diff --git a/mlir/include/mlir/ExecutionEngine/RunnerUtils.h b/mlir/include/mlir/ExecutionEngine/RunnerUtils.h
--- a/mlir/include/mlir/ExecutionEngine/RunnerUtils.h
+++ b/mlir/include/mlir/ExecutionEngine/RunnerUtils.h
@@ -159,7 +159,7 @@
                                  int64_t rank, int64_t offset,
                                  const int64_t *sizes, const int64_t *strides) {
   if (dim == 0) {
-    os << base[offset];
+    os << base[offset] << "@" << &base[offset];
     return;
   }
   printFirst(os, base, dim, rank, offset, sizes, strides);
@@ -217,12 +217,16 @@
 // Currently exposed C API.
 ////////////////////////////////////////////////////////////////////////////////
 extern "C" MLIR_RUNNERUTILS_EXPORT void
+_mlir_ciface_print_memref_i1(UnrankedMemRefType<bool> *M);
+extern "C" MLIR_RUNNERUTILS_EXPORT void
 _mlir_ciface_print_memref_i8(UnrankedMemRefType<int8_t> *M);
 extern "C" MLIR_RUNNERUTILS_EXPORT void
 _mlir_ciface_print_memref_f32(UnrankedMemRefType<float> *M);
 extern "C" MLIR_RUNNERUTILS_EXPORT void
 _mlir_ciface_print_memref_f64(UnrankedMemRefType<double> *M);
 
+extern "C" MLIR_RUNNERUTILS_EXPORT void print_memref_i1(int64_t rank,
+                                                        void *ptr);
 extern "C" MLIR_RUNNERUTILS_EXPORT void print_memref_i32(int64_t rank,
                                                          void *ptr);
 extern "C" MLIR_RUNNERUTILS_EXPORT void print_memref_i64(int64_t rank,
diff --git a/mlir/integration_test/Dialect/Standard/CPU/bug.mlir b/mlir/integration_test/Dialect/Standard/CPU/bug.mlir
new file mode 100644
--- /dev/null
+++ b/mlir/integration_test/Dialect/Standard/CPU/bug.mlir
@@ -0,0 +1,34 @@
+// RUN: mlir-opt %s -lower-affine -convert-vector-to-llvm -print-ir-after-all | \
+// RUN: mlir-translate -mlir-to-llvmir
+
+// RUN: mlir-opt %s -lower-affine -convert-vector-to-llvm | \
+// RUN: mlir-cpu-runner -e main -entry-point-result=void \
+// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_runner_utils%shlibext
+
+func @main() -> () {
+    %mem = alloca() : memref<3xi1>
+
+    %c0 = constant 0 : index
+    %c1 = constant 1 : index
+    %c2 = constant 2 : index
+
+    %true = constant true
+    %false = constant false
+
+    store %false, %mem[%c0] : memref<3xi1>
+    store %true, %mem[%c1] : memref<3xi1>
+    store %true, %mem[%c2] : memref<3xi1>
+
+    %scalar = load %mem[%c1] : memref<3xi1>
+    vector.print %scalar : i1
+
+    %v = affine.vector_load %mem[0] : memref<3xi1>, vector<3xi1>
+    vector.print %v : vector<3xi1>
+
+    %unranked = memref_cast %mem : memref<3xi1> to memref<*xi1>
+    call @print_memref_i1(%unranked) : (memref<*xi1>) -> ()
+
+    return
+  }
+
+func private @print_memref_i1(%ptr : memref<*xi1>) attributes { llvm.emit_c_interface }
diff --git a/mlir/lib/ExecutionEngine/RunnerUtils.cpp b/mlir/lib/ExecutionEngine/RunnerUtils.cpp
--- a/mlir/lib/ExecutionEngine/RunnerUtils.cpp
+++ b/mlir/lib/ExecutionEngine/RunnerUtils.cpp
@@ -24,6 +24,9 @@
   impl::printMemRef(*M);
 }
 
+extern "C" void _mlir_ciface_print_memref_i1(UnrankedMemRefType<bool> *M) {
+  impl::printMemRef(*M);
+}
 extern "C" void _mlir_ciface_print_memref_i8(UnrankedMemRefType<int8_t> *M) {
   impl::printMemRef(*M);
 }
@@ -44,6 +47,11 @@
   impl::printMemRef(*M);
 }
 
+extern "C" void print_memref_i1(int64_t rank, void *ptr) {
+  UnrankedMemRefType<bool> descriptor = {rank, ptr};
+  _mlir_ciface_print_memref_i1(&descriptor);
+}
+
 extern "C" void print_memref_i32(int64_t rank, void *ptr) {
   UnrankedMemRefType<int32_t> descriptor = {rank, ptr};
   _mlir_ciface_print_memref_i32(&descriptor);