Index: lib/Transforms/Scalar/SROA.cpp
===================================================================
--- lib/Transforms/Scalar/SROA.cpp
+++ lib/Transforms/Scalar/SROA.cpp
@@ -2698,7 +2698,7 @@
       assert(!IsSplit);
       assert(NewBeginOffset == BeginOffset);
       II.setDest(getNewAllocaSlicePtr(IRB, OldPtr->getType()));
-      II.setAlignment(getSliceAlign());
+      II.setDestAlignment(getSliceAlign());
 
       deleteIfTriviallyDead(OldPtr);
       return false;
@@ -2819,13 +2819,13 @@
     // update both source and dest of a single call.
     if (!IsSplittable) {
       Value *AdjustedPtr = getNewAllocaSlicePtr(IRB, OldPtr->getType());
-      if (IsDest)
+      if (IsDest) {
         II.setDest(AdjustedPtr);
-      else
+        II.setDestAlignment(SliceAlign);
+      }
+      else {
         II.setSource(AdjustedPtr);
-
-      if (II.getAlignment() > SliceAlign) {
-        II.setAlignment(MinAlign(II.getAlignment(), SliceAlign));
+        II.setSourceAlignment(SliceAlign);
       }
 
       DEBUG(dbgs() << "          to: " << II << "\n");
@@ -2878,8 +2878,10 @@
     // Compute the relative offset for the other pointer within the transfer.
     unsigned IntPtrWidth = DL.getPointerSizeInBits(OtherAS);
     APInt OtherOffset(IntPtrWidth, NewBeginOffset - BeginOffset);
-    unsigned OtherAlign = MinAlign(II.getAlignment() ? II.getAlignment() : 1,
-                                   OtherOffset.zextOrTrunc(64).getZExtValue());
+    unsigned OtherAlign =
+      IsDest ? II.getSourceAlignment() : II.getDestAlignment();
+    OtherAlign =  MinAlign(OtherAlign ? OtherAlign : 1,
+                           OtherOffset.zextOrTrunc(64).getZExtValue());
 
     if (EmitMemCpy) {
       // Compute the other pointer, folding as much as possible to produce
@@ -2891,9 +2893,22 @@
       Type *SizeTy = II.getLength()->getType();
       Constant *Size = ConstantInt::get(SizeTy, NewEndOffset - NewBeginOffset);
 
-      CallInst *New = IRB.CreateMemCpy(
-          IsDest ? OurPtr : OtherPtr, IsDest ? OtherPtr : OurPtr, Size,
-          MinAlign(SliceAlign, OtherAlign), II.isVolatile());
+      Value *DestPtr, *SrcPtr;
+      unsigned DestAlign, SrcAlign;
+      // Note: IsDest is true iff we're copying into the new alloca slice
+      if (IsDest) {
+        DestPtr = OurPtr;
+        DestAlign = SliceAlign;
+        SrcPtr = OtherPtr;
+        SrcAlign = OtherAlign;
+      } else {
+        DestPtr = OtherPtr;
+        DestAlign = OtherAlign;
+        SrcPtr = OurPtr;
+        SrcAlign = SliceAlign;
+      }
+      CallInst *New = IRB.CreateMemCpy(DestPtr, DestAlign, SrcPtr, SrcAlign,
+                                       Size, II.isVolatile());
       if (AATags)
         New->setAAMetadata(AATags);
       DEBUG(dbgs() << "          to: " << *New << "\n");
Index: test/Transforms/SROA/basictest.ll
===================================================================
--- test/Transforms/SROA/basictest.ll
+++ test/Transforms/SROA/basictest.ll
@@ -65,7 +65,7 @@
   ret i64 %Z
 }
 
-define void @test3(i8* %dst, i8* %src) {
+define void @test3(i8* %dst, i8* align 8 %src) {
 ; CHECK-LABEL: @test3(
 
 entry:
@@ -80,9 +80,9 @@
 ; CHECK-NEXT: %[[test3_a7:.*]] = alloca [85 x i8]
 
   %b = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 0
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 300, i1 false), !tbaa !0
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* align 8 %src, i32 300, i1 false), !tbaa !0
 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a1]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %src, i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 8 %src, i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 42
 ; CHECK-NEXT: %[[test3_r1:.*]] = load i8, i8* %[[gep]], {{.*}}, !tbaa [[TAG_0]]
 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 43
@@ -90,18 +90,18 @@
 ; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 99, {{.*}}), !tbaa [[TAG_0:!.*]]
 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 142
 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [16 x i8], [16 x i8]* %[[test3_a3]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 16, {{.*}}), !tbaa [[TAG_0:!.*]]
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 2 %[[gep_src]], i32 16, {{.*}}), !tbaa [[TAG_0:!.*]]
 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 158
 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 2 %[[gep_src]], i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 200
 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 8 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 207
 ; CHECK-NEXT: %[[test3_r2:.*]] = load i8, i8* %[[gep]], {{.*}}, !tbaa [[TAG_0]]
 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 208
 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 8 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 215
 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0
 ; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 85, {{.*}}), !tbaa [[TAG_0:!.*]]
@@ -778,7 +778,7 @@
 ; CHECK-NEXT: %[[srccast1:.*]] = bitcast i8* %[[srcgep1]] to i32*
 ; CHECK-NEXT: %[[srcload:.*]] = load i32, i32* %[[srccast1]], {{.*}}, !tbaa [[TAG_0]]
 ; CHECK-NEXT: %[[agep1:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[agep1]], i8* %src, i32 %size, {{.*}}), !tbaa [[TAG_3]]
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[agep1]], i8* %src, i32 %size, {{.*}}), !tbaa [[TAG_3]]
 ; CHECK-NEXT: %[[agep2:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
 ; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[agep2]], i8 42, i32 %size, {{.*}}), !tbaa [[TAG_5]]
 ; CHECK-NEXT: %[[dstcast1:.*]] = bitcast i8* %dst to i32*
@@ -787,7 +787,7 @@
 ; CHECK-NEXT: %[[dstcast2:.*]] = bitcast i8* %[[dstgep1]] to i32*
 ; CHECK-NEXT: store i32 %[[srcload]], i32* %[[dstcast2]], {{.*}}, !tbaa [[TAG_9]]
 ; CHECK-NEXT: %[[agep3:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %[[agep3]], i32 %size, {{.*}}), !tbaa [[TAG_11]]
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* align 1 %[[agep3]], i32 %size, {{.*}}), !tbaa [[TAG_11]]
 ; CHECK-NEXT: ret void
 
 entry: