RFR: 8342601: AArch64: Micro-optimize bit shift in copy_memory [v3]

Andrew Haley aph at openjdk.org
Tue Oct 22 10:16:22 UTC 2024


On Mon, 21 Oct 2024 20:14:30 GMT, Dean Long <dlong at openjdk.org> wrote:

> BTW, apparently Neoverse has 0 latency moves even for 32-bit registers, so they must do something clever with clearing the high bits.

So they are. Some dark magic there. :-)

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

PR Comment: https://git.openjdk.org/jdk/pull/21589#issuecomment-2428871730


More information about the hotspot-compiler-dev mailing list