tree cb498b71f1170dab2847197e29311edfab333783
parent b61a918989854abfa364b7b6849fa130c1064b09
author mariecwhite <mariewhite@google.com> 1710803266 +1100
committer GitHub <noreply@github.com> 1710803266 +1100
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJl+MlCCRC1aQ7uu5UhlAAAj2MQADXOVI+PTPbXsCEF+7zK6BT8
 va/6enM7/inkjvqf3+Ok4+VZzRBmuFl8jxmJ8bnbKl2zws1KL7uMY5SEFwsY8HHk
 n50Q3gs89SpBly/JZ6yQkpRv3vRvjACXQS47aR5lseKH3CXnfqN0h0WKnyfdgeCs
 JK7cnCknINGmok3bpKNzHn2nPtCZ44XpVo3uk/vnBH2f30pQxu9h7c5+Dh/uZ/o7
 IJDqxYAZouMZxC6n2Wa0NvnD49UkCznGN/ua0pFUsbLfQRYj4MVPfcGlke9kVwV6
 DYCAQIGmJdZeukTKYj1Pq8vnIvV2PDR0KoZ46lCKcv/nhoyZbAxIJ9lE2GO2U4xP
 0pNoR10jqPxzqD/54HQ36zs1lEnIquGFhF3I6sySVj2bTGmtKT8lm+xj7vVchDL+
 HVblRz4tHhfrFSf9q+WZXTAwVFyvY0rj1+3yEzY0FBT0bLsvHakV9mKbX8Qc6+Lu
 B1enwBjXaIP0Kl/qvFyMK0w//ssfYWQHpfl4a4qFfCCUmVE3EavD8ON3TZRnqzZY
 mJ60aiO6jXLVK81lyqcKDi+5tjukkQ73+Srkxf7z6OzrlQHnGPuFmFvaunXXDhkx
 qu1Wcf3WDDcltCU2zs20rFwWfBPFEb7lE586Ev1ViU42VaX/S59Q6TOZlHbLDt+k
 33fFuyREorw7EYqPl1OM
 =lIhe
 -----END PGP SIGNATURE-----
 

[CPU] Add s8s4s32 i8mm ukernel (#16678)

Adds ukernel for `i8 * i4 -> i32` using the `ssmla` instruction
available in +i8mm. Uses 2 separate functions: one for M0=1 and another
for M0=2, M0=4, M0=8.

```
-----------------------------------------------------------------------------------------------------------
Benchmark                                                 Time             CPU   Iterations UserCounters...
-----------------------------------------------------------------------------------------------------------
BM_mmt4d_s8s4s32_tile_1x16x2/real_time                0.690 us        0.689 us      1048575 items_per_second=23.735G/s
BM_mmt4d_s8s4s32_tile_2x16x2/real_time                0.803 us        0.801 us      1048575 items_per_second=40.8248G/s
BM_mmt4d_s8s4s32_tile_4x16x2/real_time                 1.68 us         1.68 us       524287 items_per_second=38.9081G/s
BM_mmt4d_s8s4s32_tile_1x8x8_dotprod/real_time      0.640 us        0.638 us      1048575 items_per_second=51.185G/s
BM_mmt4d_s8s4s32_tile_2x8x8_dotprod/real_time      0.369 us        0.368 us      2097151 items_per_second=177.561G/s
BM_mmt4d_s8s4s32_tile_4x8x8_dotprod/real_time      0.540 us        0.539 us      1048575 items_per_second=242.718G/s
BM_mmt4d_s8s4s32_tile_8x8x8_dotprod/real_time      0.934 us        0.932 us      1048575 items_per_second=280.543G/s
BM_mmt4d_s8s4s32_tile_1x8x16_i8mm/real_time      0.451 us        0.450 us      2097151 items_per_second=145.412G/s
BM_mmt4d_s8s4s32_tile_2x8x16_i8mm/real_time      0.509 us        0.509 us      1048575 items_per_second=257.577G/s
BM_mmt4d_s8s4s32_tile_4x8x16_i8mm/real_time      0.806 us        0.805 us      1048575 items_per_second=325.353G/s
BM_mmt4d_s8s4s32_tile_8x8x16_i8mm/real_time       1.76 us         1.76 us       524287 items_per_second=297.277G/s
```