Avoid an unnecessary call to CFStringGetCharactersPtr in bridging

[Catfish-Man]

No description provided.

[Catfish-Man]

@swift-ci please smoke test

[Catfish-Man]

@swift-ci please benchmark

[Catfish-Man]

@swift-ci Apple Silicon benchmark

[swift-ci]

Performance (x86_64): -O

Regression	OLD	NEW	DELTA	RATIO
ArrayAppendOptionals	1330	2460	+85.0%	0.54x (?)
DictionaryOfAnyHashableStrings_insert	3010	5558	+84.7%	0.54x
ObjectiveCBridgeStubFromNSDate	6300	7140	+13.3%	0.88x (?)
DictionaryKeysContainsNative	23	26	+13.0%	0.88x (?)

Code size: -O

Performance (x86_64): -Osize

Regression	OLD	NEW	DELTA	RATIO
FlattenListFlatMap	6119	6815	+11.4%	0.90x (?)
Improvement	OLD	NEW	DELTA	RATIO
ObjectiveCBridgeStubFromNSDate	7360	6270	-14.8%	1.17x (?)

Code size: -Osize

Performance (x86_64): -Onone

Regression	OLD	NEW	DELTA	RATIO
NSError	617	690	+11.8%	0.89x (?)
String.data.Medium	164	182	+11.0%	0.90x (?)
String.data.LargeUnicode	167	180	+7.8%	0.93x (?)
String.data.Small	79	85	+7.6%	0.93x (?)
Improvement	OLD	NEW	DELTA	RATIO
ObjectiveCBridgeFromNSStringForced	3030	2800	-7.6%	1.08x (?)

Code size: -swiftlibs

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

[Catfish-Man]

Looks like the win is smaller than the 7% threshold the benchmark will report. Not entirely surprising. Still worth doing I think.

[swift-ci]

Performance (arm64): -O

Regression	OLD	NEW	DELTA	RATIO
DictionaryOfAnyHashableStrings_insert	1260	2282	+81.1%	0.55x (?)
Set.isDisjoint.Int25	86	130	+51.2%	0.66x (?)
StringRemoveDupes	117	142	+21.4%	0.82x (?)
DictionaryGroupOfObjects	441	531	+20.4%	0.83x (?)
SubstringFromLongStringGeneric	5	6	+20.0%	0.83x (?)
Set.isStrictSubset.Box25	83	94	+13.3%	0.88x (?)
SetIsSubsetBox25	83	94	+13.3%	0.88x (?)
DictionaryRemove	1730	1930	+11.6%	0.90x (?)
DictionaryGroup	114	127	+11.4%	0.90x (?)
NSArray.bridged.objectAtIndex	194	216	+11.3%	0.90x (?)
StringHasPrefixAscii	1210	1340	+10.7%	0.90x (?)
StringHasSuffixAscii	1310	1430	+9.2%	0.92x (?)
SetIsSubsetInt50	83	90	+8.4%	0.92x (?)
LazilyFilteredArrays2	1300	1400	+7.7%	0.93x (?)
Improvement	OLD	NEW	DELTA	RATIO
LessSubstringSubstring	21	18	-14.3%	1.17x (?)
EqualSubstringSubstring	21	18	-14.3%	1.17x (?)
EqualStringSubstring	21	18	-14.3%	1.17x (?)
EqualSubstringSubstringGenericEquatable	21	18	-14.3%	1.17x (?)
EqualSubstringString	21	18	-14.3%	1.17x (?)
LessSubstringSubstringGenericComparable	21	18	-14.3%	1.17x (?)
ArrayAppendToGeneric	190	170	-10.5%	1.12x (?)
ArrayAppendToFromGeneric	190	170	-10.5%	1.12x (?)
Set.filter.Int100.24k	853	778	-8.8%	1.10x (?)
Dict.CopyKeyValue.24k	867	796	-8.2%	1.09x (?)
Set.filter.Int100.20k	729	671	-8.0%	1.09x (?)
Dict.CopyKeyValue.20k	742	691	-6.9%	1.07x (?)

Code size: -O

Improvement	OLD	NEW	DELTA	RATIO
BufferFill.o	7314	7118	-2.7%	1.03x

Performance (arm64): -Osize

Improvement	OLD	NEW	DELTA	RATIO
RawBufferCopyBytes	249	12	-95.2%	20.75x
EqualStringSubstring	21	18	-14.3%	1.17x (?)
EqualSubstringString	21	18	-14.3%	1.17x (?)
LessSubstringSubstring	22	19	-13.6%	1.16x (?)
EqualSubstringSubstring	22	19	-13.6%	1.16x (?)
EqualSubstringSubstringGenericEquatable	22	19	-13.6%	1.16x (?)
LessSubstringSubstringGenericComparable	22	19	-13.6%	1.16x (?)
NSArray.bridged.objectAtIndex	219	196	-10.5%	1.12x (?)

Code size: -Osize

Performance (arm64): -Onone

Regression	OLD	NEW	DELTA	RATIO
ArrayAppendToFromGeneric	160	180	+12.5%	0.89x (?)
Improvement	OLD	NEW	DELTA	RATIO
RawBufferCopyBytes	74031	13	-100.0%	5694.25x
ArrayAppendGenericStructs	940	430	-54.3%	2.19x (?)
LessSubstringSubstring	39	35	-10.3%	1.11x (?)
EqualSubstringSubstring	39	35	-10.3%	1.11x (?)
EqualSubstringSubstringGenericEquatable	39	35	-10.3%	1.11x (?)
LessSubstringSubstringGenericComparable	39	35	-10.3%	1.11x (?)
COWArrayGuaranteedParameterOverhead	2650	2400	-9.4%	1.10x (?)
EqualStringSubstring	39	36	-7.7%	1.08x (?)
EqualSubstringString	39	36	-7.7%	1.08x (?)

Code size: -swiftlibs

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 mini
  Model Identifier: Macmini9,1
  Total Number of Cores: 8 (4 performance and 4 efficiency)
  Memory: 16 GB