maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU/SI: Fix some invaild assumptions when folding 64-bit immediates 

Summary:
We were assuming tha if the use operand had a sub-register that
the immediate was 64-bits, but this was breaking the case of
folding a 64-bit immediate into another 64-bit instruction.

Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D12255

llvm-svn: 246354
This commit is contained in:
Tom Stellard 2015-08-29 01:58:21 +00:00
parent b8ce14c4c3
commit eea72ccbf2
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View File

@ -211,8 +211,12 @@ static void foldOperand(MachineOperand &OpToFold, MachineInstr *UseMI,
Imm = APInt(64, OpToFold.getImm());
const MCInstrDesc &FoldDesc = TII->get(OpToFold.getParent()->getOpcode());
const TargetRegisterClass *FoldRC =
TRI.getRegClass(FoldDesc.OpInfo[0].RegClass);
// Split 64-bit constants into 32-bits for folding.
if (UseOp.getSubReg()) {
if (FoldRC->getSize() == 8 && UseOp.getSubReg()) {
if (UseRC->getSize() != 8)
return;