RFR: 8373026: C2 SuperWord and Vector API: vector algorithms test and benchmark [v10]

[Emanuel Peter]

On Tue, 20 Jan 2026 07:12:05 GMT, Xiaohong Gong <xgong at openjdk.org> wrote:

> > If the Vector API code can be fully intrinsified, we get fast code. But somtimes, the Vector API is horribly slow, much slower than scalar loop performance.
> > linux_aarch64_server: filterI, scanAddI, reduceAddIFieldsX4 are very slow
> 
> Hi @eme64 , I noticed that these benchmarks have even much worse performance on AAch64. May I ask whether the machine supports SVE/SVE2 feature? Thanks!

@XiaohongGong thanks for reviewing!

No, I only have access to NEON machines, unfortunately. I added a comment to the PR description for that just now :)

> test/micro/org/openjdk/bench/vm/compiler/VectorAlgorithmsImpl.java line 598:
> 
>> 596:             if (mask.anyTrue()) {
>> 597:                 var ml = mask.toLong();
>> 598:                 return i + Long.numberOfTrailingZeros(ml);
> 
> Can we use `mask.firstTrue()` here?

Yes we can! Great suggestion. I applied the change :)

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

PR Comment: https://git.openjdk.org/jdk/pull/28639#issuecomment-3771397665
PR Review Comment: https://git.openjdk.org/jdk/pull/28639#discussion_r2707076289