report for 2023-10-18.

Author: pnkfelix

triage/2023-10-18.md

@@ -1,8 +1,14 @@
 # 2023-10-18 Triage Log
 
-TODO: Summary
-
-Triage done by **@???**.
+Overall an interesting week performance wise, with small improvements to a vast
+number of benchmarks seeming to outweigh an isolated set of (slightly) larger
+regressions. It included a number of PRs regressed instruction counts but did
+not matter for cycle times, plus one mysterious regression to `check_match` and
+`mir_borrowck` from reworking constructor splitting (see report on PR 116391 for
+details), and an awesome broad set of improvements from automatically inlining
+small functions across crates (see report on PR 116505 for details).
+
+Triage done by **@pnkfelix**.
 Revision range: [84d44dd1..b9832e72](https://perf.rust-lang.org/?start=84d44dd1d8ec1e98fff94272ba4f96b2a1f044ca&end=b9832e72c9223f4e96049aa5911effd258b92591&absolute=false&stat=instructions%3Au)
 
 **Summary**:
@@ -16,7 +22,7 @@ Revision range: [84d44dd1..b9832e72](https://perf.rust-lang.org/?start=84d44dd1d
 | All ❌✅ (primary)                 | -0.9% | [-17.9%, 12.2%] | 138   |
 
 
-4 Regressions, 1 Improvements, 4 Mixed; ??? of them in rollups
+4 Regressions, 1 Improvements, 4 Mixed; 3 of them in rollups
 84 artifact comparisons made in total
 
 #### Regressions
@@ -31,6 +37,9 @@ Rollup of 7 pull requests [#116605](https://github.com/rust-lang/rust/pull/11660
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | 0.4% | [0.2%, 0.6%] | 7     |
 
+* solely rustdoc regression
+* believed to be caused by [PR 109422](https://github.com/rust-lang/rust/pull/109422) "rustdoc-search: add impl disambiguator to duplicate assoc items"
+* already marked as triaged
 
 Optimize `librustc_driver.so` with BOLT  [#116352](https://github.com/rust-lang/rust/pull/116352) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=ee8c9d3c34719a129f280cd91ba5d324017bb02b&end=c543b6f3516767150af84d94c14a27b19d4b0291&stat=instructions:u)
 
@@ -42,6 +51,9 @@ Optimize `librustc_driver.so` with BOLT  [#116352](https://github.com/rust-lang/
 | Improvements ✅ <br /> (secondary) | -0.3% | [-0.3%, -0.3%] | 4     |
 | All ❌✅ (primary)                 | 2.3%  | [0.2%, 5.7%]   | 10    |
 
+* primary instruction-count regressions were restricted to helloworld and html5ever
+* As noted in comment by Kobzol, the instruction counts regressed for many benchmarks, but the [cycle counts](https://perf.rust-lang.org/compare.html?start=ee8c9d3c34719a129f280cd91ba5d324017bb02b&end=c543b6f3516767150af84d94c14a27b19d4b0291&stat=cycles:u) solely improved, significantly so, and bootstrap time improved (628.052s -> 623.517s (-0.72%)).
+* already marked as triaged
 
 Rollup of 3 pull requests [#116742](https://github.com/rust-lang/rust/pull/116742) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=c543b6f3516767150af84d94c14a27b19d4b0291&end=e292fec36880f48101bda4054be37097312e73c0&stat=instructions:u)
 
@@ -53,6 +65,9 @@ Rollup of 3 pull requests [#116742](https://github.com/rust-lang/rust/pull/11674
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | 0.3% | [0.3%, 0.4%] | 3     |
 
+* Regressions are solely to bitmaps full scenarios.
+* Looks like a blip (i.e. noise) based on the graph over time.
+* marking as triaged.
 
 don't UB on dangling ptr deref, instead check inbounds on projections [#114330](https://github.com/rust-lang/rust/pull/114330) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=a00c09e9d80b763fb29206b47b04e1d99c3ace96&end=e7bdc5f9f869219e8d20060b42a09ea10a837851&stat=instructions:u)
 
@@ -64,6 +79,11 @@ don't UB on dangling ptr deref, instead check inbounds on projections [#114330](
 | Improvements ✅ <br /> (secondary) | -    | -            | 0     |
 | All ❌✅ (primary)                 | -    | -            | 0     |
 
+* From skimming the PR, one can see that the PR author (RalfJung) iterated on this to identify a solution that would minimize regressions.
+* As noted by the PR author, only secondary benchmarks were affected.
+* Also, while instruction-counts regressed, the [cycle-counts](https://perf.rust-lang.org/compare.html?start=a00c09e9d80b763fb29206b47b04e1d99c3ace96&end=e7bdc5f9f869219e8d20060b42a09ea10a837851&stat=cycles%3Au)
+  did not, at least not enough to pass our noise threshold.
+* marking as triaged.
 
 #### Improvements
 
@@ -77,6 +97,7 @@ optimize zipping over array iterators [#115515](https://github.com/rust-lang/rus
 | Improvements ✅ <br /> (secondary) | -     | -              | 0     |
 | All ❌✅ (primary)                 | -0.3% | [-0.4%, -0.2%] | 3     |
 
+* A small win from a PR addressing user-filed performance regression, namely [issue #115339](https://github.com/rust-lang/rust/issues/115339), "Performance regression of array::IntoIter vs slice::Iter"
 
 #### Mixed
 
@@ -90,6 +111,9 @@ Also consider call and yield as MIR SSA. [#113915](https://github.com/rust-lang/
 | Improvements ✅ <br /> (secondary) | -0.4% | [-0.6%, -0.3%] | 5     |
 | All ❌✅ (primary)                 | -0.2% | [-0.9%, 3.9%]  | 27    |
 
+* The try perf run had sole primary regression of unicode-normalization-0.1.19 opt-full (1.19%), while the perf run against master had sole primary regression of exa-0.10.1 opt-full (3.90%).
+* The exa regression has persisted forward (i.e. it is not transient noise).
+* It was already been marked as triaged, as the performance changes were deemed a wash, apart from object code sizes which saw "small but clear" improvement.
 
 Rollup of 5 pull requests [#116640](https://github.com/rust-lang/rust/pull/116640) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=c1691db366c0f2e2341c60377c248ca2d9335076&end=475c71da0710fd1d40c046f9cee04b733b5b2b51&stat=instructions:u)
 
@@ -101,6 +125,9 @@ Rollup of 5 pull requests [#116640](https://github.com/rust-lang/rust/pull/11664
 | Improvements ✅ <br /> (secondary) | -0.4% | [-0.5%, -0.4%] | 6     |
 | All ❌✅ (primary)                 | -0.3% | [-0.4%, -0.2%] | 4     |
 
+* sole regression was to secondary benchmark coercions debug incr-patched: add static arr item
+* Looks like a blip (i.e. noise) based on the graph over time.
+* marking as triaged
 
 exhaustiveness: Rework constructor splitting [#116391](https://github.com/rust-lang/rust/pull/116391) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=df4379b4eb5357263f0cf75475953f9b5c48c31f&end=e20cb7702117f1ad8127a16406ba9edd230c4f65&stat=instructions:u)
 
@@ -112,6 +139,16 @@ exhaustiveness: Rework constructor splitting [#116391](https://github.com/rust-l
 | Improvements ✅ <br /> (secondary) | -     | -              | 0     |
 | All ❌✅ (primary)                 | 0.1%  | [-0.4%, 0.3%]  | 5     |
 
+* the primary regressions were to cranelift-codegen-0.82.1 and cargo-0.60.0 in various incremental settings (mostly check builds)
+* the large (>5%) secondary regressions are all to match-stress.
+* the above cases were regressions for instruction-counts, but the cycle-counts didn't get marked as regressed in *any* of the same cases.
+* in all cases, the performance loss from these regressions was subsequently recovered (or masked) by [PR 116505](https://github.com/rust-lang/rust/pull/116505) "Automatically enable cross-crate inlining for small functions".
+  (I don't know if that's actually related or just an awesome change that bought so much performance that it masked this problem).
+* Since the match-stress one was relatively large, I looked at the
+  self-profile results in the [details](https://perf.rust-lang.org/detailed-query.html?commit=e20cb7702117f1ad8127a16406ba9edd230c4f65&benchmark=match-stress-check&scenario=full&base_commit=df4379b4eb5357263f0cf75475953f9b5c48c31f)
+  which indicates a change in the delta(time) for match-stress might be due to new overheads in `check_match` and `mir_borrowck`.
+* But this is strange; I cannot tell how this PR could have affected codegen, which would be the only way I could imagine those functions being impacted.
+* Not marking as triaged for now; this mystery might be worth looking into a bit more. (But then again, the only significant regression was to a secondary stress test, so maybe its not worth spending time on.)
 
 Automatically enable cross-crate inlining for small functions [#116505](https://github.com/rust-lang/rust/pull/116505) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=ca89f732ec0f910fc92111a45dd7e6829baa9d4b&end=5d5edf0248d967baa6ac5cbea09b91c7c9947942&stat=instructions:u)
 
@@ -123,6 +160,9 @@ Automatically enable cross-crate inlining for small functions [#116505](https://
 | Improvements ✅ <br /> (secondary) | -2.2% | [-39.8%, -0.2%] | 209   |
 | All ❌✅ (primary)                 | -1.0% | [-18.1%, 13.0%] | 156   |
 
+* Already marked as triaged
+* This was clearly awesome and amazing (all the more amazing if you review the history)
+* 'Nuff said.
 
 #### Untriaged Pull Requests
 
@@ -156,8 +196,3 @@ Automatically enable cross-crate inlining for small functions [#116505](https://
 - [#112963 Stop bubbling out hidden types from the eval obligation queries](https://github.com/rust-lang/rust/pull/112963)
 - [#112882 Rewrite `UnDerefer`](https://github.com/rust-lang/rust/pull/112882)
 - [#112420 Rollup of 4 pull requests](https://github.com/rust-lang/rust/pull/112420)
-
-#### Nags requiring follow up
-
-TODO: Nags
-