Emit memmove, not memcpy, for structure copies; this is unfortunately
required for correctness in cases of copying a struct to itself or to
an overlapping struct (itself for cases like *a = *a, and overlapping
is possible with unions).
Hopefully, this won't end up being a perf issue; LLVM *should* be able
to optimize memmove to memcpy in a lot of cases, and for small copies
the generated code *should* be mostly comparable. (In reality, LLVM
is currently horrible at optimizing memmove, but that's a bug, not a
fundamental issue.)
gcc currently generates wrong code; that's
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=32667.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@51566 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/CodeGen/CGExprAgg.cpp b/lib/CodeGen/CGExprAgg.cpp
index f584980..30ff9ec 100644
--- a/lib/CodeGen/CGExprAgg.cpp
+++ b/lib/CodeGen/CGExprAgg.cpp
@@ -131,7 +131,7 @@
llvm::Value *SrcPtr, QualType Ty) {
assert(!Ty->isAnyComplexType() && "Shouldn't happen for complex");
- // Aggregate assignment turns into llvm.memcpy.
+ // Aggregate assignment turns into llvm.memmove.
const llvm::Type *BP = llvm::PointerType::getUnqual(llvm::Type::Int8Ty);
if (DestPtr->getType() != BP)
DestPtr = Builder.CreateBitCast(DestPtr, BP, "tmp");
@@ -144,14 +144,14 @@
// FIXME: Handle variable sized types.
const llvm::Type *IntPtr = llvm::IntegerType::get(CGF.LLVMPointerWidth);
- llvm::Value *MemCpyOps[4] = {
+ llvm::Value *MemMoveOps[4] = {
DestPtr, SrcPtr,
// TypeInfo.first describes size in bits.
llvm::ConstantInt::get(IntPtr, TypeInfo.first/8),
llvm::ConstantInt::get(llvm::Type::Int32Ty, TypeInfo.second/8)
};
- Builder.CreateCall(CGF.CGM.getMemCpyFn(), MemCpyOps, MemCpyOps+4);
+ Builder.CreateCall(CGF.CGM.getMemMoveFn(), MemMoveOps, MemMoveOps+4);
}