RFR: 8268229: Aarch64: Use Neon in intrinsics for String.equals

[Andrew Haley]

On Thu, 17 Jun 2021 01:55:17 GMT, Wang Huang <whuang at openjdk.org> wrote:

>> I guess it can be done with:
>> 
>> umaxv(v1, T4S, v0);
>> mov(tmp1, v1, T4S, 0);
>> cbnz(tmp1, DONE0);
>
> I have tested @dgbo 's suggestion and found that the performance degradation happened by using `umaxv`.

I guess I'm not surprised it's slower: even Firestorm has a 3-cycle latency for UMAX, and its output is used immediately.

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

PR: https://git.openjdk.java.net/jdk/pull/4423