[aarch64-port-dev ] RFR(M): 8212043: Add floating-point Math.min/max intrinsics

Andrew Haley aph at redhat.com
Mon Nov 5 09:23:50 UTC 2018

On 11/05/2018 08:38 AM, Andrew Dinn wrote:
> I am also ok with this patch as it stands (so it now has two reviews).
> As Andrew Haley said it doesn't look like it will offer any great
> performance benefit on its own but it should be easy to vectorize it as
> a follow-up step.

Let us do the vectorization now, while we've got the lid open. It should
be pretty easy, given that {min,max} is associative, commutative, and in
general behaves in the same way as addition.

Andrew Haley
Java Platform Lead Engineer
Red Hat UK Ltd. <https://www.redhat.com>
EAC8 43EB D3EF DB98 CC77 2FAD A5CD 6035 332F A671

More information about the hotspot-compiler-dev mailing list