You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I just followed the README but generated the following error when trying the vectorAdd.cu test
$user:~/cuda-half2$ ./detect_vars.sh test/vectorAdd.cu
warning: Unknown CUDA version. cuda.h: CUDA_VERSION=11070. Assuming the latest supported version 10.1 [-Wunknown-cuda-version]
error: cannot find libdevice for sm_20. Provide path to different CUDA installation via --cuda-path, or pass -nocudalib to build without linking with libdevice.
error: GPU arch sm_20 is supported by CUDA versions between 7.0 and 8.0 (inclusive), but installation at /usr/local/cuda-11.7 is 11.0. Use --cuda-path to specify a different CUDA install, pass a different GPU arch with --cuda-gpu-arch, or pass --no-cuda-version-check.
* Creating AST consumer for: /home/xinyi/cuda-half2/test/vectorAdd.cu
<built-in>:1:10: fatal error: '__clang_cuda_runtime_wrapper.h' file not found
#include "__clang_cuda_runtime_wrapper.h"
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
visit VarDecl
int
i
has init 0
visit VarDecl
float
test_val
has init 0
visit VarDecl
float
test_val2
has init 0
** EndSourceFileAction for: /home/xinyi/cuda-half2/test/vectorAdd.cu
1 error generated when compiling for sm_20.
I cannot find a way to change the architecture of GPU. Is there any way to solve this issue?
The text was updated successfully, but these errors were encountered:
I just followed the
README
but generated the following error when trying thevectorAdd.cu
testI cannot find a way to change the architecture of GPU. Is there any way to solve this issue?
The text was updated successfully, but these errors were encountered: