ASSERT_EQ(kernel_list.kernel_size(), 1);
  EXPECT_EQ(kernel_list.kernel(0).op(), "TestOpWithSingleKernel");
  EXPECT_EQ(kernel_list.kernel(0).device_type(), "CPU");
  TF_DeleteBuffer(kernel_list_buf);
  TF_DeleteStatus(status);
}

TEST(TestKernel, TestGetRegisteredKernelsForOpNoKernels) {
  TF_Status* status = TF_NewStatus();

  TF_DeleteStatus(s);
  return NULL;
}

// A compute function. This will never actually get called in this test, it's
// just nice to know that it compiles.
void compute(void* kernel, TF_OpKernelContext* ctx) {
  TF_Tensor* input;
  TF_Status* s = TF_NewStatus();
  TF_GetInput(ctx, 0, &input, s);
  TF_DeleteTensor(input);
  TF_DeleteStatus(s);
}

// Exercises tensorflow's C API.

#include "tensorflow/core/framework/cpp_shape_inference.pb.h"
#include "tensorflow/core/framework/full_type.pb.h"
#include "tensorflow/core/framework/kernel_def.pb.h"
#include "tensorflow/core/framework/log_memory.h"
#include "tensorflow/core/framework/node_def_util.h"
#include "tensorflow/core/framework/op_kernel.h"
#include "tensorflow/core/framework/partial_tensor_shape.h"
#include "tensorflow/core/framework/shape_inference.h"

        mean, var = tf.nn.moments(self.kernel, axes=[0, 1, 2], keepdims=True)
        return self.convolution_op(inputs, (self.kernel - mean) / tf.sqrt(var +
        1e-10))` Alternatively, you can override `convolution_op`: `python class
        StandardizedConv2D(tf.keras.Layer): def convolution_op(self, inputs,
        kernel): mean, var = tf.nn.moments(kernel, axes=[0, 1, 2],

build:mkl --define=tensorflow_mkldnn_contraction_kernel=0
build:mkl --define=build_with_openmp=true
build:mkl -c opt

# config to build OneDNN backend with a user specified threadpool.
build:mkl_threadpool --define=build_with_mkl=true --define=enable_mkl=true
build:mkl_threadpool --define=tensorflow_mkldnn_contraction_kernel=0
build:mkl_threadpool --define=build_with_mkl_opensource=true

  // scheduled on that same threadpool, causing a deadlock in cases where the
  // caller of event_mgr->ThenExecute() blocks on the completion of the callback
  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).
  // Setting a larger thread pool does not help with the Swift caller, as we use
  // a different TFE context for each thread of execution (for running graph