chromium/third_party/tflite/src/tensorflow/lite/kernels/internal/optimized/integer_ops/fully_connected.h

/* Copyright 2019 The TensorFlow Authors. All Rights Reserved.

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
==============================================================================*/
#ifndef TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_INTEGER_OPS_FULLY_CONNECTED_H_
#define TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_INTEGER_OPS_FULLY_CONNECTED_H_

#include "ruy/profiler/instrumentation.h"  // from @ruy
#include "tensorflow/lite/kernels/cpu_backend_context.h"
#include "tensorflow/lite/kernels/cpu_backend_gemm.h"
#include "tensorflow/lite/kernels/cpu_backend_gemm_params.h"
#include "tensorflow/lite/kernels/internal/common.h"
#include "tensorflow/lite/kernels/internal/compatibility.h"
#include "tensorflow/lite/kernels/internal/reference/integer_ops/fully_connected.h"
#include "tensorflow/lite/kernels/internal/types.h"

namespace tflite {
namespace optimized_integer_ops {

template <typename InputScalar, typename DstScalar>
inline void FullyConnectedPerChannel(
    const FullyConnectedParams& params, const int32_t* output_multiplier,
    const int* output_shift, const RuntimeShape& input_shape,
    const InputScalar* input_data, const RuntimeShape& filter_shape,
    const int8_t* filter_data, const RuntimeShape& bias_shape,
    const int32_t* bias_data, const RuntimeShape& output_shape,
    DstScalar* output_data, CpuBackendContext* cpu_backend_context) { … }

template <typename InputScalar, typename DstScalar>
inline void FullyConnected(
    const FullyConnectedParams& params, const RuntimeShape& input_shape,
    const InputScalar* input_data, const RuntimeShape& filter_shape,
    const int8_t* filter_data, const RuntimeShape& bias_shape,
    const int32_t* bias_data, const RuntimeShape& output_shape,
    DstScalar* output_data, CpuBackendContext* cpu_backend_context) { … }

}  // namespace optimized_integer_ops
}  // namespace tflite

#endif  // TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_INTEGER_OPS_FULLY_CONNECTED_H_