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

Avoid folding a load instruction into an instruction that redefines the register. 

The target hook doesn't know how to do that. (Neither do I).

llvm-svn: 125108
This commit is contained in:
Jakob Stoklund Olesen 2011-02-08 19:33:55 +00:00
parent 968fa38e0a
commit c6a2041d99
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/CodeGen/InlineSpiller.cpp
View File

@ -157,7 +157,8 @@ bool InlineSpiller::reMaterializeFor(MachineBasicBlock::iterator MI) {
// Finally we can rematerialize OrigMI before MI.
SlotIndex DefIdx = edit_->rematerializeAt(*MI->getParent(), MI, NewLI.reg, RM,
lis_, tii_, tri_);
DEBUG(dbgs() << "\tremat: " << DefIdx << '\n');
DEBUG(dbgs() << "\tremat: " << DefIdx << '\t'
<< *lis_.getInstructionFromIndex(DefIdx));
// Replace operands
for (unsigned i = 0, e = Ops.size(); i != e; ++i) {
@ -270,6 +271,9 @@ bool InlineSpiller::foldMemoryOperand(MachineBasicBlock::iterator MI,
// FIXME: Teach targets to deal with subregs.
if (MO.getSubReg())
return false;
// We cannot fold a load instruction into a def.
if (LoadMI && MO.isDef())
return false;
// Tied use operands should not be passed to foldMemoryOperand.
if (!MI->isRegTiedToDefOperand(Idx))
FoldOps.push_back(Idx);