Files
blis/frame/3
Shubham Sharma. bee1640b38 Fixed failures for mixed precision on ZEN5 in GEMM
- Optimized macro kernel (bli_dgemm_avx512_asm_8x24_macro_kernel)
  for zen5 do not support alpha scaling. Alpha scaling is
  supported by zen5 micro kernel (bli_dgemm_avx512_asm_8x24).
- Optimized macro kernel expects alpha scaling to be done during
  packing. The packing kernel used for mixed precision do not support
  alpha scaling. Therefore, the optimized Zen5 macro kernel is not
  compatible with existing packing logic.
- Changes have been made to use the generic macro kernel which in turn
  used zen5 micro kernel for mixed precision which supports alpha scaling.

AMD-Internal: [CPUPL-5058]
Change-Id: I1bfeb32ae07eedafadad7dd2c62d63913a46e446
2024-08-20 02:22:26 -04:00
..
2024-08-05 16:18:51 -04:00
2023-11-23 08:54:31 -05:00
2024-08-06 06:56:01 -04:00
2021-04-29 12:35:30 +05:30
2024-07-08 06:09:11 -04:00