improved shifting by 48-63 in llshr#784
Merged
mateoconlechuga merged 1 commit intomasterfrom Apr 18, 2026
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The compiler often emits
__llshru(63)to get the signbit of(u)int64_t, which takes around ~1550F clock cycles instead of 2Fbit 7, b. This contributes to the very slow performance oflong doubleoperations which often need to shift by 52 or 63 bits. Similarly,__llshrs(63)also appears when doing a "branchless"long long llabs(long long).I have added an optimized path for
__llshr(u/s)that handles shift amounts of 48-63, taking no more than 100F to complete. The new worst case is shifting by 47 (1165F + 110R + 108W + 141)