Vignesh Balasubramanian cf31fcd020 Fine tuned threshold and aocl dynamic for zgemm for skinny matrices. ...

-Updated optimal threads in zgemm sup path for skinny matrices.
-Fine tuned the threshold values for small and sup paths
 to improve overall zgemm.
-Zgemm small is selected for inputs with transb as N.
-Redirection of input among small, sup and native path
 was fine tuned.

AMD-Internal : [CPUPL-1900]

Change-Id: Ide37c8255def770b4b74bc6e7c6edb5ee15d3b1f

2022-08-19 01:19:14 -04:00

..

old

This check in has changes w.r.t Copyright information, which is changed to (start year) - 2019

2019-05-27 16:24:43 +05:30

amd_config.mk

Enabled znver3 flag for gcc version above 11

2021-11-12 08:58:48 +05:30

bli_cntx_init_zen.c

Fine tuned threshold and aocl dynamic for zgemm for skinny matrices.

2022-08-19 01:19:14 -04:00

bli_family_zen.h

DNRM2 : Disable dnrm2 Fast math implementation.

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

CMakeLists.txt

AOCL Windows: 3.1 BLIS changes

2021-03-08 19:04:17 +05:30

make_defs.mk

Fixed scalapack xcsep failer due to cdotxv kernel.

2022-05-17 18:10:40 +05:30