This is an archive of the discontinued LLVM Phabricator instance.

[CUDA] disable attribute-based overloading for __global__ functions.
ClosedPublic

Authored by tra on Feb 24 2016, 1:31 PM.

Details

Reviewers
jlebar
Summary

global functions are present on both host and device side,
so providing host or device overloads is not going to
do anything useful.

Diff Detail

Event Timeline

tra updated this revision to Diff 48973.Feb 24 2016, 1:31 PM
tra retitled this revision from to [CUDA] disable attribute-based overloading for __global__ functions..
tra updated this object.
tra added a reviewer: jlebar.
tra added a subscriber: cfe-commits.
jlebar accepted this revision.Feb 24 2016, 1:33 PM
jlebar edited edge metadata.
This revision is now accepted and ready to land.Feb 24 2016, 1:33 PM
jlebar closed this revision.Feb 29 2016, 5:46 PM

Landed in rL261778.