Add cuda::ptx:tensormap_{replace,cp_fenceproxy} (#1441)
#105
| Job | Run time |
|---|---|
| 3m 17s | |
| 7s | |
| 3m 24s |
cuda::ptx:tensormap_{replace,cp_fenceproxy} (#1441)
#105
| Job | Run time |
|---|---|
| 3m 17s | |
| 7s | |
| 3m 24s |