perf: improve performance of translate by reusing buffers #19533
+130
−21
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
viirya
force-pushed
the
translate_optimize
branch
from
c452244 to
d8d7f97
Compare
Optimize translate function by reusing HashMap and Vec buffers across all rows instead of allocating new ones for each row. Changes: - Moved HashMap and Vec allocations outside the main loop - Clear and reuse buffers for each row instead of reallocating - Use explicit loops instead of chained iterators for better control - Added benchmark to measure performance improvements Optimization: - Before: Allocated HashMap + 4 Vecs for every row - After: Single set of reusable buffers cleared for each row Benchmark Results: - size=1024, str_len=8: 234.6 µs → 147.9 µs (37% faster) - size=1024, str_len=32: 628.6 µs → 394.2 µs (37% faster) - size=4096, str_len=8: 964.4 µs → 575.2 µs (40% faster) - size=4096, str_len=32: 2.54 ms → 1.56 ms (39% faster) The optimization shows exceptional 37-40% performance improvements across all test cases. The HashMap reuse is particularly impactful since HashMap creation/destruction has significant overhead with hashing, bucket allocation, and internal bookkeeping. Combined with eliminating 4 Vec allocations per row, this becomes the most significant optimization in this series.
viirya
force-pushed
the
translate_optimize
branch
from
d8d7f97 to
647b56a
Compare
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Outdated suggestions cannot be applied.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.
Optimize translate function by reusing HashMap and Vec buffers across all rows instead of allocating new ones for each row.
Changes:
Optimization:
Benchmark Results:
The optimization shows exceptional 37-40% performance improvements across all test cases. The HashMap reuse is particularly impactful since HashMap creation/destruction has significant overhead with hashing, bucket allocation, and internal bookkeeping. Combined with eliminating 4 Vec allocations per row, this becomes the most significant optimization in this series.
Which issue does this PR close?
Rationale for this change
What changes are included in this PR?
Are these changes tested?
Are there any user-facing changes?