[benchmark] Janitor Duty: Thesaurus Heirloom

[palimondo]

This PR follows-up #20861, #21413, #21516 and #21794. It's a next batch of benchmark clean-up to enable robust performance measurements by adjusting workloads to run in reasonable time (< 1000 μs), minimizing the accumulated error. To maintain long-term performance tracking, it applies legacy factor where necessary.

This one's without a unifying theme, just trodding down the alphabet, skipping over troublemakers.

[palimondo]

@swift-ci please benchmark

[palimondo]

Hmm… let's make this easier by postponing the changes to benchmarks that result in side-effects for later. I'm going to force-push update that includes only the no-changes subset.

[palimondo]

@swift-ci please benchmark

[palimondo]

@swift-ci please smoke test

[swift-ci]

Build comment file:

Performance: -O

TEST	OLD	NEW	DELTA	RATIO
Regression
DataAppendDataLargeToLarge	37200	52000	+39.8%	0.72x (?)
Improvement
DictionaryBridgeToObjC_Access	943	854	-9.4%	1.10x (?)
MapReduce	396	368	-7.1%	1.08x (?)

Code size: -O

TEST	OLD	NEW	DELTA	RATIO
Regression
LinkedList.o	1942	2376	+22.3%	0.82x

Performance: -Osize

TEST	OLD	NEW	DELTA	RATIO
Improvement
RandomShuffleLCG2	1744	1568	-10.1%	1.11x

Code size: -Osize

TEST	OLD	NEW	DELTA	RATIO
Regression
LinkedList.o	1969	2313	+17.5%	0.85x
Improvement
MapReduce.o	26547	26163	-1.4%	1.01x

Performance: -Onone

TEST	OLD	NEW	DELTA	RATIO
Regression
DataAppendDataLargeToLarge	38800	51600	+33.0%	0.75x (?)
Phonebook	61902	74732	+20.7%	0.83x

How to read the data

The tables contain differences in performance which are larger than 8% and differences in code size which are larger than 1%.

If you see any unexpected regressions, you should consider fixing the
regressions before you merge the PR.

Noise: Sometimes the performance results (not code size!) contain false
alarms. Unexpected regressions which are marked with '(?)' are probably noise.
If you see regressions which you cannot explain you can try to run the
benchmarks again. If regressions still show up, please consult with the
performance team (@eeckstein).

Hardware Overview

  Model Name: Mac Pro
  Model Identifier: MacPro6,1
  Processor Name: 12-Core Intel Xeon E5
  Processor Speed: 2.7 GHz
  Number of Processors: 1
  Total Number of Cores: 12
  L2 Cache (per Core): 256 KB
  L3 Cache: 30 MB
  Memory: 64 GB

--------------

[palimondo]

@eeckstein Please review 🙏
The -O changes are in unmodified benchmarks 🤷‍♂️ . I don't know why RandomShuffleLCG2 improved in -Osize. Phonebook comes up in -Onone because of the non-linear relationship between un-/optimized builds(?). I'm assuming this is all fine.

cc @phausler, @itaiferber FYI: The unmodified DataAppendDataLargeToLarge (-O: +39.8%, -Osize: unchanged, -Onone: +33.0%) seems to be highly sensitive to code alignment, as it's popping up quite often during this cleanup. DataAppendDataMediumToLarge (-O: -39.5%) also showed up in the first benchmark report — see collapsed 3rd comment.