%0 = func.call @func_0_CPU_QUANTIZED_INT8(%arg0, %arg1, %arg2) {tac.device = "CPU", tac.inference_type = "QUANTIZED_INT8", tac.interface_name = "func_0"} : (tensor<100x!quant.uniform<i8:f32, 2.000000e-01:-3>>,...

}

func.func @not_modified(%arg0: tensor<f32>, %arg1: tensor<1x224x224x3xf32>) -> (tensor<1x401408xf32>, tensor<1x224x224x3xf32>) attributes {tf.entry_function = {control_outputs = "", inputs = "input0,input1", outputs = "output0,output1"}} {
  %cst = arith.constant dense<[1, 401408]> : tensor<2xi32>

  func.func @gather_with_float_output(%arg0: tensor<1x3x2x1024xf32> {tf_saved_model.index_path = ["input1"]}, %arg1: tensor<1xi32> {tf_saved_model.index_path = ["input2"]}) -> (tensor<1x3x1x1xf32> {tf_saved_model.index_path = ["output"]}) attributes {tf.entry_function = {control_outputs = "", inputs = "serving_default_input:0", outputs = "PartitionedCall:0"}, tf_saved_model.exported_names = ["serving_default"]} {

					// it must find at least one space to consume.
					if !isSpace(inputc) && inputc != eof {
						s.errorString("expected space in input to match format")
					}
					if inputc == '\n' {
						s.errorString("newline in input does not match format")
					}
				}
				for isSpace(inputc) && inputc != '\n' {
					inputc = s.getRune()
				}
				if inputc != eof {
					s.UnreadRune()
				}
			}
			continue

		if input.limit > remaining {
			input.limit = remaining
		}
	}
	return input, true
}

// sentInput updates internal counters after an input is sent to c.inputC.
func (c *coordinator) sentInput(input fuzzInput) {
	c.inputQueue.dequeue()
	c.countWaiting += input.limit
}

// refillInputQueue refills the input queue from the corpus after it becomes
// empty.

is used instead.

Operands are replicated inputs and packed inputs.

replicated_inputs: each group of `n` inputs corresponds to an input for a single
individual replica and is mapped to a single region argument. Inside one group
the operands are matching in order the `devices` attribute. Each replicated
input must have compatible shapes and types.
packed_inputs: each input corresponds to an input broadcasted across all

        }
        if (TF::TPUReplicatedInputOp input =
                llvm::dyn_cast<TF::TPUReplicatedInputOp>(user)) {
          if (!input.getIsPacked()) {
            input.emitOpError() << "unexpected variable input, not packed";
            return LogicalResult::failure();
          }

          if (is_variable) {
            input.emitOpError() << "unexpected multiple TPUReplicatedInputOp "

      arg.kind = XlaCompiler::Argument::kConstant;
      arg.type = input->dtype();
      arg.shape = input->shape();
      arg.constant_value = *input;
    } else {
      // Normal inputs.
      TF_RET_CHECK(input->dtype() != DT_RESOURCE);
      if (input->NumElements() > 0) {
        arg.kind = XlaCompiler::Argument::kParameter;
      } else {

    rep.emitOpError(
        "TF2XLA TPU bridge input check: packed with number of inputs not 1.")
        << " num_replicas=" << num_replicas << " no. of inputs=" << arity;
    return false;
  } else if (!rep.getIsPacked() && arity != num_replicas) {
    rep.emitOpError(
        "TF2XLA TPU bridge input check: number of inputs inconsistent.")
        << " num_replicas=" << num_replicas << " no. of inputs=" << arity;
    return false;
  }

[[implementation_unknown]]
== Cannot use an input with an unknown implementation

This error indicates that a task uses a class as an input and Gradle cannot track the implementation of the class.
Gradle considers the implementation of the following classes as inputs to a task:

- the task class,
- the classes of the actions of the task,
- and the classes of nested inputs of the task, i.e. inputs annotated with `@Nested`.