fix LayerNorm f16 CPU implementation #22479
Merged
Conversation
This file contains 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
tianleiwu
reviewed
Oct 17, 2024
amarin16
previously approved these changes
Oct 17, 2024
tianleiwu
reviewed
Oct 17, 2024
tianleiwu
reviewed
Oct 17, 2024
tianleiwu
requested changes
Oct 17, 2024
|
Updated to resolve the comments.
|
tianleiwu
previously approved these changes
Oct 17, 2024
tianleiwu
reviewed
Oct 17, 2024
tianleiwu
reviewed
Oct 17, 2024
tianleiwu
approved these changes
Oct 17, 2024
guschmue
pushed a commit
that referenced
this pull request
Oct 18, 2024
### Description The recent PR #22223 introduced 2 bugs in implementation of CPU LayerNorm f16: - possible access to nullptr for bias `const TensorShape& bias_shape = bias->Shape();` will crash when `bias` does not exist. (amazingly seems this one is not coverred by any test case) - fix: guard with pointer check - a racing condition inside ComputeJob `ComputeJob()` is dispatched to threadpool and it internally tries to modify `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_`, which are `std::unique_ptr`s and are not thread-safe. - fix: move the modification of `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_` out of `ComputeJob()` and put into `LayerNormImpl::ComputeWithoutContext()`. It may still have racing condition because `ConcurrentRunSupported` is set to `true` for CPU EP. Added an OrtMutex. This should fixes the recent flaky tests as well.
tianleiwu
pushed a commit
that referenced
this pull request
Oct 18, 2024
### Description The recent PR #22223 introduced 2 bugs in implementation of CPU LayerNorm f16: - possible access to nullptr for bias `const TensorShape& bias_shape = bias->Shape();` will crash when `bias` does not exist. (amazingly seems this one is not coverred by any test case) - fix: guard with pointer check - a racing condition inside ComputeJob `ComputeJob()` is dispatched to threadpool and it internally tries to modify `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_`, which are `std::unique_ptr`s and are not thread-safe. - fix: move the modification of `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_` out of `ComputeJob()` and put into `LayerNormImpl::ComputeWithoutContext()`. It may still have racing condition because `ConcurrentRunSupported` is set to `true` for CPU EP. Added an OrtMutex. This should fixes the recent flaky tests as well.
apsonawane
pushed a commit
that referenced
this pull request
Oct 22, 2024
### Description The recent PR #22223 introduced 2 bugs in implementation of CPU LayerNorm f16: - possible access to nullptr for bias `const TensorShape& bias_shape = bias->Shape();` will crash when `bias` does not exist. (amazingly seems this one is not coverred by any test case) - fix: guard with pointer check - a racing condition inside ComputeJob `ComputeJob()` is dispatched to threadpool and it internally tries to modify `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_`, which are `std::unique_ptr`s and are not thread-safe. - fix: move the modification of `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_` out of `ComputeJob()` and put into `LayerNormImpl::ComputeWithoutContext()`. It may still have racing condition because `ConcurrentRunSupported` is set to `true` for CPU EP. Added an OrtMutex. This should fixes the recent flaky tests as well.
ishwar-raut1
pushed a commit
to ishwar-raut1/onnxruntime
that referenced
this pull request
Nov 19, 2024
### Description The recent PR microsoft#22223 introduced 2 bugs in implementation of CPU LayerNorm f16: - possible access to nullptr for bias `const TensorShape& bias_shape = bias->Shape();` will crash when `bias` does not exist. (amazingly seems this one is not coverred by any test case) - fix: guard with pointer check - a racing condition inside ComputeJob `ComputeJob()` is dispatched to threadpool and it internally tries to modify `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_`, which are `std::unique_ptr`s and are not thread-safe. - fix: move the modification of `LayerNormImpl::scale_fp32_` and `LayerNormImpl::bias_fp32_` out of `ComputeJob()` and put into `LayerNormImpl::ComputeWithoutContext()`. It may still have racing condition because `ConcurrentRunSupported` is set to `true` for CPU EP. Added an OrtMutex. This should fixes the recent flaky tests as well.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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
The recent PR #22223 introduced 2 bugs in implementation of CPU LayerNorm f16:
const TensorShape& bias_shape = bias->Shape();will crash whenbiasdoes not exist. (amazingly seems this one is not coverred by any test case)ComputeJob()is dispatched to threadpool and it internally tries to modifyLayerNormImpl::scale_fp32_andLayerNormImpl::bias_fp32_, which arestd::unique_ptrs and are not thread-safe.LayerNormImpl::scale_fp32_andLayerNormImpl::bias_fp32_out ofComputeJob()and put intoLayerNormImpl::ComputeWithoutContext(). It may still have racing condition becauseConcurrentRunSupportedis set totruefor CPU EP. Added an OrtMutex.This should fixes the recent flaky tests as well.