diff options
author | Martijn Berger <martijn.berger@gmail.com> | 2013-11-22 17:16:47 +0400 |
---|---|---|
committer | Brecht Van Lommel <brechtvanlommel@gmail.com> | 2013-11-22 17:42:41 +0400 |
commit | e3a79258d17e6cdca26120eab7a2c48c7c4d4a0f (patch) | |
tree | 77d59694458125dd7525faf59ed56ce505533981 /intern/cycles/CMakeLists.txt | |
parent | 5feb0d2bfe8f6723bf48073b1760b732bc6a5ceb (diff) |
Cycles: test code for sse 4.1 kernel and alignment for some vector types.
This is mostly work towards enabling the __KERNEL_SSE__ option to start using
SIMD operations for vector math operations. This 4.1 kernel performes about 8%
faster with that option but overall is still slower than without the option.
WITH_CYCLES_OPTIMIZED_KERNEL_SSE41 is the cmake flag for testing this kernel.
Alignment of int3, int4, float3, float4 to 16 bytes seems to give a slight 1-2%
speedup on tested systems with the current kernel already, so is enabled now.
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 6821e93ad87..9b84f882046 100644 --- a/intern/cycles/CMakeLists.txt +++ b/intern/cycles/CMakeLists.txt @@ -17,9 +17,11 @@ if(WIN32 AND MSVC) if(CMAKE_CL_64) 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-") 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-") endif() set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /fp:fast -D_CRT_SECURE_NO_WARNINGS /Gs-") @@ -29,10 +31,12 @@ if(WIN32 AND MSVC) elseif(CMAKE_COMPILER_IS_GNUCC) set(CYCLES_SSE2_KERNEL_FLAGS "-ffast-math -msse -msse2 -mfpmath=sse") set(CYCLES_SSE3_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3 -mfpmath=sse") + set(CYCLES_SSE41_KERNEL_FLAGS "-ffast-math -msse -msse2 -msse3 -mssse3 -msse4.1 -mfpmath=sse") set(CMAKE_CXX_FLAGS "${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(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -ffast-math") endif() |