Skip to content

Commit 415bf0d

Browse files
authored
Merge pull request #2636 from pnkfelix/patch-11
add performance triage report for this week
2 parents 38f2144 + ae7fb15 commit 415bf0d

File tree

1 file changed

+7
-14
lines changed

1 file changed

+7
-14
lines changed

draft/2021-11-24-this-week-in-rust.md

Lines changed: 7 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -146,25 +146,18 @@ If you are a Rust project owner and are looking for contributors, please submit
146146

147147
### Rust Compiler Performance Triage
148148

149-
A large amount of noise in the comparisons this week, likely due to new
150-
probabilistic query hash verification increasing likelihood of changes in each
151-
benchmark; solutions are being tracked in [rustc-perf#1105].
152149

153-
Otherwise, though, the week largely amounted to a neutral one for performance.
154-
There were some regressions, particularly in doc builds, as a result of the
155-
addition of portable SIMD. These are relatively speaking minor and primarily
156-
impact small crates.
150+
This week, there were a number of cases where the `incr-unchanged` variants of `inflate` went up or down by 5% to 6%; we believe these are instances of increased noise in benchmarks documented on [rustc-perf#1105](https://github.com/rust-lang/rustc-perf/issues/1105). I was tempted to remove these from the report, but its non-trivial to re-construct the report "as if" some benchmark were omitted.
157151

158-
[rustc-perf#1105]: https://github.com/rust-lang/rustc-perf/issues/1105
152+
Otherwise, there were some nice wins for performance. For example, PR [#90996](https://github.com/rust-lang/rust/issues/90996) more than halved the time to document builds of `diesel` by revising how we hash `ObligationCauseData`. If anyone is interested, it might be good to follow-up on the effects of PR [#90352](https://github.com/rust-lang/rust/issues/90352), "Simplify `for` loop desugar", where we have hypothesized that the increased compilation time is due to more LLVM optimizations being applied.
159153

160-
Triage done by **@simulacrum**.
161-
Revision range: [eee8b9c7..934624f](https://perf.rust-lang.org/?start=eee8b9c7bafade55981d155dae71657f1cc55a22&end=934624fe5f66ce3fb8abf0597a6deb079783335f&absolute=false&stat=instructions%3Au)
154+
Triage done by **@pnkfelix**.
155+
Revision range: [934624fe..22c2d9dd](https://perf.rust-lang.org/?start=934624fe5f66ce3fb8abf0597a6deb079783335f&end=22c2d9ddbf356bcdb718e88ca6ee3665e1e42690&absolute=false&stat=instructions%3Au)
162156

163-
5 Regressions, 2 Improvements, 6 Mixed; 2 of them in rollups
157+
1 Regressions, 3 Improvements, 8 Mixed; 3 of them in rollups
158+
34 comparisons made in total
164159

165-
41 comparisons made in total
166-
167-
[Full report here](https://github.com/rust-lang/rustc-perf/blob/master/triage/2021-11-16.md)
160+
[Full report here](https://github.com/rust-lang/rustc-perf/blob/master/triage/2021-11-23.md)
168161

169162
### Approved RFCs
170163

0 commit comments

Comments
 (0)