auto setting for max prefetch #1937
Open
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
mooskagh
reviewed
Feb 28, 2024
| @@ -240,6 +240,10 @@ class SearchWorker { | |||
| max_out_of_order_ = | |||
| std::max(1, static_cast<int>(params_.GetMaxOutOfOrderEvalsFactor() * | |||
| target_minibatch_size_)); | |||
| max_prefetch_batch_ = params.GetMaxPrefetchBatch(); | |||
| if (max_prefetch_batch_ < 0) { | |||
| max_prefetch_batch_ = search_->network_->IsCpu() ? 0 : 32; | |||
There was a problem hiding this comment.
Would it be possible to also make sure that max_prefetch_batch_ + target_minibatch_size_ is <= GetBatchSize() returned by backends?
(also, maybe rename backend's function GetBatchSize() to something more strictly sounding? Like "GetBatchSizeLimit()orGetMaxSupportedBatchSize()`?)
There was a problem hiding this comment.
I think max prefetch should never exceed the requested batch size. I'll think about it.
Regarding the function naming, I plan a final revision of the API after all planned functionality is in (currently missing a backend max batch setting).
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Outdated suggestions cannot be applied.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.
This is the next in the auto-configure series, dealing with max-prefetch, 0 for cpu backends and 32 otherwise. It also removes the params_override.h mechanism as it isn't used any more.