This is an archive of the discontinued LLVM Phabricator instance.

AMDGPU/SI: Add support for AMD code object version 2.
ClosedPublic

Authored by tstellarAMD on Apr 19 2016, 1:24 PM.

Details

Summary

Version 2 is now the default. If you want to emit version 1, use
the amdgcn--amdhsa-amdcov1 triple.

Diff Detail

Repository
rL LLVM

Event Timeline

tstellarAMD retitled this revision from to AMDGPU/SI: Add support for AMD code object version 2..
tstellarAMD updated this object.
tstellarAMD added reviewers: arsenm, kzhuravl.
tstellarAMD added a subscriber: llvm-commits.
arsenm added inline comments.Apr 19 2016, 2:40 PM
lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
107–111 ↗(On Diff #54250)

This looks like it should be a select on the value to pass to the function

lib/Target/AMDGPU/AMDGPUSubtarget.h
328–329 ↗(On Diff #54250)

Why are the extra checks needed here?

Drop support for code object version 1.

kzhuravl accepted this revision.May 2 2016, 12:51 PM
kzhuravl edited edge metadata.

LGTM

This revision is now accepted and ready to land.May 2 2016, 12:51 PM
This revision was automatically updated to reflect the committed changes.