AMX int8/bf16 tile GEMM — enable, fix 5 bugs, optimize (0→197 GMAC/s) + vertical-SIMD primitives #546
| Job | Run time |
|---|---|
| 1m 30s | |
| 47s | |
| 7m 59s | |
| 20s | |
| 30s | |
| 27s | |
| 4s | |
| 0s | |
| -1s | |
| -1s | |
| -1s | |
| -9s | |
| 58s | |
| 11m 0s | |
| 11m 17s | |
| 11m 1s | |
| -1s | |
| 45m 40s |
| Job | Run time |
|---|---|
| 1m 30s | |
| 47s | |
| 7m 59s | |
| 20s | |
| 30s | |
| 27s | |
| 4s | |
| 0s | |
| -1s | |
| -1s | |
| -1s | |
| -9s | |
| 58s | |
| 11m 0s | |
| 11m 17s | |
| 11m 1s | |
| -1s | |
| 45m 40s |