Page MenuHomePhabricator

[hip] Claim builtin type `__float128` supported if the host target supports it.
ClosedPublic

Authored by hliao on Apr 20 2020, 12:36 PM.

Diff Detail

Event Timeline

hliao created this revision.Apr 20 2020, 12:36 PM

Currently if instructions of float128 get to amdgpu backend, are we going to crash?

hliao added a comment.EditedApr 20 2020, 2:20 PM

Currently if instructions of float128 get to amdgpu backend, are we going to crash?

As Float128Format is re-defined as double, there won't be any issue in the backend. But, it won't function as the developer expects. That's quite similar to long double in clang.

yaxunl accepted this revision.Apr 21 2020, 11:10 AM

LGTM. Thanks.

This revision is now accepted and ready to land.Apr 21 2020, 11:10 AM
This revision was automatically updated to reflect the committed changes.