|
| 1 | +# 2024-02-20 Triage Log |
| 2 | + |
| 3 | +Relatively few PRs affecting performance, but massive improvements thanks to the |
| 4 | +update to LLVM 18 (PR #12005), as well as the merging of two related compiler |
| 5 | +queries (PR #120919) and other small improvements from a rollup (PR #121055). |
| 6 | + |
| 7 | +Triage done by **@pnkfelix**. |
| 8 | +Revision range: [74c3f5a1..5af21304](https://perf.rust-lang.org/?start=74c3f5a146860c94ff4d179fc3bfa34f879adf41&end=5af2130440c198afefbe5b8099342057cf272ef4&absolute=false&stat=instructions%3Au) |
| 9 | + |
| 10 | +**Summary**: |
| 11 | + |
| 12 | +| (instructions:u) | mean | range | count | |
| 13 | +|:----------------------------------:|:-----:|:---------------:|:-----:| |
| 14 | +| Regressions ❌ <br /> (primary) | 0.5% | [0.5%, 0.5%] | 1 | |
| 15 | +| Regressions ❌ <br /> (secondary) | 7.1% | [0.5%, 78.5%] | 17 | |
| 16 | +| Improvements ✅ <br /> (primary) | -2.4% | [-13.9%, -0.4%] | 222 | |
| 17 | +| Improvements ✅ <br /> (secondary) | -2.0% | [-9.8%, -0.3%] | 155 | |
| 18 | +| All ❌✅ (primary) | -2.4% | [-13.9%, 0.5%] | 223 | |
| 19 | + |
| 20 | + |
| 21 | +3 Regressions, 1 Improvements, 6 Mixed; 1 of them in rollups |
| 22 | +65 artifact comparisons made in total |
| 23 | + |
| 24 | +#### Regressions |
| 25 | + |
| 26 | +Tracking import use types for more accurate redundant import checking [#117772](https://github.com/rust-lang/rust/pull/117772) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=6f726205a1b7992537ddec96c83f2b054b03e04f&end=8b21296b5db6d5724d6b8440dcf459fa82fd88b5&stat=instructions:u) |
| 27 | + |
| 28 | +| (instructions:u) | mean | range | count | |
| 29 | +|:----------------------------------:|:----:|:------------:|:-----:| |
| 30 | +| Regressions ❌ <br /> (primary) | 0.4% | [0.2%, 1.0%] | 44 | |
| 31 | +| Regressions ❌ <br /> (secondary) | 0.7% | [0.4%, 1.1%] | 13 | |
| 32 | +| Improvements ✅ <br /> (primary) | - | - | 0 | |
| 33 | +| Improvements ✅ <br /> (secondary) | - | - | 0 | |
| 34 | +| All ❌✅ (primary) | 0.4% | [0.2%, 1.0%] | 44 | |
| 35 | + |
| 36 | +* regressions are [explained by petrochenkov](https://github.com/rust-lang/rust/pull/117772#issuecomment-1951430297): This lint is newly firing against benchmark code, which means that lint reporting machinery is being exercised that was previously not being exercised. |
| 37 | +* marked as triaged and filed rust-lang/rustc-perf#1819 to follow up with potential counter-action in benchmark tooling. |
| 38 | + |
| 39 | +macro_rules: Preserve all metavariable spans in a global side table [#119673](https://github.com/rust-lang/rust/pull/119673) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=8a497723e311a62fccb1f0bf40e79c6519744a12&end=2bf78d12d33ae02d10010309a0d85dd04e7cff72&stat=instructions:u) |
| 40 | + |
| 41 | +| (instructions:u) | mean | range | count | |
| 42 | +|:----------------------------------:|:----:|:------------:|:-----:| |
| 43 | +| Regressions ❌ <br /> (primary) | 0.4% | [0.1%, 1.3%] | 26 | |
| 44 | +| Regressions ❌ <br /> (secondary) | 0.5% | [0.1%, 3.3%] | 12 | |
| 45 | +| Improvements ✅ <br /> (primary) | - | - | 0 | |
| 46 | +| Improvements ✅ <br /> (secondary) | - | - | 0 | |
| 47 | +| All ❌✅ (primary) | 0.4% | [0.1%, 1.3%] | 26 | |
| 48 | + |
| 49 | +* Instruction count regressions flagged against serde_derive, diesel, serde, html5ever, syn |
| 50 | +* Most of these were anticipated in the final perf runs against the try builds. |
| 51 | +* Marking as triaged under assumption that the reviewers deemed this change to be worth the predicted cost. |
| 52 | + |
| 53 | + |
| 54 | +Always evaluate free constants and statics, even if previous errors occurred [#121087](https://github.com/rust-lang/rust/pull/121087) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=5af2130440c198afefbe5b8099342057cf272ef4&end=cce6a6e22e715bd74455f2560a956ab920c3a914&stat=instructions:u) |
| 55 | + |
| 56 | +| (instructions:u) | mean | range | count | |
| 57 | +|:----------------------------------:|:----:|:------------:|:-----:| |
| 58 | +| Regressions ❌ <br /> (primary) | 0.8% | [0.4%, 2.0%] | 4 | |
| 59 | +| Regressions ❌ <br /> (secondary) | 1.0% | [0.3%, 5.2%] | 11 | |
| 60 | +| Improvements ✅ <br /> (primary) | - | - | 0 | |
| 61 | +| Improvements ✅ <br /> (secondary) | - | - | 0 | |
| 62 | +| All ❌✅ (primary) | 0.8% | [0.4%, 2.0%] | 4 | |
| 63 | + |
| 64 | + |
| 65 | +#### Improvements |
| 66 | + |
| 67 | +pattern_analysis: Move constructor selection logic to `PlaceInfo` [#120692](https://github.com/rust-lang/rust/pull/120692) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=0b9f6ad99482c9fc35baa5f40cebf21be4fd98b3&end=bcea3cb748040aa507f44abbd66c50725f35ea4f&stat=instructions:u) |
| 68 | + |
| 69 | +| (instructions:u) | mean | range | count | |
| 70 | +|:----------------------------------:|:-----:|:--------------:|:-----:| |
| 71 | +| Regressions ❌ <br /> (primary) | - | - | 0 | |
| 72 | +| Regressions ❌ <br /> (secondary) | - | - | 0 | |
| 73 | +| Improvements ✅ <br /> (primary) | - | - | 0 | |
| 74 | +| Improvements ✅ <br /> (secondary) | -1.8% | [-1.9%, -1.7%] | 6 | |
| 75 | +| All ❌✅ (primary) | - | - | 0 | |
| 76 | + |
| 77 | + |
| 78 | +#### Mixed |
| 79 | + |
| 80 | +Merge `impl_polarity` and `impl_trait_ref` queries [#120919](https://github.com/rust-lang/rust/pull/120919) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=0a5b998c57a8681acc13206b5917340b053b3a30&end=d26b41711282042c4ea0c5733e7332b07cfa4933&stat=instructions:u) |
| 81 | + |
| 82 | +| (instructions:u) | mean | range | count | |
| 83 | +|:----------------------------------:|:-----:|:--------------:|:-----:| |
| 84 | +| Regressions ❌ <br /> (primary) | 0.6% | [0.5%, 0.7%] | 3 | |
| 85 | +| Regressions ❌ <br /> (secondary) | 1.5% | [1.5%, 1.5%] | 1 | |
| 86 | +| Improvements ✅ <br /> (primary) | -0.3% | [-0.7%, -0.2%] | 43 | |
| 87 | +| Improvements ✅ <br /> (secondary) | -0.4% | [-0.5%, -0.2%] | 5 | |
| 88 | +| All ❌✅ (primary) | -0.3% | [-0.7%, 0.7%] | 46 | |
| 89 | + |
| 90 | +* already marked as triaged (more wins than losses) |
| 91 | + |
| 92 | +Update to LLVM 18 [#120055](https://github.com/rust-lang/rust/pull/120055) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=bc1b9e0e9a813d27a09708b293dc2d41c472f0d0&end=eaff1af8fdd18ee3eb05167b2836042b7d4315f6&stat=instructions:u) |
| 93 | + |
| 94 | +| (instructions:u) | mean | range | count | |
| 95 | +|:----------------------------------:|:-----:|:---------------:|:-----:| |
| 96 | +| Regressions ❌ <br /> (primary) | - | - | 0 | |
| 97 | +| Regressions ❌ <br /> (secondary) | 1.1% | [0.7%, 3.5%] | 7 | |
| 98 | +| Improvements ✅ <br /> (primary) | -2.4% | [-14.1%, -0.5%] | 233 | |
| 99 | +| Improvements ✅ <br /> (secondary) | -1.6% | [-8.0%, -0.3%] | 160 | |
| 100 | +| All ❌✅ (primary) | -2.4% | [-14.1%, -0.5%] | 233 | |
| 101 | + |
| 102 | +* already marked as triaged (more wins than losses) |
| 103 | + |
| 104 | +Rollup of 8 pull requests [#121055](https://github.com/rust-lang/rust/pull/121055) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=37b65339c8cf1d18e331f184dbf70bbddcb1e4f7&end=7508c3e4c1349e3dd405547bc7dd8d9549e105b6&stat=instructions:u) |
| 105 | + |
| 106 | +| (instructions:u) | mean | range | count | |
| 107 | +|:----------------------------------:|:-----:|:--------------:|:-----:| |
| 108 | +| Regressions ❌ <br /> (primary) | 0.2% | [0.2%, 0.2%] | 2 | |
| 109 | +| Regressions ❌ <br /> (secondary) | 0.9% | [0.8%, 0.9%] | 2 | |
| 110 | +| Improvements ✅ <br /> (primary) | -0.9% | [-1.8%, -0.2%] | 9 | |
| 111 | +| Improvements ✅ <br /> (secondary) | -0.6% | [-1.1%, -0.3%] | 21 | |
| 112 | +| All ❌✅ (primary) | -0.7% | [-1.8%, 0.2%] | 11 | |
| 113 | + |
| 114 | +* already marked as triaged (more wins than losses) |
| 115 | + |
| 116 | + |
| 117 | +`cargo update` [#120454](https://github.com/rust-lang/rust/pull/120454) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=7508c3e4c1349e3dd405547bc7dd8d9549e105b6&end=cc1c0990ab6f7136d1d54fd008598095b2c53c66&stat=instructions:u) |
| 118 | + |
| 119 | +| (instructions:u) | mean | range | count | |
| 120 | +|:----------------------------------:|:-----:|:--------------:|:-----:| |
| 121 | +| Regressions ❌ <br /> (primary) | - | - | 0 | |
| 122 | +| Regressions ❌ <br /> (secondary) | 1.4% | [0.8%, 1.9%] | 10 | |
| 123 | +| Improvements ✅ <br /> (primary) | - | - | 0 | |
| 124 | +| Improvements ✅ <br /> (secondary) | -0.9% | [-3.4%, -0.2%] | 15 | |
| 125 | +| All ❌✅ (primary) | - | - | 0 | |
| 126 | + |
| 127 | +* already marked as triaged (improvements and regressions balanced out, and the binary size regressions were deemed due to upstream dependencies) |
| 128 | + |
| 129 | +Store static initializers in metadata instead of the MIR of statics. [#116564](https://github.com/rust-lang/rust/pull/116564) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=4ae1e79876fcee94a56c1edf7c029a677084d7fc&end=6a4222b5119bce8c24e74dd3ad44006ce0c803e6&stat=instructions:u) |
| 130 | + |
| 131 | +| (instructions:u) | mean | range | count | |
| 132 | +|:----------------------------------:|:-----:|:--------------:|:-----:| |
| 133 | +| Regressions ❌ <br /> (primary) | - | - | 0 | |
| 134 | +| Regressions ❌ <br /> (secondary) | 15.9% | [0.4%, 81.2%] | 8 | |
| 135 | +| Improvements ✅ <br /> (primary) | -0.4% | [-0.5%, -0.2%] | 8 | |
| 136 | +| Improvements ✅ <br /> (secondary) | -2.5% | [-8.9%, -0.4%] | 18 | |
| 137 | +| All ❌✅ (primary) | -0.4% | [-0.5%, -0.2%] | 8 | |
| 138 | + |
| 139 | +* already marked as triaged: the benchmark stress test is now writing an 8MB constant to metadata instead of a tiny bit of MIR |
| 140 | + |
| 141 | +Clean up potential_query_instability with FxIndexMap and UnordMap [#120931](https://github.com/rust-lang/rust/pull/120931) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=6a4222b5119bce8c24e74dd3ad44006ce0c803e6&end=fa9f77ff35b4b63ed0cef9a9642c8f881b33f14f&stat=instructions:u) |
| 142 | + |
| 143 | +| (instructions:u) | mean | range | count | |
| 144 | +|:----------------------------------:|:-----:|:--------------:|:-----:| |
| 145 | +| Regressions ❌ <br /> (primary) | - | - | 0 | |
| 146 | +| Regressions ❌ <br /> (secondary) | 0.2% | [0.2%, 0.2%] | 4 | |
| 147 | +| Improvements ✅ <br /> (primary) | -0.2% | [-0.2%, -0.2%] | 2 | |
| 148 | +| Improvements ✅ <br /> (secondary) | -6.6% | [-6.6%, -6.6%] | 1 | |
| 149 | +| All ❌✅ (primary) | -0.2% | [-0.2%, -0.2%] | 2 | |
| 150 | + |
| 151 | +* regressions are solely to the secondary many-assoc-items benchmark (check full, check/debug/opt incr-full), and was anticipated. |
| 152 | +* marking as triaged |
0 commit comments