I made hello.cu,
Then I compiled it by this ::
nvcc -o hello hello.cu
Why GPU only run when using option with nvprof??
I want to get “Hello CUDA from GPU” just by ./hello
nvcc -V :: 10.1.243
I made hello.cu,
Then I compiled it by this ::
nvcc -o hello hello.cu
Why GPU only run when using option with nvprof??
I want to get “Hello CUDA from GPU” just by ./hello
nvcc -V :: 10.1.243
if you’re running on a laptop with a discrete gpu and an integrated gpu, it may be necessary to use a tool like optirun to get the laptop discrete GPU to work properly.
You could also try running with cuda-memcheck
to see if any useful error information is reported.