e3a79258d1
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.
49 lines
665 B
CMake
49 lines
665 B
CMake
|
|
set(INC
|
|
.
|
|
../kernel
|
|
../kernel/svm
|
|
../kernel/osl
|
|
../util
|
|
../render
|
|
)
|
|
|
|
set(INC_SYS
|
|
${OPENGL_INCLUDE_DIR}
|
|
${GLEW_INCLUDE_PATH}
|
|
)
|
|
|
|
if(WITH_CYCLES_OPTIMIZED_KERNEL_SSE41)
|
|
add_definitions(-DWITH_CYCLES_OPTIMIZED_KERNEL_SSE41=1)
|
|
endif()
|
|
|
|
set(SRC
|
|
device.cpp
|
|
device_cpu.cpp
|
|
device_cuda.cpp
|
|
device_multi.cpp
|
|
device_opencl.cpp
|
|
device_task.cpp
|
|
)
|
|
|
|
if(WITH_NETWORK)
|
|
list(APPEND SRC
|
|
device_network.cpp
|
|
)
|
|
endif()
|
|
|
|
set(SRC_HEADERS
|
|
device.h
|
|
device_memory.h
|
|
device_intern.h
|
|
device_network.h
|
|
device_task.h
|
|
)
|
|
|
|
add_definitions(-DGLEW_STATIC)
|
|
|
|
include_directories(${INC})
|
|
include_directories(SYSTEM ${INC_SYS})
|
|
|
|
add_library(cycles_device ${SRC} ${SRC_HEADERS})
|