microsoft / microsoft/onnxruntime

bf16 kernel (OpSet13) for MatMul in CPU EP

Open
#20,630 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

core runtime feature request
Dominant language
C++
Stars
21.9k
Forks
4.2k
Avg merge
4d 11h
Merged PRs (30d)
184

Description

### Describe the issue

MatMul in ONNX OpSet 13 started to support bf16 (https://onnx.ai/onnx/operators/onnx__MatMul.html)

However, we dont see the implementation for bfloat16 in the CPU EP for matmul(13), https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/core/providers/cpu/math/matmul.cc#L61-L89

Is there any reason this is still not supported since OpSet was released long time ago?

If we want to implement it on our own, is there any PR i can reference to?

Ping @snnn @pranavsharma for help

### To reproduce

NA

### Urgency

_No response_

### Platform

Windows

### OS Version

11

### ONNX Runtime Installation

Built from Source

### ONNX Runtime Version or Commit ID

NA

### ONNX Runtime API

Python

### Architecture

X64

### Execution Provider

Default CPU

### Execution Provider Library Version

_No response_

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with onnxruntime/core/providers/cpu/math/matmul.cc, especially lines 61-89, and compare the implementation with the ONNX MatMul OpSet 13 specification linked in the issue. Determine the CPU EP changes needed for bfloat16 MatMul and add or update coverage so the feature is verified for the supported CPU path.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.