diff options
| author | Thomas Dinges <blender@dingto.org> | 2014-01-16 20:04:11 +0400 |
|---|---|---|
| committer | Thomas Dinges <blender@dingto.org> | 2014-01-16 20:04:11 +0400 |
| commit | de28a4d4b2c9397c5233a5ee1dbf1400f450a15c (patch) | |
| tree | 1fe23de963e206af3fb2ff2d9e2e3393cd89149c /intern/cycles/CMakeLists.txt | |
| parent | 7c6d52eb07c4bd8142a95eca1dbdc794063859b8 (diff) | |
Cycles: Add an AVX kernel for CPU rendering.
* AVX is available on Intel Sandy Bridge and newer and AMD Bulldozer and newer.
* We don't use dedicated AVX intrinsics yet, but gcc auto vectorization gives a 3% performance improvement for Caminandes. Tested on an i5-3570, Linux x64.
* No change for Windows yet, MSVC 2008 does not support AVX.
Reviewed by: brecht
Differential Revision: https://developer.blender.org/D216
Diffstat (limited to 'intern/cycles/CMakeLists.txt')
| -rw-r--r-- | intern/cycles/CMakeLists.txt | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/intern/cycles/CMakeLists.txt b/intern/cycles/CMakeLists.txt index 6fa6260c81e..cc1f5978dc1 100644 --- a/intern/cycles/CMakeLists.txt +++ b/intern/cycles/CMakeLists.txt @@ -14,10 +14,12 @@ if(WIN32 AND MSVC) set(CYCLES_SSE2_KERNEL_FLAGS "/fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") set(CYCLES_SSE3_KERNEL_FLAGS "/fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") set(CYCLES_SSE41_KERNEL_FLAGS "/fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") + set(CYCLES_AVX_KERNEL_FLAGS "/fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") #/arch:AVX for VC2012 and above else() set(CYCLES_SSE2_KERNEL_FLAGS "/arch:SSE2 /fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") set(CYCLES_SSE3_KERNEL_FLAGS "/arch:SSE2 /fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") set(CYCLES_SSE41_KERNEL_FLAGS "/arch:SSE2 /fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") + set(CYCLES_AVX_KERNEL_FLAGS "/arch:SSE2 /fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") #/arch:AVX for VC2012 and above endif() set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") @@ -28,11 +30,13 @@ elseif(CMAKE_COMPILER_IS_GNUCC) set(CYCLES_SSE2_KERNEL_FLAGS "-ffast-math -msse -msse2 -mfpmath=sse") set(CYCLES_SSE3_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3 -mfpmath=sse") set(CYCLES_SSE41_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3 -msse4.1 -mfpmath=sse") + set(CYCLES_AVX_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3 -msse4.1 -mavx -mfpmath=sse") set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -ffast-math") elseif(CMAKE_CXX_COMPILER_ID MATCHES "Clang") set(CYCLES_SSE2_KERNEL_FLAGS "-ffast-math -msse -msse2") set(CYCLES_SSE3_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3") set(CYCLES_SSE41_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3 -msse4.1") + set(CYCLES_SSE41_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3 -msse4.1 -mavx") set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -ffast-math") endif() |