Update FindAVX.cmake (#404)

* make AVX_FOUND is default value to WITH AVX
* let AVX_FLAG always keep -mavx flag since compiler can build binary with -mavx even CPU does not support avx.

CMakeLists.txt

@@ -109,11 +109,9 @@ else()
     set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} "-g -O3 --use_fast_math")
 
     if(WITH_AVX)
-        if(AVX_FOUND)
-            set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} "-Xcompiler -mavx")
-        endif(AVX_FOUND)
+        set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} "-Xcompiler ${AVX_FLAG}")
     else(WITH_AVX)
-        set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} "-Xcompiler -msse3")
+        set(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS} "-Xcompiler ${SSE3_FLAG}")
     endif(WITH_AVX)
 
     if(WITH_DSO)
@@ -138,11 +136,11 @@ if(NOT WITH_TIMER)
 endif(NOT WITH_TIMER)
 
 if(WITH_AVX)
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${AVX_FLAGS}")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${AVX_FLAGS}")
+    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${AVX_FLAG}")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${AVX_FLAG}")
 else(WITH_AVX)
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -msse3")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse3")
+    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${SSE3_FLAG}")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${SSE3_FLAG}")
 endif(WITH_AVX)
 
 if(WITH_PYTHON)

cmake/FindAVX.cmake

@@ -3,36 +3,55 @@
 
 INCLUDE(CheckCXXSourceRuns)
 
-SET(FIND_AVX_10)
-SET(FIND_AVX_20)
-SET(AVX_FLAGS)
-SET(AVX_FOUND)
-
-# Check AVX 2
-SET(CMAKE_REQUIRED_FLAGS)
 IF(CMAKE_COMPILER_IS_GNUCC OR CMAKE_COMPILER_IS_GNUCXX OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")
-  SET(CMAKE_REQUIRED_FLAGS "-mavx2")
-ELSEIF(MSVC AND NOT CMAKE_CL_64)  # reserve for WINDOWS
-  SET(CMAKE_REQUIRED_FLAGS "/arch:AVX2")
+    set(MMX_FLAG "-mmmx")
+    set(SSE2_FLAG "-msse2")
+    set(SSE3_FLAG "-msse3")
+    SET(AVX_FLAG "-mavx")
+    SET(AVX2_FLAG "-mavx2")
+ELSEIF(MSVC)
+    set(MMX_FLAG "/arch:MMX")
+    set(SSE2_FLAG "/arch:SSE2")
+    set(SSE3_FLAG "/arch:SSE3")
+    SET(AVX_FLAG "/arch:AVX")
+    SET(AVX2_FLAG "/arch:AVX2")
 ENDIF()
 
+# Check  MMX
+set(CMAKE_REQUIRED_FLAGS ${MMX_FLAG})
 CHECK_CXX_SOURCE_RUNS("
-#include <immintrin.h>
+#include <mmintrin.h>
 int main()
 {
-    __m256i a = _mm256_set_epi32 (-1, 2, -3, 4, -1, 2, -3, 4);
-    __m256i result = _mm256_abs_epi32 (a);
+    _mm_setzero_si64();
     return 0;
-}" FIND_AVX_20)
+}" MMX_FOUND)
 
-# Check AVX
-SET(CMAKE_REQUIRED_FLAGS)
-IF(CMAKE_COMPILER_IS_GNUCC OR CMAKE_COMPILER_IS_GNUCXX OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")
-    SET(CMAKE_REQUIRED_FLAGS "-mavx")
-ELSEIF(MSVC AND NOT CMAKE_CL_64)
-    SET(CMAKE_REQUIRED_FLAGS "/arch:AVX")
-endif()
+# Check SSE2
+set(CMAKE_REQUIRED_FLAGS ${SSE2_FLAG})
+CHECK_CXX_SOURCE_RUNS("
+#include <emmintrin.h>
+int main()
+{
+    _mm_setzero_si128();
+    return 0;
+}" SSE2_FOUND)
 
+# Check SSE3
+set(CMAKE_REQUIRED_FLAGS ${SSE3_FLAG})
+CHECK_CXX_SOURCE_RUNS("
+#include <pmmintrin.h>
+int main()
+{
+    __m128d a = _mm_set1_pd(6.28);
+    __m128d b = _mm_set1_pd(3.14);
+    __m128d result = _mm_addsub_pd(a, b);
+    result = _mm_movedup_pd(result);
+    return 0;
+}" SSE3_FOUND)
+
+# Check AVX
+set(CMAKE_REQUIRED_FLAGS ${AVX_FLAG})
 CHECK_CXX_SOURCE_RUNS("
 #include <immintrin.h>
 int main()
@@ -41,25 +60,17 @@ int main()
     __m256 b = _mm256_set_ps (1.0f, 2.0f, 3.0f, 4.0f, 1.0f, 2.0f, 3.0f, 4.0f);
     __m256 result = _mm256_add_ps (a, b);
     return 0;
-}" FIND_AVX_10)
-
-IF(${FIND_AVX_20})
-    IF(CMAKE_COMPILER_IS_GNUCC OR CMAKE_COMPILER_IS_GNUCXX OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")
-        SET(AVX_FLAGS "${AVX_FLAGS} -mavx2")
-    ELSEIF(MSVC)
-        SET(AVX_FLAGS "${AVX_FLAGS} /arch:AVX2")
-    ENDIF()
-ENDIF()
+}" AVX_FOUND)
 
-IF(${FIND_AVX_10})
-    IF(CMAKE_COMPILER_IS_GNUCC OR CMAKE_COMPILER_IS_GNUCXX OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")
-        SET(AVX_FLAGS "${AVX_FLAGS} -mavx")
-    ELSEIF(MSVC)
-        SET(AVX_FLAGS "${AVX_FLAGS} /arch:AVX")
-    ENDIF()
-ENDIF()
+# Check AVX 2
+set(CMAKE_REQUIRED_FLAGS ${AVX2_FLAG})
+CHECK_CXX_SOURCE_RUNS("
+#include <immintrin.h>
+int main()
+{
+    __m256i a = _mm256_set_epi32 (-1, 2, -3, 4, -1, 2, -3, 4);
+    __m256i result = _mm256_abs_epi32 (a);
+    return 0;
+}" AVX2_FOUND)
 
-IF(${FIND_AVX_10})
-    SET(AVX_FOUND TRUE)
-    MESSAGE(STATUS "Find CPU supports ${AVX_FLAGS}.")
-ENDIF()
+mark_as_advanced(MMX_FOUND SSE2_FOUND SSE3_FOUND AVX_FOUND AVX2_FOUND)