}
	globalCtx, globalSpan := Start(ctx, rootSpan)
	return globalCtx, func() {
		globalSpan.End()
		shutdown()
	}, nil
}

func Start(ctx context.Context, span string) (context.Context, traceapi.Span) {
	return tracer().Start(ctx, span)

            if (progressPredicate.isSatisfiedBy(op)) {
                op.progress.each { p ->
                    def repr = p.hasDetailsOfType(StyledTextOutputEvent) ? p.details.spans*.text.join('') : "$p.detailsType.simpleName ${p.details?.toString() ?: ''}\n"
                    print "${'  ' * (level + 1)} $repr"
                }
            }

  virtual Status SetDeviceName(const char* name) = 0;

  virtual Status AddInput(AbstractTensorHandle* input) = 0;
  virtual Status AddInputList(
      absl::Span<AbstractTensorHandle* const> inputs) = 0;
  virtual Status Execute(absl::Span<AbstractTensorHandle*> retvals,
                         int* num_retvals) = 0;

  virtual Status SetAttrString(const char* attr_name, const char* data,

<div class="badge-wrapper">
    <a class="badge" href="https://dpeuniversity.gradle.com/app/courses/012de84f-fcd3-45d4-9c4c-284382eb3f3f/" target="_blank">
        <span class="badge-type button--blue">LEARN</span>
        <span class="badge-text">Introduction to Gradle for Developers&nbsp;&nbsp;&nbsp;&gt;</span>
    </a>
</div>
++++

Everyone has to start somewhere, and if you're new to Gradle, this is where to begin.

To get started using Gradle:

#include "tensorflow/c/experimental/gradients/not_differentiable.h"

namespace tensorflow {
namespace gradients {
Status NotDifferentiableGradientFunction::Compute(
    AbstractContext* ctx, absl::Span<AbstractTensorHandle* const> grad_outputs,
    absl::Span<AbstractTensorHandle*> grad_inputs) {
  for (int i = 0; i < grad_inputs.size(); i++) {
    grad_inputs[i] = nullptr;
  }
  return absl::OkStatus();
}

class NotDifferentiableGradientFunction : public GradientFunction {
  Status Compute(AbstractContext* ctx,
                 absl::Span<AbstractTensorHandle* const> grad_outputs,
                 absl::Span<AbstractTensorHandle*> grad_inputs) override;
};
// Shorthand for registry->Register(op, new NotDifferentiableGradientFunction)

string ArgTypeView::TypeName() const {
  if (arg_type_.is_read_only()) {
    if (arg_type_.is_list()) {
      return "absl::Span<AbstractTensorHandle* const>";
    } else {
      return "AbstractTensorHandle* const";
    }
  } else {
    if (arg_type_.is_list()) {
      return "absl::Span<AbstractTensorHandle*>";
    } else {
      return "AbstractTensorHandle**";
    }
  }
}

}  // namespace cpp

  std::optional<AttrKeyValuePair> attr_;
};

::testing::Matcher<const Node*> NodeWith(
    absl::Span<const NodeMatcherProperties> props);

impl::NodeMatcherProperties Inputs(
    absl::Span<const ::testing::Matcher<OutEdge>> inputs);

impl::NodeMatcherProperties CtrlDeps(
    absl::Span<const ::testing::Matcher<const Node*>> control_deps);

impl::NodeMatcherProperties Attr(std::pair<string, AttrValue> attrs);

  // XlaCompilationResult pointed to by `result`.
  virtual Status Compile(const XlaCompiler::CompileOptions& options,
                         const NameAttrList& function,
                         absl::Span<const XlaArgument> args,
                         XlaCompilationResult* result) = 0;

  // Compiles a Tensorflow single op to an HloModuleProto stored in the
  // XlaCompilationResult pointed to by `result`.

==============================================================================*/
#ifndef TENSORFLOW_C_EAGER_GRADIENT_CHECKER_H_
#define TENSORFLOW_C_EAGER_GRADIENT_CHECKER_H_

#include <memory>

#include "absl/types/span.h"
#include "tensorflow/c/eager/abstract_tensor_handle.h"
#include "tensorflow/c/eager/unified_api_testutil.h"

namespace tensorflow {
namespace gradients {