Meghana Vankadari d5b4d3aa5e Fixing control flow in aocl_gemm_bf16s4f32of32|bf16 ...

- Fixed framework of bf16s4f32of32 API to correct
  pointer updations.
- Modified pre_op structure to exclude pre-op-offset.
  Now offset is passed as a separate parameter to the
  scale-pack functions.
- Fixed work-distribution among threads in MT scenario.
- Added Blocksizes and kernel-pointers and verified
  functionality for the new API.

AMD-Internal: [SWLCSG-2943]
Change-Id: I58fece240d62c798c880a2b2b7fa64e560cc753d

2024-07-29 05:12:09 -04:00

..

bf16bf16f32

Fixing control flow in aocl_gemm_bf16s4f32of32|bf16

2024-07-29 05:12:09 -04:00

s8s8s16

Added NEW LPGEMM TYPE- s8s8s16os16 and s8s8s16os8

2023-04-21 05:30:38 -04:00

s8s8s32

Added transB in all AVX512 based int8 API's

2024-05-23 03:46:13 +05:30

u8s8s16

Added Trans A feature for all INT8 LPGEMM APIs

2024-01-30 03:40:56 -05:00

u8s8s32

Int4 B matrix reordering support in LPGEMM.

2024-06-24 07:55:34 -04:00

lpgemm_kernels.h

Implemented LPGEMV(n=1) for AVX2-INT8 variants

2024-06-18 12:09:18 +05:30

lpgemm_utils_kernels.h

aocl_softmax_f32 api's for softmax computation as part of lpgemm.

2023-04-21 05:26:08 -04:00