mirror of
https://github.com/amd/blis.git
synced 2026-07-19 01:54:14 +00:00
- Change begin_asm and end_asm comments and unused code in files
kernels/haswell/3/sup/s6x16/bli_gemmsup_rv_haswell_asm_sMx6.c
kernels/zen4/3/sup/bli_gemmsup_cd_zen4_asm_z12x4m.c
to avoid problems in clobber checking script.
- Add missing clobbers in files
kernels/zen4/1m/bli_packm_zen4_asm_d24xk.c
kernels/zen4/1m/bli_packm_zen4_asm_z12xk.c
kernels/zen4/3/sup/bli_gemmsup_cv_zen4_asm_z12x4m.c
- Add missing newline at end of files.
- Update some copyright years for recent changes.
- Standardize license text formatting.
AMD-Internal: [CPUPL-6579]
30 lines
1008 B
Plaintext
30 lines
1008 B
Plaintext
f32f32f32of32:group_count=2
|
|
group_size=4
|
|
r n n n n 6 64 128 128 64 64 bias=bf16,relu,swish
|
|
group_size=3
|
|
r n t n n 78 9810 1229 1229 9810 9810 matrix_add=bf16,matrix_mul=f32
|
|
s8s8s32obf16:group_count=1
|
|
group_size=5
|
|
r n n n r 67 21 1823 1823 21 21 scale=vector,zp=scalar,relu,clip
|
|
f32f32f32of32:group_count=1
|
|
group_size=7
|
|
r n t n n 43 2240 1553 1553 1553 2240 scale=vector,zp=scalar,relu,clip
|
|
bf16bf16f32obf16:group_count=1
|
|
group_size=6
|
|
r n n n r 79 2676 1995 1995 2676 2676 bias=na,swish
|
|
bf16bf16f32of32:group_count=1
|
|
group_size=6
|
|
r t n n r 143 1943 730 143 1943 1943 bias=na,clip
|
|
bf16s4f32of32:group_count=1
|
|
group_size=6
|
|
r t n n r 79 1177 1968 79 1177 1177 scale=vector,zp=scalar,relu,clip
|
|
bf16s4f32obf16:group_count=1
|
|
group_size=6
|
|
r n n n r 17 2714 468 468 2714 2714 scale=vector,zp=vector,bias=na
|
|
s8s8s32obf16:group_count=1
|
|
group_size=4
|
|
r n n n n 43 2240 1553 1553 2240 2240 scale=vector,zp=scalar,relu,clip
|
|
*:group_count=1
|
|
group_size=3
|
|
r t t n n 92 1479 589 92 589 1479 scale=vector,zp=vector,bias=na,clip
|