RFR: 8301869: Regression ~14% in J2dBench-bimg_misc-* in 21-b5 only on linux-aarch64 [v3]

[Sergey Bylokhov]

On Tue, 28 Feb 2023 06:55:36 GMT, Jayathirth D V <jdv at openjdk.org> wrote:

>> Under https://bugs.openjdk.org/browse/JDK-8264846 we moved to -O3 level of gcc optimizations from -O1 level for libawt build. This improved our J2DBench performance numbers in some options considerably.
>> 
>> Recent changes done under https://bugs.openjdk.org/browse/JDK-8299337 causes difference in generated code by gcc and this is resulting in performance regression for bimg_misc-* J2DBench options in our performance servers. Under https://bugs.openjdk.org/browse/JDK-8299337 we have just removed unused variables and it is a cleanup task.
>> 
>> We can force gcc to generate position independent code by using -fpic option.Also i have removed -fgcse-after-reload option for gcc, because this is by default covered under -O3 level of optimization introduced under https://bugs.openjdk.org/browse/JDK-8264846.
>> 
>> With this change bimg_misc-* J2DBench option performance regression is resolved and there are no regression in other options of J2DBench or SwingMark and it is verified in our performance servers.
>
> Jayathirth D V has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Shift comment

When I mention that option in the JBS, I meant that we should take a look on how the methods in the library are "packed" since for some reason "-fpic" make some difference, probably we should use "static" more often or something like that. It is better to check what is the actual difference in the generated/packed code.

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

PR: https://git.openjdk.org/jdk/pull/12761