Problems encountered when run 'nv-nsight-cu-cli............', the question is about 'vectorized_elementwise_kernel'

Developer Tools Nsight Compute
1

BELOW is details:

02-17-2023 16:24:02.019220 : START PROGRAM
==PROF== Connected to process 188302
==PROF== Profiling “vectorized_elementwise_kernel” - 1:
==ERROR== Error 0: Failed to initialize PerfWorks/LOP
==ERROR== Failed to profile kernel “vectorized_elementwise_kernel” in process

==ERROR== Error 0: UnsupportedGpu
5933.04 PyTorchInit total ms
waiting for 3 seconds after PyTorchInit
waiting for 3 seconds after warmup
main jit-load: 341.684warmup: 1.84467e+13
[vgg16] 02-17-2023 16:24:20.356390 : START EXEC
[vgg16] 02-17-2023 16:24:20.376660 : END EXEC
latency: 20.142350
02-17-2023 16:24:20.377925 : END PROGRAM
==PROF== Disconnected from process 188302
==ERROR== An error occurred while trying to profile
==WARNING== No kernels were profiled
==WARNING== Profiling kernels launched by child processes requires the --target-processes all option

2

I solved it! CUDA reinstalled！

1 Like
3

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.