Vignesh Balasubramanian f23b8e636b AVX2 and AVX512 optimizations for DAXPYV ...

- Removed some of the unrolling factors that affected the
  performance of AVX2 DAXPYV kernel. In addition to improving
  the current performance on sizes compatible to single-threaded
  runs, this will now perform better for tiny sizes as well
  since the overhead to reach the computation is less.

- Updated the vector partitioning logic, by using
  bli_thread_range_sub( ... ), which ensures that there is no
  false sharing among multiple threads.

- Updated the AOCL-DYNAMIC logic for the API, to include thresholds
  or zen4 and zen5 micro-architectures.

AMD-Internal: [CPUPL-5514]
Change-Id: Iee9edddac685334213cd6694421ab3df3547e930

2024-07-31 09:24:36 -04:00

..

attic

CMake: Adding new portable CMake system.

2023-11-09 15:49:45 +05:30

blis/thread

CMake: Adding new portable CMake system.

2023-11-09 15:49:45 +05:30

cblas

Improvements to CBLAS xerbla functionality

2024-07-26 10:36:37 -04:00

check

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

f2c

Bugfix for ?OMATCOPY2 and ?IMATCOPY APIs

2024-05-21 11:13:28 +05:30

bla_amax_amd.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_amax.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_amax.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_amin.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_amin.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_asum.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_asum.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_axpby_amd.c

AVX512 optimizations for DAXPBYV API

2024-07-22 11:32:19 +05:30

bla_axpby.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_axpby.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_axpy_amd.c

AVX2 and AVX512 optimizations for DAXPYV

2024-07-31 09:24:36 -04:00

bla_axpy.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_axpy.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_copy_amd.c

Optimization for DCOPY and SCOPY API

2024-07-24 08:23:07 -04:00

bla_copy.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_copy.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_dot_amd.c

ZDOTV AVX512 Kernel with MT Support

2024-05-08 04:54:05 -04:00

bla_dot.c

Updated DOTV DTL in bla_dot.c

2024-05-08 01:46:17 -04:00

bla_dot.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemm3m.c

Merge commit 'cfa3db3f' into amd-main

2024-07-08 06:09:11 -04:00

bla_gemm3m.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemm_amd.c

AVX512 optimizations for ZGEMM to handle k = 1 cases

2024-07-09 07:07:24 -04:00

bla_gemm_batch.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemm_batch.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemm_compute.c

Code cleanup: No newline at end of file

2023-11-22 17:11:10 -05:00

bla_gemm_compute.h

Code cleanup: No newline at end of file

2023-11-22 17:11:10 -05:00

bla_gemm_pack_get_size.c

Added Parameter Checks and DTL Trace for Extension APIs

2023-11-09 18:53:59 +05:30

bla_gemm_pack_get_size.h

Code cleanup: No newline at end of file

2023-11-22 17:11:10 -05:00

bla_gemm_pack.c

Added Parameter Checks and DTL Trace for Extension APIs

2023-11-09 18:53:59 +05:30

bla_gemm_pack.h

Code cleanup: No newline at end of file

2023-11-22 17:11:10 -05:00

bla_gemm.c

Merge commit 'cfa3db3f' into amd-main

2024-07-08 06:09:11 -04:00

bla_gemm.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemmt.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_gemmt.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemv_amd.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemv.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_gemv.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_ger.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_ger.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_hemm.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_hemm.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_hemv.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_hemv.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_her2.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_her2.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_her2k.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_her2k.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_her.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_her.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_herk.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_herk.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_imatcopy.c

Bugfix for ?OMATCOPY2 and ?IMATCOPY APIs

2024-05-21 11:13:28 +05:30

bla_imatcopy.h

Code cleanup: No newline at end of file

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

bla_nrm2.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_nrm2.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_omatadd.c

Merge commit 'b683d01b' into amd-main

2023-08-21 07:01:38 -04:00

bla_omatadd.h

Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2

2020-11-18 12:55:36 +05:30

bla_omatcopy2.c

Bugfix for ?OMATCOPY2 and ?IMATCOPY APIs

2024-05-21 11:13:28 +05:30

bla_omatcopy2.h

Code cleanup: No newline at end of file

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

bla_omatcopy.c

Fixed bug in omatcopy for when trans="t"

2024-05-06 12:57:38 -04:00

bla_omatcopy.h

Code cleanup: No newline at end of file

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

bla_scal_amd.c

CSCALV Framework Bugfix

2024-07-17 00:27:47 +05:30

bla_scal.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_scal.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_swap_amd.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_swap.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_swap.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_symm.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_symm.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_symv.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_symv.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_syr2.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_syr2.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_syr2k.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_syr2k.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_syr.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_syr.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_syrk.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_syrk.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_trmm.c

BLIS: Implement zen5 sub-configuration

2024-04-12 07:26:31 -04:00

bla_trmm.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_trmv.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_trmv.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_trsm_amd.c

Merge commit 'cfa3db3f' into amd-main

2024-07-08 06:09:11 -04:00

bla_trsm.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_trsm.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_trsv.c

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bla_trsv.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00

bli_blas.h

Code cleanup: AMD copyright notice

2023-11-23 08:54:31 -05:00