perf: Hint -Zdisable-fast-paths as false

[ShoyuVanilla]

This might mitigate the perf regressions in #156172 (comment) 🤔

[ShoyuVanilla]

@bors try @rust-timer queue

[Noratrieb]

Our primary metric is instruction counts, which will not be affected by branch mispredictions, so this won't have an effect on the primary metrics (and in general, changes like this won't affect it).
You'd need to look at the more noisy cycle counts, which are neutral on the other PR, so I'm not sure it's worth worrying about.

[rust-bors]

☀️ Try build successful (CI)
Build commit: d752daa (d752daa192dcd6e5ccbd03e6b23b231562b523bb, parent: 9ae765da471fd0bc3b305953e72c4eb12f304416)

[rust-timer]

Finished benchmarking commit (d752daa): comparison URL.

Overall result: ❌ regressions - please read:

Benchmarking means the PR may be perf-sensitive. It's automatically marked not fit for rolling up. Overriding is possible but disadvised: it risks changing compiler perf.

Next, please: If you can, justify the regressions found in this try perf run in writing along with @rustbot label: +perf-regression-triaged. If not, fix the regressions and do another perf run. Neutral or positive results will clear the label automatically.

@bors rollup=never
@rustbot label: -S-waiting-on-perf +perf-regression

Instruction count

Our most reliable metric. Used to determine the overall result above. However, even this metric can be noisy.

	mean	range	count
Regressions ❌ (primary)	0.7%	[0.7%, 0.7%]	1
Regressions ❌ (secondary)	0.4%	[0.4%, 0.4%]	1
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-	-	0
All ❌✅ (primary)	0.7%	[0.7%, 0.7%]	1

Max RSS (memory usage)

Results (primary -0.3%, secondary 1.1%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	3.9%	[3.4%, 4.5%]	2
Regressions ❌ (secondary)	6.6%	[6.4%, 6.7%]	2
Improvements ✅ (primary)	-4.6%	[-5.0%, -4.2%]	2
Improvements ✅ (secondary)	-2.6%	[-3.5%, -1.9%]	3
All ❌✅ (primary)	-0.3%	[-5.0%, 4.5%]	4

Cycles

Results (primary -3.5%, secondary -3.3%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	-	-	0
Regressions ❌ (secondary)	2.1%	[2.1%, 2.1%]	1
Improvements ✅ (primary)	-3.5%	[-5.9%, -1.3%]	109
Improvements ✅ (secondary)	-3.4%	[-14.9%, -1.0%]	99
All ❌✅ (primary)	-3.5%	[-5.9%, -1.3%]	109

Binary size

Results (primary 0.0%, secondary 0.0%)

A less reliable metric. May be of interest, but not used to determine the overall result above.

	mean	range	count
Regressions ❌ (primary)	0.0%	[0.0%, 0.0%]	4
Regressions ❌ (secondary)	0.0%	[0.0%, 0.0%]	1
Improvements ✅ (primary)	-	-	0
Improvements ✅ (secondary)	-	-	0
All ❌✅ (primary)	0.0%	[0.0%, 0.0%]	4

Bootstrap: 515.26s -> 513.764s (-0.29%)
Artifact size: 400.73 MiB -> 400.72 MiB (-0.00%)

[ShoyuVanilla]

Our primary metric is instruction counts, which will not be affected by branch mispredictions, so this won't have an effect on the primary metrics (and in general, changes like this won't affect it). You'd need to look at the more noisy cycle counts, which are neutral on the other PR, so I'm not sure it's worth worrying about.

Oh, thanks for the explanation 😄 That makes sense!