chromium/third_party/tflite/src/tensorflow/lite/kernels/internal/optimized/integer_ops/mul.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_MUL_H_
#define TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_INTEGER_OPS_MUL_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/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/mul.h"
#include "tensorflow/lite/kernels/internal/types.h"

namespace tflite {
namespace optimized_integer_ops {

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

// Broadcast mul that can often be used for inner loop of broadcast Mul.
inline void MulSimpleBroadcast(int size, const ArithmeticParams& params,
                               const int8 broadcast_value,
                               const int8* input2_data, int8* output_data) { … }

inline void Mul(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 BroadcastMulDispatch(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_MUL_H_