"Fossies" - the Fresh Open Source Software Archive  

Source code changes of the file "Modules/FindCUDA/select_compute_arch.cmake" between
cmake-3.18.3.tar.gz and cmake-3.18.4.tar.gz

About: CMake is a cross-platform build system designed to build, test and package software.

select_compute_arch.cmake  (cmake-3.18.3):select_compute_arch.cmake  (cmake-3.18.4)
# Synopsis: # Synopsis:
# CUDA_SELECT_NVCC_ARCH_FLAGS(out_variable [target_CUDA_architectures]) # CUDA_SELECT_NVCC_ARCH_FLAGS(out_variable [target_CUDA_architectures])
# -- Selects GPU arch flags for nvcc based on target_CUDA_architectures # -- Selects GPU arch flags for nvcc based on target_CUDA_architectures
# target_CUDA_architectures : Auto | Common | All | LIST(ARCH_AND_PTX ...) # target_CUDA_architectures : Auto | Common | All | LIST(ARCH_AND_PTX ...)
# - "Auto" detects local machine GPU compute arch at runtime. # - "Auto" detects local machine GPU compute arch at runtime.
# - "Common" and "All" cover common and entire subsets of architectures # - "Common" and "All" cover common and entire subsets of architectures
# ARCH_AND_PTX : NAME | NUM.NUM | NUM.NUM(NUM.NUM) | NUM.NUM+PTX # ARCH_AND_PTX : NAME | NUM.NUM | NUM.NUM(NUM.NUM) | NUM.NUM+PTX
# NAME: Fermi Kepler Maxwell Kepler+Tegra Kepler+Tesla Maxwell+Tegra Pascal Volta Turing Ampere # NAME: Fermi Kepler Maxwell Kepler+Tegra Kepler+Tesla Maxwell+Tegra Pascal Volta Turing Ampere
# NUM: Any number. Only those pairs are currently accepted by NVCC though: # NUM: Any number. Only those pairs are currently accepted by NVCC though:
# 2.0 2.1 3.0 3.2 3.5 3.7 5.0 5.2 5.3 6.0 6.2 7.0 7.2 7.5 8.0 # 2.0 2.1 3.0 3.2 3.5 3.7 5.0 5.2 5.3 6.0 6.2 7.0 7.2 7.5 8.0 8.6
# Returns LIST of flags to be added to CUDA_NVCC_FLAGS in ${out_variable} # Returns LIST of flags to be added to CUDA_NVCC_FLAGS in ${out_variable}
# Additionally, sets ${out_variable}_readable to the resulting numeric list # Additionally, sets ${out_variable}_readable to the resulting numeric list
# Example: # Example:
# CUDA_SELECT_NVCC_ARCH_FLAGS(ARCH_FLAGS 3.0 3.5+PTX 5.2(5.0) Maxwell) # CUDA_SELECT_NVCC_ARCH_FLAGS(ARCH_FLAGS 3.0 3.5+PTX 5.2(5.0) Maxwell)
# LIST(APPEND CUDA_NVCC_FLAGS ${ARCH_FLAGS}) # LIST(APPEND CUDA_NVCC_FLAGS ${ARCH_FLAGS})
# #
# More info on CUDA architectures: https://en.wikipedia.org/wiki/CUDA # More info on CUDA architectures: https://en.wikipedia.org/wiki/CUDA
# #
if(CMAKE_CUDA_COMPILER_LOADED) # CUDA as a language if(CMAKE_CUDA_COMPILER_LOADED) # CUDA as a language
skipping to change at line 85 skipping to change at line 85
set(CUDA_LIMIT_GPU_ARCHITECTURE "8.0") set(CUDA_LIMIT_GPU_ARCHITECTURE "8.0")
endif() endif()
endif() endif()
if(CUDA_VERSION VERSION_GREATER_EQUAL "10.0") if(CUDA_VERSION VERSION_GREATER_EQUAL "10.0")
list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Turing") list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Turing")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "7.5") list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "7.5")
list(APPEND CUDA_ALL_GPU_ARCHITECTURES "7.5") list(APPEND CUDA_ALL_GPU_ARCHITECTURES "7.5")
if(CUDA_VERSION VERSION_LESS "11.0") if(CUDA_VERSION VERSION_LESS "11.0")
set(CUDA_LIMIT_GPU_ARCHITECTURE "8.0")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "7.5+PTX") list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "7.5+PTX")
set(CUDA_LIMIT_GPU_ARCHITECTURE "8.0")
endif() endif()
endif() endif()
if(CUDA_VERSION VERSION_GREATER_EQUAL "11.0") if(CUDA_VERSION VERSION_GREATER_EQUAL "11.0")
list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Ampere") list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Ampere")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "8.0" "8.0+PTX") list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "8.0")
list(APPEND CUDA_ALL_GPU_ARCHITECTURES "8.0") list(APPEND CUDA_ALL_GPU_ARCHITECTURES "8.0")
if(CUDA_VERSION VERSION_LESS "11.1")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "8.0+PTX")
set(CUDA_LIMIT_GPU_ARCHITECTURE "8.6")
endif()
endif()
if(CUDA_VERSION VERSION_GREATER_EQUAL "11.1")
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "8.6" "8.6+PTX")
list(APPEND CUDA_ALL_GPU_ARCHITECTURES "8.6")
if(CUDA_VERSION VERSION_LESS "12.0") if(CUDA_VERSION VERSION_LESS "12.0")
set(CUDA_LIMIT_GPU_ARCHITECTURE "9.0") set(CUDA_LIMIT_GPU_ARCHITECTURE "9.0")
endif() endif()
endif() endif()
################################################################################ ################ ################################################################################ ################
# A function for automatic detection of GPUs installed (if autodetection is ena bled) # A function for automatic detection of GPUs installed (if autodetection is ena bled)
# Usage: # Usage:
# CUDA_DETECT_INSTALLED_GPUS(OUT_VARIABLE) # CUDA_DETECT_INSTALLED_GPUS(OUT_VARIABLE)
# #
 End of changes. 5 change blocks. 
3 lines changed or deleted 13 lines changed or added

Home  |  About  |  Features  |  All  |  Newest  |  Dox  |  Diffs  |  RSS Feeds  |  Screenshots  |  Comments  |  Imprint  |  Privacy  |  HTTP(S)