mirror of
https://github.com/amd/blis.git
synced 2026-05-11 09:39:59 +00:00
Developed AVX512 based "sup" kernels for SGEMM
- Only for RRR case, var2m kernels are added - Main kernel is of 12x32 (AVX512), associated fringe kernels of - 8x32, 4x32, 2x32, 1x32 (AVX512) - 12x16, 8x16, 4x16, 2x16, 1x16 (AVX512) - 12x8, 8x8 (AVX2) - 12x4, 8x4 (SSE4) - 12x2, 8x2 (SSE4) - existing AVX2/SSE4 kernels are used for other fringe cases - Currently, these kernels are not invoked in zen4 path - Once all AVX512 kernels (n and rd) are done, invoke all of them together in zen4 config AMD-Internal: [CPUPL-2801] Change-Id: I7a206fee9151e92319d83dcc5f3eed61d3bf1196
This commit is contained in:
4019
kernels/zen4/3/bli_gemmsup_rv_zen_s12x32m.c
Normal file
4019
kernels/zen4/3/bli_gemmsup_rv_zen_s12x32m.c
Normal file
File diff suppressed because it is too large
Load Diff
@@ -39,4 +39,22 @@ AMAXV_KER_PROT( float, s, amaxv_zen_int_avx512 )
|
||||
AMAXV_KER_PROT( double, d, amaxv_zen_int_avx512 )
|
||||
|
||||
GEMMTRSM_UKR_PROT( double, d, gemmtrsm_l_zen_asm_16x14)
|
||||
GEMMTRSM_UKR_PROT( double, d, gemmtrsm_u_zen_asm_16x14)
|
||||
GEMMTRSM_UKR_PROT( double, d, gemmtrsm_u_zen_asm_16x14)
|
||||
|
||||
//sgemm rv sup
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_12x32m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_8x16m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_4x16m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_2x16m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_1x16m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_8x8m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_8x4m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_8x2m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_12x16m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_12x8m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_12x4m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_12x2m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_8x32m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_4x32m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_2x32m )
|
||||
GEMMSUP_KER_PROT( float, s, gemmsup_rv_zen_asm_1x32m )
|
||||
|
||||
Reference in New Issue
Block a user