Elementwise Benchmarks¶
Note
This page will be populated with benchmark data from nightly CI runs.
Unary Operations¶
| Op | Shape | Dtype | TileOPs (ms) | PyTorch (ms) | Speedup | Bandwidth (GB/s) |
|---|---|---|---|---|---|---|
| — | — | — | — | — | — | — |
Binary Operations¶
| Op | Shape | Dtype | TileOPs (ms) | PyTorch (ms) | Speedup | Bandwidth (GB/s) |
|---|---|---|---|---|---|---|
| — | — | — | — | — | — | — |
Fused Gated Activations¶
| Activation | Shape | Dtype | TileOPs (ms) | Separate Ops (ms) | Speedup |
|---|---|---|---|---|---|
| — | — | — | — | — | — |