Add support for vmapped linesearch in Newton-Raphson solver. - #2353
Open
copybara-service[bot] wants to merge 1 commit into
Open
Add support for vmapped linesearch in Newton-Raphson solver.#2353copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
Evaluating multiple linesearch step sizes sequentially using a while loop is slow on GPU. Vmapping the linesearch allows evaluating multiple trial step sizes in parallel, which has near-zero overhead on GPU and improves performance when backtracking occurs. PiperOrigin-RevId: 962100894
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add support for vmapped linesearch in Newton-Raphson solver.
Evaluating multiple linesearch step sizes sequentially using a while loop is slow on GPU. Vmapping the linesearch allows evaluating multiple trial step sizes in parallel, which has near-zero overhead on GPU and improves performance when backtracking occurs.