projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: d6c53f8) | patch
AMDGPU/SI: Add support for spilling VGPRs without having to scavenge registers
authorTom Stellard <thomas.stellard@amd.com>
Wed, 13 Apr 2016 20:44:16 +0000 (20:44 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Wed, 13 Apr 2016 20:44:16 +0000 (20:44 +0000)
commitb951f10701d2d306b09017dba36f5d271ab7438d
treea978deedfe4f95c7934d21b04a5b043006f8a579tree | snapshot
parentd6c53f87273b3892089e16525ac040fcc7c0f70dcommit | diff
AMDGPU/SI: Add support for spilling VGPRs without having to scavenge registers

Summary:
When we are spilling SGPRs to scratch memory, we usually don't have
free SGPRs to do the address calculation, so we need to re-use the
ScratchOffset register for the calculation.

Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D18917

llvm-svn: 266244
llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp diff | blob | history
llvm/lib/Target/AMDGPU/SIRegisterInfo.h diff | blob | history
Domain: System / Toolchain;