Optimizations of log2 for ivec4

test/core/core_func_common.cpp

@@ -887,12 +887,6 @@ namespace sign
 			Error += Data[i].Return == Result ? 0 : 1;
 		}
 
-		for(std::size_t i = 0; i < sizeof(Data) / sizeof(type<glm::int32>); ++i)
-		{
-			glm::int32 Result = sign_sub(Data[i].Value);
-			Error += Data[i].Return == Result ? 0 : 1;
-		}
-
 		return Error;
 	}
 

test/gtc/gtc_integer.cpp

@@ -7,9 +7,11 @@
 // File    : test/gtc/integer.cpp
 ///////////////////////////////////////////////////////////////////////////////////////////////////
 
+#define GLM_FORCE_INLINE
 #include <glm/gtc/integer.hpp>
 #include <glm/gtc/type_precision.hpp>
 #include <glm/gtc/vec1.hpp>
+#include <glm/gtx/type_aligned.hpp>
 #include <glm/vector_relational.hpp>
 #include <glm/vec2.hpp>
 #include <glm/vec3.hpp>
@@ -48,6 +50,126 @@ namespace log2_
 	int perf()
 	{
 		int Error = 0;
+		std::size_t const Count(100000000);
+
+		{
+			std::vector<int> Result;
+			Result.resize(Count);
+
+			std::clock_t Begin = clock();
+
+			for(std::size_t i = 0; i < Count; ++i)
+				Result[i] = glm::log2(static_cast<int>(i));
+
+			std::clock_t End = clock();
+
+			printf("glm::log2<int>: %d clocks\n", End - Begin);
+		}
+
+		{
+			std::vector<glm::ivec4> Result;
+			Result.resize(Count);
+
+			std::clock_t Begin = clock();
+
+			for(std::size_t i = 0; i < Count; ++i)
+				Result[i] = glm::log2(glm::ivec4(i));
+
+			std::clock_t End = clock();
+
+			printf("glm::log2<ivec4>: %d clocks\n", End - Begin);
+		}
+
+#		if(GLM_ARCH != GLM_ARCH_PURE) && (GLM_COMPILER & (GLM_COMPILER_VC | GLM_COMPILER_APPLE_CLANG | GLM_COMPILER_LLVM))
+		{
+			std::vector<glm::ivec4> Result;
+			Result.resize(Count);
+
+			std::clock_t Begin = clock();
+
+			for(std::size_t i = 0; i < Count; ++i)
+			{
+				glm::tvec4<unsigned long, glm::defaultp> Tmp(glm::uninitialize);
+				_BitScanReverse(&Tmp.x, i);
+				_BitScanReverse(&Tmp.y, i);
+				_BitScanReverse(&Tmp.z, i);
+				_BitScanReverse(&Tmp.w, i);
+				Result[i] = glm::ivec4(Tmp);
+			}
+
+			std::clock_t End = clock();
+
+			printf("glm::log2<ivec4> inlined: %d clocks\n", End - Begin);
+		}
+
+
+		{
+			std::vector<glm::tvec4<unsigned long, glm::defaultp> > Result;
+			Result.resize(Count);
+
+			std::clock_t Begin = clock();
+
+			for(std::size_t i = 0; i < Count; ++i)
+			{
+				_BitScanReverse(&Result[i].x, i);
+				_BitScanReverse(&Result[i].y, i);
+				_BitScanReverse(&Result[i].z, i);
+				_BitScanReverse(&Result[i].w, i);
+			}
+
+			std::clock_t End = clock();
+
+			printf("glm::log2<ivec4> inlined no cast: %d clocks\n", End - Begin);
+		}
+
+
+		{
+			std::vector<glm::ivec4> Result;
+			Result.resize(Count);
+
+			std::clock_t Begin = clock();
+
+			for(std::size_t i = 0; i < Count; ++i)
+			{
+				_BitScanReverse(reinterpret_cast<unsigned long*>(&Result[i].x), i);
+				_BitScanReverse(reinterpret_cast<unsigned long*>(&Result[i].y), i);
+				_BitScanReverse(reinterpret_cast<unsigned long*>(&Result[i].z), i);
+				_BitScanReverse(reinterpret_cast<unsigned long*>(&Result[i].w), i);
+			}
+
+			std::clock_t End = clock();
+
+			printf("glm::log2<ivec4> reinterpret: %d clocks\n", End - Begin);
+		}
+#		endif//GLM_ARCH != GLM_ARCH_PURE
+
+		{
+			std::vector<float> Result;
+			Result.resize(Count);
+
+			std::clock_t Begin = clock();
+
+			for(std::size_t i = 0; i < Count; ++i)
+				Result[i] = glm::log2(static_cast<float>(i));
+
+			std::clock_t End = clock();
+
+			printf("glm::log2<float>: %d clocks\n", End - Begin);
+		}
+
+		{
+			std::vector<glm::vec4> Result;
+			Result.resize(Count);
+
+			std::clock_t Begin = clock();
+
+			for(std::size_t i = 0; i < Count; ++i)
+				Result[i] = glm::log2(glm::vec4(i));
+
+			std::clock_t End = clock();
+
+			printf("glm::log2<vec4>: %d clocks\n", End - Begin);
+		}
 
 		return Error;
 	}