Sharma, Shubham b5c8124d3d Derive TRSM ref kernels from TRSM blkzsz instead of GEMM blszs (#148) ...

- Currently TRSM reference kernels are derived from GEMM blocksizes and GEMM_UKR.
- This does not allow the flexibility to use different GEMM_UKR for GEMM and TRSM if optimized TRSM_UKR are not available.
- Made changes so that ref TRSM kernels are derived from TRSM blocksizes.
- Changed ZEN4 and ZEN5 cntx to use AVX2 kernels for CTRSM.

AMD-Internal: [SWLCSG-3702]

2025-08-21 11:25:45 +05:30

..

1

SCALV alpha=zero BLAS compliance

2024-09-16 07:10:28 -04:00

1f

CMake: Adding new portable CMake system.

2023-11-09 15:49:45 +05:30

1m

Merge commit 'cfa3db3f' into amd-main

2024-07-08 06:09:11 -04:00

3

Derive TRSM ref kernels from TRSM blkzsz instead of GEMM blszs (#148)

2025-08-21 11:25:45 +05:30

ind

CMake: Adding new portable CMake system.

2023-11-09 15:49:45 +05:30

bli_cntx_ref.c

Merge commit 'cfa3db3f' into amd-main

2024-07-08 06:09:11 -04:00