Skip to content

Commit 0dd5af8

Browse files
rylevrylev
authored
Merge pull request #1949 from rylev/perf-triage-2024-07-16
Add perf triage for 2024-07-16
2 parents c7f0297 + 50147b7 commit 0dd5af8

File tree

1 file changed

+107
-0
lines changed

1 file changed

+107
-0
lines changed

‎triage/2024-07-16.md

Lines changed: 107 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,107 @@
1+
# 2024-07-16 Triage Log
2+
3+
Fairly quiet week with the only pure regressions being small and coming from correctness fixes. The biggest single change came from turning off the `-Zenforce-type-length-limit` check which had positive impacts across many different benchmarks since the compiler is doing strictly less work.
4+
5+
Triage done by **@rylev**.
6+
Revision range: [a2d58197..5572759b](https://perf.rust-lang.org/?start=a2d58197a766085856504328948c89a33a6a36e8&end=5572759b8d7012fa34eba47f4885c76fa06d9251&absolute=false&stat=instructions%3Au)
7+
8+
**Summary**:
9+
10+
| (instructions:u) | mean | range | count |
11+
|:----------------------------------:|:-----:|:---------------:|:-----:|
12+
| Regressions ❌ <br /> (primary) | 0.3% | [0.2%, 0.7%] | 12 |
13+
| Regressions ❌ <br /> (secondary) | 0.4% | [0.2%, 0.9%] | 45 |
14+
| Improvements ✅ <br /> (primary) | -0.7% | [-1.5%, -0.2%] | 37 |
15+
| Improvements ✅ <br /> (secondary) | -3.3% | [-13.5%, -0.4%] | 21 |
16+
| All ❌✅ (primary) | -0.4% | [-1.5%, 0.7%] | 49 |
17+
18+
19+
2 Regressions, 3 Improvements, 2 Mixed; 1 of them in rollups
20+
56 artifact comparisons made in total
21+
22+
#### Regressions
23+
24+
Fix regression in the MIR lowering of or-patterns [#127028](https://github.com/rust-lang/rust/pull/127028) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=f25e92bd42b14e45440c0a30a4ed751ea502f430&end=9dcaa7f92cf3ed0a9d2e93824025243533bb5541&stat=instructions:u)
25+
26+
| (instructions:u) | mean | range | count |
27+
|:----------------------------------:|:----:|:------------:|:-----:|
28+
| Regressions ❌ <br /> (primary) | 0.7% | [0.3%, 1.2%] | 3 |
29+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
30+
| Improvements ✅ <br /> (primary) | - | - | 0 |
31+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
32+
| All ❌✅ (primary) | 0.7% | [0.3%, 1.2%] | 3 |
33+
- Given this is a correctness fix, and the regressions seem in line with previous historical performance (i.e., it regressed back to a previous baseline), I think it's safe to call this triaged
34+
35+
36+
Avoid follow-up errors and ICEs after missing lifetime errors on data structures [#127311](https://github.com/rust-lang/rust/pull/127311) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=fdf7ea6b5b1cac83c0f29e681202cf18bf25b01c&end=c92a8e4d4d7e8da53aa05309ef8d4fac2c9af52f&stat=instructions:u)
37+
38+
| (instructions:u) | mean | range | count |
39+
|:----------------------------------:|:----:|:------------:|:-----:|
40+
| Regressions ❌ <br /> (primary) | 0.3% | [0.2%, 0.4%] | 8 |
41+
| Regressions ❌ <br /> (secondary) | 0.3% | [0.2%, 0.4%] | 16 |
42+
| Improvements ✅ <br /> (primary) | - | - | 0 |
43+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
44+
| All ❌✅ (primary) | 0.3% | [0.2%, 0.4%] | 8 |
45+
- Instruction counts go up, cycles do not (deeply nested multi is probably just noise in mono collection). In any case, this is a correctness fix so it seems like a small perf hit would be acceptable in any case.
46+
47+
48+
#### Improvements
49+
50+
Fix `Parser::look_ahead` [#127636](https://github.com/rust-lang/rust/pull/127636) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=5d76a13bbedebd773b4960432bff14f40acf3840&end=62c068feeafd1f4abbf87243d69cf8862e4dd277&stat=instructions:u)
51+
52+
| (instructions:u) | mean | range | count |
53+
|:----------------------------------:|:-----:|:--------------:|:-----:|
54+
| Regressions ❌ <br /> (primary) | - | - | 0 |
55+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
56+
| Improvements ✅ <br /> (primary) | -0.3% | [-0.3%, -0.2%] | 3 |
57+
| Improvements ✅ <br /> (secondary) | -2.4% | [-2.4%, -2.4%] | 1 |
58+
| All ❌✅ (primary) | -0.3% | [-0.3%, -0.2%] | 3 |
59+
60+
61+
Gate the type length limit check behind a nightly flag [#127670](https://github.com/rust-lang/rust/pull/127670) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=a241cf1c49c46c57ee2ea9b19df4e7e2cc41449d&end=88fa119c77682e6d55ce21001cf761675cfebeae&stat=instructions:u)
62+
63+
| (instructions:u) | mean | range | count |
64+
|:----------------------------------:|:-----:|:--------------:|:-----:|
65+
| Regressions ❌ <br /> (primary) | - | - | 0 |
66+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
67+
| Improvements ✅ <br /> (primary) | -0.6% | [-1.4%, -0.2%] | 28 |
68+
| Improvements ✅ <br /> (secondary) | -1.1% | [-1.5%, -0.4%] | 8 |
69+
| All ❌✅ (primary) | -0.6% | [-1.4%, -0.2%] | 28 |
70+
71+
72+
find_field does not need to be a query. [#127718](https://github.com/rust-lang/rust/pull/127718) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=d9284afea99e0969a0e692b9e9fd61ea4ba21366&end=8b72d7a9d7a02cb4f2b21c1497651c84a912550a&stat=instructions:u)
73+
74+
| (instructions:u) | mean | range | count |
75+
|:----------------------------------:|:-----:|:---------------:|:-----:|
76+
| Regressions ❌ <br /> (primary) | - | - | 0 |
77+
| Regressions ❌ <br /> (secondary) | - | - | 0 |
78+
| Improvements ✅ <br /> (primary) | - | - | 0 |
79+
| Improvements ✅ <br /> (secondary) | -7.5% | [-13.5%, -2.7%] | 9 |
80+
| All ❌✅ (primary) | - | - | 0 |
81+
82+
83+
#### Mixed
84+
85+
Rollup of 7 pull requests [#127580](https://github.com/rust-lang/rust/pull/127580) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=b215beb567857000fdaa868cbb78702bc5ee0ee9&end=c092b289764530221d09e000a789222bddb2c53c&stat=instructions:u)
86+
87+
| (instructions:u) | mean | range | count |
88+
|:----------------------------------:|:-----:|:--------------:|:-----:|
89+
| Regressions ❌ <br /> (primary) | - | - | 0 |
90+
| Regressions ❌ <br /> (secondary) | 2.6% | [2.6%, 2.6%] | 1 |
91+
| Improvements ✅ <br /> (primary) | -0.6% | [-1.0%, -0.2%] | 9 |
92+
| Improvements ✅ <br /> (secondary) | - | - | 0 |
93+
| All ❌✅ (primary) | -0.6% | [-1.0%, -0.2%] | 9 |
94+
- Noise
95+
96+
97+
Only track mentioned places for jump threading [#127087](https://github.com/rust-lang/rust/pull/127087) [(Comparison Link)](https://perf.rust-lang.org/compare.html?start=8a63c84af5e7a201239e87d2175128907495b028&end=0ffbddd09e02a00b762d838ea1598bfa89dd1668&stat=instructions:u)
98+
99+
| (instructions:u) | mean | range | count |
100+
|:----------------------------------:|:-----:|:--------------:|:-----:|
101+
| Regressions ❌ <br /> (primary) | 0.5% | [0.4%, 0.6%] | 3 |
102+
| Regressions ❌ <br /> (secondary) | 1.1% | [0.2%, 1.6%] | 7 |
103+
| Improvements ✅ <br /> (primary) | -0.6% | [-1.3%, -0.2%] | 6 |
104+
| Improvements ✅ <br /> (secondary) | -0.6% | [-2.0%, -0.3%] | 8 |
105+
| All ❌✅ (primary) | -0.2% | [-1.3%, 0.6%] | 9 |
106+
- The perf impact was expected given the pre-merge runs and is less severe than it was pre-merge.
107+

0 commit comments

Comments
 (0)