[mlir] [VectorOps] Add create mask integration tests

[aartbik]

Summary

Two integration tests focused on i1 vectors, which exposed omissions
in the llvm backend which have since then been fixed. Note that this also
exposed an inaccuracy for print_i1 which has been fixed in this CL:
for a pure C ABI, int should be used rather than bool.

[bkramer]

I'm a bit worried that we now call a function taking an int with an i1 argument. This probably works because the x86 ABI passes it in a big register anyways, but it's technically undefined behavior. Can we make this int32 and call it with i32? This is fine for a followup.

[aartbik]

In D81957#2098497, @bkramer wrote:

I'm a bit worried that we now call a function taking an int with an i1 argument. This probably works because the x86 ABI passes it in a big register anyways, but it's technically undefined behavior. Can we make this int32 and call it with i32? This is fine for a followup.

It was my understanding that calling from C++ ABI with i1, i.e. bool, to C ABI using int is correct. But if you are worried we can indeed fix this in a follow up by letting the vector.print lowering part force it into a int32 and use that instead as parameter.

mlir/include/mlir/ExecutionEngine/CRunnerUtils.h

public:
   int64_t offset;
   const int64_t *sizes;
   const int64_t *strides;
 };
 
 //===----------------------------------------------------------------------===//
 // Small runtime support "lib" for vector.print lowering during codegen.
 //===----------------------------------------------------------------------===//
-extern "C" MLIR_CRUNNERUTILS_EXPORT void print_i1(bool b);
+extern "C" MLIR_CRUNNERUTILS_EXPORT void print_i1(int b);
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_i32(int32_t i);
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_i64(int64_t l);
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_f32(float f);
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_f64(double d);
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_open();
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_close();
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_comma();
 extern "C" MLIR_CRUNNERUTILS_EXPORT void print_newline();
 
 #endif // EXECUTIONENGINE_CRUNNERUTILS_H_
 

mlir/integration_test/Dialect/Vector/CPU/test-create-mask-v4i1.mlir

+// RUN: mlir-opt %s -convert-scf-to-std -convert-vector-to-llvm -convert-std-to-llvm | \
+// RUN: mlir-cpu-runner -e entry -entry-point-result=void  \
+// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+
+// NOTE: This is similar to test-create-mask.mlir, but with a different length,
+//       because the v4i1 vector specifially exposed bugs in the LLVM backend.
+
+func @entry() {
+  %c0 = constant 0 : index
+  %c1 = constant 1 : index
+  %c2 = constant 2 : index
+  %c3 = constant 3 : index
+  %c5 = constant 5 : index
+
+  //
+  // 1-D.
+  //
+
+  %1 = vector.create_mask %c2 : vector<4xi1>
+  vector.print %1 : vector<4xi1>
+  // CHECK: ( 1, 1, 0, 0 )
+
+  scf.for %i = %c0 to %c5 step %c1 {
+    %2 = vector.create_mask %i : vector<4xi1>
+    vector.print %2 : vector<4xi1>
+  }
+  // CHECK: ( 0, 0, 0, 0 )
+  // CHECK: ( 1, 0, 0, 0 )
+  // CHECK: ( 1, 1, 0, 0 )
+  // CHECK: ( 1, 1, 1, 0 )
+  // CHECK: ( 1, 1, 1, 1 )
+
+  //
+  // 2-D.
+  //
+
+  %3 = vector.create_mask %c2, %c3 : vector<4x4xi1>
+  vector.print %3 : vector<4x4xi1>
+  // CHECK: ( ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+
+  %4 = vector.create_mask %c3, %c2 : vector<4x4xi1>
+  vector.print %4 : vector<4x4xi1>
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ) )
+
+  scf.for %i = %c0 to %c5 step %c1 {
+    %5 = vector.create_mask %c2, %i : vector<4x4xi1>
+    vector.print %5 : vector<4x4xi1>
+  }
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0 ), ( 1, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1 ), ( 1, 1, 1, 1 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+
+  scf.for %i = %c0 to %c5 step %c1 {
+    %6 = vector.create_mask %i, %c2 : vector<4x4xi1>
+    vector.print %6 : vector<4x4xi1>
+  }
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ) )
+
+  scf.for %i = %c0 to %c5 step %c1 {
+    scf.for %j = %c0 to %c5 step %c1 {
+      %7 = vector.create_mask %i, %j : vector<4x4xi1>
+      vector.print %7 : vector<4x4xi1>
+    }
+  }
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0 ), ( 1, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1 ), ( 1, 1, 1, 1 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0 ), ( 1, 0, 0, 0 ), ( 1, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1 ), ( 1, 1, 1, 1 ), ( 1, 1, 1, 1 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ), ( 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0 ), ( 1, 0, 0, 0 ), ( 1, 0, 0, 0 ), ( 1, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ), ( 1, 1, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ), ( 1, 1, 1, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1 ), ( 1, 1, 1, 1 ), ( 1, 1, 1, 1 ), ( 1, 1, 1, 1 ) )
+
+  return
+}

mlir/integration_test/Dialect/Vector/CPU/test-create-mask.mlir

+// RUN: mlir-opt %s -convert-scf-to-std -convert-vector-to-llvm -convert-std-to-llvm | \
+// RUN: mlir-cpu-runner -e entry -entry-point-result=void  \
+// RUN:   -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
+// RUN: FileCheck %s
+
+func @entry() {
+  %c0 = constant 0 : index
+  %c1 = constant 1 : index
+  %c2 = constant 2 : index
+  %c3 = constant 3 : index
+  %c6 = constant 6 : index
+
+  //
+  // 1-D.
+  //
+
+  %1 = vector.create_mask %c2 : vector<5xi1>
+  vector.print %1 : vector<5xi1>
+  // CHECK: ( 1, 1, 0, 0, 0 )
+
+  scf.for %i = %c0 to %c6 step %c1 {
+    %2 = vector.create_mask %i : vector<5xi1>
+    vector.print %2 : vector<5xi1>
+  }
+  // CHECK: ( 0, 0, 0, 0, 0 )
+  // CHECK: ( 1, 0, 0, 0, 0 )
+  // CHECK: ( 1, 1, 0, 0, 0 )
+  // CHECK: ( 1, 1, 1, 0, 0 )
+  // CHECK: ( 1, 1, 1, 1, 0 )
+  // CHECK: ( 1, 1, 1, 1, 1 )
+
+  //
+  // 2-D.
+  //
+
+  %3 = vector.create_mask %c2, %c3 : vector<5x5xi1>
+  vector.print %3 : vector<5x5xi1>
+  // CHECK: ( ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+
+  %4 = vector.create_mask %c3, %c2 : vector<5x5xi1>
+  vector.print %4 : vector<5x5xi1>
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+
+  scf.for %i = %c0 to %c6 step %c1 {
+    %5 = vector.create_mask %c2, %i : vector<5x5xi1>
+    vector.print %5 : vector<5x5xi1>
+  }
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+
+  scf.for %i = %c0 to %c6 step %c1 {
+    %6 = vector.create_mask %i, %c2 : vector<5x5xi1>
+    vector.print %6 : vector<5x5xi1>
+  }
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ) )
+
+  scf.for %i = %c0 to %c6 step %c1 {
+    scf.for %j = %c0 to %c6 step %c1 {
+      %7 = vector.create_mask %i, %j : vector<5x5xi1>
+      vector.print %7 : vector<5x5xi1>
+    }
+  }
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 1 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ), ( 0, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ), ( 1, 0, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ), ( 1, 1, 0, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ), ( 1, 1, 1, 0, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ), ( 1, 1, 1, 1, 0 ) )
+  // CHECK: ( ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ), ( 1, 1, 1, 1, 1 ) )
+
+  return
+}

mlir/lib/ExecutionEngine/CRunnerUtils.cpp

 #include <cstdio>
 
 #ifdef MLIR_CRUNNERUTILS_DEFINE_FUNCTIONS
 
 // Small runtime support "lib" for vector.print lowering.
 // By providing elementary printing methods only, this
 // library can remain fully unaware of low-level implementation
 // details of our vectors. Also useful for direct LLVM IR output.
-extern "C" void print_i1(bool b) { fputc(b ? '1' : '0', stdout); }
+extern "C" void print_i1(int b) { fputc(b ? '1' : '0', stdout); }
 extern "C" void print_i32(int32_t i) { fprintf(stdout, "%" PRId32, i); }
 extern "C" void print_i64(int64_t l) { fprintf(stdout, "%" PRId64, l); }
 extern "C" void print_f32(float f) { fprintf(stdout, "%g", f); }
 extern "C" void print_f64(double d) { fprintf(stdout, "%lg", d); }
 extern "C" void print_open() { fputs("( ", stdout); }
 extern "C" void print_close() { fputs(" )", stdout); }
 extern "C" void print_comma() { fputs(", ", stdout); }
 extern "C" void print_newline() { fputc('\n', stdout); }
 
 #endif