diff --git a/SingleSource/UnitTests/Vectorizer/CMakeLists.txt b/SingleSource/UnitTests/Vectorizer/CMakeLists.txt
--- a/SingleSource/UnitTests/Vectorizer/CMakeLists.txt
+++ b/SingleSource/UnitTests/Vectorizer/CMakeLists.txt
@@ -1 +1,2 @@
 llvm_singlesource()
+set_property(TARGET runtime-checks PROPERTY CXX_STANDARD 17)
diff --git a/SingleSource/UnitTests/Vectorizer/runtime-checks.cpp b/SingleSource/UnitTests/Vectorizer/runtime-checks.cpp
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/runtime-checks.cpp
@@ -0,0 +1,273 @@
+#include <functional>
+#include <iostream>
+#include <limits>
+#include <memory>
+#include <random>
+
+// Tests for memory runtime checks generated by the vectorizer. Runs scalar and
+// vectorized versions of a loop requiring runtime checks on the same inputs
+// with pointers to the same buffer using various offsets between reads and
+// writes. Fails if they do not produce the same results.
+
+static std::mt19937 rng;
+
+// Initialize arrays A with random numbers.
+template <typename Ty>
+static void init_data(const std::unique_ptr<Ty[]> &A, unsigned N) {
+  std::uniform_int_distribution<Ty> distrib(std::numeric_limits<Ty>::min(),
+                                            std::numeric_limits<Ty>::max());
+  for (unsigned i = 0; i < N; i++)
+    A[i] = distrib(rng);
+}
+
+template <typename Ty>
+static void check(const std::unique_ptr<Ty[]> &Reference,
+                  const std::unique_ptr<Ty[]> &Tmp, unsigned NumElements,
+                  int Offset) {
+  if (!std::equal(&Reference[0], &Reference[0] + NumElements, &Tmp[0])) {
+    std::cerr << "Miscompare with offset " << Offset << "\n";
+    exit(1);
+  }
+}
+
+#define DEFINE_SCALAR_AND_VECTOR_FN2(Loop)                                     \
+  auto ScalarFn = [](auto *A, auto *B, unsigned TC) {                          \
+    _Pragma("clang loop vectorize(disable)") Loop                              \
+  };                                                                           \
+  auto VectorFn = [](auto *A, auto *B, unsigned TC) {                          \
+    _Pragma("clang loop vectorize(enable)") Loop                               \
+  };
+
+#define DEFINE_SCALAR_AND_VECTOR_FN3(Loop)                                     \
+  auto ScalarFn = [](auto *A, auto *B, auto *C, unsigned TC) {                 \
+    _Pragma("clang loop vectorize(disable)") Loop                              \
+  };                                                                           \
+  auto VectorFn = [](auto *A, auto *B, auto *C, unsigned TC) {                 \
+    _Pragma("clang loop vectorize(enable)") Loop                               \
+  };
+
+// Helper to call \p f with \p args and acts as optimization barrier for \p f.
+template <typename F, typename... Args>
+__attribute__((optnone)) static void callThroughOptnone(F &&f, Args &&...args) {
+  f(std::forward<Args>(args)...);
+}
+
+template <typename Ty> using Fn2Ty = std::function<void(Ty *, Ty *, unsigned)>;
+
+// Run both \p ScalarFn and \p VectorFn on the same inputs with pointers to the
+// same buffer. Fail if they do not produce the same results.
+template <typename Ty>
+static void checkOverlappingMemoryOneRuntimeCheck(Fn2Ty<Ty> ScalarFn,
+                                                  Fn2Ty<Ty> VectorFn,
+                                                  const char *Name) {
+  std::cout << "Checking " << Name << "\n";
+
+  unsigned N = 100;
+  // Make sure we have enough extra elements so we can be liberal with offsets.
+  unsigned NumArrayElements = N * 8;
+  std::unique_ptr<Ty[]> Input1(new Ty[NumArrayElements]);
+  std::unique_ptr<Ty[]> Reference(new Ty[NumArrayElements]);
+  std::unique_ptr<Ty[]> ToCheck(new Ty[NumArrayElements]);
+
+  auto CheckWithOffset = [&](int Offset) {
+    init_data(Input1, NumArrayElements);
+    for (unsigned i = 0; i < NumArrayElements; i++) {
+      Reference[i] = Input1[i];
+      ToCheck[i] = Input1[i];
+    }
+
+    // Run scalar function to generate reference output.
+    Ty *ReferenceStart = &Reference[NumArrayElements / 2];
+    ScalarFn(ReferenceStart + Offset, ReferenceStart, N);
+
+    // Run vector function to generate output to check.
+    Ty *StartPtr = &ToCheck[NumArrayElements / 2];
+    callThroughOptnone(VectorFn, StartPtr + Offset, StartPtr, N);
+
+    // Compare scalar and vector output.
+    check(Reference, ToCheck, NumArrayElements, Offset);
+  };
+
+  for (int i = -100; i <= 100; i++)
+    CheckWithOffset(i);
+}
+
+template <typename Ty>
+using Fn3Ty = std::function<void(Ty *, Ty *, Ty *, unsigned)>;
+template <typename Ty>
+static void checkOverlappingMemoryTwoRuntimeChecks(Fn3Ty<Ty> ScalarFn,
+                                                   Fn3Ty<Ty> VectorFn,
+                                                   const char *Name) {
+  std::cout << "Checking " << Name << "\n";
+
+  unsigned N = 100;
+  // Make sure we have enough extra elements so we can be liberal with offsets.
+  unsigned NumArrayElements = N * 8;
+  std::unique_ptr<Ty[]> Input1(new Ty[NumArrayElements]);
+  std::unique_ptr<Ty[]> Input2(new Ty[NumArrayElements]);
+  std::unique_ptr<Ty[]> Reference(new Ty[NumArrayElements]);
+  std::unique_ptr<Ty[]> ToCheck(new Ty[NumArrayElements]);
+
+  auto CheckWithOffsetSecond = [&](int Offset) {
+    init_data(Input1, NumArrayElements);
+    init_data(Input2, NumArrayElements);
+    for (unsigned i = 0; i < NumArrayElements; i++) {
+      Reference[i] = Input1[i];
+      ToCheck[i] = Input1[i];
+    }
+
+    // Run scalar function to generate reference output.
+    Ty *ReferenceStart = &Reference[NumArrayElements / 2];
+    ScalarFn(ReferenceStart + Offset, &Input2[0], ReferenceStart, N);
+
+    // Run vector function to generate output to check.
+    Ty *StartPtr = &ToCheck[NumArrayElements / 2];
+    callThroughOptnone(VectorFn, StartPtr + Offset, &Input2[0], StartPtr, N);
+
+    // Compare scalar and vector output.
+    check(Reference, ToCheck, NumArrayElements, Offset);
+  };
+
+  for (int i = -100; i <= 100; i++)
+    CheckWithOffsetSecond(i);
+}
+
+int main(void) {
+  rng = std::mt19937(15);
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN2(
+      for (unsigned i = 0; i < TC; i++)
+        A[i] = B[i] + 10;
+    );
+
+    checkOverlappingMemoryOneRuntimeCheck<char>(
+        ScalarFn, VectorFn, "1 read, 1 write, step 1, char");
+    checkOverlappingMemoryOneRuntimeCheck<int>(ScalarFn, VectorFn,
+                                               "1 read, 1 write, step 1, int");
+    checkOverlappingMemoryOneRuntimeCheck<long long>(
+        ScalarFn, VectorFn, "1 read, 1 write, step 1, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN2(
+      for (unsigned i = 0; i < TC; i++)
+        A[i] = B[i + 3] + 10;
+    );
+
+    checkOverlappingMemoryOneRuntimeCheck<char>(
+        ScalarFn, VectorFn, "1 read, 1 write, offset 3, char");
+    checkOverlappingMemoryOneRuntimeCheck<int>(
+        ScalarFn, VectorFn, "1 read, 1 write, offset 3, int");
+    checkOverlappingMemoryOneRuntimeCheck<long long>(
+        ScalarFn, VectorFn, "1 read, 1 write, offset 3, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN2(
+      for (unsigned i = 3; i < TC; i++)
+        A[i] = B[i - 3] + 10;
+    );
+
+    checkOverlappingMemoryOneRuntimeCheck<char>(
+        ScalarFn, VectorFn, "1 read, 1 write, offset -3, char");
+    checkOverlappingMemoryOneRuntimeCheck<int>(
+        ScalarFn, VectorFn, "1 read, 1 write, offset -3, int");
+    checkOverlappingMemoryOneRuntimeCheck<long long>(
+        ScalarFn, VectorFn, "1 read, 1 write, offset -3, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN2(
+      for (unsigned i = TC; i > 0; i--)
+        A[i] = B[i] + 10;);
+
+    checkOverlappingMemoryOneRuntimeCheck<char>(
+        ScalarFn, VectorFn, "1 read, 1 write, index count down, char");
+    checkOverlappingMemoryOneRuntimeCheck<int>(
+        ScalarFn, VectorFn, "1 read, 1 write, index count down, int");
+    checkOverlappingMemoryOneRuntimeCheck<long long>(
+        ScalarFn, VectorFn, "1 read, 1 write, index count down, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN2(
+      for (unsigned i = TC; i > 2; i -= 2)
+        A[i] = B[i] + 10;
+    );
+
+    checkOverlappingMemoryOneRuntimeCheck<char>(
+        ScalarFn, VectorFn, "1 read, 1 write, index count down 2, char");
+    checkOverlappingMemoryOneRuntimeCheck<int>(
+        ScalarFn, VectorFn, "1 read, 1 write, index count down 2, int");
+    checkOverlappingMemoryOneRuntimeCheck<long long>(
+        ScalarFn, VectorFn, "1 read, 1 write, index count down 2, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN2(
+      for (unsigned i = 0, j = 0; i < TC; i++) {
+        A[i] = B[j] + 10;
+        j += 2;
+      }
+    );
+    checkOverlappingMemoryOneRuntimeCheck<char>(
+        ScalarFn, VectorFn,
+        "1 read, 1 write, 2 inductions, different steps, char");
+    checkOverlappingMemoryOneRuntimeCheck<int>(
+        ScalarFn, VectorFn,
+        "1 read, 1 write, 2 inductions, different steps, int");
+    checkOverlappingMemoryOneRuntimeCheck<long long>(
+        ScalarFn, VectorFn,
+        "1 read, 1 write, 2 inductions, different steps, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN2(
+      _Pragma("clang loop unroll(disable)")
+      for (unsigned i = 0; i < TC; i += 2)
+        A[i] = B[i] + 10;
+    );
+
+    checkOverlappingMemoryOneRuntimeCheck<char>(
+        ScalarFn, VectorFn, "1 read, 1 write, induction increment 2, char");
+    checkOverlappingMemoryOneRuntimeCheck<int>(
+        ScalarFn, VectorFn, "1 read, 1 write, induction increment 2, int");
+    checkOverlappingMemoryOneRuntimeCheck<long long>(
+        ScalarFn, VectorFn,
+        "1 read, 1 write, induction increment 2, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN3(
+      for (unsigned i = 0; i < TC; i++)
+        A[i] = B[i] + C[i] + 10;
+    );
+
+    checkOverlappingMemoryTwoRuntimeChecks<int>(
+        ScalarFn, VectorFn, "2 reads, 1 write, simple indices, int");
+    checkOverlappingMemoryTwoRuntimeChecks<char>(
+        ScalarFn, VectorFn, "2 reads, 1 write, simple indices, char");
+    checkOverlappingMemoryTwoRuntimeChecks<long long>(
+        ScalarFn, VectorFn, "2 reads, 1 write, simple indices, long long");
+  }
+
+  {
+    DEFINE_SCALAR_AND_VECTOR_FN3(
+      for (unsigned i = 0; i < TC; i++) {
+        auto X = C[i] + 10;
+        A[i] = X;
+        B[i] = X + 9;
+      }
+    );
+
+    checkOverlappingMemoryTwoRuntimeChecks<char>(
+        ScalarFn, VectorFn, "1 read, 2 writes, simple indices, char");
+    checkOverlappingMemoryTwoRuntimeChecks<int>(
+        ScalarFn, VectorFn, "1 read, 2 writes, simple indices, int");
+    checkOverlappingMemoryTwoRuntimeChecks<long long>(
+        ScalarFn, VectorFn, "1 read, 2 writes, simple indices, long long");
+  }
+
+  return 0;
+}
diff --git a/SingleSource/UnitTests/Vectorizer/runtime-checks.reference_output b/SingleSource/UnitTests/Vectorizer/runtime-checks.reference_output
new file mode 100644
--- /dev/null
+++ b/SingleSource/UnitTests/Vectorizer/runtime-checks.reference_output
@@ -0,0 +1,28 @@
+Checking 1 read, 1 write, step 1, char
+Checking 1 read, 1 write, step 1, int
+Checking 1 read, 1 write, step 1, long long
+Checking 1 read, 1 write, offset 3, char
+Checking 1 read, 1 write, offset 3, int
+Checking 1 read, 1 write, offset 3, long long
+Checking 1 read, 1 write, offset -3, char
+Checking 1 read, 1 write, offset -3, int
+Checking 1 read, 1 write, offset -3, long long
+Checking 1 read, 1 write, index count down, char
+Checking 1 read, 1 write, index count down, int
+Checking 1 read, 1 write, index count down, long long
+Checking 1 read, 1 write, index count down 2, char
+Checking 1 read, 1 write, index count down 2, int
+Checking 1 read, 1 write, index count down 2, long long
+Checking 1 read, 1 write, 2 inductions, different steps, char
+Checking 1 read, 1 write, 2 inductions, different steps, int
+Checking 1 read, 1 write, 2 inductions, different steps, long long
+Checking 1 read, 1 write, induction increment 2, char
+Checking 1 read, 1 write, induction increment 2, int
+Checking 1 read, 1 write, induction increment 2, long long
+Checking 2 reads, 1 write, simple indices, int
+Checking 2 reads, 1 write, simple indices, char
+Checking 2 reads, 1 write, simple indices, long long
+Checking 1 read, 2 writes, simple indices, char
+Checking 1 read, 2 writes, simple indices, int
+Checking 1 read, 2 writes, simple indices, long long
+exit 0