On Sat, 12 Mar 2022 12:30:39 GMT, Andrew Haley <a...@openjdk.org> wrote:
> 1ns Incidentally, there must be a lot of speculation and bypassing going on there. I can see 15 cycles of latency, probably 20, so that'd be more like 5ns start to finish. M1 is a remarkable thing. ------------- PR: https://git.openjdk.java.net/jdk/pull/7727
