Index: lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
===================================================================
--- lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
+++ lib/Target/X86/X86AvoidStoreForwardingBlocks.cpp
@@ -641,21 +641,23 @@
   if (BlockingStoresDispSizeMap.size() <= 1)
     return;
 
-  int64_t PrevDisp = BlockingStoresDispSizeMap.begin()->first;
-  unsigned PrevSize = BlockingStoresDispSizeMap.begin()->second;
-  SmallVector<int64_t, 2> ForRemoval;
-  for (auto DispSizePair = std::next(BlockingStoresDispSizeMap.begin());
+  SmallVector<std::pair<const int64_t, unsigned>, 0> DispSizeStack;
+  for (auto DispSizePair = BlockingStoresDispSizeMap.begin();
        DispSizePair != BlockingStoresDispSizeMap.end(); ++DispSizePair) {
     int64_t CurrDisp = DispSizePair->first;
     unsigned CurrSize = DispSizePair->second;
-    if (CurrDisp + CurrSize <= PrevDisp + PrevSize) {
-      ForRemoval.push_back(PrevDisp);
+    while (DispSizeStack.size()) {
+      int64_t PrevDisp = DispSizeStack.back().first;
+      unsigned PrevSize = DispSizeStack.back().second;
+      if (CurrDisp + CurrSize > PrevDisp + PrevSize)
+        break;
+      DispSizeStack.pop_back();
     }
-    PrevDisp = CurrDisp;
-    PrevSize = CurrSize;
+    DispSizeStack.push_back(*DispSizePair);
   }
-  for (auto Disp : ForRemoval)
-    BlockingStoresDispSizeMap.erase(Disp);
+  BlockingStoresDispSizeMap.clear();
+  for (auto Disp : DispSizeStack)
+    BlockingStoresDispSizeMap.insert(Disp);
 }
 
 bool X86AvoidSFBPass::runOnMachineFunction(MachineFunction &MF) {
Index: test/CodeGen/X86/pr38743.ll
===================================================================
--- /dev/null
+++ test/CodeGen/X86/pr38743.ll
@@ -0,0 +1,57 @@
+; RUN: llc < %s
+
+%0 = type { %1 }
+%1 = type { %2 }
+%2 = type { %3 }
+%3 = type { %4 }
+%4 = type { %5 }
+%5 = type { i64, i64, i8* }
+%6 = type { %7, [23 x i8] }
+%7 = type { i8 }
+
+@.str.16 = external dso_local unnamed_addr constant [16 x i8], align 1
+@.str.17 = external dso_local unnamed_addr constant [12 x i8], align 1
+@.str.18 = external dso_local unnamed_addr constant [15 x i8], align 1
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #0
+
+define void @pr38743() #1 align 2 {
+bb:
+  %tmp = alloca %0, align 16
+  %tmp1 = bitcast %0* %tmp to i8*
+  switch i32 undef, label %bb11 [
+    i32 1, label %bb2
+    i32 4, label %bb5
+    i32 2, label %bb5
+    i32 3, label %bb8
+  ]
+
+bb2:                                              ; preds = %bb
+  %tmp3 = bitcast %0* %tmp to %6*
+  %tmp4 = getelementptr inbounds %6, %6* %tmp3, i64 0, i32 1, i64 0
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 1 %tmp4, i8* align 1 getelementptr inbounds ([16 x i8], [16 x i8]* @.str.16, i64 0, i64 0), i64 15, i1 false)
+  br label %bb12
+
+bb5:                                              ; preds = %bb, %bb
+  %tmp6 = bitcast %0* %tmp to %6*
+  %tmp7 = getelementptr inbounds %6, %6* %tmp6, i64 0, i32 1, i64 0
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 1 %tmp7, i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str.17, i64 0, i64 0), i64 11, i1 false)
+  br label %bb12
+
+bb8:                                              ; preds = %bb
+  %tmp9 = bitcast %0* %tmp to %6*
+  %tmp10 = getelementptr inbounds %6, %6* %tmp9, i64 0, i32 1, i64 0
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 1 %tmp10, i8* align 1 getelementptr inbounds ([15 x i8], [15 x i8]* @.str.18, i64 0, i64 0), i64 14, i1 false)
+  br label %bb12
+
+bb11:                                             ; preds = %bb
+  unreachable
+
+bb12:                                             ; preds = %bb8, %bb5, %bb2
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 undef, i8* nonnull align 16 %tmp1, i64 24, i1 false) #2
+  ret void
+}
+
+attributes #0 = { argmemonly nounwind }
+attributes #1 = { "target-features"="+sse,+sse2,+sse3,+sse4.2" }
+attributes #2 = { nounwind }