[5.0] Data Inlinability Refinements

[itaiferber]

What's in this pull request?
Cherry-picks #21754 to swift-5.0-branch. Resolves 46780357

[itaiferber]

@swift-ci Please benchmark

[itaiferber]

@swift-ci Please test

[swift-ci]

Build comment file:

Performance: -O

TEST	OLD	NEW	DELTA	RATIO
Regression
StringToDataSmall	791	892	+12.8%	0.89x
StringToDataEmpty	698	760	+8.9%	0.92x

Code size: -O

TEST	OLD	NEW	DELTA	RATIO
Improvement
DataBenchmarks.o	87535	66530	-24.0%	1.32x
ObjectiveCBridgingStubs.o	27411	23204	-15.3%	1.18x

Performance: -Osize

TEST	OLD	NEW	DELTA	RATIO
Regression
StringToDataEmpty	705	786	+11.5%	0.90x
DataAccessBytesSmall	95	105	+10.5%	0.90x (?)

Code size: -Osize

TEST	OLD	NEW	DELTA	RATIO
Improvement
DataBenchmarks.o	36355	33242	-8.6%	1.09x

Performance: -Onone

TEST	OLD	NEW	DELTA	RATIO
Improvement
DataSetCountMedium	770	583	-24.3%	1.32x

Code size: -swiftlibs

TEST	OLD	NEW	DELTA	RATIO
Improvement
libswiftFoundation.dylib	1667072	1638400	-1.7%	1.02x

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

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

[itaiferber]

@parkera Who should we get to review here?

[airspeedswift]

@itaiferber I can approve from a landing-in-5.0 perspective but it probably needs a second engineer from Foundation to review for correctness.

[phausler]

@airspeedswift it looks good to me, this is just a cherry-pick from master of the work Itai did for annotating the reasons for inlines and slight tweaks for those.

[itaiferber]

Thanks @airspeedswift!