diff options
| author | Tom Stellard <thomas.stellard@amd.com> | 2016-05-02 19:37:56 +0000 |
|---|---|---|
| committer | Tom Stellard <thomas.stellard@amd.com> | 2016-05-02 19:37:56 +0000 |
| commit | ce5e994887f7700da3b22bd1b027f52092e5cabb (patch) | |
| tree | 1e5e5461269f83a9cb3f5f2630ba6c1b1e4214e7 /llvm/lib/Object/Object.cpp | |
| parent | 4f8d21f3874064bed5fabb0ebecf57b33489aad6 (diff) | |
| download | llvm-ce5e994887f7700da3b22bd1b027f52092e5cabb.zip llvm-ce5e994887f7700da3b22bd1b027f52092e5cabb.tar.gz llvm-ce5e994887f7700da3b22bd1b027f52092e5cabb.tar.bz2 | |
AMDGPU/SI: Set the kill flag on temp VGPRs used to restore SGPRs from scratch
Summary:
When we restore an SGPR value from scratch, we first load it into a
temporary VGPR and then use v_readlane_b32 to copy the value from the
VGPR back into an SGPR.
We weren't setting the kill flag on the VGPR in the v_readlane_b32
instruction, so the register scavenger wasn't able to re-use this
temp value later.
I wasn't able to create a lit test for this.
Reviewers: arsenm
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D19744
llvm-svn: 268287
Diffstat (limited to 'llvm/lib/Object/Object.cpp')
0 files changed, 0 insertions, 0 deletions