feat[gpu_prover]: try acting on 10 columns (depth-first) instead of 1 in hypercube bench#210
Closed
mcarilli wants to merge 1 commit intorr/hypercube-monomialsfrom
Closed
feat[gpu_prover]: try acting on 10 columns (depth-first) instead of 1 in hypercube bench#210mcarilli wants to merge 1 commit intorr/hypercube-monomialsfrom
mcarilli wants to merge 1 commit intorr/hypercube-monomialsfrom
Conversation
shamatar
reviewed
Mar 2, 2026
| let mut d_src = DeviceAllocation::alloc(rows * COLS)?; | ||
| let d_dst = DeviceAllocation::alloc(rows * COLS)?; | ||
|
|
||
| // Fill once to avoid benchmarking uninitialized memory reads. |
Member
There was a problem hiding this comment.
Believe me, you can get into benchmarking allocator here - as it's zeroed memory and it may be allocated lazily
Author
There was a problem hiding this comment.
It's a good point that i should ensure all first touch overhead happens before benchmarking iterations, but this particular spot allocates gpu memory which doesn't have the same lazy first touch behavior as cpu ram.
Anyway, RobertGPT fixed the whole issue a different way here, so my patch is no longer needed.
Author
|
Fixed by Robert in 7ab528b |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What ❔
"Augments" hypercube bench to act on 10 columns depth-first, instead of 1 column repeatedly.
Why ❔
Possibly more realistic, and eliminates spurious L2 residency of a single column across bench iterations.
Is this a breaking change?
Checklist