Conversation
\`mangle_param\` called \`findfirst(isequal(x), substitutions)\` with \`x\`
a type — which builds a \`Base.Fix{2, isequal, Type{X}}\` closure that
\`findfirst\` then specializes on. Every unique type mangled during a
CUDA kernel-function compile therefore produced a fresh \`findnext\` +
\`Fix\` specialization.
Trace-compile on CUDA.jl's gpuarrays/broadcasting suite showed
~1771 \`isequal\` + ~867 \`findnext\` events before this fix (5680 total
trace lines); after this fix, 0 of either (3953 total, a 30 % drop),
with the broadcasting testset's wall-clock dropping ~8 s.
The fix: replace the closure-creating \`findfirst\` with a manual
\`===\` loop that \`@nospecialize\`s its argument, and \`@nospecialize\`
\`mangle_param\` / \`mangle_sig\` / \`safe_name\` themselves so they
don't duplicate one compiled body per distinct mangled type.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #783 +/- ##
==========================================
+ Coverage 75.42% 75.43% +0.01%
==========================================
Files 24 24
Lines 3857 3859 +2
==========================================
+ Hits 2909 2911 +2
Misses 948 948 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.