Fix integer overflow in LongformerAttention#12435
Merged
Conversation
wangyems
approved these changes
Aug 3, 2022
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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:
LongformerAttention might need >2GB memory for large batch size. GetScratch1Size function might encounter integer overflow. For example batch_size=64, sequence_length=4096, window=256, num_heads=12, element_size=2. The value will be larger than 2GB thus cause integer overflow. If user uses smaller batch size like 16 (or 32), this error will not be triggered.
Motivation and Context
LongformerAttention cuda might fail with large batch size. For debug build, assertion error will be triggered at
assert(current_pointer == scratch2). For release build, the error is likeonnxruntime::CudaCall] CUDA failure 700: an illegal memory access was encountered