ASSERT_EQ(errors::OK, status_.code()) << status_.message();

  bool transpose_a_vals[] = {false, false, true, true};
  bool transpose_b_vals[] = {false, true, false, true};
  float dA_vals[4][9] = {{24, 15, 6, 24, 15, 6, 24, 15, 6},
                         {18, 15, 12, 18, 15, 12, 18, 15, 12},
                         {24, 24, 24, 15, 15, 15, 6, 6, 6},

    ASSERT_EQ(errors::OK, s.code()) << s.message();
    B.reset(B_raw);
  }

  float expected_dA[4] = {-.5f, 2.0f, -.5f, 2.0f};
  ASSERT_NO_FATAL_FAILURE(CompareNumericalAndManualGradients(
      MatMulModel, ctx_.get(), {A.get(), B.get()}, 0, expected_dA, 4,
      UseFunction()));
}

TEST_P(GradientCheckerTest, TestMul) {
  AbstractTensorHandlePtr x;
  {

                 absl::Span<AbstractTensorHandle*> grad_inputs) override {
    /* Given upstream grad U and a BiasAdd: A + bias, the gradients are:
     *
     *    dA = U
     *    dbias = reduceSum(U, dims = channel_dim)
     */

    AbstractTensorHandle* upstream_grad = grad_outputs[0];
    DCHECK(upstream_grad);

    // Recover data format from forward pass for gradient.

                 absl::Span<AbstractTensorHandle*> grad_inputs) override {
    /* Given upstream grad U and a matmul op A*B, the gradients are:
     *
     *    dA = U * B.T
     *    dB = A.T * U
     *
     *    where A.T means `transpose(A)`
     */
    AbstractTensorHandle* upstream_grad = grad_outputs[0];

    // Get transpose attrs
    bool t_a;

Rawat, Astropeak, Ayush Agrawal, Bairen Yi, Bas Aarts, Bastian Eichenberger, Ben
Barsdell, Benjamin Peterson, bhack, Bharat Raghunathan, Bhavani Subramanian,
Bryan Cutler, candy.dc, Cao Zongyan, Captain-Pool, Casper Da Costa-Luis, Chen
Guoyin, Cheng Chang, chengchingwen, Chong Yan, Choong Yin Thong, Christopher
Yeh, Clayne Robison, Coady, Patrick, Dan Ganea, David Norman, Denis Khalikov,