Vadim Markovtsev 8783c41851 Replace 0x1f with 0xffffffff in __shfl_sync (#1097) ...

This fixes compatibility with H100 and resolves #1094

2023-09-18 19:58:19 -04:00

..

device

CUTLASS 3.1 (#915)

2023-04-14 23:19:34 -04:00

kernel

Replace 0x1f with 0xffffffff in __shfl_sync (#1097)

2023-09-18 19:58:19 -04:00

thread

New updates for 2.11 (#775)

2023-01-20 16:32:57 -05:00

threadblock

More updates for 3.1 (#958)

2023-05-24 10:17:16 -04:00

CMakeLists.txt

New updates for 2.11 (#775)

2023-01-20 16:32:57 -05:00

dual_gemm_common.h

Update dual_gemm_common.h

2023-02-13 15:35:33 -05:00

dual_gemm_run.h

CUTLASS 3.1 (#915)

2023-04-14 23:19:34 -04:00

dual_gemm.cu

CUTLASS 3.1 (#915)

2023-04-14 23:19:34 -04:00

test_run.h

New updates for 2.11 (#775)

2023-01-20 16:32:57 -05:00