[jdk17u] RFR: 8271567: AArch64: AES Galois CounterMode (GCM) interleaved implementation using vector instructions

[Andrew Dinn]

On Fri, 24 Sep 2021 15:07:41 GMT, Andrew Haley <aph at openjdk.org> wrote:

> This is a backport of the big AES/GCM patch from JDK head. It's a
> major change and it's had very little time (almost a day) to mature in
> head, so perhaps it shouldn't be backported for some time, However, there is a good reason for a
> backport: OpenJDK on x86 has a major advantage. AES/GCM is an
> important cipher, the current AArch64 implementation is much slower
> than x86, and some workloads are severely impacted.
> 
> I'm open to all arguments about why this should or shouldn't be pushed,
> and I'm quite happy to wait for another release cycle or two if people
> think that's the best course of action.

I'd be happy with "include the patch but disable the intrinsic by default". That poses a pretty low risk for users who don't need this but, as you say, should a big difference for apps that need AES GCM -- enough for them to want it despite the limited upstream baking time.

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

PR: https://git.openjdk.java.net/jdk17u/pull/87