ExecuteAdd(
      /*async=*/false,
      /*forward_input*/ false,
      /*tfrt*/ false);
}
// TODO(b/234067483): Investigate flakiness and re-enable.
TEST(CAPI, DISABLED_ExecuteAddAsync) {
  ExecuteAdd(
      /*async=*/true,
      /*forward_input*/ false,
      /*tfrt*/ false);
}
TEST(CAPI, ExecuteAddForward) {
  ExecuteAdd(
      /*async=*/false,
      /*forward_input*/ true,
      /*tfrt*/ false);
}

    //   |      dz|          |
    //   |        |          |
    //   |     Const_3       |
    //   |                   |
    //   |        ^          |
    //   |       z|          |     // MatMul Forward Graph
    //   |        |          |
    //   |      MatMul       |
    //   |     /       \     |
    //   |    ^         ^    |
    //   |    |         |    |
    //   |---x|        y|----|

#include "tensorflow/c/tf_tensor.h"
#include "tensorflow/c/tf_tstring.h"

// --------------------------------------------------------------------------
// C API for TensorFlow.
//
// The API leans towards simplicity and uniformity instead of convenience
// since most usage will be by language specific wrappers.
//
// Conventions:
// * We use the prefix TF_ for everything in the API.

# This is the same as the official TensorFlow builds.
# See https://developer.nvidia.com/cuda-gpus#compute
# `compute_XY` enables PTX embedding in addition to SASS. PTX
# is forward compatible beyond the current compute capability major
# release while SASS is only forward compatible inside the current
# major release. Example: sm_80 kernels can run on sm_89 GPUs but
# not on sm_90 GPUs. compute_80 kernels though can also run on sm_90 GPUs.