Mangala V e9124ffca7 BUGFIX: Updated ZGEMM microkernel to handle alpha = 0 case
BUG:
When alpha real and imaginary is zero
Output is computed as C= Beta * C + A * B instead of C = Beta * C

FIX:
Updated kernel to scale A * B product with alpha in case of alpha=0

Existing framework design:
- When alpha real and imaginary value is zero, framework handles to skip
kernel call to avoid alpha * A * B operation
- SCALM is invoked to perform Beta * C

- Accuracy issue was not observed as alpha=0 was handled in framework
- If we call kernel directly with alpha=0, results would be wrong
- Issue was figured out during microkernel testing using gtestsuite

AMD-Internal: [CPUPL-4454]
Change-Id: Ib6113f5226cd7c26a63781cdd20d35660f453803
2024-06-20 02:58:43 -04:00
2024-06-18 19:31:17 +05:30
2019-05-23 12:51:17 -05:00
2023-11-23 08:54:31 -05:00
2019-10-02 10:16:22 +01:00
2021-03-22 17:42:33 -05:00
2023-11-10 13:05:12 -05:00
2018-08-07 14:21:07 -05:00
2023-11-23 08:54:31 -05:00
2023-05-25 14:46:33 +00:00

AOCL-BLAS library

AOCL-BLAS is AMD's optimized version of BLAS targeted for AMD EPYC and Ryzen CPUs. It is developed as a forked version of BLIS (https://github.com/flame/blis), which is developed by members of the Science of High-Performance Computing (SHPC) group in the Institute for Computational Engineering and Sciences at The University of Texas at Austin and other collaborators (including AMD). All known features and functionalities of BLIS are retained and supported in AOCL-BLAS library. AOCL-BLAS is regularly updated with the improvements from the upstream repository.

AOCL BLAS is optimized with SSE2, AVX2, AVX512 instruction sets which would be enabled based on the target Zen architecture using the dynamic dispatch feature. All prominent Level 3, Level 2 and Level 1 APIs are designed and optimized for specific paths targeting different size spectrums e.g., Small, Medium and Large sizes. These algorithms are designed and customized to exploit the architectural improvements of the target platform.

For detailed instructions on how to configure, build, install, and link against AOCL-BLAS on AMD CPUs, please refer to the AOCL User Guide located on AMD developer portal.

The upstream repository (https://github.com/flame/blis) contains further information on BLIS, including background information on BLIS design, usage examples, and a complete BLIS API reference.

AOCL-BLAS is developed and maintained by AMD. You can contact us on the email-id toolchainsupport@amd.com. You can also raise any issue/suggestion on the git-hub repository at https://github.com/amd/blis/issues.

Description
BLAS-like Library Instantiation Software Framework
Readme BSD-3-Clause 72 MiB
Languages
C 86.3%
C++ 9.5%
Fortran 1.9%
Makefile 0.8%
MATLAB 0.5%
Other 0.9%