[aarch64-port-dev ] [PATCH] 8217561 : X86: Add floating-point Math.min/max intrinsics, approval request

Andrew Dinn adinn at redhat.com
Mon Mar 11 11:30:59 UTC 2019

Hi Pengfei,

On 11/03/2019 10:32, Pengfei Li (Arm Technology China) wrote:
> Ah~ Perhaps the armARM doc is hard to read sometimes.

Doh! It is obviously difficult for me to read :-)

> In the D.a version: - The FMAXV instruction is defined in section
> C7.2.103 on page 1501-1502. - The FMINV instruction is defined in
> section C7.2.113 on page 1521-1522. - Section C7.2.104 which follows
> the FMAXV section defines the "FMIN (vector)" instruction. This is
> actually the binary vector operation, not used for reduction fmin.
> The armARM just sorts these sections in alphabetical order. Opposite
> instructions are not necessarily adjacent.

Thank you for the correction!

> I've already posted it in a new thread. See 
> https://mail.openjdk.java.net/pipermail/aarch64-port-dev/2019-March/007039.html

Yes, got it. I will reply in that thread.


Andrew Dinn
Senior Principal Software Engineer
Red Hat UK Ltd
Registered in England and Wales under Company Registration No. 03798903
Directors: Michael Cunningham, Michael ("Mike") O'Neill, Eric Shander

More information about the hotspot-compiler-dev mailing list