[jdk21u-dev] RFR: 8320379: C2: Sort spilling/unspilling sequence for better ld/st merging into ldp/stp on AArch64

[Andrew Haley]

On Thu, 6 Jun 2024 09:45:40 GMT, Andrew Haley <aph at openjdk.org> wrote:

>>> Did you submit a jdk22 backport request?
>> 
>> This issue is fixed in 22 originally, so no JDK 22u backport is needed.
>> 
>> Aside: my read of https://mail.openjdk.org/pipermail/jdk-updates-dev/2024-June/033864.html is that 22u is effectively dead anyway.
>
>> > Did you submit a jdk22 backport request?
>> 
>> This issue is fixed in 22 originally, so no JDK 22u backport is needed.
> 
> OK.
> 
>> Aside: my read of https://mail.openjdk.org/pipermail/jdk-updates-dev/2024-June/033864.html is that 22u is effectively dead anyway.
> 
> Ah, right. I didn't see that.
> 
> This is a pretty minor performance tweak, so it's marginal whether it should be back ported. I'm not sure the churn is justified.

> Thanks @theRealAph and @shipilev for the review and discussion. We have very large AArch64 fleet in our prod, which magnifies the minor performance improvements.

I understand that, but wouldn't that apply to all minor performance improvements? And wouldn't the direct consequence of following that principle to its conclusion be that if anyone wanted a stable release, too bad: there isn't a stable release? I totally get why this low-risk fix is a good thing, but...

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

PR Comment: https://git.openjdk.org/jdk21u-dev/pull/665#issuecomment-2155187609