support WebAssembly SIMD for qgemm#9191
Merged
Merged
Conversation
fs-eire
added
the
platform:web
hanbitmyths
approved these changes
Sep 29, 2021
Collaborator
hanbitmyths
left a comment
hanbitmyths
left a comment
There was a problem hiding this comment.
looks correctly converted from qgemm_kernel_sse
siweic0
pushed a commit
to siweic0/onnxruntime-web
that referenced
this pull request
May 9, 2024
* support WebAssembly SIMD for qgemm * remove '--experimental-wasm-bulk-memory' for test
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description: This change implemented QGEMM ( MlasGemmBatch for u8 ), which is used by common kernels in quantized model (eg. DynamicQuantizeMatMul, MatMulIntegerToFloat) for WebAssembly SIMD.
Motivation and Context
This implementation helps to improve performance for quantized model on ONNX Runtime Web (where SIMD is supported).
this change helps to improve performance referred in Performance comparison between onnxruntime-web and onnxruntime-python #9161.
The change is implemented based on the SSE qgemm implementation.
There are 2 newly added wasm SIMD instructions:
Minimum requirement: