saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update cuda capabilities (#4936)

Browse source
This commit is contained in:
George Wu 2020-08-27 23:38:18 +00:00 committed by GitHub
parent efdd96595f
commit e6b6736e48
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
cmake/CMakeLists.txt
View file

@ -938,14 +938,18 @@ if (onnxruntime_USE_CUDA)
list(APPEND onnxruntime_EXTERNAL_LIBRARIES ${ONNXRUNTIME_CUDA_LIBRARIES})
if(CMAKE_LIBRARY_ARCHITECTURE STREQUAL "aarch64-linux-gnu")
string (APPEND CMAKE_CUDA_FLAGS "-gencode=arch=compute_53,code=sm_53 -gencode=arch=compute_62,code=sm_62 ") #nano, TX1, TX2
string (APPEND CMAKE_CUDA_FLAGS "-gencode=arch=compute_72,code=sm_72") # Jetson N
# Support for Jetson/Tegra ARM devices
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_53,code=sm_53") # TX1, Nano
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_62,code=sm_62") # TX2
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_72,code=sm_72") # AGX Xavier, NX Xavier
else()
# the following compute capabilities are deprecated in CUDA 11 Toolkit
# the following compute capabilities are removed in CUDA 11 Toolkit
if (CMAKE_CUDA_COMPILER_VERSION VERSION_LESS 11)
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_30,code=sm_30") # K series
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_50,code=sm_50") # M series
endif()
# 37, 50 still work in CUDA 11 but are marked deprecated and will be removed in future CUDA version.
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_37,code=sm_37") # K80
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_50,code=sm_50") # M series
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_52,code=sm_52") # M60
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_60,code=sm_60") # P series