You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by zh...@apache.org on 2018/11/21 02:49:14 UTC
[incubator-mxnet] branch master updated: add Volta and Turing arch
(#13069)
This is an automated email from the ASF dual-hosted git repository.
zhasheng pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/master by this push:
new 2c33574 add Volta and Turing arch (#13069)
2c33574 is described below
commit 2c3357443ec3d49a11e93c89f278264ce10c2f08
Author: Hu Shiwen <ya...@gmail.com>
AuthorDate: Wed Nov 21 10:48:59 2018 +0800
add Volta and Turing arch (#13069)
add 75 in Makefile
---
Makefile | 2 +-
cmake/FirstClassLangCuda.cmake | 10 ++++++++++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index ad7f0ff..16ea59f 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 f7ffcbb..8d79c2b 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: