amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-05-12 10:05:38 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
76fbf1233d68d00a54ebf62691d6457cef623c8b
blis/frame/compat
History
Mangala V 6c1acc74c8 ZGEMM optimizations 
-- Conditionally packing of B matrix is enabled in zgemmsup path
   which is performing better when B matrix is large

-- Incorporated decision logic to choose between zgemm_small vs
   zgemm sup based on matrix dimensions "m, n and k".

-- Calling of ZGEMV when matrix dimension m or n = 1.
   Very good performance improvement is observed.

Change-Id: I7c64020f4f78a6a51617b184cc88076213b5527d
2022-07-28 14:55:24 +05:30
..
attic
AOCL Windows: 3.1 BLIS changes
2021-03-08 19:04:17 +05:30
blis
AOCL Windows: 3.1 BLIS changes
2021-03-08 19:04:17 +05:30
cblas
Fixed dynamic dispatch crash issue on non-zen architecture.
2021-11-12 08:58:58 +05:30
check
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
f2c
Enabled processing of zero inputs of x in tbsv to provide NaN
2021-11-12 08:58:53 +05:30
bla_amax_amd.c
Added support for AVX512 for Windows and AMAVX
2022-06-08 11:09:48 +05:30
bla_amax.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_amax.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_amin.c
Added BLIS, BLAS, and CBLAS interface for cblas?amin
2020-10-28 17:50:27 +05:30
bla_amin.h
Added BLIS, BLAS, and CBLAS interface for cblas?amin
2020-10-28 17:50:27 +05:30
bla_asum.c
Added debug log support for axpy, axpyb, amax, asum, hemv, her2
2020-11-03 20:44:12 +05:30
bla_asum.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_axpby.c
Added debug log support for axpy, axpyb, amax, asum, hemv, her2
2020-11-03 20:44:12 +05:30
bla_axpby.h
Added BLAS and CBLAS interfaces for axpby API
2020-09-16 09:49:31 +05:30
bla_axpy_amd.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_axpy.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_axpy.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_copy_amd.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_copy.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_copy.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_dot_amd.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_dot.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_dot.h
BLIS:merge:
2021-04-27 11:09:48 +05:30
bla_gemm3m.c
Added BLAS Extension API's: CBLAS_?GEMM3M
2020-10-29 17:06:30 +05:30
bla_gemm3m.h
Added BLAS Extension API's: CBLAS_?GEMM3M
2020-10-29 17:06:30 +05:30
bla_gemm_amd.c
ZGEMM optimizations
2022-07-28 14:55:24 +05:30
bla_gemm_batch.c
Added BLAS interface for gemm_batch API
2020-09-24 23:52:31 -04:00
bla_gemm_batch.h
Added BLAS interface for gemm_batch API
2020-09-24 23:52:31 -04:00
bla_gemm.c
Added functionality support for dzgemm
2022-05-17 18:01:55 +05:30
bla_gemm.h
Added functionality support for dzgemm
2022-05-17 18:01:55 +05:30
bla_gemmt.c
Modified log routines for gemm, gemmt and trsm
2020-11-23 04:53:15 -05:00
bla_gemmt.h
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
bla_gemv_amd.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_gemv.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_gemv.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_ger.c
Added debug trace and log support for copy and ger routines
2020-11-02 22:56:58 -05:00
bla_ger.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_hemm.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_hemm.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_hemv.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_hemv.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_her2.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_her2.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_her2k.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_her2k.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_her.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_her.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_herk.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_herk.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_imatcopy.c
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_imatcopy.h
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_nrm2.c
Logging
2020-11-06 10:16:31 +05:30
bla_nrm2.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_omatadd.c
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_omatadd.h
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_omatcopy2.c
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_omatcopy2.h
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_omatcopy.c
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_omatcopy.h
Added Blas interface for ?imatcopy, ?omatcopy, ?omatadd, ?omatcopy2
2020-11-18 12:55:36 +05:30
bla_scal_amd.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_scal.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_scal.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_swap_amd.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_swap.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_swap.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_symm.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_symm.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_symv.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_symv.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_syr2.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_syr2.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_syr2k.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_syr2k.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_syr.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_syr.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_syrk.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_syrk.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_trmm.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_trmm.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_trmv.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_trmv.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_trsm_amd.c
Fixed crash issue in TRSM on non-avx platform.
2022-05-17 18:10:39 +05:30
bla_trsm.c
Removed Arch specific code from BLIS framework.
2022-01-18 11:51:08 +05:30
bla_trsm.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bla_trsv.c
DTL logs corrections
2021-06-04 15:24:13 +05:30
bla_trsv.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bli_blas.h
AOCL Windows: 3.1 BLIS changes
2021-03-08 19:04:17 +05:30
CMakeLists.txt
Added support for AVX512 for Windows and AMAVX
2022-06-08 11:09:48 +05:30