EnzymeAD / EnzymeAD/Enzyme-JAX

Missing Transpose Optimizations

Open
#217 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
MLIR
Stars
131
Forks
53
Avg merge
1d 10h
Merged PRs (30d)
193

Description

I realized it is better to create sub-issues than open multiple issues:

- [x] `transpose(unary(...))` #213
- [x] `transpose(binary(...))` when op is used only in that binary op #210
- [ ] `stablehlo.clamp`

```mlir
module {
func.func @main(%arg0: tensor<2x2xf64>) -> tensor<2x2xf64> {
%cst = stablehlo.constant dense<1.000000e+00> : tensor<2x2xf64>
%cst_0 = stablehlo.constant dense<0.000000e+00> : tensor<2x2xf64>
%0 = stablehlo.transpose %arg0, dims = [1, 0] : (tensor<2x2xf64>) -> tensor<2x2xf64>
%1 = stablehlo.clamp %cst_0, %0, %cst : tensor<2x2xf64>
%2 = stablehlo.transpose %1, dims = [1, 0] : (tensor<2x2xf64>) -> tensor<2x2xf64>
return %2 : tensor<2x2xf64>
}
}
```

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.