amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-05-14 03:02:08 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
5bdf5e2aaa5a36282cd5d7829c7e9ee4e5a8c569
blis/frame/3
History
Meghana Vankadari 79e174ff0a Level-3 triangular routines now use different block sizes and kernels. 
Details:
    - Eliminated the need for override function in SUP for GEMMT/SYRK.
    - New set of block sizes, kernels and kernel preferences
      are added to cntx data structure for level-3 triangular routines.
    - Added supporting functions to set and get the above parameters from cntx.
    - Modified GEMMT/SYRK SUP code to use these new block sizes/kernels.
      In case they are not set, use the default block sizes/kernels of
      Level-3 SUP.

AMD-Internal: [CPUPL-3649]
Change-Id: Iee11bd4c4f1d8fbbb749c296258d1b8121c009a0
2023-07-26 01:26:11 -04:00
..
gemm
AOCL progress callback pointer update per thread
2023-04-20 05:33:12 -04:00
gemmt
Level-3 triangular routines now use different block sizes and kernels.
2023-07-26 01:26:11 -04:00
hemm
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
her2k
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
herk
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
old
"Merge Selective Packing code from amd branch flame/blis"
2020-08-06 10:09:28 +05:30
symm
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
syr2k
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
syrk
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
trmm
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
trmm3
Code cleanup: spelling corrections
2023-04-19 12:44:56 -04:00
trsm
AOCL progress callback pointer update per thread
2023-04-20 05:33:12 -04:00
bli_l3_blocksize.c
Removed dependency on AOCL_BLIS_ZEN for TRSM blocksizes.
2021-08-16 00:12:33 -04:00
bli_l3_blocksize.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +05:30
bli_l3_check.c
Added functionality support for dzgemm
2022-05-17 18:01:55 +05:30
bli_l3_check.h
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
bli_l3_cntl.c
Added framework support and interface APIs for GEMMT
2020-07-06 00:51:16 -04:00
bli_l3_cntl.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +05:30
bli_l3_direct.c
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_direct.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +05:30
bli_l3_ft_ex.h
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_ft_ukr.h
Added a new field in cntx to store l3 threshold function pointers
2021-08-16 00:10:01 -04:00
bli_l3_oapi_ba.c
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_oapi_ex.c
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_oapi.c
BLIS: Nested parallelism issues
2022-10-21 07:38:39 -04:00
bli_l3_oapi.h
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
bli_l3_oft_var.h
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_oft.h
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
bli_l3_packm.c
Code cleanup and warnings fixes
2023-01-09 04:34:52 -05:00
bli_l3_packm.h
Copyright modification
2022-10-14 12:43:35 +05:30
bli_l3_prune.c
Export functions without def file (#303)
2020-08-03 11:46:07 +05:30
bli_l3_prune.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +05:30
bli_l3_smart_threading.c
Smart Threading for SGEMM SUP for Zen4 Architecture
2023-04-21 12:54:03 +05:30
bli_l3_smart_threading.h
Smart Threading for GEMM (sgemm) v1.
2022-05-17 18:10:39 +05:30
bli_l3_sup_ft_ker.h
Implemented gemm on skinny/unpacked matrices.
2019-08-23 14:18:08 +05:30
bli_l3_sup_int_amd.c
Level-3 triangular routines now use different block sizes and kernels.
2023-07-26 01:26:11 -04:00
bli_l3_sup_int.c
Copyright modification
2022-10-14 12:43:35 +05:30
bli_l3_sup_int.h
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
bli_l3_sup_ker_prot.h
Enable DTRSM small multithreading path for BLAS interface
2023-03-23 12:07:22 -04:00
bli_l3_sup_ker.h
Implemented gemm on skinny/unpacked matrices.
2019-08-23 14:18:08 +05:30
bli_l3_sup_oft.h
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
bli_l3_sup_packm_a.c
Copyright modification
2022-10-14 12:43:35 +05:30
bli_l3_sup_packm_a.h
Rebased amd-staging-milan-3.0 branch on master
2020-08-06 10:09:29 +05:30
bli_l3_sup_packm_b.c
Copyright modification
2022-10-14 12:43:35 +05:30
bli_l3_sup_packm_b.h
Rebased amd-staging-milan-3.0 branch on master
2020-08-06 10:09:29 +05:30
bli_l3_sup_packm_var.c
Rebased amd-staging-milan-3.0 branch on master
2020-08-06 10:09:29 +05:30
bli_l3_sup_packm_var.h
Support multithreading within the sup framework.
2020-08-06 10:09:28 +05:30
bli_l3_sup_ref.c
AOCL DTL - Added thread and execution time details in logs
2021-11-12 08:58:54 +05:30
bli_l3_sup_ref.h
BLIS:merge:
2021-04-27 11:09:48 +05:30
bli_l3_sup_var1n2m.c
Improve DGEMM sup for RCR case
2021-11-12 08:58:51 +05:30
bli_l3_sup_var12.c
Implemented gemm on skinny/unpacked matrices.
2019-08-23 14:18:08 +05:30
bli_l3_sup_vars.h
Implemented AVX-512 based 12x4 m-variant SUP kernels for ZGEMM
2023-04-06 04:49:15 -04:00
bli_l3_sup.c
Level-3 triangular routines now use different block sizes and kernels.
2023-07-26 01:26:11 -04:00
bli_l3_sup.h
Added sup functionality for SYRK
2021-04-29 12:35:30 +05:30
bli_l3_tapi_ba.c
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_tapi_ex.c
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_tapi.c
Fixed typed API definition for gemmt (#476)
2021-03-01 16:58:24 -06:00
bli_l3_tapi.h
Fixed typed API definition for gemmt (#476)
2021-03-01 16:58:24 -06:00
bli_l3_thrinfo.c
Support multithreading within the sup framework.
2020-03-13 01:09:29 -04:00
bli_l3_thrinfo.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +05:30
bli_l3_ukr_fpa.c
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_ukr_fpa.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +05:30
bli_l3_ukr_oapi.c
Export functions without def file (#303)
2020-08-03 11:46:07 +05:30
bli_l3_ukr_oapi.h
Add symbol export macro for all functions (#302)
2019-08-23 14:18:07 +05:30
bli_l3_ukr_prot.h
Add low-precision POWER10 gemm kernels (#467)
2021-03-05 13:53:43 -06:00
bli_l3_ukr_tapi.c
Export functions without def file (#303)
2020-08-03 11:46:07 +05:30
bli_l3_ukr_tapi.h
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3_ukr.h
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
bli_l3.h
Smart Threading for GEMM (sgemm) v1.
2022-05-17 18:10:39 +05:30
CMakeLists.txt
Added support for AVX512 for Windows and AMAVX
2022-06-08 11:09:48 +05:30