eashdash e36f699939 Implemented ERF Based GeLU Activation for LPEGMM and SGEMM ...

1. Implemented efficient AVX-512, AVX-2 and SSE-2 version of the
   error function - ERF
2. Added error function based GeLU activation post-ops for the
   S32, S16 and BF16 (LPGEMM) and SGEMM APIs.
3. Changes for this includes frame and micro-kernel level changes in
   addition to adding the marco based function definations of the
   ERF function in the math-utils and gelu headerfiles.

AMD-Internal: [CPUPL-3036]
Change-Id: Ie50f6dcabf8896b7a6d30bbc16aa44392cc512be

2023-03-13 06:10:31 -04:00

..

1

Bugfix on the memory access for nrm2 AVX2 implementations.

2023-03-08 04:21:36 -05:00

1f

ZAXPYF4 optimization

2023-02-04 12:34:50 -05:00

2

BLIS-Nov2022: HPL memory issues with GCC.

2022-12-06 05:10:34 -05:00

3

Extended the support for beta scaling in 3x4 RD kernels of ZGEMM SUP

2023-03-08 06:16:58 -05:00

lpgemm

Implemented ERF Based GeLU Activation for LPEGMM and SGEMM

2023-03-13 06:10:31 -04:00

util

Copyright modification

2022-10-14 12:43:35 +05:30

bli_kernels_zen.h

Vectorized SCAL2V for double complex

2023-02-28 06:59:23 -05:00

CMakeLists.txt

Removed packm kernels of zen

2021-11-12 08:58:51 +05:30