Harsh Dave f17d043e1c Implemented optimal dotxv kernel ...

Details:
- Intrinsic implementation of zdotxv, cdotxv kernel
- Unrolling in multiple of 8, remaining corner
  cases are handled serially for zdotxv kernel
- Unrolling in multiple of 16, remainig corner
  cases are handled serially for cdotxv kernel
- Added declaration in zen contexts

AMD-Internal: [CPUPL-2050]
Change-Id: Id58b0dbfdb7a782eb50eecc7142f051b630d9211

2022-05-17 18:10:39 +05:30

..

bli_cntx_init_zen3.c

Implemented optimal dotxv kernel

2022-05-17 18:10:39 +05:30

bli_family_zen3.h

DNRM2 : Disable dnrm2 Fast math implementation.

2021-11-12 08:58:56 +05:30

CMakeLists.txt

Cmake script changes and blis.h changes for amd-staging-milan-3.0

2020-11-24 06:12:25 -05:00

make_defs.mk

Removed Arch specific code from BLIS framework.

2022-01-18 11:51:08 +05:30