| ------------------------------------------------------- ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ | |
| Name Self CPU % Self CPU CPU total % CPU total CPU time avg Self CUDA Self CUDA % CUDA total CUDA time avg # of Calls | |
| ------------------------------------------------------- ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ | |
| void cutlass::Kernel2<cutlass_80_tensorop_bf16_s1681... 0.00% 0.000us 0.00% 0.000us 0.000us 4.960ms 94.69% 4.960ms 1.240ms 4 | |
| matmul_add 0.00% 0.000us 0.00% 0.000us 0.000us 3.932ms 75.07% 3.932ms 1.311ms 3 | |
| ProfilerStep* 0.82% 48.111us 8.59% 501.261us 167.087us 0.000us 0.00% 3.927ms 1.309ms 3 | |
| matmul_add 5.92% 345.465us 7.77% 453.150us 151.050us 0.000us 0.00% 3.927ms 1.309ms 3 | |
| aten::matmul 0.11% 6.323us 1.41% 82.207us 27.402us 0.000us 0.00% 3.718ms 1.239ms 3 | |
| aten::mm 1.00% 58.231us 1.30% 75.884us 25.295us 3.718ms 70.99% 3.718ms 1.239ms 3 | |
| void at::native::vectorized_elementwise_kernel<4, at... 0.00% 0.000us 0.00% 0.000us 0.000us 277.903us 5.31% 277.903us 69.476us 4 | |
| aten::add 0.28% 16.621us 0.44% 25.478us 8.493us 208.627us 3.98% 208.627us 69.542us 3 | |
| cudaDeviceGetAttribute 0.02% 1.051us 0.02% 1.051us 0.350us 0.000us 0.00% 0.000us 0.000us 3 | |
| cuLaunchKernel 0.28% 16.602us 0.28% 16.602us 5.534us 0.000us 0.00% 0.000us 0.000us 3 | |
| cudaLaunchKernel 0.15% 8.857us 0.15% 8.857us 2.952us 0.000us 0.00% 0.000us 0.000us 3 | |
| cudaDeviceSynchronize 91.41% 5.332ms 91.41% 5.332ms 5.332ms 0.000us 0.00% 0.000us 0.000us 1 | |
| ------------------------------------------------------- ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ ------------ | |
| Self CPU time total: 5.834ms | |
| Self CUDA time total: 5.238ms | |
Xet Storage Details
- Size:
- 3.23 kB
- Xet hash:
- 5e7a450815416827ea6fa27679d616458b87f09675f198ae5a9ffcfcddd0bfb5
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.