Fix PR26051: Memcpy optimization should introduce a call to memcpy before the store destination position

This is a conservative fix, I expect Amaury to relax this.
Follow-up for r256923

From: Mehdi Amini <mehdi.amini@apple.com>
llvm-svn: 256999

2 files changed, 18 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
index 5711a775df8..6b43b0f7a2a 100644
--- a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -529,11 +529,13 @@ bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) {
 
           // We found an instruction that may write to the loaded memory.
           // We can try to promote at this position instead of the store
-          // position if nothing alias the store memory after this.
+          // position if nothing alias the store memory after this and the store
+          // destination is not in the range.
           P = &*I;
           for (; I != E; ++I) {
             MemoryLocation StoreLoc = MemoryLocation::get(SI);
-            if (AA.getModRefInfo(&*I, StoreLoc) != MRI_NoModRef) {
+            if (&*I == SI->getOperand(1) ||
+                AA.getModRefInfo(&*I, StoreLoc) != MRI_NoModRef) {
               P = nullptr;
               break;
             }
diff --git a/llvm/test/Transforms/MemCpyOpt/fca2memcpy.ll b/llvm/test/Transforms/MemCpyOpt/fca2memcpy.ll
index 3c3b22bb335..c8a126848b0 100644
--- a/llvm/test/Transforms/MemCpyOpt/fca2memcpy.ll
+++ b/llvm/test/Transforms/MemCpyOpt/fca2memcpy.ll
@@ -72,3 +72,17 @@ define void @copyalias(%S* %src, %S* %dst) {
   store %S %2, %S* %dst
   ret void
 }
+
+
+; The GEP is present after the aliasing store, preventing to move the memcpy before
+; (without further analysis/transformation)
+define void @copyaliaswithproducerinbetween(%S* %src, %S* %dst) {
+; CHECK-LABEL: copyalias
+; CHECK-NEXT: [[LOAD:%[a-z0-9\.]+]] = load %S, %S* %src
+; CHECK-NOT: call
+  %1 = load %S, %S* %src
+  store %S undef, %S* %dst
+  %dst2 = getelementptr %S , %S* %dst, i64 1
+  store %S %1, %S* %dst2
+  ret void
+}