345
+             347: 26(i64vec4) VectorShuffle 346 344 4 5 2 3
+                              Store 345 347
+             348:      6(int) Load 8(invocation)
+             349:    308(ptr) AccessChain 34(data) 59 299
+             350: 26(i64vec4) Load 349
+             351:318(i64vec3) VectorShuffle 350 350 0 1 2
+             352:      6(int) Load 8(invocation)
+             353:318(i64vec3) GroupNonUniformShuffleXor 43 351 352
+             354:    308(ptr) AccessChain 34(data) 348 299
+             355: 26(i64vec4) Load 354
+             356: 26(i64vec4) VectorShuffle 355 353 4 5 6 3
+                              Store 354 356
+             357:      6(int) Load 8(invocation)
+             358:    308(ptr) AccessChain 34(data) 70 299
+             359: 26(i64vec4) Load 358
+             360:      6(int) Load 8(invocation)
+             361: 26(i64vec4) GroupNonUniformShuffleXor 43 359 360
+             362:    308(ptr) AccessChain 34(data) 357 299
+                              Store 362 361
+             363:      6(int) Load 8(invocation)
+             366:    365(ptr) AccessChain 34(data) 37 364 38
+             367: 27(int64_t) Load 366
+             368:      6(int) Load 8(invocation)
+             369: 27(int64_t) GroupNonUniformShuffle 43 367 368
+             370:    365(ptr) AccessChain 34(data) 363 364 38
+                              Store 370 369
+             371:      6(int) Load 8(invocation)
+             374:    373(ptr) AccessChain 34(data) 47 364
+             375: 28(i64vec4) Load 374
+             376:372(i64vec2) VectorShuffle 375 375 0 1
+             377:      6(int) Load 8(invocation)
+             378:372(i64vec2) GroupNonUniformShuffle 43 376 377
+             379:    373(ptr) AccessChain 34(data) 371 364
+             380: 28(i64vec4) Load 379
+             381: 28(i64vec4) VectorShuffle 380 378 4 5 2 3
+                              Store 379 381
+             382:      6(int) Load 8(invocation)
+             384:    373(ptr) AccessChain 34(data) 59 364
+             385: 28(i64vec4) Load 384
+             386:383(i64vec3) VectorShuffle 385 385 0 1 2
+             387:      6(int) Load 8(invocation)
+             388:383(i64vec3) GroupNonUniformShuffle 43 386 387
+             389:    373(ptr) AccessChain 34(data) 382 364
+             390: 28(i64vec4) Load 389
+             391: 28(i64vec4) VectorShuffle 390 388 4 5 6 3
+                              Store 389 391
+             392:      6(int) Load 8(invocation)
+             393:    373(ptr) AccessChain 34(data) 70 364
+             394: 28(i64vec4) Load 393
+             395:      6(int) Load 8(invocation)
+             396: 28(i64vec4) GroupNonUniformShuffle 43 394 395
+             397:    373(ptr) AccessChain 34(data) 392 364
+                              Store 397 396
+             398:      6(int) Load 8(invocation)
+             399:    365(ptr) AccessChain 34(data) 37 364 38
+             400: 27(int64_t) Load 399
+             401:      6(int) Load 8(invocation)
+             402: 27(int64_t) GroupNonUniformShuffleXor 43 400 401
+             403:    365(ptr) AccessChain 34(data) 398 364 38
+                              Store 403 402
+             404:      6(int) Load 8(invocation)
+             405:    373(ptr) AccessChain 34(data) 47 364
+             406: 28(i64vec4) Load 405
+             407:372(i64vec2) VectorShuffle 406 406 0 1
+             408:      6(int) Load 8(invocation)
+             409:372(i64vec2) GroupNonUniformShuffleXor 43 407 408
+             410:    373(ptr) AccessChain 34(data) 404 364
+             411: 28(i64vec4) Load 410
+             412: 28(i64vec4) VectorShuffle 411 409 4 5 2 3
+                              Store 410 412
+             413:      6(int) Load 8(invocation)
+             414:    373(ptr) AccessChain 34(data) 59 364
+             415: 28(i64vec4) Load 414
+             416:383(i64vec3) VectorShuffle 415 415 0 1 2
+             417:      6(int) Load 8(invocation)
+             418:383(i64vec3) GroupNonUniformShuffleXor 43 416 417
+             419:    373(ptr) AccessChain 34(data) 413 364
+             420: 28(i64vec4) Load 419
+             421: 28(i64vec4) VectorShuffle 420 418 4 5 6 3
+                              Store 419 421
+             422:      6(int) Load 8(invocation)
+             423:    373(ptr) AccessChain 34(data) 70 364
+             424: 28(i64vec4) Load 423
+             425:      6(int) Load 8(invocation)
+             426: 28(i64vec4) GroupNonUniformShuffleXor 43 424 425
+             427:    373(ptr) AccessChain 34(data) 422 364
+                              Store 427 426
+             428:      6(int) Load 8(invocation)
+             431:    430(ptr) AccessChain 34(data) 37 429 38
+             432:29(float16_t) Load 431
+             433:      6(int) Load 8(invocation)
+             434:29(float16_t) GroupNonUniformShuffle 43 432 433
+             435:    430(ptr) AccessChain 34(data) 428 429 38
+                              Store 435 434
+             436:      6(int) Load 8(invocation)
+             439:    438(ptr) AccessChain 34(data) 47 429
+             440: 30(f16vec4) Load 439
+             441:437(f16vec2) VectorShuffle 440 440 0 1
+             442:      6(int) Load 8(invocation)
+             443:437(f16vec2) GroupNonUniformShuffle 43 441 442
+             444:    438(ptr) AccessChain 34(data) 436 429
+             445: 30(f16vec4) Load 444
+             446: 30(f16vec4) VectorShuffle 445 443 4 5 2 3
+                              Store 444 446
+             447:      6(int) Load 8(invocation)
+             449:    438(ptr) AccessChain 34(data) 59 429
+             450: 30(f16vec4) Load 449
+             451:448(f16vec3) VectorShuffle 450 450 0 1 2
+             452:      6(int) Load 8(invocation)
+             453:448(f16vec3) GroupNonUniformShuffle 43 451 452
+             454:    438(ptr) AccessChain 34(data) 447 429
+             455: 30(f16vec4) Load 454
+             456: 30(f16vec4) VectorShuffle 455 453 4 5 6 3
+                              Store 454 456
+             457:      6(int) Load 8(invocation)
+             458:    438(ptr) AccessChain 34(data) 70 429
+             459: 30(f16vec4) Load 458
+             460:      6(int) Load 8(invocation)
+             461: 30(f16vec4) GroupNonUniformShuffle 43 459 460
+             462:    438(ptr) AccessChain 34(data) 457 429
+                              Store 462 461
+             463:      6(int) Load 8(invocation)
+             464:    430(ptr) AccessChain 34(data) 37 429 38
+             465:29(float16_t) Load 464
+             466:      6(int) Load 8(invocation)
+             467:29(float16_t) GroupNonUniformShuffleXor 43 465 466
+             468:    430(ptr) AccessChain 34(data) 463 429 38
+                              Store 468 467
+             469:      6(int) Load 8(invocation)
+             470:    438(ptr) AccessChain 34(data) 47 429
+             471: 30(f16vec4) Load 470
+             472:437(f16vec2) VectorShuffle 471 471 0 1
+             473:      6(int) Load 8(invocation)
+             474:437(f16vec2) GroupNonUniformShuffleXor 43 472 473
+             475:    438(ptr) AccessChain 34(data) 469 429
+             476: 30(f16vec4) Load 475
+             477: 30(f16vec4) VectorShuffle 476 474 4 5 2 3
+                              Store 475 477
+             478:      6(int) Load 8(invocation)
+             479:    438(ptr) AccessChain 34(data) 59 429
+             480: 30(f16vec4) Load 479
+             481:448(f16vec3) VectorShuffle 480 480 0 1 2
+             482:      6(int) Load 8(invocation)
+             483:448(f16vec3) GroupNonUniformShuffleXor 43 481 482
+             484:    438(ptr) AccessChain 34(data) 478 429
+             485: 30(f16vec4) Load 484
+             486: 30(f16vec4) VectorShuffle 485 483 4 5 6 3
+                              Store 484 486
+             487:      6(int) Load 8(invocation)
+             488:    438(ptr) AccessChain 34(data) 70 429
+             489: 30(f16vec4) Load 488
+             490:      6(int) Load 8(invocation)
+             491: 30(f16vec4) GroupNonUniformShuffleXor 43 489 490
+             492:    438(ptr) AccessChain 34(data) 487 429
+                              Store 492 491
+                              Return
+                              FunctionEnd

Test/baseResults/spv.subgroupExtendedTypesShuffleNeg.comp.out

@@ -0,0 +1,61 @@
+spv.subgroupExtendedTypesShuffleNeg.comp
+ERROR: 0:26: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:27: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:28: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:29: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:31: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:33: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:34: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:36: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:38: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:39: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:41: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:42: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:43: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:44: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:46: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:47: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:48: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:49: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:51: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:52: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:53: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:54: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:56: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:57: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:58: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:59: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:61: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:62: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:63: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:64: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:66: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:67: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:68: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:69: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:71: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:72: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:73: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:74: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:76: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:77: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:78: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:79: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:81: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:82: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:83: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:84: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:86: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:87: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:88: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:89: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:91: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:92: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:93: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:94: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 56 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesShuffleRelative.comp.out

@@ -0,0 +1,616 @@
+spv.subgroupExtendedTypesShuffleRelative.comp
+// Module Version 10300
+// Generated by (magic number): 80007
+// Id's are bound by 497
+
+                              Capability Shader
+                              Capability Float16
+                              Capability Int64
+                              Capability Int16
+                              Capability Int8
+                              Capability GroupNonUniform
+                              Capability GroupNonUniformShuffleRelative
+                              Capability StorageUniformBufferBlock16
+                              Capability StorageBuffer8BitAccess
+                              Extension  "SPV_KHR_8bit_storage"
+               1:             ExtInstImport  "GLSL.std.450"
+                              MemoryModel Logical GLSL450
+                              EntryPoint GLCompute 4  "main" 10 12
+                              ExecutionMode 4 LocalSize 8 1 1
+                              Source GLSL 450
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_float16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int64"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int8"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_float16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int64"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int8"
+                              SourceExtension  "GL_KHR_shader_subgroup_basic"
+                              SourceExtension  "GL_KHR_shader_subgroup_shuffle_relative"
+                              Name 4  "main"
+                              Name 8  "invocation"
+                              Name 10  "gl_SubgroupInvocationID"
+                              Name 12  "gl_SubgroupSize"
+                              Name 31  "Buffers"
+                              MemberName 31(Buffers) 0  "i8"
+                              MemberName 31(Buffers) 1  "u8"
+                              MemberName 31(Buffers) 2  "i16"
+                              MemberName 31(Buffers) 3  "u16"
+                              MemberName 31(Buffers) 4  "i64"
+                              MemberName 31(Buffers) 5  "u64"
+                              MemberName 31(Buffers) 6  "f16"
+                              Name 34  "data"
+                              Decorate 10(gl_SubgroupInvocationID) RelaxedPrecision
+                              Decorate 10(gl_SubgroupInvocationID) BuiltIn SubgroupLocalInvocationId
+                              Decorate 11 RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) BuiltIn SubgroupSize
+                              Decorate 13 RelaxedPrecision
+                              Decorate 14 RelaxedPrecision
+                              Decorate 16 RelaxedPrecision
+                              MemberDecorate 31(Buffers) 0 Offset 0
+                              MemberDecorate 31(Buffers) 1 Offset 4
+                              MemberDecorate 31(Buffers) 2 Offset 8
+                              MemberDecorate 31(Buffers) 3 Offset 16
+                              MemberDecorate 31(Buffers) 4 Offset 32
+                              MemberDecorate 31(Buffers) 5 Offset 64
+                              MemberDecorate 31(Buffers) 6 Offset 96
+                              Decorate 31(Buffers) Block
+                              Decorate 34(data) DescriptorSet 0
+                              Decorate 34(data) Binding 0
+                              Decorate 496 BuiltIn WorkgroupSize
+               2:             TypeVoid
+               3:             TypeFunction 2
+               6:             TypeInt 32 0
+               7:             TypePointer Function 6(int)
+               9:             TypePointer Input 6(int)
+10(gl_SubgroupInvocationID):      9(ptr) Variable Input
+12(gl_SubgroupSize):      9(ptr) Variable Input
+              15:      6(int) Constant 4
+              17:             TypeInt 8 1
+              18:             TypeVector 17(int8_t) 4
+              19:             TypeInt 8 0
+              20:             TypeVector 19(int8_t) 4
+              21:             TypeInt 16 1
+              22:             TypeVector 21(int16_t) 4
+              23:             TypeInt 16 0
+              24:             TypeVector 23(int16_t) 4
+              25:             TypeInt 64 1
+              26:             TypeVector 25(int64_t) 4
+              27:             TypeInt 64 0
+              28:             TypeVector 27(int64_t) 4
+              29:             TypeFloat 16
+              30:             TypeVector 29(float16_t) 4
+     31(Buffers):             TypeStruct 18(i8vec4) 20(i8vec4) 22(i16vec4) 24(i16vec4) 26(i64vec4) 28(i64vec4) 30(f16vec4)
+              32:             TypeArray 31(Buffers) 15
+              33:             TypePointer StorageBuffer 32
+        34(data):     33(ptr) Variable StorageBuffer
+              36:             TypeInt 32 1
+              37:     36(int) Constant 0
+              38:      6(int) Constant 0
+              39:             TypePointer StorageBuffer 17(int8_t)
+              43:      6(int) Constant 3
+              47:     36(int) Constant 1
+              48:             TypeVector 17(int8_t) 2
+              49:             TypePointer StorageBuffer 18(i8vec4)
+              59:     36(int) Constant 2
+              60:             TypeVector 17(int8_t) 3
+              70:     36(int) Constant 3
+             107:             TypePointer StorageBuffer 19(int8_t)
+             114:             TypeVector 19(int8_t) 2
+             115:             TypePointer StorageBuffer 20(i8vec4)
+             125:             TypeVector 19(int8_t) 3
+             171:             TypePointer StorageBuffer 21(int16_t)
+             178:             TypeVector 21(int16_t) 2
+             179:             TypePointer StorageBuffer 22(i16vec4)
+             189:             TypeVector 21(int16_t) 3
+             235:             TypePointer StorageBuffer 23(int16_t)
+             242:             TypeVector 23(int16_t) 2
+             243:             TypePointer StorageBuffer 24(i16vec4)
+             253:             TypeVector 23(int16_t) 3
+             299:     36(int) Constant 4
+             300:             TypePointer StorageBuffer 25(int64_t)
+             307:             TypeVector 25(int64_t) 2
+             308:             TypePointer StorageBuffer 26(i64vec4)
+             318:             TypeVector 25(int64_t) 3
+             364:     36(int) Constant 5
+             365:             TypePointer StorageBuffer 27(int64_t)
+             372:             TypeVector 27(int64_t) 2
+             373:             TypePointer StorageBuffer 28(i64vec4)
+             383:             TypeVector 27(int64_t) 3
+             429:     36(int) Constant 6
+             430:             TypePointer StorageBuffer 29(float16_t)
+             437:             TypeVector 29(float16_t) 2
+             438:             TypePointer StorageBuffer 30(f16vec4)
+             448:             TypeVector 29(float16_t) 3
+             493:             TypeVector 6(int) 3
+             494:      6(int) Constant 8
+             495:      6(int) Constant 1
+             496:  493(ivec3) ConstantComposite 494 495 495
+         4(main):           2 Function None 3
+               5:             Label
+   8(invocation):      7(ptr) Variable Function
+              11:      6(int) Load 10(gl_SubgroupInvocationID)
+              13:      6(int) Load 12(gl_SubgroupSize)
+              14:      6(int) IAdd 11 13
+              16:      6(int) UMod 14 15
+                              Store 8(invocation) 16
+              35:      6(int) Load 8(invocation)
+              40:     39(ptr) AccessChain 34(data) 37 37 38
+              41:  17(int8_t) Load 40
+              42:      6(int) Load 8(invocation)
+              44:  17(int8_t) GroupNonUniformShuffleUp 43 41 42
+              45:     39(ptr) AccessChain 34(data) 35 37 38
+                              Store 45 44
+              46:      6(int) Load 8(invocation)
+              50:     49(ptr) AccessChain 34(data) 47 37
+              51:  18(i8vec4) Load 50
+              52:  48(i8vec2) VectorShuffle 51 51 0 1
+              53:      6(int) Load 8(invocation)
+              54:  48(i8vec2) GroupNonUniformShuffleUp 43 52 53
+              55:     49(ptr) AccessChain 34(data) 46 37
+              56:  18(i8vec4) Load 55
+              57:  18(i8vec4) VectorShuffle 56 54 4 5 2 3
+                              Store 55 57
+              58:      6(int) Load 8(invocation)
+              61:     49(ptr) AccessChain 34(data) 59 37
+              62:  18(i8vec4) Load 61
+              63:  60(i8vec3) VectorShuffle 62 62 0 1 2
+              64:      6(int) Load 8(invocation)
+              65:  60(i8vec3) GroupNonUniformShuffleUp 43 63 64
+              66:     49(ptr) AccessChain 34(data) 58 37
+              67:  18(i8vec4) Load 66
+              68:  18(i8vec4) VectorShuffle 67 65 4 5 6 3
+                              Store 66 68
+              69:      6(int) Load 8(invocation)
+              71:     49(ptr) AccessChain 34(data) 70 37
+              72:  18(i8vec4) Load 71
+              73:      6(int) Load 8(invocation)
+              74:  18(i8vec4) GroupNonUniformShuffleUp 43 72 73
+              75:     49(ptr) AccessChain 34(data) 69 37
+                              Store 75 74
+              76:      6(int) Load 8(invocation)
+              77:     39(ptr) AccessChain 34(data) 37 37 38
+              78:  17(int8_t) Load 77
+              79:      6(int) Load 8(invocation)
+              80:  17(int8_t) GroupNonUniformShuffleDown 43 78 79
+              81:     39(ptr) AccessChain 34(data) 76 37 38
+                              Store 81 80
+              82:      6(int) Load 8(invocation)
+              83:     49(ptr) AccessChain 34(data) 47 37
+              84:  18(i8vec4) Load 83
+              85:  48(i8vec2) VectorShuffle 84 84 0 1
+              86:      6(int) Load 8(invocation)
+              87:  48(i8vec2) GroupNonUniformShuffleDown 43 85 86
+              88:     49(ptr) AccessChain 34(data) 82 37
+              89:  18(i8vec4) Load 88
+              90:  18(i8vec4) VectorShuffle 89 87 4 5 2 3
+                              Store 88 90
+              91:      6(int) Load 8(invocation)
+              92:     49(ptr) AccessChain 34(data) 59 37
+              93:  18(i8vec4) Load 92
+              94:  60(i8vec3) VectorShuffle 93 93 0 1 2
+              95:      6(int) Load 8(invocation)
+              96:  60(i8vec3) GroupNonUniformShuffleDown 43 94 95
+              97:     49(ptr) AccessChain 34(data) 91 37
+              98:  18(i8vec4) Load 97
+              99:  18(i8vec4) VectorShuffle 98 96 4 5 6 3
+                              Store 97 99
+             100:      6(int) Load 8(invocation)
+             101:     49(ptr) AccessChain 34(data) 70 37
+             102:  18(i8vec4) Load 101
+             103:      6(int) Load 8(invocation)
+             104:  18(i8vec4) GroupNonUniformShuffleDown 43 102 103
+             105:     49(ptr) AccessChain 34(data) 100 37
+                              Store 105 104
+             106:      6(int) Load 8(invocation)
+             108:    107(ptr) AccessChain 34(data) 37 47 38
+             109:  19(int8_t) Load 108
+             110:      6(int) Load 8(invocation)
+             111:  19(int8_t) GroupNonUniformShuffleUp 43 109 110
+             112:    107(ptr) AccessChain 34(data) 106 47 38
+                              Store 112 111
+             113:      6(int) Load 8(invocation)
+             116:    115(ptr) AccessChain 34(data) 47 47
+             117:  20(i8vec4) Load 116
+             118: 114(i8vec2) VectorShuffle 117 117 0 1
+             119:      6(int) Load 8(invocation)
+             120: 114(i8vec2) GroupNonUniformShuffleUp 43 118 119
+             121:    115(ptr) AccessChain 34(data) 113 47
+             122:  20(i8vec4) Load 121
+             123:  20(i8vec4) VectorShuffle 122 120 4 5 2 3
+                              Store 121 123
+             124:      6(int) Load 8(invocation)
+             126:    115(ptr) AccessChain 34(data) 59 47
+             127:  20(i8vec4) Load 126
+             128: 125(i8vec3) VectorShuffle 127 127 0 1 2
+             129:      6(int) Load 8(invocation)
+             130: 125(i8vec3) GroupNonUniformShuffleUp 43 128 129
+             131:    115(ptr) AccessChain 34(data) 124 47
+             132:  20(i8vec4) Load 131
+             133:  20(i8vec4) VectorShuffle 132 130 4 5 6 3
+                              Store 131 133
+             134:      6(int) Load 8(invocation)
+             135:    115(ptr) AccessChain 34(data) 70 47
+             136:  20(i8vec4) Load 135
+             137:      6(int) Load 8(invocation)
+             138:  20(i8vec4) GroupNonUniformShuffleUp 43 136 137
+             139:    115(ptr) AccessChain 34(data) 134 47
+                              Store 139 138
+             140:      6(int) Load 8(invocation)
+             141:    107(ptr) AccessChain 34(data) 37 47 38
+             142:  19(int8_t) Load 141
+             143:      6(int) Load 8(invocation)
+             144:  19(int8_t) GroupNonUniformShuffleDown 43 142 143
+             145:    107(ptr) AccessChain 34(data) 140 47 38
+                              Store 145 144
+             146:      6(int) Load 8(invocation)
+             147:    115(ptr) AccessChain 34(data) 47 47
+             148:  20(i8vec4) Load 147
+             149: 114(i8vec2) VectorShuffle 148 148 0 1
+             150:      6(int) Load 8(invocation)
+             151: 114(i8vec2) GroupNonUniformShuffleDown 43 149 150
+             152:    115(ptr) AccessChain 34(data) 146 47
+             153:  20(i8vec4) Load 152
+             154:  20(i8vec4) VectorShuffle 153 151 4 5 2 3
+                              Store 152 154
+             155:      6(int) Load 8(invocation)
+             156:    115(ptr) AccessChain 34(data) 59 47
+             157:  20(i8vec4) Load 156
+             158: 125(i8vec3) VectorShuffle 157 157 0 1 2
+             159:      6(int) Load 8(invocation)
+             160: 125(i8vec3) GroupNonUniformShuffleDown 43 158 159
+             161:    115(ptr) AccessChain 34(data) 155 47
+             162:  20(i8vec4) Load 161
+             163:  20(i8vec4) VectorShuffle 162 160 4 5 6 3
+                              Store 161 163
+             164:      6(int) Load 8(invocation)
+             165:    115(ptr) AccessChain 34(data) 70 47
+             166:  20(i8vec4) Load 165
+             167:      6(int) Load 8(invocation)
+             168:  20(i8vec4) GroupNonUniformShuffleDown 43 166 167
+             169:    115(ptr) AccessChain 34(data) 164 47
+                              Store 169 168
+             170:      6(int) Load 8(invocation)
+             172:    171(ptr) AccessChain 34(data) 37 59 38
+             173: 21(int16_t) Load 172
+             174:      6(int) Load 8(invocation)
+             175: 21(int16_t) GroupNonUniformShuffleUp 43 173 174
+             176:    171(ptr) AccessChain 34(data) 170 59 38
+                              Store 176 175
+             177:      6(int) Load 8(invocation)
+             180:    179(ptr) AccessChain 34(data) 47 59
+             181: 22(i16vec4) Load 180
+             182:178(i16vec2) VectorShuffle 181 181 0 1
+             183:      6(int) Load 8(invocation)
+             184:178(i16vec2) GroupNonUniformShuffleUp 43 182 183
+             185:    179(ptr) AccessChain 34(data) 177 59
+             186: 22(i16vec4) Load 185
+             187: 22(i16vec4) VectorShuffle 186 184 4 5 2 3
+                              Store 185 187
+             188:      6(int) Load 8(invocation)
+             190:    179(ptr) AccessChain 34(data) 59 59
+             191: 22(i16vec4) Load 190
+             192:189(i16vec3) VectorShuffle 191 191 0 1 2
+             193:      6(int) Load 8(invocation)
+             194:189(i16vec3) GroupNonUniformShuffleUp 43 192 193
+             195:    179(ptr) AccessChain 34(data) 188 59
+             196: 22(i16vec4) Load 195
+             197: 22(i16vec4) VectorShuffle 196 194 4 5 6 3
+                              Store 195 197
+             198:      6(int) Load 8(invocation)
+             199:    179(ptr) AccessChain 34(data) 70 59
+             200: 22(i16vec4) Load 199
+             201:      6(int) Load 8(invocation)
+             202: 22(i16vec4) GroupNonUniformShuffleUp 43 200 201
+             203:    179(ptr) AccessChain 34(data) 198 59
+                              Store 203 202
+             204:      6(int) Load 8(invocation)
+             205:    171(ptr) AccessChain 34(data) 37 59 38
+             206: 21(int16_t) Load 205
+             207:      6(int) Load 8(invocation)
+             208: 21(int16_t) GroupNonUniformShuffleDown 43 206 207
+             209:    171(ptr) AccessChain 34(data) 204 59 38
+                              Store 209 208
+             210:      6(int) Load 8(invocation)
+             211:    179(ptr) AccessChain 34(data) 47 59
+             212: 22(i16vec4) Load 211
+             213:178(i16vec2) VectorShuffle 212 212 0 1
+             214:      6(int) Load 8(invocation)
+             215:178(i16vec2) GroupNonUniformShuffleDown 43 213 214
+             216:    179(ptr) AccessChain 34(data) 210 59
+             217: 22(i16vec4) Load 216
+             218: 22(i16vec4) VectorShuffle 217 215 4 5 2 3
+                              Store 216 218
+             219:      6(int) Load 8(invocation)
+             220:    179(ptr) AccessChain 34(data) 59 59
+             221: 22(i16vec4) Load 220
+             222:189(i16vec3) VectorShuffle 221 221 0 1 2
+             223:      6(int) Load 8(invocation)
+             224:189(i16vec3) GroupNonUniformShuffleDown 43 222 223
+             225:    179(ptr) AccessChain 34(data) 219 59
+             226: 22(i16vec4) Load 225
+             227: 22(i16vec4) VectorShuffle 226 224 4 5 6 3
+                              Store 225 227
+             228:      6(int) Load 8(invocation)
+             229:    179(ptr) AccessChain 34(data) 70 59
+             230: 22(i16vec4) Load 229
+             231:      6(int) Load 8(invocation)
+             232: 22(i16vec4) GroupNonUniformShuffleDown 43 230 231
+             233:    179(ptr) AccessChain 34(data) 228 59
+                              Store 233 232
+             234:      6(int) Load 8(invocation)
+             236:    235(ptr) AccessChain 34(data) 37 70 38
+             237: 23(int16_t) Load 236
+             238:      6(int) Load 8(invocation)
+             239: 23(int16_t) GroupNonUniformShuffleUp 43 237 238
+             240:    235(ptr) AccessChain 34(data) 234 70 38
+                              Store 240 239
+             241:      6(int) Load 8(invocation)
+             244:    243(ptr) AccessChain 34(data) 47 70
+             245: 24(i16vec4) Load 244
+             246:242(i16vec2) VectorShuffle 245 245 0 1
+             247:      6(int) Load 8(invocation)
+             248:242(i16vec2) GroupNonUniformShuffleUp 43 246 247
+             249:    243(ptr) AccessChain 34(data) 241 70
+             250: 24(i16vec4) Load 249
+             251: 24(i16vec4) VectorShuffle 250 248 4 5 2 3
+                              Store 249 251
+             252:      6(int) Load 8(invocation)
+             254:    243(ptr) AccessChain 34(data) 59 70
+             255: 24(i16vec4) Load 254
+             256:253(i16vec3) VectorShuffle 255 255 0 1 2
+             257:      6(int) Load 8(invocation)
+             258:253(i16vec3) GroupNonUniformShuffleUp 43 256 257
+             259:    243(ptr) AccessChain 34(data) 252 70
+             260: 24(i16vec4) Load 259
+             261: 24(i16vec4) VectorShuffle 260 258 4 5 6 3
+                              Store 259 261
+             262:      6(int) Load 8(invocation)
+             263:    243(ptr) AccessChain 34(data) 70 70
+             264: 24(i16vec4) Load 263
+             265:      6(int) Load 8(invocation)
+             266: 24(i16vec4) GroupNonUniformShuffleUp 43 264 265
+             267:    243(ptr) AccessChain 34(data) 262 70
+                              Store 267 266
+             268:      6(int) Load 8(invocation)
+             269:    235(ptr) AccessChain 34(data) 37 70 38
+             270: 23(int16_t) Load 269
+             271:      6(int) Load 8(invocation)
+             272: 23(int16_t) GroupNonUniformShuffleDown 43 270 271
+             273:    235(ptr) AccessChain 34(data) 268 70 38
+                              Store 273 272
+             274:      6(int) Load 8(invocation)
+             275:    243(ptr) AccessChain 34(data) 47 70
+             276: 24(i16vec4) Load 275
+             277:242(i16vec2) VectorShuffle 276 276 0 1
+             278:      6(int) Load 8(invocation)
+             279:242(i16vec2) GroupNonUniformShuffleDown 43 277 278
+             280:    243(ptr) AccessChain 34(data) 274 70
+             281: 24(i16vec4) Load 280
+             282: 24(i16vec4) VectorShuffle 281 279 4 5 2 3
+                              Store 280 282
+             283:      6(int) Load 8(invocation)
+             284:    243(ptr) AccessChain 34(data) 59 70
+             285: 24(i16vec4) Load 284
+             286:253(i16vec3) VectorShuffle 285 285 0 1 2
+             287:      6(int) Load 8(invocation)
+             288:253(i16vec3) GroupNonUniformShuffleDown 43 286 287
+             289:    243(ptr) AccessChain 34(data) 283 70
+             290: 24(i16vec4) Load 289
+             291: 24(i16vec4) VectorShuffle 290 288 4 5 6 3
+                              Store 289 291
+             292:      6(int) Load 8(invocation)
+             293:    243(ptr) AccessChain 34(data) 70 70
+             294: 24(i16vec4) Load 293
+             295:      6(int) Load 8(invocation)
+             296: 24(i16vec4) GroupNonUniformShuffleDown 43 294 295
+             297:    243(ptr) AccessChain 34(data) 292 70
+                              Store 297 296
+             298:      6(int) Load 8(invocation)
+             301:    300(ptr) AccessChain 34(data) 37 299 38
+             302: 25(int64_t) Load 301
+             303:      6(int) Load 8(invocation)
+             304: 25(int64_t) GroupNonUniformShuffleUp 43 302 303
+             305:    300(ptr) AccessChain 34(data) 298 299 38
+                              Store 305 304
+             306:      6(int) Load 8(invocation)
+             309:    308(ptr) AccessChain 34(data) 47 299
+             310: 26(i64vec4) Load 309
+             311:307(i64vec2) VectorShuffle 310 310 0 1
+             312:      6(int) Load 8(invocation)
+             313:307(i64vec2) GroupNonUniformShuffleUp 43 311 312
+             314:    308(ptr) AccessChain 34(data) 306 299
+             315: 26(i64vec4) Load 314
+             316: 26(i64vec4) VectorShuffle 315 313 4 5 2 3
+                              Store 314 316
+             317:      6(int) Load 8(invocation)
+             319:    308(ptr) AccessChain 34(data) 59 299
+             320: 26(i64vec4) Load 319
+             321:318(i64vec3) VectorShuffle 320 320 0 1 2
+             322:      6(int) Load 8(invocation)
+             323:318(i64vec3) GroupNonUniformShuffleUp 43 321 322
+             324:    308(ptr) AccessChain 34(data) 317 299
+             325: 26(i64vec4) Load 324
+             326: 26(i64vec4) VectorShuffle 325 323 4 5 6 3
+                              Store 324 326
+             327:      6(int) Load 8(invocation)
+             328:    308(ptr) AccessChain 34(data) 70 299
+             329: 26(i64vec4) Load 328
+             330:      6(int) Load 8(invocation)
+             331: 26(i64vec4) GroupNonUniformShuffleUp 43 329 330
+             332:    308(ptr) AccessChain 34(data) 327 299
+                              Store 332 331
+             333:      6(int) Load 8(invocation)
+             334:    300(ptr) AccessChain 34(data) 37 299 38
+             335: 25(int64_t) Load 334
+             336:      6(int) Load 8(invocation)
+             337: 25(int64_t) GroupNonUniformShuffleDown 43 335 336
+             338:    300(ptr) AccessChain 34(data) 333 299 38
+                              Store 338 337
+             339:      6(int) Load 8(invocation)
+             340:    308(ptr) AccessChain 34(data) 47 299
+             341: 26(i64vec4) Load 340
+             342:307(i64vec2) VectorShuffle 341 341 0 1
+             343:      6(int) Load 8(invocation)
+             344:307(i64vec2) GroupNonUniformShuffleDown 43 342 343
+             345:    308(ptr) AccessChain 34(data) 339 299
+             346: 26(i64vec4) Load 345
+             347: 26(i64vec4) VectorShuffle 346 344 4 5 2 3
+                              Store 345 347
+             348:      6(int) Load 8(invocation)
+             349:    308(ptr) AccessChain 34(data) 59 299
+             350: 26(i64vec4) Load 349
+             351:318(i64vec3) VectorShuffle 350 350 0 1 2
+             352:      6(int) Load 8(invocation)
+             353:318(i64vec3) GroupNonUniformShuffleDown 43 351 352
+             354:    308(ptr) AccessChain 34(data) 348 299
+             355: 26(i64vec4) Load 354
+             356: 26(i64vec4) VectorShuffle 355 353 4 5 6 3
+                              Store 354 356
+             357:      6(int) Load 8(invocation)
+             358:    308(ptr) AccessChain 34(data) 70 299
+             359: 26(i64vec4) Load 358
+             360:      6(int) Load 8(invocation)
+             361: 26(i64vec4) GroupNonUniformShuffleDown 43 359 360
+             362:    308(ptr) AccessChain 34(data) 357 299
+                              Store 362 361
+             363:      6(int) Load 8(invocation)
+             366:    365(ptr) AccessChain 34(data) 37 364 38
+             367: 27(int64_t) Load 366
+             368:      6(int) Load 8(invocation)
+             369: 27(int64_t) GroupNonUniformShuffleUp 43 367 368
+             370:    365(ptr) AccessChain 34(data) 363 364 38
+                              Store 370 369
+             371:      6(int) Load 8(invocation)
+             374:    373(ptr) AccessChain 34(data) 47 364
+             375: 28(i64vec4) Load 374
+             376:372(i64vec2) VectorShuffle 375 375 0 1
+             377:      6(int) Load 8(invocation)
+             378:372(i64vec2) GroupNonUniformShuffleUp 43 376 377
+             379:    373(ptr) AccessChain 34(data) 371 364
+             380: 28(i64vec4) Load 379
+             381: 28(i64vec4) VectorShuffle 380 378 4 5 2 3
+                              Store 379 381
+             382:      6(int) Load 8(invocation)
+             384:    373(ptr) AccessChain 34(data) 59 364
+             385: 28(i64vec4) Load 384
+             386:383(i64vec3) VectorShuffle 385 385 0 1 2
+             387:      6(int) Load 8(invocation)
+             388:383(i64vec3) GroupNonUniformShuffleUp 43 386 387
+             389:    373(ptr) AccessChain 34(data) 382 364
+             390: 28(i64vec4) Load 389
+             391: 28(i64vec4) VectorShuffle 390 388 4 5 6 3
+                              Store 389 391
+             392:      6(int) Load 8(invocation)
+             393:    373(ptr) AccessChain 34(data) 70 364
+             394: 28(i64vec4) Load 393
+             395:      6(int) Load 8(invocation)
+             396: 28(i64vec4) GroupNonUniformShuffleUp 43 394 395
+             397:    373(ptr) AccessChain 34(data) 392 364
+                              Store 397 396
+             398:      6(int) Load 8(invocation)
+             399:    365(ptr) AccessChain 34(data) 37 364 38
+             400: 27(int64_t) Load 399
+             401:      6(int) Load 8(invocation)
+             402: 27(int64_t) GroupNonUniformShuffleDown 43 400 401
+             403:    365(ptr) AccessChain 34(data) 398 364 38
+                              Store 403 402
+             404:      6(int) Load 8(invocation)
+             405:    373(ptr) AccessChain 34(data) 47 364
+             406: 28(i64vec4) Load 405
+             407:372(i64vec2) VectorShuffle 406 406 0 1
+             408:      6(int) Load 8(invocation)
+             409:372(i64vec2) GroupNonUniformShuffleDown 43 407 408
+             410:    373(ptr) AccessChain 34(data) 404 364
+             411: 28(i64vec4) Load 410
+             412: 28(i64vec4) VectorShuffle 411 409 4 5 2 3
+                              Store 410 412
+             413:      6(int) Load 8(invocation)
+             414:    373(ptr) AccessChain 34(data) 59 364
+             415: 28(i64vec4) Load 414
+             416:383(i64vec3) VectorShuffle 415 415 0 1 2
+             417:      6(int) Load 8(invocation)
+             418:383(i64vec3) GroupNonUniformShuffleDown 43 416 417
+             419:    373(ptr) AccessChain 34(data) 413 364
+             420: 28(i64vec4) Load 419
+             421: 28(i64vec4) VectorShuffle 420 418 4 5 6 3
+                              Store 419 421
+             422:      6(int) Load 8(invocation)
+             423:    373(ptr) AccessChain 34(data) 70 364
+             424: 28(i64vec4) Load 423
+             425:      6(int) Load 8(invocation)
+             426: 28(i64vec4) GroupNonUniformShuffleDown 43 424 425
+             427:    373(ptr) AccessChain 34(data) 422 364
+                              Store 427 426
+             428:      6(int) Load 8(invocation)
+             431:    430(ptr) AccessChain 34(data) 37 429 38
+             432:29(float16_t) Load 431
+             433:      6(int) Load 8(invocation)
+             434:29(float16_t) GroupNonUniformShuffleUp 43 432 433
+             435:    430(ptr) AccessChain 34(data) 428 429 38
+                              Store 435 434
+             436:      6(int) Load 8(invocation)
+             439:    438(ptr) AccessChain 34(data) 47 429
+             440: 30(f16vec4) Load 439
+             441:437(f16vec2) VectorShuffle 440 440 0 1
+             442:      6(int) Load 8(invocation)
+             443:437(f16vec2) GroupNonUniformShuffleUp 43 441 442
+             444:    438(ptr) AccessChain 34(data) 436 429
+             445: 30(f16vec4) Load 444
+             446: 30(f16vec4) VectorShuffle 445 443 4 5 2 3
+                              Store 444 446
+             447:      6(int) Load 8(invocation)
+             449:    438(ptr) AccessChain 34(data) 59 429
+             450: 30(f16vec4) Load 449
+             451:448(f16vec3) VectorShuffle 450 450 0 1 2
+             452:      6(int) Load 8(invocation)
+             453:448(f16vec3) GroupNonUniformShuffleUp 43 451 452
+             454:    438(ptr) AccessChain 34(data) 447 429
+             455: 30(f16vec4) Load 454
+             456: 30(f16vec4) VectorShuffle 455 453 4 5 6 3
+                              Store 454 456
+             457:      6(int) Load 8(invocation)
+             458:    438(ptr) AccessChain 34(data) 70 429
+             459: 30(f16vec4) Load 458
+             460:      6(int) Load 8(invocation)
+             461: 30(f16vec4) GroupNonUniformShuffleUp 43 459 460
+             462:    438(ptr) AccessChain 34(data) 457 429
+                              Store 462 461
+             463:      6(int) Load 8(invocation)
+             464:    430(ptr) AccessChain 34(data) 37 429 38
+             465:29(float16_t) Load 464
+             466:      6(int) Load 8(invocation)
+             467:29(float16_t) GroupNonUniformShuffleDown 43 465 466
+             468:    430(ptr) AccessChain 34(data) 463 429 38
+                              Store 468 467
+             469:      6(int) Load 8(invocation)
+             470:    438(ptr) AccessChain 34(data) 47 429
+             471: 30(f16vec4) Load 470
+             472:437(f16vec2) VectorShuffle 471 471 0 1
+             473:      6(int) Load 8(invocation)
+             474:437(f16vec2) GroupNonUniformShuffleDown 43 472 473
+             475:    438(ptr) AccessChain 34(data) 469 429
+             476: 30(f16vec4) Load 475
+             477: 30(f16vec4) VectorShuffle 476 474 4 5 2 3
+                              Store 475 477
+             478:      6(int) Load 8(invocation)
+             479:    438(ptr) AccessChain 34(data) 59 429
+             480: 30(f16vec4) Load 479
+             481:448(f16vec3) VectorShuffle 480 480 0 1 2
+             482:      6(int) Load 8(invocation)
+             483:448(f16vec3) GroupNonUniformShuffleDown 43 481 482
+             484:    438(ptr) AccessChain 34(data) 478 429
+             485: 30(f16vec4) Load 484
+             486: 30(f16vec4) VectorShuffle 485 483 4 5 6 3
+                              Store 484 486
+             487:      6(int) Load 8(invocation)
+             488:    438(ptr) AccessChain 34(data) 70 429
+             489: 30(f16vec4) Load 488
+             490:      6(int) Load 8(invocation)
+             491: 30(f16vec4) GroupNonUniformShuffleDown 43 489 490
+             492:    438(ptr) AccessChain 34(data) 487 429
+                              Store 492 491
+                              Return
+                              FunctionEnd

Test/baseResults/spv.subgroupExtendedTypesShuffleRelativeNeg.comp.out

@@ -0,0 +1,61 @@
+spv.subgroupExtendedTypesShuffleRelativeNeg.comp
+ERROR: 0:26: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:27: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:28: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:29: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:31: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:33: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:34: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:36: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:38: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:39: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:41: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:42: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:43: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:44: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:46: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:47: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:48: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:49: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:51: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:52: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:53: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:54: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:56: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:57: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:58: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:59: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:61: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:62: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:63: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:64: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:66: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:67: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:68: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:69: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:71: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:72: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:73: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:74: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:76: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:77: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:78: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:79: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:81: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:82: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:83: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:84: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:86: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:87: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:88: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:89: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:91: ' temp highp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:92: ' temp highp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:93: ' temp highp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:94: 'layout( column_major std430) buffer highp 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 56 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/baseResults/spv.subgroupExtendedTypesVote.comp.out

@@ -0,0 +1,377 @@
+spv.subgroupExtendedTypesVote.comp
+// Module Version 10300
+// Generated by (magic number): 80007
+// Id's are bound by 277
+
+                              Capability Shader
+                              Capability Float16
+                              Capability Int64
+                              Capability Int16
+                              Capability Int8
+                              Capability GroupNonUniform
+                              Capability GroupNonUniformVote
+                              Capability StorageUniformBufferBlock16
+                              Capability StorageBuffer8BitAccess
+                              Extension  "SPV_KHR_8bit_storage"
+               1:             ExtInstImport  "GLSL.std.450"
+                              MemoryModel Logical GLSL450
+                              EntryPoint GLCompute 4  "main" 10 12
+                              ExecutionMode 4 LocalSize 8 1 1
+                              Source GLSL 450
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_float16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int16"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int64"
+                              SourceExtension  "GL_EXT_shader_explicit_arithmetic_types_int8"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_float16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int16"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int64"
+                              SourceExtension  "GL_EXT_shader_subgroup_extended_types_int8"
+                              SourceExtension  "GL_KHR_shader_subgroup_basic"
+                              SourceExtension  "GL_KHR_shader_subgroup_vote"
+                              Name 4  "main"
+                              Name 8  "invocation"
+                              Name 10  "gl_SubgroupInvocationID"
+                              Name 12  "gl_SubgroupSize"
+                              Name 32  "Buffers"
+                              MemberName 32(Buffers) 0  "i8"
+                              MemberName 32(Buffers) 1  "u8"
+                              MemberName 32(Buffers) 2  "i16"
+                              MemberName 32(Buffers) 3  "u16"
+                              MemberName 32(Buffers) 4  "i64"
+                              MemberName 32(Buffers) 5  "u64"
+                              MemberName 32(Buffers) 6  "f16"
+                              MemberName 32(Buffers) 7  "r"
+                              Name 35  "data"
+                              Decorate 10(gl_SubgroupInvocationID) RelaxedPrecision
+                              Decorate 10(gl_SubgroupInvocationID) BuiltIn SubgroupLocalInvocationId
+                              Decorate 11 RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) RelaxedPrecision
+                              Decorate 12(gl_SubgroupSize) BuiltIn SubgroupSize
+                              Decorate 13 RelaxedPrecision
+                              Decorate 14 RelaxedPrecision
+                              Decorate 16 RelaxedPrecision
+                              MemberDecorate 32(Buffers) 0 Offset 0
+                              MemberDecorate 32(Buffers) 1 Offset 4
+                              MemberDecorate 32(Buffers) 2 Offset 8
+                              MemberDecorate 32(Buffers) 3 Offset 16
+                              MemberDecorate 32(Buffers) 4 Offset 32
+                              MemberDecorate 32(Buffers) 5 Offset 64
+                              MemberDecorate 32(Buffers) 6 Offset 96
+                              MemberDecorate 32(Buffers) 7 Offset 104
+                              Decorate 32(Buffers) Block
+                              Decorate 35(data) DescriptorSet 0
+                              Decorate 35(data) Binding 0
+                              Decorate 276 BuiltIn WorkgroupSize
+               2:             TypeVoid
+               3:             TypeFunction 2
+               6:             TypeInt 32 0
+               7:             TypePointer Function 6(int)
+               9:             TypePointer Input 6(int)
+10(gl_SubgroupInvocationID):      9(ptr) Variable Input
+12(gl_SubgroupSize):      9(ptr) Variable Input
+              15:      6(int) Constant 4
+              17:             TypeInt 8 1
+              18:             TypeVector 17(int8_t) 4
+              19:             TypeInt 8 0
+              20:             TypeVector 19(int8_t) 4
+              21:             TypeInt 16 1
+              22:             TypeVector 21(int16_t) 4
+              23:             TypeInt 16 0
+              24:             TypeVector 23(int16_t) 4
+              25:             TypeInt 64 1
+              26:             TypeVector 25(int64_t) 4
+              27:             TypeInt 64 0
+              28:             TypeVector 27(int64_t) 4
+              29:             TypeFloat 16
+              30:             TypeVector 29(float16_t) 4
+              31:             TypeInt 32 1
+     32(Buffers):             TypeStruct 18(i8vec4) 20(i8vec4) 22(i16vec4) 24(i16vec4) 26(i64vec4) 28(i64vec4) 30(f16vec4) 31(int)
+              33:             TypeArray 32(Buffers) 15
+              34:             TypePointer StorageBuffer 33
+        35(data):     34(ptr) Variable StorageBuffer
+              37:     31(int) Constant 7
+              38:             TypePointer StorageBuffer 31(int)
+              41:     31(int) Constant 0
+              42:             TypeBool
+              44:      6(int) Constant 3
+              49:      6(int) Constant 0
+              50:             TypePointer StorageBuffer 17(int8_t)
+              54:     31(int) Constant 1
+              58:             TypeVector 17(int8_t) 2
+              59:             TypePointer StorageBuffer 18(i8vec4)
+              67:     31(int) Constant 2
+              68:             TypeVector 17(int8_t) 3
+              76:     31(int) Constant 3
+              83:             TypePointer StorageBuffer 19(int8_t)
+              90:             TypeVector 19(int8_t) 2
+              91:             TypePointer StorageBuffer 20(i8vec4)
+              99:             TypeVector 19(int8_t) 3
+             113:             TypePointer StorageBuffer 21(int16_t)
+             120:             TypeVector 21(int16_t) 2
+             121:             TypePointer StorageBuffer 22(i16vec4)
+             129:             TypeVector 21(int16_t) 3
+             143:             TypePointer StorageBuffer 23(int16_t)
+             150:             TypeVector 23(int16_t) 2
+             151:             TypePointer StorageBuffer 24(i16vec4)
+             159:             TypeVector 23(int16_t) 3
+             181:     31(int) Constant 4
+             182:             TypePointer StorageBuffer 25(int64_t)
+             189:             TypeVector 25(int64_t) 2
+             190:             TypePointer StorageBuffer 26(i64vec4)
+             198:             TypeVector 25(int64_t) 3
+             212:     31(int) Constant 5
+             213:             TypePointer StorageBuffer 27(int64_t)
+             220:             TypeVector 27(int64_t) 2
+             221:             TypePointer StorageBuffer 28(i64vec4)
+             229:             TypeVector 27(int64_t) 3
+             243:     31(int) Constant 6
+             244:             TypePointer StorageBuffer 29(float16_t)
+             251:             TypeVector 29(float16_t) 2
+             252:             TypePointer StorageBuffer 30(f16vec4)
+             260:             TypeVector 29(float16_t) 3
+             273:             TypeVector 6(int) 3
+             274:      6(int) Constant 8
+             275:      6(int) Constant 1
+             276:  273(ivec3) ConstantComposite 274 275 275
+         4(main):           2 Function None 3
+               5:             Label
+   8(invocation):      7(ptr) Variable Function
+              11:      6(int) Load 10(gl_SubgroupInvocationID)
+              13:      6(int) Load 12(gl_SubgroupSize)
+              14:      6(int) IAdd 11 13
+              16:      6(int) UMod 14 15
+                              Store 8(invocation) 16
+              36:      6(int) Load 8(invocation)
+              39:     38(ptr) AccessChain 35(data) 36 37
+              40:     31(int) Load 39
+              43:    42(bool) SLessThan 40 41
+              45:    42(bool) GroupNonUniformAll 44 43
+                              SelectionMerge 47 None
+                              BranchConditional 45 46 172
+              46:               Label
+              48:      6(int)   Load 8(invocation)
+              51:     50(ptr)   AccessChain 35(data) 41 41 49
+              52:  17(int8_t)   Load 51
+              53:    42(bool)   GroupNonUniformAllEqual 44 52
+              55:     31(int)   Select 53 54 41
+              56:     38(ptr)   AccessChain 35(data) 48 37
+                                Store 56 55
+              57:      6(int)   Load 8(invocation)
+              60:     59(ptr)   AccessChain 35(data) 54 41
+              61:  18(i8vec4)   Load 60
+              62:  58(i8vec2)   VectorShuffle 61 61 0 1
+              63:    42(bool)   GroupNonUniformAllEqual 44 62
+              64:     31(int)   Select 63 54 41
+              65:     38(ptr)   AccessChain 35(data) 57 37
+                                Store 65 64
+              66:      6(int)   Load 8(invocation)
+              69:     59(ptr)   AccessChain 35(data) 67 41
+              70:  18(i8vec4)   Load 69
+              71:  68(i8vec3)   VectorShuffle 70 70 0 1 2
+              72:    42(bool)   GroupNonUniformAllEqual 44 71
+              73:     31(int)   Select 72 54 41
+              74:     38(ptr)   AccessChain 35(data) 66 37
+                                Store 74 73
+              75:      6(int)   Load 8(invocation)
+              77:     59(ptr)   AccessChain 35(data) 76 41
+              78:  18(i8vec4)   Load 77
+              79:    42(bool)   GroupNonUniformAllEqual 44 78
+              80:     31(int)   Select 79 54 41
+              81:     38(ptr)   AccessChain 35(data) 75 37
+                                Store 81 80
+              82:      6(int)   Load 8(invocation)
+              84:     83(ptr)   AccessChain 35(data) 41 54 49
+              85:  19(int8_t)   Load 84
+              86:    42(bool)   GroupNonUniformAllEqual 44 85
+              87:     31(int)   Select 86 54 41
+              88:     38(ptr)   AccessChain 35(data) 82 37
+                                Store 88 87
+              89:      6(int)   Load 8(invocation)
+              92:     91(ptr)   AccessChain 35(data) 54 54
+              93:  20(i8vec4)   Load 92
+              94:  90(i8vec2)   VectorShuffle 93 93 0 1
+              95:    42(bool)   GroupNonUniformAllEqual 44 94
+              96:     31(int)   Select 95 54 41
+              97:     38(ptr)   AccessChain 35(data) 89 37
+                                Store 97 96
+              98:      6(int)   Load 8(invocation)
+             100:     91(ptr)   AccessChain 35(data) 67 54
+             101:  20(i8vec4)   Load 100
+             102:  99(i8vec3)   VectorShuffle 101 101 0 1 2
+             103:    42(bool)   GroupNonUniformAllEqual 44 102
+             104:     31(int)   Select 103 54 41
+             105:     38(ptr)   AccessChain 35(data) 98 37
+                                Store 105 104
+             106:      6(int)   Load 8(invocation)
+             107:     91(ptr)   AccessChain 35(data) 76 54
+             108:  20(i8vec4)   Load 107
+             109:    42(bool)   GroupNonUniformAllEqual 44 108
+             110:     31(int)   Select 109 54 41
+             111:     38(ptr)   AccessChain 35(data) 106 37
+                                Store 111 110
+             112:      6(int)   Load 8(invocation)
+             114:    113(ptr)   AccessChain 35(data) 41 67 49
+             115: 21(int16_t)   Load 114
+             116:    42(bool)   GroupNonUniformAllEqual 44 115
+             117:     31(int)   Select 116 54 41
+             118:     38(ptr)   AccessChain 35(data) 112 37
+                                Store 118 117
+             119:      6(int)   Load 8(invocation)
+             122:    121(ptr)   AccessChain 35(data) 54 67
+             123: 22(i16vec4)   Load 122
+             124:120(i16vec2)   VectorShuffle 123 123 0 1
+             125:    42(bool)   GroupNonUniformAllEqual 44 124
+             126:     31(int)   Select 125 54 41
+             127:     38(ptr)   AccessChain 35(data) 119 37
+                                Store 127 126
+             128:      6(int)   Load 8(invocation)
+             130:    121(ptr)   AccessChain 35(data) 67 67
+             131: 22(i16vec4)   Load 130
+             132:129(i16vec3)   VectorShuffle 131 131 0 1 2
+             133:    42(bool)   GroupNonUniformAllEqual 44 132
+             134:     31(int)   Select 133 54 41
+             135:     38(ptr)   AccessChain 35(data) 128 37
+                                Store 135 134
+             136:      6(int)   Load 8(invocation)
+             137:    121(ptr)   AccessChain 35(data) 76 67
+             138: 22(i16vec4)   Load 137
+             139:    42(bool)   GroupNonUniformAllEqual 44 138
+             140:     31(int)   Select 139 54 41
+             141:     38(ptr)   AccessChain 35(data) 136 37
+                                Store 141 140
+             142:      6(int)   Load 8(invocation)
+             144:    143(ptr)   AccessChain 35(data) 41 76 49
+             145: 23(int16_t)   Load 144
+             146:    42(bool)   GroupNonUniformAllEqual 44 145
+             147:     31(int)   Select 146 54 41
+             148:     38(ptr)   AccessChain 35(data) 142 37
+                                Store 148 147
+             149:      6(int)   Load 8(invocation)
+             152:    151(ptr)   AccessChain 35(data) 54 76
+             153: 24(i16vec4)   Load 152
+             154:150(i16vec2)   VectorShuffle 153 153 0 1
+             155:    42(bool)   GroupNonUniformAllEqual 44 154
+             156:     31(int)   Select 155 54 41
+             157:     38(ptr)   AccessChain 35(data) 149 37
+                                Store 157 156
+             158:      6(int)   Load 8(invocation)
+             160:    151(ptr)   AccessChain 35(data) 67 76
+             161: 24(i16vec4)   Load 160
+             162:159(i16vec3)   VectorShuffle 161 161 0 1 2
+             163:    42(bool)   GroupNonUniformAllEqual 44 162
+             164:     31(int)   Select 163 54 41
+             165:     38(ptr)   AccessChain 35(data) 158 37
+                                Store 165 164
+             166:      6(int)   Load 8(invocation)
+             167:    151(ptr)   AccessChain 35(data) 76 76
+             168: 24(i16vec4)   Load 167
+             169:    42(bool)   GroupNonUniformAllEqual 44 168
+             170:     31(int)   Select 169 54 41
+             171:     38(ptr)   AccessChain 35(data) 166 37
+                                Store 171 170
+                                Branch 47
+             172:               Label
+             173:      6(int)   Load 8(invocation)
+             174:     38(ptr)   AccessChain 35(data) 173 37
+             175:     31(int)   Load 174
+             176:    42(bool)   SLessThan 175 41
+             177:    42(bool)   GroupNonUniformAny 44 176
+                                SelectionMerge 179 None
+                                BranchConditional 177 178 179
+             178:                 Label
+             180:      6(int)     Load 8(invocation)
+             183:    182(ptr)     AccessChain 35(data) 41 181 49
+             184: 25(int64_t)     Load 183
+             185:    42(bool)     GroupNonUniformAllEqual 44 184
+             186:     31(int)     Select 185 54 41
+             187:     38(ptr)     AccessChain 35(data) 180 37
+                                  Store 187 186
+             188:      6(int)     Load 8(invocation)
+             191:    190(ptr)     AccessChain 35(data) 54 181
+             192: 26(i64vec4)     Load 191
+             193:189(i64vec2)     VectorShuffle 192 192 0 1
+             194:    42(bool)     GroupNonUniformAllEqual 44 193
+             195:     31(int)     Select 194 54 41
+             196:     38(ptr)     AccessChain 35(data) 188 37
+                                  Store 196 195
+             197:      6(int)     Load 8(invocation)
+             199:    190(ptr)     AccessChain 35(data) 67 181
+             200: 26(i64vec4)     Load 199
+             201:198(i64vec3)     VectorShuffle 200 200 0 1 2
+             202:    42(bool)     GroupNonUniformAllEqual 44 201
+             203:     31(int)     Select 202 54 41
+             204:     38(ptr)     AccessChain 35(data) 197 37
+                                  Store 204 203
+             205:      6(int)     Load 8(invocation)
+             206:    190(ptr)     AccessChain 35(data) 76 181
+             207: 26(i64vec4)     Load 206
+             208:    42(bool)     GroupNonUniformAllEqual 44 207
+             209:     31(int)     Select 208 54 41
+             210:     38(ptr)     AccessChain 35(data) 205 37
+                                  Store 210 209
+             211:      6(int)     Load 8(invocation)
+             214:    213(ptr)     AccessChain 35(data) 41 212 49
+             215: 27(int64_t)     Load 214
+             216:    42(bool)     GroupNonUniformAllEqual 44 215
+             217:     31(int)     Select 216 54 41
+             218:     38(ptr)     AccessChain 35(data) 211 37
+                                  Store 218 217
+             219:      6(int)     Load 8(invocation)
+             222:    221(ptr)     AccessChain 35(data) 54 212
+             223: 28(i64vec4)     Load 222
+             224:220(i64vec2)     VectorShuffle 223 223 0 1
+             225:    42(bool)     GroupNonUniformAllEqual 44 224
+             226:     31(int)     Select 225 54 41
+             227:     38(ptr)     AccessChain 35(data) 219 37
+                                  Store 227 226
+             228:      6(int)     Load 8(invocation)
+             230:    221(ptr)     AccessChain 35(data) 67 212
+             231: 28(i64vec4)     Load 230
+             232:229(i64vec3)     VectorShuffle 231 231 0 1 2
+             233:    42(bool)     GroupNonUniformAllEqual 44 232
+             234:     31(int)     Select 233 54 41
+             235:     38(ptr)     AccessChain 35(data) 228 37
+                                  Store 235 234
+             236:      6(int)     Load 8(invocation)
+             237:    221(ptr)     AccessChain 35(data) 76 212
+             238: 28(i64vec4)     Load 237
+             239:    42(bool)     GroupNonUniformAllEqual 44 238
+             240:     31(int)     Select 239 54 41
+             241:     38(ptr)     AccessChain 35(data) 236 37
+                                  Store 241 240
+             242:      6(int)     Load 8(invocation)
+             245:    244(ptr)     AccessChain 35(data) 41 243 49
+             246:29(float16_t)     Load 245
+             247:    42(bool)     GroupNonUniformAllEqual 44 246
+             248:     31(int)     Select 247 54 41
+             249:     38(ptr)     AccessChain 35(data) 242 37
+                                  Store 249 248
+             250:      6(int)     Load 8(invocation)
+             253:    252(ptr)     AccessChain 35(data) 54 243
+             254: 30(f16vec4)     Load 253
+             255:251(f16vec2)     VectorShuffle 254 254 0 1
+             256:    42(bool)     GroupNonUniformAllEqual 44 255
+             257:     31(int)     Select 256 54 41
+             258:     38(ptr)     AccessChain 35(data) 250 37
+                                  Store 258 257
+             259:      6(int)     Load 8(invocation)
+             261:    252(ptr)     AccessChain 35(data) 67 243
+             262: 30(f16vec4)     Load 261
+             263:260(f16vec3)     VectorShuffle 262 262 0 1 2
+             264:    42(bool)     GroupNonUniformAllEqual 44 263
+             265:     31(int)     Select 264 54 41
+             266:     38(ptr)     AccessChain 35(data) 259 37
+                                  Store 266 265
+             267:      6(int)     Load 8(invocation)
+             268:    252(ptr)     AccessChain 35(data) 76 243
+             269: 30(f16vec4)     Load 268
+             270:    42(bool)     GroupNonUniformAllEqual 44 269
+             271:     31(int)     Select 270 54 41
+             272:     38(ptr)     AccessChain 35(data) 267 37
+                                  Store 272 271
+                                  Branch 179
+             179:               Label
+                                Branch 47
+              47:             Label
+                              Return
+                              FunctionEnd

Test/baseResults/spv.subgroupExtendedTypesVoteNeg.comp.out

@@ -0,0 +1,33 @@
+spv.subgroupExtendedTypesVoteNeg.comp
+ERROR: 0:29: ' temp int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:30: ' temp 2-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:31: ' temp 3-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:32: 'layout( column_major std430) buffer 4-component vector of int8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:34: ' temp uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:35: ' temp 2-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:36: ' temp 3-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:37: 'layout( column_major std430) buffer 4-component vector of uint8_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int8
+ERROR: 0:39: ' temp int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:40: ' temp 2-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:41: ' temp 3-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:42: 'layout( column_major std430) buffer 4-component vector of int16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:44: ' temp uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:45: ' temp 2-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:46: ' temp 3-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:47: 'layout( column_major std430) buffer 4-component vector of uint16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int16
+ERROR: 0:51: ' temp int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:52: ' temp 2-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:53: ' temp 3-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:54: 'layout( column_major std430) buffer 4-component vector of int64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:56: ' temp uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:57: ' temp 2-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:58: ' temp 3-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:59: 'layout( column_major std430) buffer 4-component vector of uint64_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_int64
+ERROR: 0:61: ' temp float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:62: ' temp 2-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:63: ' temp 3-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 0:64: 'layout( column_major std430) buffer 4-component vector of float16_t' : required extension not requested: GL_EXT_shader_subgroup_extended_types_float16
+ERROR: 28 compilation errors.  No code generated.
+
+
+SPIR-V is not generated for failed compile or link

Test/spv.subgroupExtendedTypesArithmetic.comp

@@ -0,0 +1,715 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_arithmetic: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupAdd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupAdd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupAdd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupAdd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupMul(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupMul(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupMul(data[2].i8.xyz);
+    data[invocation].i8     = subgroupMul(data[3].i8);
+
+    data[invocation].i8.x   = subgroupMin(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupMin(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupMin(data[2].i8.xyz);
+    data[invocation].i8     = subgroupMin(data[3].i8);
+
+    data[invocation].i8.x   = subgroupMax(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupMax(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupMax(data[2].i8.xyz);
+    data[invocation].i8     = subgroupMax(data[3].i8);
+
+    data[invocation].i8.x   = subgroupAnd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupAnd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupAnd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupAnd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupOr(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupOr(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupOr(data[2].i8.xyz);
+    data[invocation].i8     = subgroupOr(data[3].i8);
+
+    data[invocation].i8.x   = subgroupXor(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupXor(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupXor(data[2].i8.xyz);
+    data[invocation].i8     = subgroupXor(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveAdd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveAdd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveAdd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveAdd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveMul(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveMul(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveMul(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveMul(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveMin(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveMin(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveMin(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveMin(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveMax(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveMax(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveMax(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveMax(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveAnd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveAnd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveAnd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveAnd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveOr(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveOr(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveOr(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveOr(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveXor(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveXor(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveXor(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveXor(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveAdd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveAdd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveAdd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveAdd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveMul(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveMul(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveMul(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveMul(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveMin(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveMin(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveMin(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveMin(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveMax(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveMax(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveMax(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveMax(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveAnd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveAnd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveAnd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveAnd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveOr(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveOr(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveOr(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveOr(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveXor(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveXor(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveXor(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveXor(data[3].i8);
+
+    data[invocation].u8.x   = subgroupAdd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupAdd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupAdd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupAdd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupMul(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupMul(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupMul(data[2].u8.xyz);
+    data[invocation].u8     = subgroupMul(data[3].u8);
+
+    data[invocation].u8.x   = subgroupMin(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupMin(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupMin(data[2].u8.xyz);
+    data[invocation].u8     = subgroupMin(data[3].u8);
+
+    data[invocation].u8.x   = subgroupMax(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupMax(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupMax(data[2].u8.xyz);
+    data[invocation].u8     = subgroupMax(data[3].u8);
+
+    data[invocation].u8.x   = subgroupAnd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupAnd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupAnd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupAnd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupOr(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupOr(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupOr(data[2].u8.xyz);
+    data[invocation].u8     = subgroupOr(data[3].u8);
+
+    data[invocation].u8.x   = subgroupXor(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupXor(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupXor(data[2].u8.xyz);
+    data[invocation].u8     = subgroupXor(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveAdd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveAdd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveAdd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveAdd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveMul(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveMul(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveMul(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveMul(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveMin(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveMin(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveMin(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveMin(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveMax(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveMax(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveMax(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveMax(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveAnd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveAnd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveAnd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveAnd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveOr(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveOr(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveOr(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveOr(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveXor(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveXor(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveXor(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveXor(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveAdd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveAdd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveAdd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveAdd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveMul(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveMul(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveMul(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveMul(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveMin(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveMin(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveMin(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveMin(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveMax(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveMax(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveMax(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveMax(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveAnd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveAnd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveAnd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveAnd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveOr(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveOr(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveOr(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveOr(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveXor(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveXor(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveXor(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveXor(data[3].u8);
+
+    data[invocation].i16.x   = subgroupAdd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupAdd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupAdd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupAdd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupMul(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupMul(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupMul(data[2].i16.xyz);
+    data[invocation].i16     = subgroupMul(data[3].i16);
+
+    data[invocation].i16.x   = subgroupMin(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupMin(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupMin(data[2].i16.xyz);
+    data[invocation].i16     = subgroupMin(data[3].i16);
+
+    data[invocation].i16.x   = subgroupMax(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupMax(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupMax(data[2].i16.xyz);
+    data[invocation].i16     = subgroupMax(data[3].i16);
+
+    data[invocation].i16.x   = subgroupAnd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupAnd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupAnd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupAnd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupOr(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupOr(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupOr(data[2].i16.xyz);
+    data[invocation].i16     = subgroupOr(data[3].i16);
+
+    data[invocation].i16.x   = subgroupXor(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupXor(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupXor(data[2].i16.xyz);
+    data[invocation].i16     = subgroupXor(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveAdd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveAdd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveAdd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveAdd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveMul(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveMul(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveMul(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveMul(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveMin(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveMin(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveMin(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveMin(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveMax(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveMax(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveMax(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveMax(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveAnd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveAnd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveAnd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveAnd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveOr(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveOr(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveOr(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveOr(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveXor(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveXor(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveXor(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveXor(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveAdd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveAdd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveAdd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveAdd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveMul(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveMul(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveMul(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveMul(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveMin(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveMin(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveMin(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveMin(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveMax(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveMax(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveMax(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveMax(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveAnd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveAnd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveAnd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveAnd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveOr(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveOr(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveOr(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveOr(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveXor(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveXor(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveXor(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveXor(data[3].i16);
+
+    data[invocation].u16.x   = subgroupAdd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupAdd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupAdd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupAdd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupMul(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupMul(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupMul(data[2].u16.xyz);
+    data[invocation].u16     = subgroupMul(data[3].u16);
+
+    data[invocation].u16.x   = subgroupMin(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupMin(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupMin(data[2].u16.xyz);
+    data[invocation].u16     = subgroupMin(data[3].u16);
+
+    data[invocation].u16.x   = subgroupMax(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupMax(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupMax(data[2].u16.xyz);
+    data[invocation].u16     = subgroupMax(data[3].u16);
+
+    data[invocation].u16.x   = subgroupAnd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupAnd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupAnd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupAnd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupOr(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupOr(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupOr(data[2].u16.xyz);
+    data[invocation].u16     = subgroupOr(data[3].u16);
+
+    data[invocation].u16.x   = subgroupXor(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupXor(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupXor(data[2].u16.xyz);
+    data[invocation].u16     = subgroupXor(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveAdd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveAdd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveAdd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveAdd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveMul(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveMul(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveMul(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveMul(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveMin(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveMin(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveMin(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveMin(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveMax(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveMax(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveMax(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveMax(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveAnd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveAnd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveAnd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveAnd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveOr(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveOr(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveOr(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveOr(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveXor(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveXor(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveXor(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveXor(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveAdd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveAdd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveAdd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveAdd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveMul(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveMul(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveMul(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveMul(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveMin(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveMin(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveMin(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveMin(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveMax(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveMax(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveMax(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveMax(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveAnd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveAnd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveAnd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveAnd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveOr(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveOr(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveOr(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveOr(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveXor(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveXor(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveXor(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveXor(data[3].u16);
+
+    data[invocation].i64.x   = subgroupAdd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupAdd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupAdd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupAdd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupMul(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupMul(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupMul(data[2].i64.xyz);
+    data[invocation].i64     = subgroupMul(data[3].i64);
+
+    data[invocation].i64.x   = subgroupMin(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupMin(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupMin(data[2].i64.xyz);
+    data[invocation].i64     = subgroupMin(data[3].i64);
+
+    data[invocation].i64.x   = subgroupMax(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupMax(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupMax(data[2].i64.xyz);
+    data[invocation].i64     = subgroupMax(data[3].i64);
+
+    data[invocation].i64.x   = subgroupAnd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupAnd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupAnd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupAnd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupOr(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupOr(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupOr(data[2].i64.xyz);
+    data[invocation].i64     = subgroupOr(data[3].i64);
+
+    data[invocation].i64.x   = subgroupXor(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupXor(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupXor(data[2].i64.xyz);
+    data[invocation].i64     = subgroupXor(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveAdd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveAdd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveAdd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveAdd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveMul(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveMul(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveMul(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveMul(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveMin(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveMin(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveMin(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveMin(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveMax(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveMax(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveMax(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveMax(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveAnd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveAnd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveAnd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveAnd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveOr(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveOr(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveOr(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveOr(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveXor(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveXor(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveXor(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveXor(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveAdd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveAdd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveAdd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveAdd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveMul(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveMul(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveMul(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveMul(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveMin(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveMin(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveMin(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveMin(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveMax(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveMax(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveMax(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveMax(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveAnd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveAnd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveAnd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveAnd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveOr(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveOr(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveOr(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveOr(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveXor(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveXor(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveXor(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveXor(data[3].i64);
+
+    data[invocation].u64.x   = subgroupAdd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupAdd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupAdd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupAdd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupMul(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupMul(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupMul(data[2].u64.xyz);
+    data[invocation].u64     = subgroupMul(data[3].u64);
+
+    data[invocation].u64.x   = subgroupMin(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupMin(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupMin(data[2].u64.xyz);
+    data[invocation].u64     = subgroupMin(data[3].u64);
+
+    data[invocation].u64.x   = subgroupMax(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupMax(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupMax(data[2].u64.xyz);
+    data[invocation].u64     = subgroupMax(data[3].u64);
+
+    data[invocation].u64.x   = subgroupAnd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupAnd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupAnd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupAnd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupOr(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupOr(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupOr(data[2].u64.xyz);
+    data[invocation].u64     = subgroupOr(data[3].u64);
+
+    data[invocation].u64.x   = subgroupXor(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupXor(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupXor(data[2].u64.xyz);
+    data[invocation].u64     = subgroupXor(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveAdd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveAdd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveAdd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveAdd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveMul(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveMul(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveMul(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveMul(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveMin(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveMin(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveMin(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveMin(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveMax(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveMax(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveMax(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveMax(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveAnd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveAnd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveAnd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveAnd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveOr(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveOr(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveOr(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveOr(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveXor(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveXor(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveXor(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveXor(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveAdd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveAdd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveAdd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveAdd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveMul(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveMul(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveMul(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveMul(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveMin(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveMin(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveMin(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveMin(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveMax(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveMax(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveMax(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveMax(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveAnd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveAnd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveAnd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveAnd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveOr(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveOr(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveOr(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveOr(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveXor(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveXor(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveXor(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveXor(data[3].u64);
+
+    data[invocation].f16.x   = subgroupAdd(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupAdd(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupAdd(data[2].f16.xyz);
+    data[invocation].f16     = subgroupAdd(data[3].f16);
+
+    data[invocation].f16.x   = subgroupMul(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupMul(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupMul(data[2].f16.xyz);
+    data[invocation].f16     = subgroupMul(data[3].f16);
+
+    data[invocation].f16.x   = subgroupMin(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupMin(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupMin(data[2].f16.xyz);
+    data[invocation].f16     = subgroupMin(data[3].f16);
+
+    data[invocation].f16.x   = subgroupMax(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupMax(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupMax(data[2].f16.xyz);
+    data[invocation].f16     = subgroupMax(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveAdd(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveAdd(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveAdd(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveAdd(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveMul(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveMul(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveMul(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveMul(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveMin(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveMin(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveMin(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveMin(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveMax(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveMax(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveMax(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveMax(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveAdd(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveAdd(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveAdd(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveAdd(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveMul(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveMul(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveMul(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveMul(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveMin(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveMin(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveMin(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveMin(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveMax(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveMax(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveMax(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveMax(data[3].f16);
+}

Test/spv.subgroupExtendedTypesArithmeticNeg.comp

@@ -0,0 +1,715 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_arithmetic: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupAdd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupAdd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupAdd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupAdd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupMul(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupMul(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupMul(data[2].i8.xyz);
+    data[invocation].i8     = subgroupMul(data[3].i8);
+
+    data[invocation].i8.x   = subgroupMin(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupMin(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupMin(data[2].i8.xyz);
+    data[invocation].i8     = subgroupMin(data[3].i8);
+
+    data[invocation].i8.x   = subgroupMax(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupMax(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupMax(data[2].i8.xyz);
+    data[invocation].i8     = subgroupMax(data[3].i8);
+
+    data[invocation].i8.x   = subgroupAnd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupAnd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupAnd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupAnd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupOr(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupOr(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupOr(data[2].i8.xyz);
+    data[invocation].i8     = subgroupOr(data[3].i8);
+
+    data[invocation].i8.x   = subgroupXor(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupXor(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupXor(data[2].i8.xyz);
+    data[invocation].i8     = subgroupXor(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveAdd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveAdd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveAdd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveAdd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveMul(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveMul(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveMul(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveMul(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveMin(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveMin(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveMin(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveMin(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveMax(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveMax(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveMax(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveMax(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveAnd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveAnd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveAnd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveAnd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveOr(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveOr(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveOr(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveOr(data[3].i8);
+
+    data[invocation].i8.x   = subgroupInclusiveXor(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupInclusiveXor(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupInclusiveXor(data[2].i8.xyz);
+    data[invocation].i8     = subgroupInclusiveXor(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveAdd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveAdd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveAdd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveAdd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveMul(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveMul(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveMul(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveMul(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveMin(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveMin(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveMin(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveMin(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveMax(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveMax(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveMax(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveMax(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveAnd(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveAnd(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveAnd(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveAnd(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveOr(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveOr(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveOr(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveOr(data[3].i8);
+
+    data[invocation].i8.x   = subgroupExclusiveXor(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupExclusiveXor(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupExclusiveXor(data[2].i8.xyz);
+    data[invocation].i8     = subgroupExclusiveXor(data[3].i8);
+
+    data[invocation].u8.x   = subgroupAdd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupAdd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupAdd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupAdd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupMul(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupMul(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupMul(data[2].u8.xyz);
+    data[invocation].u8     = subgroupMul(data[3].u8);
+
+    data[invocation].u8.x   = subgroupMin(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupMin(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupMin(data[2].u8.xyz);
+    data[invocation].u8     = subgroupMin(data[3].u8);
+
+    data[invocation].u8.x   = subgroupMax(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupMax(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupMax(data[2].u8.xyz);
+    data[invocation].u8     = subgroupMax(data[3].u8);
+
+    data[invocation].u8.x   = subgroupAnd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupAnd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupAnd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupAnd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupOr(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupOr(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupOr(data[2].u8.xyz);
+    data[invocation].u8     = subgroupOr(data[3].u8);
+
+    data[invocation].u8.x   = subgroupXor(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupXor(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupXor(data[2].u8.xyz);
+    data[invocation].u8     = subgroupXor(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveAdd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveAdd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveAdd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveAdd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveMul(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveMul(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveMul(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveMul(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveMin(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveMin(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveMin(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveMin(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveMax(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveMax(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveMax(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveMax(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveAnd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveAnd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveAnd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveAnd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveOr(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveOr(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveOr(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveOr(data[3].u8);
+
+    data[invocation].u8.x   = subgroupInclusiveXor(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupInclusiveXor(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupInclusiveXor(data[2].u8.xyz);
+    data[invocation].u8     = subgroupInclusiveXor(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveAdd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveAdd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveAdd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveAdd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveMul(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveMul(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveMul(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveMul(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveMin(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveMin(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveMin(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveMin(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveMax(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveMax(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveMax(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveMax(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveAnd(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveAnd(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveAnd(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveAnd(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveOr(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveOr(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveOr(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveOr(data[3].u8);
+
+    data[invocation].u8.x   = subgroupExclusiveXor(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupExclusiveXor(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupExclusiveXor(data[2].u8.xyz);
+    data[invocation].u8     = subgroupExclusiveXor(data[3].u8);
+
+    data[invocation].i16.x   = subgroupAdd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupAdd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupAdd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupAdd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupMul(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupMul(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupMul(data[2].i16.xyz);
+    data[invocation].i16     = subgroupMul(data[3].i16);
+
+    data[invocation].i16.x   = subgroupMin(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupMin(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupMin(data[2].i16.xyz);
+    data[invocation].i16     = subgroupMin(data[3].i16);
+
+    data[invocation].i16.x   = subgroupMax(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupMax(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupMax(data[2].i16.xyz);
+    data[invocation].i16     = subgroupMax(data[3].i16);
+
+    data[invocation].i16.x   = subgroupAnd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupAnd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupAnd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupAnd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupOr(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupOr(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupOr(data[2].i16.xyz);
+    data[invocation].i16     = subgroupOr(data[3].i16);
+
+    data[invocation].i16.x   = subgroupXor(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupXor(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupXor(data[2].i16.xyz);
+    data[invocation].i16     = subgroupXor(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveAdd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveAdd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveAdd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveAdd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveMul(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveMul(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveMul(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveMul(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveMin(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveMin(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveMin(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveMin(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveMax(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveMax(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveMax(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveMax(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveAnd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveAnd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveAnd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveAnd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveOr(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveOr(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveOr(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveOr(data[3].i16);
+
+    data[invocation].i16.x   = subgroupInclusiveXor(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupInclusiveXor(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupInclusiveXor(data[2].i16.xyz);
+    data[invocation].i16     = subgroupInclusiveXor(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveAdd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveAdd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveAdd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveAdd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveMul(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveMul(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveMul(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveMul(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveMin(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveMin(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveMin(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveMin(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveMax(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveMax(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveMax(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveMax(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveAnd(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveAnd(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveAnd(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveAnd(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveOr(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveOr(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveOr(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveOr(data[3].i16);
+
+    data[invocation].i16.x   = subgroupExclusiveXor(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupExclusiveXor(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupExclusiveXor(data[2].i16.xyz);
+    data[invocation].i16     = subgroupExclusiveXor(data[3].i16);
+
+    data[invocation].u16.x   = subgroupAdd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupAdd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupAdd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupAdd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupMul(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupMul(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupMul(data[2].u16.xyz);
+    data[invocation].u16     = subgroupMul(data[3].u16);
+
+    data[invocation].u16.x   = subgroupMin(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupMin(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupMin(data[2].u16.xyz);
+    data[invocation].u16     = subgroupMin(data[3].u16);
+
+    data[invocation].u16.x   = subgroupMax(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupMax(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupMax(data[2].u16.xyz);
+    data[invocation].u16     = subgroupMax(data[3].u16);
+
+    data[invocation].u16.x   = subgroupAnd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupAnd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupAnd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupAnd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupOr(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupOr(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupOr(data[2].u16.xyz);
+    data[invocation].u16     = subgroupOr(data[3].u16);
+
+    data[invocation].u16.x   = subgroupXor(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupXor(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupXor(data[2].u16.xyz);
+    data[invocation].u16     = subgroupXor(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveAdd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveAdd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveAdd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveAdd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveMul(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveMul(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveMul(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveMul(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveMin(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveMin(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveMin(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveMin(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveMax(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveMax(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveMax(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveMax(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveAnd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveAnd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveAnd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveAnd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveOr(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveOr(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveOr(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveOr(data[3].u16);
+
+    data[invocation].u16.x   = subgroupInclusiveXor(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupInclusiveXor(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupInclusiveXor(data[2].u16.xyz);
+    data[invocation].u16     = subgroupInclusiveXor(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveAdd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveAdd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveAdd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveAdd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveMul(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveMul(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveMul(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveMul(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveMin(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveMin(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveMin(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveMin(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveMax(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveMax(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveMax(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveMax(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveAnd(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveAnd(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveAnd(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveAnd(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveOr(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveOr(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveOr(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveOr(data[3].u16);
+
+    data[invocation].u16.x   = subgroupExclusiveXor(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupExclusiveXor(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupExclusiveXor(data[2].u16.xyz);
+    data[invocation].u16     = subgroupExclusiveXor(data[3].u16);
+
+    data[invocation].i64.x   = subgroupAdd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupAdd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupAdd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupAdd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupMul(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupMul(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupMul(data[2].i64.xyz);
+    data[invocation].i64     = subgroupMul(data[3].i64);
+
+    data[invocation].i64.x   = subgroupMin(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupMin(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupMin(data[2].i64.xyz);
+    data[invocation].i64     = subgroupMin(data[3].i64);
+
+    data[invocation].i64.x   = subgroupMax(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupMax(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupMax(data[2].i64.xyz);
+    data[invocation].i64     = subgroupMax(data[3].i64);
+
+    data[invocation].i64.x   = subgroupAnd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupAnd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupAnd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupAnd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupOr(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupOr(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupOr(data[2].i64.xyz);
+    data[invocation].i64     = subgroupOr(data[3].i64);
+
+    data[invocation].i64.x   = subgroupXor(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupXor(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupXor(data[2].i64.xyz);
+    data[invocation].i64     = subgroupXor(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveAdd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveAdd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveAdd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveAdd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveMul(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveMul(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveMul(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveMul(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveMin(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveMin(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveMin(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveMin(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveMax(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveMax(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveMax(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveMax(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveAnd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveAnd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveAnd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveAnd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveOr(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveOr(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveOr(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveOr(data[3].i64);
+
+    data[invocation].i64.x   = subgroupInclusiveXor(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupInclusiveXor(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupInclusiveXor(data[2].i64.xyz);
+    data[invocation].i64     = subgroupInclusiveXor(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveAdd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveAdd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveAdd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveAdd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveMul(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveMul(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveMul(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveMul(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveMin(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveMin(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveMin(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveMin(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveMax(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveMax(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveMax(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveMax(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveAnd(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveAnd(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveAnd(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveAnd(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveOr(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveOr(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveOr(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveOr(data[3].i64);
+
+    data[invocation].i64.x   = subgroupExclusiveXor(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupExclusiveXor(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupExclusiveXor(data[2].i64.xyz);
+    data[invocation].i64     = subgroupExclusiveXor(data[3].i64);
+
+    data[invocation].u64.x   = subgroupAdd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupAdd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupAdd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupAdd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupMul(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupMul(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupMul(data[2].u64.xyz);
+    data[invocation].u64     = subgroupMul(data[3].u64);
+
+    data[invocation].u64.x   = subgroupMin(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupMin(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupMin(data[2].u64.xyz);
+    data[invocation].u64     = subgroupMin(data[3].u64);
+
+    data[invocation].u64.x   = subgroupMax(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupMax(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupMax(data[2].u64.xyz);
+    data[invocation].u64     = subgroupMax(data[3].u64);
+
+    data[invocation].u64.x   = subgroupAnd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupAnd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupAnd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupAnd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupOr(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupOr(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupOr(data[2].u64.xyz);
+    data[invocation].u64     = subgroupOr(data[3].u64);
+
+    data[invocation].u64.x   = subgroupXor(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupXor(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupXor(data[2].u64.xyz);
+    data[invocation].u64     = subgroupXor(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveAdd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveAdd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveAdd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveAdd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveMul(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveMul(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveMul(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveMul(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveMin(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveMin(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveMin(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveMin(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveMax(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveMax(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveMax(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveMax(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveAnd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveAnd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveAnd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveAnd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveOr(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveOr(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveOr(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveOr(data[3].u64);
+
+    data[invocation].u64.x   = subgroupInclusiveXor(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupInclusiveXor(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupInclusiveXor(data[2].u64.xyz);
+    data[invocation].u64     = subgroupInclusiveXor(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveAdd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveAdd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveAdd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveAdd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveMul(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveMul(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveMul(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveMul(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveMin(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveMin(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveMin(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveMin(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveMax(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveMax(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveMax(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveMax(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveAnd(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveAnd(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveAnd(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveAnd(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveOr(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveOr(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveOr(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveOr(data[3].u64);
+
+    data[invocation].u64.x   = subgroupExclusiveXor(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupExclusiveXor(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupExclusiveXor(data[2].u64.xyz);
+    data[invocation].u64     = subgroupExclusiveXor(data[3].u64);
+
+    data[invocation].f16.x   = subgroupAdd(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupAdd(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupAdd(data[2].f16.xyz);
+    data[invocation].f16     = subgroupAdd(data[3].f16);
+
+    data[invocation].f16.x   = subgroupMul(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupMul(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupMul(data[2].f16.xyz);
+    data[invocation].f16     = subgroupMul(data[3].f16);
+
+    data[invocation].f16.x   = subgroupMin(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupMin(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupMin(data[2].f16.xyz);
+    data[invocation].f16     = subgroupMin(data[3].f16);
+
+    data[invocation].f16.x   = subgroupMax(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupMax(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupMax(data[2].f16.xyz);
+    data[invocation].f16     = subgroupMax(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveAdd(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveAdd(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveAdd(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveAdd(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveMul(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveMul(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveMul(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveMul(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveMin(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveMin(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveMin(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveMin(data[3].f16);
+
+    data[invocation].f16.x   = subgroupInclusiveMax(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupInclusiveMax(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupInclusiveMax(data[2].f16.xyz);
+    data[invocation].f16     = subgroupInclusiveMax(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveAdd(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveAdd(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveAdd(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveAdd(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveMul(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveMul(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveMul(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveMul(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveMin(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveMin(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveMin(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveMin(data[3].f16);
+
+    data[invocation].f16.x   = subgroupExclusiveMax(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupExclusiveMax(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupExclusiveMax(data[2].f16.xyz);
+    data[invocation].f16     = subgroupExclusiveMax(data[3].f16);
+}

Test/spv.subgroupExtendedTypesBallot.comp

@@ -0,0 +1,88 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_ballot: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupBroadcast(data[0].i8.x,    3);
+    data[invocation].i8.xy  = subgroupBroadcast(data[1].i8.xy,   3);
+    data[invocation].i8.xyz = subgroupBroadcast(data[2].i8.xyz,  3);
+    data[invocation].i8     = subgroupBroadcast(data[3].i8,      3);
+    data[invocation].i8.x   = subgroupBroadcastFirst(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupBroadcastFirst(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupBroadcastFirst(data[2].i8.xyz);
+    data[invocation].i8     = subgroupBroadcastFirst(data[3].i8);
+
+    data[invocation].u8.x   = subgroupBroadcast(data[0].u8.x,    3);
+    data[invocation].u8.xy  = subgroupBroadcast(data[1].u8.xy,   3);
+    data[invocation].u8.xyz = subgroupBroadcast(data[2].u8.xyz,  3);
+    data[invocation].u8     = subgroupBroadcast(data[3].u8,      3);
+    data[invocation].u8.x   = subgroupBroadcastFirst(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupBroadcastFirst(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupBroadcastFirst(data[2].u8.xyz);
+    data[invocation].u8     = subgroupBroadcastFirst(data[3].u8);
+
+    data[invocation].i16.x   = subgroupBroadcast(data[0].i16.x,    3);
+    data[invocation].i16.xy  = subgroupBroadcast(data[1].i16.xy,   3);
+    data[invocation].i16.xyz = subgroupBroadcast(data[2].i16.xyz,  3);
+    data[invocation].i16     = subgroupBroadcast(data[3].i16,      3);
+    data[invocation].i16.x   = subgroupBroadcastFirst(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupBroadcastFirst(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupBroadcastFirst(data[2].i16.xyz);
+    data[invocation].i16     = subgroupBroadcastFirst(data[3].i16);
+
+    data[invocation].u16.x   = subgroupBroadcast(data[0].u16.x,    3);
+    data[invocation].u16.xy  = subgroupBroadcast(data[1].u16.xy,   3);
+    data[invocation].u16.xyz = subgroupBroadcast(data[2].u16.xyz,  3);
+    data[invocation].u16     = subgroupBroadcast(data[3].u16,      3);
+    data[invocation].u16.x   = subgroupBroadcastFirst(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupBroadcastFirst(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupBroadcastFirst(data[2].u16.xyz);
+    data[invocation].u16     = subgroupBroadcastFirst(data[3].u16);
+
+    data[invocation].i64.x   = subgroupBroadcast(data[0].i64.x,    3);
+    data[invocation].i64.xy  = subgroupBroadcast(data[1].i64.xy,   3);
+    data[invocation].i64.xyz = subgroupBroadcast(data[2].i64.xyz,  3);
+    data[invocation].i64     = subgroupBroadcast(data[3].i64,      3);
+    data[invocation].i64.x   = subgroupBroadcastFirst(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupBroadcastFirst(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupBroadcastFirst(data[2].i64.xyz);
+    data[invocation].i64     = subgroupBroadcastFirst(data[3].i64);
+
+    data[invocation].u64.x   = subgroupBroadcast(data[0].u64.x,    3);
+    data[invocation].u64.xy  = subgroupBroadcast(data[1].u64.xy,   3);
+    data[invocation].u64.xyz = subgroupBroadcast(data[2].u64.xyz,  3);
+    data[invocation].u64     = subgroupBroadcast(data[3].u64,      3);
+    data[invocation].u64.x   = subgroupBroadcastFirst(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupBroadcastFirst(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupBroadcastFirst(data[2].u64.xyz);
+    data[invocation].u64     = subgroupBroadcastFirst(data[3].u64);
+
+    data[invocation].f16.x   = subgroupBroadcast(data[0].f16.x,    3);
+    data[invocation].f16.xy  = subgroupBroadcast(data[1].f16.xy,   3);
+    data[invocation].f16.xyz = subgroupBroadcast(data[2].f16.xyz,  3);
+    data[invocation].f16     = subgroupBroadcast(data[3].f16,      3);
+    data[invocation].f16.x   = subgroupBroadcastFirst(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupBroadcastFirst(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupBroadcastFirst(data[2].f16.xyz);
+    data[invocation].f16     = subgroupBroadcastFirst(data[3].f16);
+}

Test/spv.subgroupExtendedTypesBallotNeg.comp

@@ -0,0 +1,88 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_ballot: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupBroadcast(data[0].i8.x,    3);
+    data[invocation].i8.xy  = subgroupBroadcast(data[1].i8.xy,   3);
+    data[invocation].i8.xyz = subgroupBroadcast(data[2].i8.xyz,  3);
+    data[invocation].i8     = subgroupBroadcast(data[3].i8,      3);
+    data[invocation].i8.x   = subgroupBroadcastFirst(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupBroadcastFirst(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupBroadcastFirst(data[2].i8.xyz);
+    data[invocation].i8     = subgroupBroadcastFirst(data[3].i8);
+
+    data[invocation].u8.x   = subgroupBroadcast(data[0].u8.x,    3);
+    data[invocation].u8.xy  = subgroupBroadcast(data[1].u8.xy,   3);
+    data[invocation].u8.xyz = subgroupBroadcast(data[2].u8.xyz,  3);
+    data[invocation].u8     = subgroupBroadcast(data[3].u8,      3);
+    data[invocation].u8.x   = subgroupBroadcastFirst(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupBroadcastFirst(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupBroadcastFirst(data[2].u8.xyz);
+    data[invocation].u8     = subgroupBroadcastFirst(data[3].u8);
+
+    data[invocation].i16.x   = subgroupBroadcast(data[0].i16.x,    3);
+    data[invocation].i16.xy  = subgroupBroadcast(data[1].i16.xy,   3);
+    data[invocation].i16.xyz = subgroupBroadcast(data[2].i16.xyz,  3);
+    data[invocation].i16     = subgroupBroadcast(data[3].i16,      3);
+    data[invocation].i16.x   = subgroupBroadcastFirst(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupBroadcastFirst(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupBroadcastFirst(data[2].i16.xyz);
+    data[invocation].i16     = subgroupBroadcastFirst(data[3].i16);
+
+    data[invocation].u16.x   = subgroupBroadcast(data[0].u16.x,    3);
+    data[invocation].u16.xy  = subgroupBroadcast(data[1].u16.xy,   3);
+    data[invocation].u16.xyz = subgroupBroadcast(data[2].u16.xyz,  3);
+    data[invocation].u16     = subgroupBroadcast(data[3].u16,      3);
+    data[invocation].u16.x   = subgroupBroadcastFirst(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupBroadcastFirst(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupBroadcastFirst(data[2].u16.xyz);
+    data[invocation].u16     = subgroupBroadcastFirst(data[3].u16);
+
+    data[invocation].i64.x   = subgroupBroadcast(data[0].i64.x,    3);
+    data[invocation].i64.xy  = subgroupBroadcast(data[1].i64.xy,   3);
+    data[invocation].i64.xyz = subgroupBroadcast(data[2].i64.xyz,  3);
+    data[invocation].i64     = subgroupBroadcast(data[3].i64,      3);
+    data[invocation].i64.x   = subgroupBroadcastFirst(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupBroadcastFirst(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupBroadcastFirst(data[2].i64.xyz);
+    data[invocation].i64     = subgroupBroadcastFirst(data[3].i64);
+
+    data[invocation].u64.x   = subgroupBroadcast(data[0].u64.x,    3);
+    data[invocation].u64.xy  = subgroupBroadcast(data[1].u64.xy,   3);
+    data[invocation].u64.xyz = subgroupBroadcast(data[2].u64.xyz,  3);
+    data[invocation].u64     = subgroupBroadcast(data[3].u64,      3);
+    data[invocation].u64.x   = subgroupBroadcastFirst(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupBroadcastFirst(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupBroadcastFirst(data[2].u64.xyz);
+    data[invocation].u64     = subgroupBroadcastFirst(data[3].u64);
+
+    data[invocation].f16.x   = subgroupBroadcast(data[0].f16.x,    3);
+    data[invocation].f16.xy  = subgroupBroadcast(data[1].f16.xy,   3);
+    data[invocation].f16.xyz = subgroupBroadcast(data[2].f16.xyz,  3);
+    data[invocation].f16     = subgroupBroadcast(data[3].f16,      3);
+    data[invocation].f16.x   = subgroupBroadcastFirst(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupBroadcastFirst(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupBroadcastFirst(data[2].f16.xyz);
+    data[invocation].f16     = subgroupBroadcastFirst(data[3].f16);
+}

Test/spv.subgroupExtendedTypesClustered.comp

@@ -0,0 +1,255 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_clustered: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupClusteredAdd(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredAdd(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredAdd(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredAdd(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredMul(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredMul(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredMul(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredMul(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredMin(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredMin(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredMin(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredMin(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredMax(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredMax(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredMax(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredMax(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredAnd(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredAnd(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredAnd(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredAnd(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredOr(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredOr(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredOr(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredOr(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredXor(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredXor(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredXor(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredXor(data[3].i8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredAdd(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredAdd(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredAdd(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredAdd(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredMul(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredMul(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredMul(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredMul(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredMin(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredMin(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredMin(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredMin(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredMax(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredMax(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredMax(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredMax(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredAnd(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredAnd(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredAnd(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredAnd(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredOr(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredOr(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredOr(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredOr(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredXor(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredXor(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredXor(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredXor(data[3].u8, 1);
+
+    data[invocation].i16.x   = subgroupClusteredAdd(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredAdd(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredAdd(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredAdd(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredMul(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredMul(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredMul(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredMul(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredMin(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredMin(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredMin(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredMin(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredMax(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredMax(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredMax(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredMax(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredAnd(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredAnd(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredAnd(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredAnd(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredOr(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredOr(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredOr(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredOr(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredXor(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredXor(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredXor(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredXor(data[3].i16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredAdd(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredAdd(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredAdd(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredAdd(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredMul(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredMul(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredMul(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredMul(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredMin(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredMin(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredMin(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredMin(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredMax(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredMax(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredMax(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredMax(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredAnd(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredAnd(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredAnd(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredAnd(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredOr(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredOr(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredOr(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredOr(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredXor(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredXor(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredXor(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredXor(data[3].u16, 1);
+
+    data[invocation].i64.x   = subgroupClusteredAdd(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredAdd(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredAdd(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredAdd(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredMul(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredMul(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredMul(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredMul(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredMin(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredMin(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredMin(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredMin(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredMax(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredMax(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredMax(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredMax(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredAnd(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredAnd(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredAnd(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredAnd(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredOr(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredOr(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredOr(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredOr(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredXor(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredXor(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredXor(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredXor(data[3].i64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredAdd(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredAdd(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredAdd(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredAdd(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredMul(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredMul(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredMul(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredMul(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredMin(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredMin(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredMin(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredMin(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredMax(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredMax(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredMax(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredMax(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredAnd(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredAnd(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredAnd(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredAnd(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredOr(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredOr(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredOr(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredOr(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredXor(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredXor(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredXor(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredXor(data[3].u64, 1);
+
+    data[invocation].f16.x   = subgroupClusteredAdd(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredAdd(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredAdd(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredAdd(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupClusteredMul(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredMul(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredMul(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredMul(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupClusteredMin(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredMin(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredMin(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredMin(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupClusteredMax(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredMax(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredMax(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredMax(data[3].f16, 1);
+}

Test/spv.subgroupExtendedTypesClusteredNeg.comp

@@ -0,0 +1,255 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_clustered: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupClusteredAdd(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredAdd(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredAdd(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredAdd(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredMul(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredMul(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredMul(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredMul(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredMin(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredMin(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredMin(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredMin(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredMax(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredMax(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredMax(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredMax(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredAnd(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredAnd(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredAnd(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredAnd(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredOr(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredOr(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredOr(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredOr(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupClusteredXor(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupClusteredXor(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupClusteredXor(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupClusteredXor(data[3].i8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredAdd(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredAdd(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredAdd(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredAdd(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredMul(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredMul(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredMul(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredMul(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredMin(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredMin(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredMin(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredMin(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredMax(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredMax(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredMax(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredMax(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredAnd(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredAnd(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredAnd(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredAnd(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredOr(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredOr(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredOr(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredOr(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupClusteredXor(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupClusteredXor(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupClusteredXor(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupClusteredXor(data[3].u8, 1);
+
+    data[invocation].i16.x   = subgroupClusteredAdd(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredAdd(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredAdd(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredAdd(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredMul(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredMul(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredMul(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredMul(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredMin(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredMin(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredMin(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredMin(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredMax(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredMax(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredMax(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredMax(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredAnd(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredAnd(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredAnd(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredAnd(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredOr(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredOr(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredOr(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredOr(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupClusteredXor(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupClusteredXor(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupClusteredXor(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupClusteredXor(data[3].i16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredAdd(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredAdd(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredAdd(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredAdd(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredMul(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredMul(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredMul(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredMul(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredMin(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredMin(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredMin(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredMin(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredMax(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredMax(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredMax(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredMax(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredAnd(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredAnd(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredAnd(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredAnd(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredOr(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredOr(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredOr(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredOr(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupClusteredXor(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupClusteredXor(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupClusteredXor(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupClusteredXor(data[3].u16, 1);
+
+    data[invocation].i64.x   = subgroupClusteredAdd(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredAdd(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredAdd(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredAdd(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredMul(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredMul(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredMul(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredMul(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredMin(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredMin(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredMin(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredMin(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredMax(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredMax(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredMax(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredMax(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredAnd(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredAnd(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredAnd(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredAnd(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredOr(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredOr(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredOr(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredOr(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupClusteredXor(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupClusteredXor(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupClusteredXor(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupClusteredXor(data[3].i64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredAdd(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredAdd(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredAdd(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredAdd(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredMul(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredMul(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredMul(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredMul(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredMin(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredMin(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredMin(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredMin(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredMax(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredMax(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredMax(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredMax(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredAnd(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredAnd(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredAnd(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredAnd(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredOr(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredOr(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredOr(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredOr(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupClusteredXor(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupClusteredXor(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupClusteredXor(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupClusteredXor(data[3].u64, 1);
+
+    data[invocation].f16.x   = subgroupClusteredAdd(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredAdd(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredAdd(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredAdd(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupClusteredMul(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredMul(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredMul(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredMul(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupClusteredMin(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredMin(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredMin(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredMin(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupClusteredMax(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupClusteredMax(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupClusteredMax(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupClusteredMax(data[3].f16, 1);
+}

Test/spv.subgroupExtendedTypesPartitioned.comp

@@ -0,0 +1,291 @@
+#version 450
+
+#extension GL_NV_shader_subgroup_partitioned: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    uvec4 ballot;
+    ballot = subgroupPartitionNV(data[0].i8.x);
+    ballot = subgroupPartitionNV(data[1].i8.xy);
+    ballot = subgroupPartitionNV(data[2].i8.xyz);
+    ballot = subgroupPartitionNV(data[3].i8);
+
+    ballot = subgroupPartitionNV(data[0].u8.x);
+    ballot = subgroupPartitionNV(data[1].u8.xy);
+    ballot = subgroupPartitionNV(data[2].u8.xyz);
+    ballot = subgroupPartitionNV(data[3].u8);
+
+    ballot = subgroupPartitionNV(data[0].i16.x);
+    ballot = subgroupPartitionNV(data[1].i16.xy);
+    ballot = subgroupPartitionNV(data[2].i16.xyz);
+    ballot = subgroupPartitionNV(data[3].i16);
+
+    ballot = subgroupPartitionNV(data[0].u16.x);
+    ballot = subgroupPartitionNV(data[1].u16.xy);
+    ballot = subgroupPartitionNV(data[2].u16.xyz);
+    ballot = subgroupPartitionNV(data[3].u16);
+
+    ballot = subgroupPartitionNV(data[0].i64.x);
+    ballot = subgroupPartitionNV(data[1].i64.xy);
+    ballot = subgroupPartitionNV(data[2].i64.xyz);
+    ballot = subgroupPartitionNV(data[3].i64);
+
+    ballot = subgroupPartitionNV(data[0].u64.x);
+    ballot = subgroupPartitionNV(data[1].u64.xy);
+    ballot = subgroupPartitionNV(data[2].u64.xyz);
+    ballot = subgroupPartitionNV(data[3].u64);
+
+    ballot = subgroupPartitionNV(data[0].f16.x);
+    ballot = subgroupPartitionNV(data[1].f16.xy);
+    ballot = subgroupPartitionNV(data[2].f16.xyz);
+    ballot = subgroupPartitionNV(data[3].f16);
+
+    data[invocation].i8.x   = subgroupPartitionedAddNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedAddNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedAddNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedAddNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedMulNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedMulNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedMulNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedMulNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedMinNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedMinNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedMinNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedMinNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedMaxNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedMaxNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedMaxNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedMaxNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedAndNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedAndNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedAndNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedAndNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedOrNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedOrNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedOrNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedOrNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedXorNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedXorNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedXorNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedXorNV(data[3].i8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedAddNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedAddNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedAddNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedAddNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedMulNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedMulNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedMulNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedMulNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedMinNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedMinNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedMinNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedMinNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedMaxNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedMaxNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedMaxNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedMaxNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedAndNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedAndNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedAndNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedAndNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedOrNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedOrNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedOrNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedOrNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedXorNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedXorNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedXorNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedXorNV(data[3].u8, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedAddNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedAddNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedAddNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedAddNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedMulNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedMulNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedMulNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedMulNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedMinNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedMinNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedMinNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedMinNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedMaxNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedMaxNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedMaxNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedMaxNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedAndNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedAndNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedAndNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedAndNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedOrNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedOrNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedOrNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedOrNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedXorNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedXorNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedXorNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedXorNV(data[3].i16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedAddNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedAddNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedAddNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedAddNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedMulNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedMulNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedMulNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedMulNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedMinNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedMinNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedMinNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedMinNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedMaxNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedMaxNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedMaxNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedMaxNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedAndNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedAndNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedAndNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedAndNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedOrNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedOrNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedOrNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedOrNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedXorNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedXorNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedXorNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedXorNV(data[3].u16, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedAddNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedAddNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedAddNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedAddNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedMulNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedMulNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedMulNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedMulNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedMinNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedMinNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedMinNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedMinNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedMaxNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedMaxNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedMaxNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedMaxNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedAndNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedAndNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedAndNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedAndNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedOrNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedOrNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedOrNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedOrNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedXorNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedXorNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedXorNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedXorNV(data[3].i64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedAddNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedAddNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedAddNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedAddNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedMulNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedMulNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedMulNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedMulNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedMinNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedMinNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedMinNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedMinNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedMaxNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedMaxNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedMaxNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedMaxNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedAndNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedAndNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedAndNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedAndNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedOrNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedOrNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedOrNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedOrNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedXorNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedXorNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedXorNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedXorNV(data[3].u64, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedAddNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedAddNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedAddNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedAddNV(data[3].f16, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedMulNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedMulNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedMulNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedMulNV(data[3].f16, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedMinNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedMinNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedMinNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedMinNV(data[3].f16, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedMaxNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedMaxNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedMaxNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedMaxNV(data[3].f16, ballot);
+}

Test/spv.subgroupExtendedTypesPartitionedNeg.comp

@@ -0,0 +1,291 @@
+#version 450
+
+#extension GL_NV_shader_subgroup_partitioned: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    uvec4 ballot;
+    ballot = subgroupPartitionNV(data[0].i8.x);
+    ballot = subgroupPartitionNV(data[1].i8.xy);
+    ballot = subgroupPartitionNV(data[2].i8.xyz);
+    ballot = subgroupPartitionNV(data[3].i8);
+
+    ballot = subgroupPartitionNV(data[0].u8.x);
+    ballot = subgroupPartitionNV(data[1].u8.xy);
+    ballot = subgroupPartitionNV(data[2].u8.xyz);
+    ballot = subgroupPartitionNV(data[3].u8);
+
+    ballot = subgroupPartitionNV(data[0].i16.x);
+    ballot = subgroupPartitionNV(data[1].i16.xy);
+    ballot = subgroupPartitionNV(data[2].i16.xyz);
+    ballot = subgroupPartitionNV(data[3].i16);
+
+    ballot = subgroupPartitionNV(data[0].u16.x);
+    ballot = subgroupPartitionNV(data[1].u16.xy);
+    ballot = subgroupPartitionNV(data[2].u16.xyz);
+    ballot = subgroupPartitionNV(data[3].u16);
+
+    ballot = subgroupPartitionNV(data[0].i64.x);
+    ballot = subgroupPartitionNV(data[1].i64.xy);
+    ballot = subgroupPartitionNV(data[2].i64.xyz);
+    ballot = subgroupPartitionNV(data[3].i64);
+
+    ballot = subgroupPartitionNV(data[0].u64.x);
+    ballot = subgroupPartitionNV(data[1].u64.xy);
+    ballot = subgroupPartitionNV(data[2].u64.xyz);
+    ballot = subgroupPartitionNV(data[3].u64);
+
+    ballot = subgroupPartitionNV(data[0].f16.x);
+    ballot = subgroupPartitionNV(data[1].f16.xy);
+    ballot = subgroupPartitionNV(data[2].f16.xyz);
+    ballot = subgroupPartitionNV(data[3].f16);
+
+    data[invocation].i8.x   = subgroupPartitionedAddNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedAddNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedAddNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedAddNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedMulNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedMulNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedMulNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedMulNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedMinNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedMinNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedMinNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedMinNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedMaxNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedMaxNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedMaxNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedMaxNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedAndNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedAndNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedAndNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedAndNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedOrNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedOrNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedOrNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedOrNV(data[3].i8, ballot);
+
+    data[invocation].i8.x   = subgroupPartitionedXorNV(data[0].i8.x, ballot);
+    data[invocation].i8.xy  = subgroupPartitionedXorNV(data[1].i8.xy, ballot);
+    data[invocation].i8.xyz = subgroupPartitionedXorNV(data[2].i8.xyz, ballot);
+    data[invocation].i8     = subgroupPartitionedXorNV(data[3].i8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedAddNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedAddNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedAddNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedAddNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedMulNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedMulNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedMulNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedMulNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedMinNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedMinNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedMinNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedMinNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedMaxNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedMaxNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedMaxNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedMaxNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedAndNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedAndNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedAndNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedAndNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedOrNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedOrNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedOrNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedOrNV(data[3].u8, ballot);
+
+    data[invocation].u8.x   = subgroupPartitionedXorNV(data[0].u8.x, ballot);
+    data[invocation].u8.xy  = subgroupPartitionedXorNV(data[1].u8.xy, ballot);
+    data[invocation].u8.xyz = subgroupPartitionedXorNV(data[2].u8.xyz, ballot);
+    data[invocation].u8     = subgroupPartitionedXorNV(data[3].u8, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedAddNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedAddNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedAddNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedAddNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedMulNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedMulNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedMulNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedMulNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedMinNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedMinNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedMinNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedMinNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedMaxNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedMaxNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedMaxNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedMaxNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedAndNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedAndNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedAndNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedAndNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedOrNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedOrNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedOrNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedOrNV(data[3].i16, ballot);
+
+    data[invocation].i16.x   = subgroupPartitionedXorNV(data[0].i16.x, ballot);
+    data[invocation].i16.xy  = subgroupPartitionedXorNV(data[1].i16.xy, ballot);
+    data[invocation].i16.xyz = subgroupPartitionedXorNV(data[2].i16.xyz, ballot);
+    data[invocation].i16     = subgroupPartitionedXorNV(data[3].i16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedAddNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedAddNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedAddNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedAddNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedMulNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedMulNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedMulNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedMulNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedMinNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedMinNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedMinNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedMinNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedMaxNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedMaxNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedMaxNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedMaxNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedAndNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedAndNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedAndNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedAndNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedOrNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedOrNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedOrNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedOrNV(data[3].u16, ballot);
+
+    data[invocation].u16.x   = subgroupPartitionedXorNV(data[0].u16.x, ballot);
+    data[invocation].u16.xy  = subgroupPartitionedXorNV(data[1].u16.xy, ballot);
+    data[invocation].u16.xyz = subgroupPartitionedXorNV(data[2].u16.xyz, ballot);
+    data[invocation].u16     = subgroupPartitionedXorNV(data[3].u16, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedAddNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedAddNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedAddNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedAddNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedMulNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedMulNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedMulNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedMulNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedMinNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedMinNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedMinNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedMinNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedMaxNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedMaxNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedMaxNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedMaxNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedAndNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedAndNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedAndNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedAndNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedOrNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedOrNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedOrNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedOrNV(data[3].i64, ballot);
+
+    data[invocation].i64.x   = subgroupPartitionedXorNV(data[0].i64.x, ballot);
+    data[invocation].i64.xy  = subgroupPartitionedXorNV(data[1].i64.xy, ballot);
+    data[invocation].i64.xyz = subgroupPartitionedXorNV(data[2].i64.xyz, ballot);
+    data[invocation].i64     = subgroupPartitionedXorNV(data[3].i64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedAddNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedAddNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedAddNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedAddNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedMulNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedMulNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedMulNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedMulNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedMinNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedMinNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedMinNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedMinNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedMaxNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedMaxNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedMaxNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedMaxNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedAndNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedAndNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedAndNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedAndNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedOrNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedOrNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedOrNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedOrNV(data[3].u64, ballot);
+
+    data[invocation].u64.x   = subgroupPartitionedXorNV(data[0].u64.x, ballot);
+    data[invocation].u64.xy  = subgroupPartitionedXorNV(data[1].u64.xy, ballot);
+    data[invocation].u64.xyz = subgroupPartitionedXorNV(data[2].u64.xyz, ballot);
+    data[invocation].u64     = subgroupPartitionedXorNV(data[3].u64, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedAddNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedAddNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedAddNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedAddNV(data[3].f16, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedMulNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedMulNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedMulNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedMulNV(data[3].f16, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedMinNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedMinNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedMinNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedMinNV(data[3].f16, ballot);
+
+    data[invocation].f16.x   = subgroupPartitionedMaxNV(data[0].f16.x, ballot);
+    data[invocation].f16.xy  = subgroupPartitionedMaxNV(data[1].f16.xy, ballot);
+    data[invocation].f16.xyz = subgroupPartitionedMaxNV(data[2].f16.xyz, ballot);
+    data[invocation].f16     = subgroupPartitionedMaxNV(data[3].f16, ballot);
+}

Test/spv.subgroupExtendedTypesQuad.comp

@@ -0,0 +1,165 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_quad: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupQuadBroadcast(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupQuadBroadcast(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupQuadBroadcast(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupQuadBroadcast(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupQuadSwapHorizontal(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupQuadSwapHorizontal(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupQuadSwapHorizontal(data[2].i8.xyz);
+    data[invocation].i8     = subgroupQuadSwapHorizontal(data[3].i8);
+
+    data[invocation].i8.x   = subgroupQuadSwapVertical(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupQuadSwapVertical(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupQuadSwapVertical(data[2].i8.xyz);
+    data[invocation].i8     = subgroupQuadSwapVertical(data[3].i8);
+
+    data[invocation].i8.x   = subgroupQuadSwapDiagonal(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupQuadSwapDiagonal(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupQuadSwapDiagonal(data[2].i8.xyz);
+    data[invocation].i8     = subgroupQuadSwapDiagonal(data[3].i8);
+
+    data[invocation].u8.x   = subgroupQuadBroadcast(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupQuadBroadcast(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupQuadBroadcast(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupQuadBroadcast(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupQuadSwapHorizontal(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupQuadSwapHorizontal(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupQuadSwapHorizontal(data[2].u8.xyz);
+    data[invocation].u8     = subgroupQuadSwapHorizontal(data[3].u8);
+
+    data[invocation].u8.x   = subgroupQuadSwapVertical(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupQuadSwapVertical(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupQuadSwapVertical(data[2].u8.xyz);
+    data[invocation].u8     = subgroupQuadSwapVertical(data[3].u8);
+
+    data[invocation].u8.x   = subgroupQuadSwapDiagonal(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupQuadSwapDiagonal(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupQuadSwapDiagonal(data[2].u8.xyz);
+    data[invocation].u8     = subgroupQuadSwapDiagonal(data[3].u8);
+
+    data[invocation].i16.x   = subgroupQuadBroadcast(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupQuadBroadcast(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupQuadBroadcast(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupQuadBroadcast(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupQuadSwapHorizontal(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupQuadSwapHorizontal(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupQuadSwapHorizontal(data[2].i16.xyz);
+    data[invocation].i16     = subgroupQuadSwapHorizontal(data[3].i16);
+
+    data[invocation].i16.x   = subgroupQuadSwapVertical(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupQuadSwapVertical(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupQuadSwapVertical(data[2].i16.xyz);
+    data[invocation].i16     = subgroupQuadSwapVertical(data[3].i16);
+
+    data[invocation].i16.x   = subgroupQuadSwapDiagonal(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupQuadSwapDiagonal(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupQuadSwapDiagonal(data[2].i16.xyz);
+    data[invocation].i16     = subgroupQuadSwapDiagonal(data[3].i16);
+
+    data[invocation].u16.x   = subgroupQuadBroadcast(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupQuadBroadcast(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupQuadBroadcast(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupQuadBroadcast(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupQuadSwapHorizontal(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupQuadSwapHorizontal(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupQuadSwapHorizontal(data[2].u16.xyz);
+    data[invocation].u16     = subgroupQuadSwapHorizontal(data[3].u16);
+
+    data[invocation].u16.x   = subgroupQuadSwapVertical(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupQuadSwapVertical(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupQuadSwapVertical(data[2].u16.xyz);
+    data[invocation].u16     = subgroupQuadSwapVertical(data[3].u16);
+
+    data[invocation].u16.x   = subgroupQuadSwapDiagonal(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupQuadSwapDiagonal(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupQuadSwapDiagonal(data[2].u16.xyz);
+    data[invocation].u16     = subgroupQuadSwapDiagonal(data[3].u16);
+
+    data[invocation].i64.x   = subgroupQuadBroadcast(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupQuadBroadcast(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupQuadBroadcast(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupQuadBroadcast(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupQuadSwapHorizontal(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupQuadSwapHorizontal(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupQuadSwapHorizontal(data[2].i64.xyz);
+    data[invocation].i64     = subgroupQuadSwapHorizontal(data[3].i64);
+
+    data[invocation].i64.x   = subgroupQuadSwapVertical(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupQuadSwapVertical(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupQuadSwapVertical(data[2].i64.xyz);
+    data[invocation].i64     = subgroupQuadSwapVertical(data[3].i64);
+
+    data[invocation].i64.x   = subgroupQuadSwapDiagonal(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupQuadSwapDiagonal(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupQuadSwapDiagonal(data[2].i64.xyz);
+    data[invocation].i64     = subgroupQuadSwapDiagonal(data[3].i64);
+
+    data[invocation].u64.x   = subgroupQuadBroadcast(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupQuadBroadcast(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupQuadBroadcast(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupQuadBroadcast(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupQuadSwapHorizontal(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupQuadSwapHorizontal(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupQuadSwapHorizontal(data[2].u64.xyz);
+    data[invocation].u64     = subgroupQuadSwapHorizontal(data[3].u64);
+
+    data[invocation].u64.x   = subgroupQuadSwapVertical(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupQuadSwapVertical(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupQuadSwapVertical(data[2].u64.xyz);
+    data[invocation].u64     = subgroupQuadSwapVertical(data[3].u64);
+
+    data[invocation].u64.x   = subgroupQuadSwapDiagonal(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupQuadSwapDiagonal(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupQuadSwapDiagonal(data[2].u64.xyz);
+    data[invocation].u64     = subgroupQuadSwapDiagonal(data[3].u64);
+
+    data[invocation].f16.x   = subgroupQuadBroadcast(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupQuadBroadcast(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupQuadBroadcast(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupQuadBroadcast(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupQuadSwapHorizontal(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupQuadSwapHorizontal(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupQuadSwapHorizontal(data[2].f16.xyz);
+    data[invocation].f16     = subgroupQuadSwapHorizontal(data[3].f16);
+
+    data[invocation].f16.x   = subgroupQuadSwapVertical(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupQuadSwapVertical(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupQuadSwapVertical(data[2].f16.xyz);
+    data[invocation].f16     = subgroupQuadSwapVertical(data[3].f16);
+
+    data[invocation].f16.x   = subgroupQuadSwapDiagonal(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupQuadSwapDiagonal(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupQuadSwapDiagonal(data[2].f16.xyz);
+    data[invocation].f16     = subgroupQuadSwapDiagonal(data[3].f16);
+}

Test/spv.subgroupExtendedTypesQuadNeg.comp

@@ -0,0 +1,165 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_quad: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupQuadBroadcast(data[0].i8.x, 1);
+    data[invocation].i8.xy  = subgroupQuadBroadcast(data[1].i8.xy, 1);
+    data[invocation].i8.xyz = subgroupQuadBroadcast(data[2].i8.xyz, 1);
+    data[invocation].i8     = subgroupQuadBroadcast(data[3].i8, 1);
+
+    data[invocation].i8.x   = subgroupQuadSwapHorizontal(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupQuadSwapHorizontal(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupQuadSwapHorizontal(data[2].i8.xyz);
+    data[invocation].i8     = subgroupQuadSwapHorizontal(data[3].i8);
+
+    data[invocation].i8.x   = subgroupQuadSwapVertical(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupQuadSwapVertical(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupQuadSwapVertical(data[2].i8.xyz);
+    data[invocation].i8     = subgroupQuadSwapVertical(data[3].i8);
+
+    data[invocation].i8.x   = subgroupQuadSwapDiagonal(data[0].i8.x);
+    data[invocation].i8.xy  = subgroupQuadSwapDiagonal(data[1].i8.xy);
+    data[invocation].i8.xyz = subgroupQuadSwapDiagonal(data[2].i8.xyz);
+    data[invocation].i8     = subgroupQuadSwapDiagonal(data[3].i8);
+
+    data[invocation].u8.x   = subgroupQuadBroadcast(data[0].u8.x, 1);
+    data[invocation].u8.xy  = subgroupQuadBroadcast(data[1].u8.xy, 1);
+    data[invocation].u8.xyz = subgroupQuadBroadcast(data[2].u8.xyz, 1);
+    data[invocation].u8     = subgroupQuadBroadcast(data[3].u8, 1);
+
+    data[invocation].u8.x   = subgroupQuadSwapHorizontal(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupQuadSwapHorizontal(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupQuadSwapHorizontal(data[2].u8.xyz);
+    data[invocation].u8     = subgroupQuadSwapHorizontal(data[3].u8);
+
+    data[invocation].u8.x   = subgroupQuadSwapVertical(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupQuadSwapVertical(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupQuadSwapVertical(data[2].u8.xyz);
+    data[invocation].u8     = subgroupQuadSwapVertical(data[3].u8);
+
+    data[invocation].u8.x   = subgroupQuadSwapDiagonal(data[0].u8.x);
+    data[invocation].u8.xy  = subgroupQuadSwapDiagonal(data[1].u8.xy);
+    data[invocation].u8.xyz = subgroupQuadSwapDiagonal(data[2].u8.xyz);
+    data[invocation].u8     = subgroupQuadSwapDiagonal(data[3].u8);
+
+    data[invocation].i16.x   = subgroupQuadBroadcast(data[0].i16.x, 1);
+    data[invocation].i16.xy  = subgroupQuadBroadcast(data[1].i16.xy, 1);
+    data[invocation].i16.xyz = subgroupQuadBroadcast(data[2].i16.xyz, 1);
+    data[invocation].i16     = subgroupQuadBroadcast(data[3].i16, 1);
+
+    data[invocation].i16.x   = subgroupQuadSwapHorizontal(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupQuadSwapHorizontal(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupQuadSwapHorizontal(data[2].i16.xyz);
+    data[invocation].i16     = subgroupQuadSwapHorizontal(data[3].i16);
+
+    data[invocation].i16.x   = subgroupQuadSwapVertical(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupQuadSwapVertical(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupQuadSwapVertical(data[2].i16.xyz);
+    data[invocation].i16     = subgroupQuadSwapVertical(data[3].i16);
+
+    data[invocation].i16.x   = subgroupQuadSwapDiagonal(data[0].i16.x);
+    data[invocation].i16.xy  = subgroupQuadSwapDiagonal(data[1].i16.xy);
+    data[invocation].i16.xyz = subgroupQuadSwapDiagonal(data[2].i16.xyz);
+    data[invocation].i16     = subgroupQuadSwapDiagonal(data[3].i16);
+
+    data[invocation].u16.x   = subgroupQuadBroadcast(data[0].u16.x, 1);
+    data[invocation].u16.xy  = subgroupQuadBroadcast(data[1].u16.xy, 1);
+    data[invocation].u16.xyz = subgroupQuadBroadcast(data[2].u16.xyz, 1);
+    data[invocation].u16     = subgroupQuadBroadcast(data[3].u16, 1);
+
+    data[invocation].u16.x   = subgroupQuadSwapHorizontal(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupQuadSwapHorizontal(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupQuadSwapHorizontal(data[2].u16.xyz);
+    data[invocation].u16     = subgroupQuadSwapHorizontal(data[3].u16);
+
+    data[invocation].u16.x   = subgroupQuadSwapVertical(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupQuadSwapVertical(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupQuadSwapVertical(data[2].u16.xyz);
+    data[invocation].u16     = subgroupQuadSwapVertical(data[3].u16);
+
+    data[invocation].u16.x   = subgroupQuadSwapDiagonal(data[0].u16.x);
+    data[invocation].u16.xy  = subgroupQuadSwapDiagonal(data[1].u16.xy);
+    data[invocation].u16.xyz = subgroupQuadSwapDiagonal(data[2].u16.xyz);
+    data[invocation].u16     = subgroupQuadSwapDiagonal(data[3].u16);
+
+    data[invocation].i64.x   = subgroupQuadBroadcast(data[0].i64.x, 1);
+    data[invocation].i64.xy  = subgroupQuadBroadcast(data[1].i64.xy, 1);
+    data[invocation].i64.xyz = subgroupQuadBroadcast(data[2].i64.xyz, 1);
+    data[invocation].i64     = subgroupQuadBroadcast(data[3].i64, 1);
+
+    data[invocation].i64.x   = subgroupQuadSwapHorizontal(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupQuadSwapHorizontal(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupQuadSwapHorizontal(data[2].i64.xyz);
+    data[invocation].i64     = subgroupQuadSwapHorizontal(data[3].i64);
+
+    data[invocation].i64.x   = subgroupQuadSwapVertical(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupQuadSwapVertical(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupQuadSwapVertical(data[2].i64.xyz);
+    data[invocation].i64     = subgroupQuadSwapVertical(data[3].i64);
+
+    data[invocation].i64.x   = subgroupQuadSwapDiagonal(data[0].i64.x);
+    data[invocation].i64.xy  = subgroupQuadSwapDiagonal(data[1].i64.xy);
+    data[invocation].i64.xyz = subgroupQuadSwapDiagonal(data[2].i64.xyz);
+    data[invocation].i64     = subgroupQuadSwapDiagonal(data[3].i64);
+
+    data[invocation].u64.x   = subgroupQuadBroadcast(data[0].u64.x, 1);
+    data[invocation].u64.xy  = subgroupQuadBroadcast(data[1].u64.xy, 1);
+    data[invocation].u64.xyz = subgroupQuadBroadcast(data[2].u64.xyz, 1);
+    data[invocation].u64     = subgroupQuadBroadcast(data[3].u64, 1);
+
+    data[invocation].u64.x   = subgroupQuadSwapHorizontal(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupQuadSwapHorizontal(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupQuadSwapHorizontal(data[2].u64.xyz);
+    data[invocation].u64     = subgroupQuadSwapHorizontal(data[3].u64);
+
+    data[invocation].u64.x   = subgroupQuadSwapVertical(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupQuadSwapVertical(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupQuadSwapVertical(data[2].u64.xyz);
+    data[invocation].u64     = subgroupQuadSwapVertical(data[3].u64);
+
+    data[invocation].u64.x   = subgroupQuadSwapDiagonal(data[0].u64.x);
+    data[invocation].u64.xy  = subgroupQuadSwapDiagonal(data[1].u64.xy);
+    data[invocation].u64.xyz = subgroupQuadSwapDiagonal(data[2].u64.xyz);
+    data[invocation].u64     = subgroupQuadSwapDiagonal(data[3].u64);
+
+    data[invocation].f16.x   = subgroupQuadBroadcast(data[0].f16.x, 1);
+    data[invocation].f16.xy  = subgroupQuadBroadcast(data[1].f16.xy, 1);
+    data[invocation].f16.xyz = subgroupQuadBroadcast(data[2].f16.xyz, 1);
+    data[invocation].f16     = subgroupQuadBroadcast(data[3].f16, 1);
+
+    data[invocation].f16.x   = subgroupQuadSwapHorizontal(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupQuadSwapHorizontal(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupQuadSwapHorizontal(data[2].f16.xyz);
+    data[invocation].f16     = subgroupQuadSwapHorizontal(data[3].f16);
+
+    data[invocation].f16.x   = subgroupQuadSwapVertical(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupQuadSwapVertical(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupQuadSwapVertical(data[2].f16.xyz);
+    data[invocation].f16     = subgroupQuadSwapVertical(data[3].f16);
+
+    data[invocation].f16.x   = subgroupQuadSwapDiagonal(data[0].f16.x);
+    data[invocation].f16.xy  = subgroupQuadSwapDiagonal(data[1].f16.xy);
+    data[invocation].f16.xyz = subgroupQuadSwapDiagonal(data[2].f16.xyz);
+    data[invocation].f16     = subgroupQuadSwapDiagonal(data[3].f16);
+}

Test/spv.subgroupExtendedTypesShuffle.comp

@@ -0,0 +1,95 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_shuffle: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupShuffle(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffle(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffle(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffle(data[3].i8,      invocation);
+
+    data[invocation].i8.x   = subgroupShuffleXor(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffleXor(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffleXor(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffleXor(data[3].i8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffle(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffle(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffle(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffle(data[3].u8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffleXor(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffleXor(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffleXor(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffleXor(data[3].u8,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffle(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffle(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffle(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffle(data[3].i16,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffleXor(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffleXor(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffleXor(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffleXor(data[3].i16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffle(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffle(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffle(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffle(data[3].u16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffleXor(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffleXor(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffleXor(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffleXor(data[3].u16,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffle(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffle(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffle(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffle(data[3].i64,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffleXor(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffleXor(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffleXor(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffleXor(data[3].i64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffle(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffle(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffle(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffle(data[3].u64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffleXor(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffleXor(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffleXor(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffleXor(data[3].u64,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffle(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffle(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffle(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffle(data[3].f16,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffleXor(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffleXor(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffleXor(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffleXor(data[3].f16,      invocation);
+}

Test/spv.subgroupExtendedTypesShuffleNeg.comp

@@ -0,0 +1,95 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_shuffle: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupShuffle(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffle(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffle(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffle(data[3].i8,      invocation);
+
+    data[invocation].i8.x   = subgroupShuffleXor(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffleXor(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffleXor(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffleXor(data[3].i8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffle(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffle(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffle(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffle(data[3].u8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffleXor(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffleXor(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffleXor(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffleXor(data[3].u8,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffle(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffle(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffle(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffle(data[3].i16,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffleXor(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffleXor(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffleXor(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffleXor(data[3].i16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffle(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffle(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffle(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffle(data[3].u16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffleXor(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffleXor(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffleXor(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffleXor(data[3].u16,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffle(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffle(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffle(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffle(data[3].i64,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffleXor(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffleXor(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffleXor(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffleXor(data[3].i64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffle(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffle(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffle(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffle(data[3].u64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffleXor(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffleXor(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffleXor(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffleXor(data[3].u64,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffle(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffle(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffle(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffle(data[3].f16,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffleXor(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffleXor(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffleXor(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffleXor(data[3].f16,      invocation);
+}

Test/spv.subgroupExtendedTypesShuffleRelative.comp

@@ -0,0 +1,95 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_shuffle_relative: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupShuffleUp(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffleUp(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffleUp(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffleUp(data[3].i8,      invocation);
+
+    data[invocation].i8.x   = subgroupShuffleDown(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffleDown(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffleDown(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffleDown(data[3].i8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffleUp(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffleUp(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffleUp(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffleUp(data[3].u8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffleDown(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffleDown(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffleDown(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffleDown(data[3].u8,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffleUp(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffleUp(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffleUp(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffleUp(data[3].i16,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffleDown(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffleDown(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffleDown(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffleDown(data[3].i16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffleUp(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffleUp(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffleUp(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffleUp(data[3].u16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffleDown(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffleDown(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffleDown(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffleDown(data[3].u16,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffleUp(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffleUp(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffleUp(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffleUp(data[3].i64,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffleDown(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffleDown(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffleDown(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffleDown(data[3].i64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffleUp(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffleUp(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffleUp(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffleUp(data[3].u64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffleDown(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffleDown(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffleDown(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffleDown(data[3].u64,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffleUp(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffleUp(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffleUp(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffleUp(data[3].f16,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffleDown(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffleDown(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffleDown(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffleDown(data[3].f16,      invocation);
+}

Test/spv.subgroupExtendedTypesShuffleRelativeNeg.comp

@@ -0,0 +1,95 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_shuffle_relative: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    data[invocation].i8.x   = subgroupShuffleUp(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffleUp(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffleUp(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffleUp(data[3].i8,      invocation);
+
+    data[invocation].i8.x   = subgroupShuffleDown(data[0].i8.x,    invocation);
+    data[invocation].i8.xy  = subgroupShuffleDown(data[1].i8.xy,   invocation);
+    data[invocation].i8.xyz = subgroupShuffleDown(data[2].i8.xyz,  invocation);
+    data[invocation].i8     = subgroupShuffleDown(data[3].i8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffleUp(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffleUp(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffleUp(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffleUp(data[3].u8,      invocation);
+
+    data[invocation].u8.x   = subgroupShuffleDown(data[0].u8.x,    invocation);
+    data[invocation].u8.xy  = subgroupShuffleDown(data[1].u8.xy,   invocation);
+    data[invocation].u8.xyz = subgroupShuffleDown(data[2].u8.xyz,  invocation);
+    data[invocation].u8     = subgroupShuffleDown(data[3].u8,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffleUp(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffleUp(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffleUp(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffleUp(data[3].i16,      invocation);
+
+    data[invocation].i16.x   = subgroupShuffleDown(data[0].i16.x,    invocation);
+    data[invocation].i16.xy  = subgroupShuffleDown(data[1].i16.xy,   invocation);
+    data[invocation].i16.xyz = subgroupShuffleDown(data[2].i16.xyz,  invocation);
+    data[invocation].i16     = subgroupShuffleDown(data[3].i16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffleUp(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffleUp(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffleUp(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffleUp(data[3].u16,      invocation);
+
+    data[invocation].u16.x   = subgroupShuffleDown(data[0].u16.x,    invocation);
+    data[invocation].u16.xy  = subgroupShuffleDown(data[1].u16.xy,   invocation);
+    data[invocation].u16.xyz = subgroupShuffleDown(data[2].u16.xyz,  invocation);
+    data[invocation].u16     = subgroupShuffleDown(data[3].u16,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffleUp(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffleUp(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffleUp(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffleUp(data[3].i64,      invocation);
+
+    data[invocation].i64.x   = subgroupShuffleDown(data[0].i64.x,    invocation);
+    data[invocation].i64.xy  = subgroupShuffleDown(data[1].i64.xy,   invocation);
+    data[invocation].i64.xyz = subgroupShuffleDown(data[2].i64.xyz,  invocation);
+    data[invocation].i64     = subgroupShuffleDown(data[3].i64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffleUp(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffleUp(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffleUp(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffleUp(data[3].u64,      invocation);
+
+    data[invocation].u64.x   = subgroupShuffleDown(data[0].u64.x,    invocation);
+    data[invocation].u64.xy  = subgroupShuffleDown(data[1].u64.xy,   invocation);
+    data[invocation].u64.xyz = subgroupShuffleDown(data[2].u64.xyz,  invocation);
+    data[invocation].u64     = subgroupShuffleDown(data[3].u64,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffleUp(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffleUp(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffleUp(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffleUp(data[3].f16,      invocation);
+
+    data[invocation].f16.x   = subgroupShuffleDown(data[0].f16.x,    invocation);
+    data[invocation].f16.xy  = subgroupShuffleDown(data[1].f16.xy,   invocation);
+    data[invocation].f16.xyz = subgroupShuffleDown(data[2].f16.xyz,  invocation);
+    data[invocation].f16     = subgroupShuffleDown(data[3].f16,      invocation);
+}

Test/spv.subgroupExtendedTypesVote.comp

@@ -0,0 +1,66 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_vote: enable
+#extension GL_EXT_shader_subgroup_extended_types_int8: enable
+#extension GL_EXT_shader_subgroup_extended_types_int16: enable
+#extension GL_EXT_shader_subgroup_extended_types_int64: enable
+#extension GL_EXT_shader_subgroup_extended_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+    int r;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    if (subgroupAll(data[invocation].r < 0))
+    {
+        data[invocation].r = int(subgroupAllEqual(data[0].i8.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].i8.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].i8.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].i8));
+
+        data[invocation].r = int(subgroupAllEqual(data[0].u8.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].u8.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].u8.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].u8));
+
+        data[invocation].r = int(subgroupAllEqual(data[0].i16.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].i16.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].i16.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].i16));
+
+        data[invocation].r = int(subgroupAllEqual(data[0].u16.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].u16.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].u16.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].u16));
+    }
+    else if (subgroupAny(data[invocation].r < 0))
+    {
+        data[invocation].r = int(subgroupAllEqual(data[0].i64.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].i64.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].i64.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].i64));
+        
+        data[invocation].r = int(subgroupAllEqual(data[0].u64.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].u64.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].u64.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].u64));
+        
+        data[invocation].r = int(subgroupAllEqual(data[0].f16.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].f16.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].f16.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].f16));
+    }
+}

Test/spv.subgroupExtendedTypesVoteNeg.comp

@@ -0,0 +1,66 @@
+#version 450
+
+#extension GL_KHR_shader_subgroup_vote: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int8: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int16: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_int64: enable
+#extension GL_EXT_shader_explicit_arithmetic_types_float16: enable
+
+layout (local_size_x = 8) in;
+
+layout(binding = 0) buffer Buffers
+{
+    i8vec4 i8;
+    u8vec4 u8;
+    i16vec4 i16;
+    u16vec4 u16;
+    i64vec4 i64;
+    u64vec4 u64;
+    f16vec4 f16;
+    int r;
+} data[4];
+
+void main()
+{
+    uint invocation = (gl_SubgroupInvocationID + gl_SubgroupSize) % 4;
+
+    if (subgroupAll(data[invocation].r < 0))
+    {
+        data[invocation].r = int(subgroupAllEqual(data[0].i8.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].i8.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].i8.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].i8));
+
+        data[invocation].r = int(subgroupAllEqual(data[0].u8.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].u8.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].u8.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].u8));
+
+        data[invocation].r = int(subgroupAllEqual(data[0].i16.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].i16.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].i16.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].i16));
+
+        data[invocation].r = int(subgroupAllEqual(data[0].u16.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].u16.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].u16.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].u16));
+    }
+    else if (subgroupAny(data[invocation].r < 0))
+    {
+        data[invocation].r = int(subgroupAllEqual(data[0].i64.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].i64.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].i64.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].i64));
+        
+        data[invocation].r = int(subgroupAllEqual(data[0].u64.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].u64.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].u64.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].u64));
+        
+        data[invocation].r = int(subgroupAllEqual(data[0].f16.x));
+        data[invocation].r = int(subgroupAllEqual(data[1].f16.xy));
+        data[invocation].r = int(subgroupAllEqual(data[2].f16.xyz));
+        data[invocation].r = int(subgroupAllEqual(data[3].f16));
+    }
+}

glslang/MachineIndependent/ParseHelper.cpp

@@ -2202,6 +2202,30 @@ void TParseContext::builtInOpCheck(const TSourceLoc& loc, const TFunction& fnCan
         // these require SPIR-V 1.3
         if (spvVersion.spv > 0 && spvVersion.spv < EShTargetSpv_1_3)
             error(loc, "requires SPIR-V 1.3", "subgroup op", "");
+
+        // Check that if extended types are being used that the correct extensions are enabled.
+        if (arg0 != nullptr) {
+            const TType& type = arg0->getType();
+            switch (type.getBasicType()) {
+            default:
+                break;
+            case EbtInt8:
+            case EbtUint8:
+                requireExtensions(loc, 1, &E_GL_EXT_shader_subgroup_extended_types_int8, type.getCompleteString().c_str());
+                break;
+            case EbtInt16:
+            case EbtUint16:
+                requireExtensions(loc, 1, &E_GL_EXT_shader_subgroup_extended_types_int16, type.getCompleteString().c_str());
+                break;
+            case EbtInt64:
+            case EbtUint64:
+                requireExtensions(loc, 1, &E_GL_EXT_shader_subgroup_extended_types_int64, type.getCompleteString().c_str());
+                break;
+            case EbtFloat16:
+                requireExtensions(loc, 1, &E_GL_EXT_shader_subgroup_extended_types_float16, type.getCompleteString().c_str());
+                break;
+            }
+        }
     }
 }
 

glslang/MachineIndependent/Versions.cpp

@@ -300,6 +300,12 @@ void TParseVersions::initializeExtensionBehavior()
     extensionBehavior[E_GL_EXT_shader_explicit_arithmetic_types_float16] = EBhDisable;
     extensionBehavior[E_GL_EXT_shader_explicit_arithmetic_types_float32] = EBhDisable;
     extensionBehavior[E_GL_EXT_shader_explicit_arithmetic_types_float64] = EBhDisable;
+
+    // subgroup extended types
+    extensionBehavior[E_GL_EXT_shader_subgroup_extended_types_int8]    = EBhDisable;
+    extensionBehavior[E_GL_EXT_shader_subgroup_extended_types_int16]   = EBhDisable;
+    extensionBehavior[E_GL_EXT_shader_subgroup_extended_types_int64]   = EBhDisable;
+    extensionBehavior[E_GL_EXT_shader_subgroup_extended_types_float16] = EBhDisable;
 }
 #endif // GLSLANG_WEB
 
@@ -447,6 +453,11 @@ void TParseVersions::getPreamble(std::string& preamble)
             "#define GL_EXT_shader_explicit_arithmetic_types_float16 1\n"
             "#define GL_EXT_shader_explicit_arithmetic_types_float32 1\n"
             "#define GL_EXT_shader_explicit_arithmetic_types_float64 1\n"
+
+            "#define GL_EXT_shader_subgroup_extended_types_int8 1\n"
+            "#define GL_EXT_shader_subgroup_extended_types_int16 1\n"
+            "#define GL_EXT_shader_subgroup_extended_types_int64 1\n"
+            "#define GL_EXT_shader_subgroup_extended_types_float16 1\n"
             ;
 
         if (version >= 150) {
@@ -826,6 +837,15 @@ void TParseVersions::updateExtensionBehavior(int line, const char* extension, co
         updateExtensionBehavior(line, "GL_EXT_buffer_reference", behaviorString);
     else if (strcmp(extension, "GL_NV_integer_cooperative_matrix") == 0)
         updateExtensionBehavior(line, "GL_NV_cooperative_matrix", behaviorString);
+    // subgroup extended types to explicit types
+    else if (strcmp(extension, "GL_EXT_shader_subgroup_extended_types_int8") == 0)
+        updateExtensionBehavior(line, "GL_EXT_shader_explicit_arithmetic_types_int8", behaviorString);
+    else if (strcmp(extension, "GL_EXT_shader_subgroup_extended_types_int16") == 0)
+        updateExtensionBehavior(line, "GL_EXT_shader_explicit_arithmetic_types_int16", behaviorString);
+    else if (strcmp(extension, "GL_EXT_shader_subgroup_extended_types_int64") == 0)
+        updateExtensionBehavior(line, "GL_EXT_shader_explicit_arithmetic_types_int64", behaviorString);
+    else if (strcmp(extension, "GL_EXT_shader_subgroup_extended_types_float16") == 0)
+        updateExtensionBehavior(line, "GL_EXT_shader_explicit_arithmetic_types_float16", behaviorString);
 }
 
 void TParseVersions::updateExtensionBehavior(const char* extension, TExtensionBehavior behavior)

glslang/MachineIndependent/Versions.h

@@ -257,7 +257,7 @@ const char* const E_GL_OES_tessellation_point_size              = "GL_OES_tessel
 const char* const E_GL_OES_texture_buffer                       = "GL_OES_texture_buffer";
 const char* const E_GL_OES_texture_cube_map_array               = "GL_OES_texture_cube_map_array";
 
-// KHX
+// EXT
 const char* const E_GL_EXT_shader_explicit_arithmetic_types          = "GL_EXT_shader_explicit_arithmetic_types";
 const char* const E_GL_EXT_shader_explicit_arithmetic_types_int8     = "GL_EXT_shader_explicit_arithmetic_types_int8";
 const char* const E_GL_EXT_shader_explicit_arithmetic_types_int16    = "GL_EXT_shader_explicit_arithmetic_types_int16";
@@ -267,6 +267,11 @@ const char* const E_GL_EXT_shader_explicit_arithmetic_types_float16  = "GL_EXT_s
 const char* const E_GL_EXT_shader_explicit_arithmetic_types_float32  = "GL_EXT_shader_explicit_arithmetic_types_float32";
 const char* const E_GL_EXT_shader_explicit_arithmetic_types_float64  = "GL_EXT_shader_explicit_arithmetic_types_float64";
 
+const char* const E_GL_EXT_shader_subgroup_extended_types_int8    = "GL_EXT_shader_subgroup_extended_types_int8";
+const char* const E_GL_EXT_shader_subgroup_extended_types_int16   = "GL_EXT_shader_subgroup_extended_types_int16";
+const char* const E_GL_EXT_shader_subgroup_extended_types_int64   = "GL_EXT_shader_subgroup_extended_types_int64";
+const char* const E_GL_EXT_shader_subgroup_extended_types_float16 = "GL_EXT_shader_subgroup_extended_types_float16";
+
 // Arrays of extensions for the above AEP duplications
 
 const char* const AEP_geometry_shader[] = { E_GL_EXT_geometry_shader, E_GL_OES_geometry_shader };

gtests/Spv.FromFile.cpp

@@ -459,6 +459,22 @@ INSTANTIATE_TEST_CASE_P(
         "spv.subgroupShuffleRelative.comp",
         "spv.subgroupQuad.comp",
         "spv.subgroupVote.comp",
+        "spv.subgroupExtendedTypesArithmetic.comp",
+        "spv.subgroupExtendedTypesArithmeticNeg.comp",
+        "spv.subgroupExtendedTypesBallot.comp",
+        "spv.subgroupExtendedTypesBallotNeg.comp",
+        "spv.subgroupExtendedTypesClustered.comp",
+        "spv.subgroupExtendedTypesClusteredNeg.comp",
+        "spv.subgroupExtendedTypesPartitioned.comp",
+        "spv.subgroupExtendedTypesPartitionedNeg.comp",
+        "spv.subgroupExtendedTypesShuffle.comp",
+        "spv.subgroupExtendedTypesShuffleNeg.comp",
+        "spv.subgroupExtendedTypesShuffleRelative.comp",
+        "spv.subgroupExtendedTypesShuffleRelativeNeg.comp",
+        "spv.subgroupExtendedTypesQuad.comp",
+        "spv.subgroupExtendedTypesQuadNeg.comp",
+        "spv.subgroupExtendedTypesVote.comp",
+        "spv.subgroupExtendedTypesVoteNeg.comp",
         "spv.vulkan110.storageBuffer.vert",
     })),
     FileNameAsCustomTestSuffix