mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-18 21:21:17 +00:00
fffefb1c22
### Description Changes in this PR: 1) use the optimized version `makeMatMulPacked[Vec4]Source` to support matmul. 2) enable the conv2dByMatMul path. 3) support broadcast 4) use IndicesHelper. MatMul with M = 512, K = 512, N = 512 becomes 2ms from 15ms when enabling profilingMode on my ADL. |
||
|---|---|---|
| .. | ||
| _example.jsonc | ||
| abs.jsonc | ||
| absr.jsonc | ||
| abss.jsonc | ||
| acos.jsonc | ||
| add.jsonc | ||
| add_int32.jsonc | ||
| and.jsonc | ||
| asin.jsonc | ||
| cast.jsonc | ||
| ceil.jsonc | ||
| concat.jsonc | ||
| conv-transpose.jsonc | ||
| conv.jsonc | ||
| cos.jsonc | ||
| depth-to-space.jsonc | ||
| div.jsonc | ||
| div_int32.jsonc | ||
| equal.jsonc | ||
| exp.jsonc | ||
| expand.jsonc | ||
| floor.jsonc | ||
| gather-elements.jsonc | ||
| gather.jsonc | ||
| gelu.jsonc | ||
| gemm.jsonc | ||
| global-average-pool.jsonc | ||
| greater.jsonc | ||
| identity.jsonc | ||
| image-scaler.jsonc | ||
| layer-norm.jsonc | ||
| leaky-relu.jsonc | ||
| less.jsonc | ||
| log.jsonc | ||
| matmul.jsonc | ||
| mul.jsonc | ||
| mul_int32.jsonc | ||
| neg.jsonc | ||
| not.jsonc | ||
| or.jsonc | ||
| pad-big.jsonc | ||
| pad.jsonc | ||
| pow-big-number.jsonc | ||
| pow.jsonc | ||
| pow_int32.jsonc | ||
| reduce-min.jsonc | ||
| relu.jsonc | ||
| reshape-int32.jsonc | ||
| reshape-pack.jsonc | ||
| reshape.jsonc | ||
| resize-pack.jsonc | ||
| shape.jsonc | ||
| sin.jsonc | ||
| skip-layer-norm.jsonc | ||
| softmax.jsonc | ||
| split.jsonc | ||
| sqrt.jsonc | ||
| sub.jsonc | ||
| sub_int32.jsonc | ||
| tan.jsonc | ||
| tile.jsonc | ||
| transpose.jsonc | ||
| transpose_int32_uint32.jsonc | ||
| upsample.jsonc | ||
| xor.jsonc | ||