diff --git a/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
index 37d6d60..2364748 100644
--- a/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -513,9 +513,13 @@
 
     ToLift.push_back(C);
     for (unsigned k = 0, e = C->getNumOperands(); k != e; ++k)
-      if (auto *A = dyn_cast<Instruction>(C->getOperand(k)))
-        if (A->getParent() == SI->getParent())
+      if (auto *A = dyn_cast<Instruction>(C->getOperand(k))) {
+        if (A->getParent() == SI->getParent()) {
+          // Cannot hoist user of P above P
+          if(A == P) return false;
           Args.insert(A);
+        }
+      }
   }
 
   // We made it, we need to lift
diff --git a/test/Transforms/MemCpyOpt/aggregate-type-crash.ll b/test/Transforms/MemCpyOpt/aggregate-type-crash.ll
new file mode 100644
index 0000000..16d1077
--- /dev/null
+++ b/test/Transforms/MemCpyOpt/aggregate-type-crash.ll
@@ -0,0 +1,30 @@
+; RUN: opt -memcpyopt -S -o - < %s | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.14.0"
+
+%my_struct = type { i8, i32 }
+
+; Function Attrs: inaccessiblemem_or_argmemonly
+declare noalias i8* @my_malloc(%my_struct*) #0
+
+define void @my_func(%my_struct* %0) {
+entry:
+; CHECK: entry:
+  %1 = load %my_struct, %my_struct* %0
+  %2 = call i8* @my_malloc(%my_struct* %0)
+  %3 = bitcast i8* %2 to %my_struct*
+  store %my_struct %1, %my_struct* %3
+; CHECK-NOT: call void @llvm.memcpy.{{.*}}.{{.*}}.{{.*}}
+  ret void
+}
+
+attributes #0 = { inaccessiblemem_or_argmemonly }
+
+!llvm.module.flags = !{!0, !1, !2}
+!llvm.ident = !{!3}
+
+!0 = !{i32 2, !"SDK Version", [2 x i32] [i32 10, i32 14]}
+!1 = !{i32 1, !"wchar_size", i32 4}
+!2 = !{i32 7, !"PIC Level", i32 2}
+!3 = !{!"Apple LLVM version 10.0.1 (clang-1001.0.46.4)"}