Arnav Sharma 0a5c057475 DGEMV Optimizations for Tiny Sizes ...

- Added reference kernel for dgemv that handles computation for tiny
  sizes (m < 8 && n < 8).

- The reference kernel, bli_dgemv_zen_ref( ... ), supports both
  row/column storage schemes as well as transpose and no transpose
  cases.

- Added additional unit-tests for functional verification.

AMD-Internal: [CPUPL-5098]
Change-Id: I66fdf0a40e90bdb3fed40152c45ab28a17a87ada

2024-08-05 12:19:42 +05:30

..

1

AVX2 and AVX512 optimizations for DAXPYV

2024-07-31 09:24:36 -04:00

1f

Updated DOTXF and AXPYF Kernels

2024-06-20 04:41:41 -04:00

2

DGEMV Optimizations for Tiny Sizes

2024-08-05 12:19:42 +05:30

3

Added new decision logic to choose between 6x8 dgemm kernel vs 24x8 kernel. The decision is based on the values of "m, n and k".

2024-08-02 14:18:58 +05:30

lpgemm

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

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

util

CMake: Adding new portable CMake system.

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

bli_kernels_zen.h

DGEMV Optimizations for Tiny Sizes

2024-08-05 12:19:42 +05:30