RFR: 8139457: Array bases are aligned at HeapWord granularity [v47]

[Roman Kennke]

On Thu, 6 Jul 2023 13:19:10 GMT, Roman Kennke <rkennke at openjdk.org> wrote:

>> See [JDK-8139457](https://bugs.openjdk.org/browse/JDK-8139457) for details.
>> 
>> Basically, when running with -XX:-UseCompressedClassPointers, arrays will have a gap between the length field and the first array element, because array elements will only start at word-aligned offsets. This is not necessary for smaller-than-word elements.
>> 
>> Also, while it is not very important now, it will become very important with Lilliput, which eliminates the Klass field and would always put the length field at offset 8, and leave a gap between offset 12 and 16.
>> 
>> Testing:
>>  - [x] runtime/FieldLayout/ArrayBaseOffsets.java (x86_64, x86_32, aarch64, arm, riscv, s390)
>>  - [x] bootcycle (x86_64, x86_32, aarch64, arm, riscv, s390)
>>  - [x] tier1 (x86_64, x86_32, aarch64, riscv)
>>  - [x] tier2 (x86_64, aarch64, riscv)
>>  - [x] tier3 (x86_64, riscv)
>
> Roman Kennke has updated the pull request incrementally with three additional commits since the last revision:
> 
>  - Use BytesPerWord
>  - Revert unnecessary change in s390
>  - Revert unnecessary change in PPC

I've simplified the PR significantly:
- The gap is now usually cleared as part of the header initialization (as is already done for instance oops). This allows to use simple and fast word-sized clearing of the rest of the array.
- Calculations of min and max array and tlab sizes are all reverted, because they are still conservatively correct. Optimizing those for a few bytes extra seems to be a rather complex task and should be done as separate PR.
- The ARM parts could be reverted wholesale (sorry, @tstuefe) because 32 bit arch doesn't require any changes anymore.

@RealFYang can you please check the RISCV port and bring it into the same shape as aarch64/x86?
@TheRealMDoerr Can you ack PPC and s390 ports? I've only done very minor cleanups there, compared to early version.
@coleenp please review again? Maybe bring others in as you see fit and/or run Mach5 testing (preferably also with -XX:-UseCompressedClassPointers, because that is what this PR is about)

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

PR Comment: https://git.openjdk.org/jdk/pull/11044#issuecomment-1623674137