RFR: 8285255: refine StringLatin1.regionMatchesCI_UTF16 [v2]

[XenoAmess]

On Wed, 20 Apr 2022 20:56:50 GMT, Roger Riggs <rriggs at openjdk.org> wrote:

>> XenoAmess has updated the pull request incrementally with one additional commit since the last revision:
>> 
>>   add jmh test
>
> Thanks for the JMH tests and data.
> 
> The only part needed from the JMH run is the last 9 lines.  The rest is noise.
> If it was formatted as a literal it would be easier to read.
> 
> What I see is that the run with == is quite a bit slower.
> 
> With the == check:
> 
> 
> StringOther.regionMatchesU1024LL  avgt   15   187.258 ±   1.038  ns/op
> StringOther.regionMatchesU1024LU  avgt   15  2589.833 ±   8.823  ns/op
> StringOther.regionMatchesU1024UL  avgt   15  2379.645 ±   6.481  ns/op
> StringOther.regionMatchesU1024UU  avgt   15   191.587 ±   7.069  ns/op
> 
> 
> Without the == check:
> 
> 
> StringOther.regionMatchesU1024LL  avgt   15   187.732 ±   1.914  ns/op
> StringOther.regionMatchesU1024LU  avgt   15  1324.156 ±  11.761  ns/op
> StringOther.regionMatchesU1024UL  avgt   15  1331.857 ±  22.509  ns/op
> StringOther.regionMatchesU1024UU  avgt   15   188.872 ±   2.396  ns/op
> 
> 
> In the JMH cases, does the long prefix of latin1 characters distort the timings?

@RogerRiggs

> What I see is that the run with == is quite a bit slower.

Yes, the result is amazing to me. Before you reply I re-run several times but similar result. So I respect the truth.

> In the JMH cases, does the long prefix of latin1 characters distort the timings?

No, the long prefix part is where real difference comes.

So according to jmh result, the = check removed.

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

PR: https://git.openjdk.java.net/jdk/pull/8308