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

[Smita Kamath]

On Fri, 5 Aug 2022 22:15:37 GMT, Joe Darcy <darcy at openjdk.org> wrote:

>> 8289552: Make intrinsic conversions between bit representations of half precision values and floats
>
> src/hotspot/share/runtime/sharedRuntime.cpp line 450:
> 
>> 448: JRT_END
>> 449: 
>> 450: JRT_LEAF(jshort, SharedRuntime::f2hf(jfloat  x))
> 
> Is it necessary/desirable to have a transliteration of the Java implementation here rather than just using the Java library implementation?

@jddarcy Thanks for your comment. I am not sure if there is a way of using Java library implementation here.

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

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