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

Self-memcpy-elision and memcpy of constant byte to memset transforms don't care how many bytes you were trying to transfer. Sink that safety test after those transforms. Noticed by inspection. 

llvm-svn: 200726
This commit is contained in:
Nick Lewycky 2014-02-04 00:18:54 +00:00
parent 36b5eea258
commit 00703e76dc
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
View File

@ -816,9 +816,8 @@ bool MemCpyOpt::processMemCpyMemCpyDependence(MemCpyInst *M, MemCpyInst *MDep,
/// circumstances). This allows later passes to remove the first memcpy
/// altogether.
bool MemCpyOpt::processMemCpy(MemCpyInst *M) {
// We can only optimize statically-sized memcpy's that are non-volatile.
ConstantInt *CopySize = dyn_cast<ConstantInt>(M->getLength());
if (CopySize == 0 || M->isVolatile()) return false;
// We can only optimize non-volatile memcpy's.
if (M->isVolatile()) return false;
// If the source and destination of the memcpy are the same, then zap it.
if (M->getSource() == M->getDest()) {
@ -832,7 +831,7 @@ bool MemCpyOpt::processMemCpy(MemCpyInst *M) {
if (GV->isConstant() && GV->hasDefinitiveInitializer())
if (Value *ByteVal = isBytewiseValue(GV->getInitializer())) {
IRBuilder<> Builder(M);
Builder.CreateMemSet(M->getRawDest(), ByteVal, CopySize,
Builder.CreateMemSet(M->getRawDest(), ByteVal, M->getLength(),
M->getAlignment(), false);
MD->removeInstruction(M);
M->eraseFromParent();
@ -840,6 +839,10 @@ bool MemCpyOpt::processMemCpy(MemCpyInst *M) {
return true;
}
// The optimizations after this point require the memcpy size.
ConstantInt *CopySize = dyn_cast<ConstantInt>(M->getLength());
if (CopySize == 0) return false;
// The are two possible optimizations we can do for memcpy:
// a) memcpy-memcpy xform which exposes redundance for DSE.
// b) call-memcpy xform for return slot optimization.