Ettore Tiotto comments

Results 18 comments of


                                            Ettore Tiotto

Getting involved, possible area of work for new contributors

**List of Learning Resources** - https://www.youtube.com/watch?v=cyICUIZ56wQ (Intro on MLIR) - https://video.ibm.com/recorded/127363418 (ONNX MLIR talk) - https://video.ibm.com/recorded/127363577 (ONNX MLIR Wrap-Up) - https://github.ibm.com/Tian-Jin2/onnx-mlir-lab/ (github repo with example) - https://mlir.llvm.org/ (MLIR documentation) -...

[RFC] Contributing an ONNX to TOSA legalization pass to onnx-mlir

So far we lower the ONNX dialect to our own internal Krnl dialect. Adding integration with TOSA might allow us to lower ONNX operators to TOSA without impacting/breaking the current...

Threat all warnings as errors.

Opinions @AlexandreEichenberger @doru1004 @tungld @sstamenova @gongsu832 @caoimhinuibrian ?

Threat all warnings as errors.

Thanks @sstamenova for the useful pointer. I was just looking at that file and I would also prefer to reuse `LLVM_ENABLE_WERROR` if that works. We could initially add the code,...

Threat all warnings as errors.

@AlexandreEichenberger not yet.

Next Ops to work on

I am working on `SpaceToDepth` (#926) and `DepthToSpace` (#927).

Next Ops to work on

I am going to look at `categorymapper` (#941).

Next Ops to work on

Working on `ScatterElements` (needed by fasterrcnn-10.onnx, maskrcnn-10.onnx). PR is https://github.com/onnx/onnx-mlir/pull/1352 `Scatter` is deprecated but we map it to `ScatterElements`. PR is https://github.com/onnx/onnx-mlir/pull/1337

Next Ops to work on

Working on `ScatterND`. PR is https://github.com/onnx/onnx-mlir/pull/1370

Next Ops to work on

Implemented `GatherElements`. PR is https://github.com/onnx/onnx-mlir/pull/1375.