Skip to content

Latest commit

 

History

History
37 lines (32 loc) · 2.43 KB

DocumentList.md

File metadata and controls

37 lines (32 loc) · 2.43 KB

Index of documents

This document serves as an index for onnx-mlir documents.

Supported ONNX Ops

  • CPU support is covered here.
  • NNPA support is covered here.

Working environment

Development

  • Onnx operation are represented with ONNX dialect in onnx-mlir.
  • This document tell you how to generate an ONNX operation into ONNX dialect.
  • After an ONNX model is imported into onnx-mlir, several graph-level transformations will be applied. These transformations include operation decomposition, constant propagation, shape inference, and canonicalization.
  • Then the ONNX dialect is lowered to Krnl dialect. To help debugging and performance tuning, onnx-mlir supports instrumentation at the ONNX operand level.
  • All the passes may be controlled with options.
  • How to handle errors can be found here.
  • How to support a new accelerator can be found here.
  • How to analyze unknown dimensions and query their equality at compile time can be found here.
  • A Jenkins monitor job was setup to help with updating LLVM commit. It locates the next commit we can update to without breaking ONNX-MLIR, as well as the commit that will break ONNX-MLIR. You can see the commit(s) here: s390x, ppc64le, amd64.

# Execution The compiled ONNX model can be executed with either a C/C++ driver python driver. or a java driver. The routine testing for onnx-mlir build is describe in this document.