RFR: 8289552: Make intrinsic conversions between bit representations of half precision values and floats [v5]

[Sandhya Viswanathan]

On Thu, 1 Sep 2022 18:26:52 GMT, Smita Kamath <svkamath at openjdk.org> wrote:

>> src/hotspot/cpu/x86/x86_64.ad line 11330:
>> 
>>> 11328:   ins_pipe( pipe_slow );
>>> 11329: %}
>>> 11330: 
>> 
>> For HF2F, good to also add optimized rule with LoadS to benefit from vcvtph2ps memory src form of instruction.
>> match(Set dst (ConvHF2F ( LoadS mem)));
>
> Hi @sviswa7 , with this rule, I dont see additional performance gain. So I have not added it in the latest update.

ok, sounds good.

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

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