Page MenuHomePhabricator

NVPTX: support f64 <-> f16 intrinsics
ClosedPublic

Authored by t.p.northover on Jul 17 2014, 5:41 AM.

Details

Reviewers
jholewinski
Summary

Hi,

I'm in the process of reworking how we handle the __fp16 type slightly. I have larger goals, but the most important immediate one is to perform extensions and truncations in one step so that this C code has IEEE-sensible semantics:

void my_round(double in, __fp16 *out) { *out = in; }

Now, I *think* this is fairly academic as far as OpenCL is concerned (you have to use the vload_half/vstore_half functions to access __fp16 at all times), but I'd like to minimise breakage as far as possible anyway.

As part of this I've made the @llvm.convert.from.fp16 and @llvm.convert.to.fp16 intrinsics polymorphic, and would like to add support for f64 variants in as many places as possible.

NVPTX already seemed to have the instructions there, waiting to be used so I added a couple of patterns and a test.

Are you happy for me to commit the change?

Cheers.

Tim.

Diff Detail

Event Timeline

t.p.northover retitled this revision from to NVPTX: support f64 <-> f16 intrinsics.
t.p.northover updated this object.
t.p.northover edited the test plan for this revision. (Show Details)
t.p.northover added a subscriber: Unknown Object (MLST).
jholewinski accepted this revision.Jul 17 2014, 6:59 AM
jholewinski added a reviewer: jholewinski.

This LGTM. Thanks for implementing this!

This revision is now accepted and ready to land.Jul 17 2014, 6:59 AM
t.p.northover closed this revision.Jul 18 2014, 1:39 AM

Thanks Justin. I've committed this as r213356.