AMDGPU/LoadStoreOptimizer: Set the correct offset whem merging MMOs
Summary:
This is a follow up to r367237. MachineFunction::getMachineMemOperand()
adds the offset parameter to the existing offset instead of resetting it.
So we need to reset the offset to the correct value after calling this
function.
Reviewers: arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65557
llvm-svn: 367881
diff --git a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
index d3048fc..bded67e 100644
--- a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -313,7 +313,12 @@
const MachineMemOperand *B) {
unsigned MinOffset = std::min(A->getOffset(), B->getOffset());
unsigned Size = A->getSize() + B->getSize();
- return MF.getMachineMemOperand(A, MinOffset, Size);
+ // This function adds the offset parameter to the existing offset for A,
+ // so we pass 0 here as the offset and then manually set it to the correct
+ // value after the call.
+ MachineMemOperand *MMO = MF.getMachineMemOperand(A, 0, Size);
+ MMO->setOffset(MinOffset);
+ return MMO;
}
bool SILoadStoreOptimizer::offsetsCanBeCombined(CombineInfo &CI) {