Fix L1 cache OOM for untilize with unpadding #16805
Open
+53
−20
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
nardoTT
requested review from
ayerofieiev-tt,
dmakoviichuk-tt,
rfurko-tt,
cfjchu,
TT-BrianLiu,
razorback3,
dongjin-na,
bbradelTT,
ntarafdar,
sjameelTT,
jaykru-tt,
yugi957,
jvegaTT and
llongTT
as code owners
bbradelTT
approved these changes
Jan 16, 2025
...ons/data_movement/untilize_with_unpadding/device/untilize_with_unpadding_program_factory.cpp
Outdated
Show resolved
Hide resolved
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Outdated suggestions cannot be applied.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.
Ticket
Link to Github Issue #16804
Problem description
In the current implementation of multi-core untilize with unpadding, the parallelization is only over the columns. This causes L1 OOM when the tensor has a large width
What's changed
Similar to tilize, we check the available space in L1, and run on a single core if the whole row doesn’t fit. Parallelization over different dimensions is to be added in the future
Checklist