Harihara Sudhan S 828ac8e2dd Partial completion of work in L1 APIs ...

- Partial completion of compute was happening since BLIS was unable
  to launch the required number of threads. This was because rntm
  was returning a thread count greater than the maximum number of
  threads that can be launched in the subsequent parallel region.
- Added 'omp_get_num_threads' inside the parallel regions to get the
  actual number of threads spawned. The work distribution happens
  based on the actual number of threads launched in that region.

AMD-Internal: [CPUPL-3268]
Change-Id: I086ad4b9b644f966b7bab439e43222396f0c2bf0

2023-04-27 15:17:26 +05:30

..

0

AOCL Windows: 3.1 BLIS changes

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

1

AOCL Windows: 3.1 BLIS changes

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

1d

AOCL Windows: 3.1 BLIS changes

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

1f

AOCL Windows: 3.1 BLIS changes

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

1m

Code cleanup: compiler warning fixes

2023-04-06 06:56:09 -04:00

2

Code cleanup: No newline at end of file

2023-04-21 10:02:48 -04:00

3

Smart Threading for SGEMM SUP for Zen4 Architecture

2023-04-21 12:54:03 +05:30

base

Code cleanup: No newline at end of file

2023-04-21 10:02:48 -04:00

compat

Partial completion of work in L1 APIs

2023-04-27 15:17:26 +05:30

include

BLIS cpuid: distinguish submodels within a microarchitecture

2023-04-20 10:47:44 -04:00

ind

3m1 turning OFF

2021-05-26 10:06:54 +05:30

thread

Bug fix in work load distribution among the given threads

2023-04-18 10:16:09 -04:00

util

Code cleanup: No newline at end of file

2023-04-21 10:02:48 -04:00

CMakeLists.txt

AOCL Windows: 3.1 BLIS changes

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