RFR: 8289552: Make intrinsic conversions between bit representations of half precision values and floats [v11]

Quan Anh Mai qamai at openjdk.org
Fri Sep 30 10:08:33 UTC 2022


On Wed, 28 Sep 2022 17:40:36 GMT, Smita Kamath <svkamath at openjdk.org> wrote:

>> 8289552: Make intrinsic conversions between bit representations of half precision values and floats
>
> Smita Kamath has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Addressed review comment to update test case

src/hotspot/cpu/x86/x86.ad line 3674:

> 3672: %}
> 3673: 
> 3674: instruct convF2HF_mem_reg(memory mem, regF src, kReg ktmp, rRegI rtmp) %{

You can use `kmovwl` instead which will relax the avx512bw constraint, however, you will need avx512vl for `evcvtps2ph`. Thanks.

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

PR: https://git.openjdk.org/jdk/pull/9781


More information about the core-libs-dev mailing list