szha closed pull request #13069: add Volta and Turing arch
URL: https://github.com/apache/incubator-mxnet/pull/13069
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/Makefile b/Makefile
index b1231173664..f90ae63f359 100644
--- a/Makefile
+++ b/Makefile
@@ -341,7 +341,7 @@ endif
# be JIT-compiled by the updated driver from the included PTX.
ifeq ($(USE_CUDA), 1)
ifeq ($(CUDA_ARCH),)
- KNOWN_CUDA_ARCHS := 30 35 50 52 60 61 70
+ KNOWN_CUDA_ARCHS := 30 35 50 52 60 61 70 75
# Run nvcc on a zero-length file to check architecture-level support.
# Create args to include SASS in the fat binary for supported levels.
CUDA_ARCH := $(foreach arch,$(KNOWN_CUDA_ARCHS), \
diff --git a/cmake/FirstClassLangCuda.cmake b/cmake/FirstClassLangCuda.cmake
index f7ffcbbb820..8d79c2b63ad 100644
--- a/cmake/FirstClassLangCuda.cmake
+++ b/cmake/FirstClassLangCuda.cmake
@@ -120,6 +120,16 @@ else()
list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "5.2+PTX")
endif ()
+if (CUDA_TOOLSET VERSION_GREATER "9.0")
+ list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Volta")
+ list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "7.0")
+endif()
+
+if (CUDA_TOOLSET VERSION_GREATER "10.0")
+ list(APPEND CUDA_KNOWN_GPU_ARCHITECTURES "Turing")
+ list(APPEND CUDA_COMMON_GPU_ARCHITECTURES "7.5")
+endif()
+
################################################################################################
# Function for selecting GPU arch flags for nvcc based on CUDA_ARCH_NAME
# Usage:
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
