use a more optimal loop implementation#131
Open
nagisa wants to merge 1 commit intosolana-program:mainfrom
Open
use a more optimal loop implementation#131nagisa wants to merge 1 commit intosolana-program:mainfrom
nagisa wants to merge 1 commit intosolana-program:mainfrom
Conversation
In platform-tools v1.53 inlining decisions of Iterator::next prevent LLVM from optimizing this loop into an unrolled index-based version of it. So where in 1.51 we'd see ```asm INLINE_MEMMOVE($from, $to, 32 bytes) jeq $length, 1, exit INLINE_MEMMOVE($from, $to, 32 bytes) jeq $length, 2, exit ... ``` In 1.53 we'd instead get a much more CU-heavy pointer-comparison based loop instead. ```asm lsh64 $index, 3 ldxdw r4, [r1 + 0] add64 r1, $index INLINE_MEMMOVE($from, $to, 32) ldxdw r6, [r10 - 48] jeq r1, r2, exit ; ... ``` Since we want an index-based loop here for optimal results, might as well write it that way directly instead of relying on optimizations to trigger. Co-authored-by: Lucas Ste <38472950+LucasSte@users.noreply.github.com>
Author
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In platform-tools v1.53 inlining decisions of Iterator::next prevent LLVM from optimizing this loop into an unrolled index-based version of it.
So where in 1.51 we'd see
In 1.53 we'd instead get a much more CU-heavy pointer-comparison based loop instead.
Since we want an index-based loop here for optimal results, might as well write it that way directly instead of relying on optimizations to trigger.