amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-05-12 18:15:37 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
75f72b7f6ea87ffafce315e456d5d9cecd4e07bf
blis/frame/3
History
Nallani Bhaskar 75f72b7f6e Added aocl dynamic feature for dtrsm for small sizes 
Details:
1. Added aocl-dynamic for dtrsm native path
   When (m,n)<512 better performance observed for nthreads=4
2. Updated trsm_small threshold such that when (m+n)<320
   trsm_small is doing better than native irrespective of
   number of threads

Change-Id: Ic2c50f14db257a05e323cc97c5d1c9b73b68f487
2021-06-18 08:46:47 -04:00
..
gemm
BLIS:merge:
2021-04-27 11:09:48 +05:30
gemmt
AOCL Windows: 3.1 BLIS changes
2021-03-08 19:04:17 +05:30
hemm
BLIS:merge:
2021-04-27 11:09:48 +05:30
her2k
BLIS:merge:
2021-04-27 11:09:48 +05:30
herk
BLIS:merge:
2021-04-27 11:09:48 +05:30
old
"Merge Selective Packing code from amd branch flame/blis"
2020-08-06 10:09:28 +05:30
symm
BLIS:merge:
2021-04-27 11:09:48 +05:30
syr2k
BLIS:merge:
2021-04-27 11:09:48 +05:30
syrk
BLIS:merge:
2021-04-27 11:09:48 +05:30
trmm
BLIS:merge:
2021-04-27 11:09:48 +05:30
trmm3
BLIS:merge:
2021-04-27 11:09:48 +05:30
trsm
Added aocl dynamic feature for dtrsm for small sizes
2021-06-18 08:46:47 -04:00
bli_l3_blocksize.c
BLIS:merge:
2021-04-27 11:09:48 +05:30
bli_l3_blocksize.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +05:30
bli_l3_check.c
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
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
Remove UT-Austin from copyright headers' clause 3.
2018-12-04 14:31:06 -06:00
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
Added sup functionality for SYRK
2021-04-29 12:35:30 +05:30
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
Renamed bli_thread_obarrier(), _obroadcast().
2020-05-21 11:54:37 +05:30
bli_l3_packm.h
Removed export macros from all internal prototypes.
2020-08-03 11:47:18 +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_sup_ft_ker.h
Implemented gemm on skinny/unpacked matrices.
2019-08-23 14:18:08 +05:30
bli_l3_sup_int.c
SUP GEMM - Enable only block panel (var2m)
2021-05-30 21:22:44 +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
Implemented gemm on skinny/unpacked matrices.
2019-08-23 14:18:08 +05:30
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
BLIS:merge:
2021-04-27 11:09:48 +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
Rebased amd-staging-milan-3.0 branch on master
2020-08-06 10:09:29 +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
Moved dynamic threading function from GEMMT to GEMM
2021-05-07 12:10:53 +05:30
bli_l3_sup_ref.h
BLIS:merge:
2021-04-27 11:09:48 +05:30
bli_l3_sup_var1n2m.c
Rebased amd-staging-milan-3.0 branch on master
2020-08-06 10:09:29 +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
Replaced use of bool_t type with C99 bool.
2020-08-03 11:27:13 +05:30
bli_l3_sup.c
Added dynamic threading support for SYRK SUP code path
2021-06-16 02:08:11 -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
Squash-merge 'pr' into 'squash'. (#457)
2020-11-14 09:39:48 -06:00
CMakeLists.txt
AOCL Windows: 3.1 BLIS changes
2021-03-08 19:04:17 +05:30