Edward Smyth 43d36b9f66 AOCL_ENABLE_INSTRUCTIONS improvements 2 ...

Use of AOCL_ENABLE_INSTRUCTIONS in dgemm tiny code path is
unnecessary and incorrectly caused AVX512 code to be run
on zen4 and later processors when AOCL_ENABLE_INSTRUCTIONS=avx2
or equivalent options was selected.

Replace with code to select kernel in a similar way to other
dgemm code paths and other APIs. Note that at present AVX2 code
is used the smallest matrix sizes on all zen platforms.

AMD-Internal: [CPUPL-5078]
Change-Id: Ie6b4895461cbbb915d2b48b92fc063f5cd6adb85

2024-06-25 04:57:38 -04:00

..

1

Bugfix and optimizations for ?AXPBYV API

2024-06-20 16:22:07 +05:30

1f

Updated DOTXF and AXPYF Kernels

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

2

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

3

AOCL_ENABLE_INSTRUCTIONS improvements 2

2024-06-25 04:57:38 -04:00

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

Bugfix and optimizations for ?AXPBYV API

2024-06-20 16:22:07 +05:30