// low tolerances
    enable_tensor_float_32_execution(false);
  }

  AbstractContextPtr ctx_;

 public:
  bool UseMlir() const { return strcmp(std::get<0>(GetParam()), "mlir") == 0; }
  bool UseFunction() const { return std::get<2>(GetParam()); }
};

TEST_P(GradientCheckerTest, TestMatMul) {
  float A_vals[] = {1.0f, 2.0f, 3.0f, 4.0f};
  int64_t A_dims[] = {2, 2};
  AbstractTensorHandlePtr A;
  {