chromium/third_party/tflite/src/tensorflow/lite/kernels/internal/optimized/integer_ops/add.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_ADD_H_
#define TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_INTEGER_OPS_ADD_H_

#include <algorithm>

#include "fixedpoint/fixedpoint.h"
#include "ruy/profiler/instrumentation.h"  // from @ruy
#include "tensorflow/lite/kernels/internal/common.h"
#include "tensorflow/lite/kernels/internal/compatibility.h"
#include "tensorflow/lite/kernels/internal/optimized/avx2_quantization_utils.h"
#include "tensorflow/lite/kernels/internal/optimized/cpu_check.h"
#include "tensorflow/lite/kernels/internal/optimized/neon_check.h"
#include "tensorflow/lite/kernels/internal/optimized/optimized_ops.h"
#include "tensorflow/lite/kernels/internal/reference/integer_ops/add.h"
#include "tensorflow/lite/kernels/internal/types.h"

namespace tflite {
namespace optimized_integer_ops {

// Element-wise add that can often be used for inner loop of broadcast add as
// well as the non-broadcast add.
inline void AddElementwiseInt8(int size, const ArithmeticParams& params,
                               const int8* input1_data, const int8* input2_data,
                               int8* output_data) {}

// Element-wise add is used for the non-broadcast add.
inline void AddElementwiseInt16(int size, const ArithmeticParams& params,
                                const int16* input1_data,
                                const int16* input2_data, int16* output_data) {}

// Scalar-broadcast add that can be used for inner loop of more general
// broadcast add, so that, for example, scalar-broadcast with batch will still
// be fast.
inline void AddScalarBroadcast(int size, const ArithmeticParams& params,
                               int8 input1_data, const int8* input2_data,
                               int8* output_data) {}

inline void Add(const ArithmeticParams& params,
                const RuntimeShape& input1_shape, const int8* input1_data,
                const RuntimeShape& input2_shape, const int8* input2_data,
                const RuntimeShape& output_shape, int8* output_data) {}

inline void Add(const ArithmeticParams& params,
                const RuntimeShape& input1_shape, const int16* input1_data,
                const RuntimeShape& input2_shape, const int16* input2_data,
                const RuntimeShape& output_shape, int16* output_data) {}

inline void BroadcastAddDispatch(const ArithmeticParams& params,
                                 const RuntimeShape& input1_shape,
                                 const int8* input1_data,
                                 const RuntimeShape& input2_shape,
                                 const int8* input2_data,
                                 const RuntimeShape& output_shape,
                                 int8* output_data) {}

}  // namespace optimized_integer_ops
}  // namespace tflite

#endif  // TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_INTEGER_OPS_ADD_H_