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

/* Copyright 2020 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_BATCH_MATMUL_H_
#define TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_BATCH_MATMUL_H_

#include "tensorflow/lite/core/c/common.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/tensor_utils.h"
#include "tensorflow/lite/kernels/internal/types.h"

namespace tflite {
namespace optimized_ops {

inline void BatchMatMul(const RuntimeShape& lhs_shape, const float* lhs_data,
                        const RuntimeShape& rhs_shape, const float* rhs_data,
                        const RuntimeShape& output_shape, float* output_data,
                        CpuBackendContext* context,
                        bool transpose_lhs = false) { … }

inline void BatchMatMul(const RuntimeShape& lhs_shape, const int8_t* lhs_data,
                        const RuntimeShape& rhs_shape, const int8_t* rhs_data,
                        const float* scaling_factors,
                        const int32_t* input_offset, int32_t* row_sums,
                        const RuntimeShape& output_shape,
                        int32_t* accum_scratch, float* output_data,
                        bool* compute_row_sums, CpuBackendContext* context) { … }

inline void BatchMatMul(const FullyConnectedParams& params,
                        const RuntimeShape& lhs_shape, const int8_t* lhs_data,
                        const RuntimeShape& rhs_shape, const int8_t* rhs_data,
                        const RuntimeShape& output_shape, int8_t* output_data,
                        CpuBackendContext* context,
                        bool transpose_lhs = false) { … }

inline void BatchMatMul(const FullyConnectedParams& params,
                        const RuntimeShape& lhs_shape, const int8_t* lhs_data,
                        const RuntimeShape& rhs_shape, const int8_t* rhs_data,
                        const RuntimeShape& output_shape, int32_t* output_data,
                        CpuBackendContext* context,
                        bool transpose_lhs = false) { … }

}  // namespace optimized_ops
}  // namespace tflite

#endif  // TENSORFLOW_LITE_KERNELS_INTERNAL_OPTIMIZED_BATCH_MATMUL_H_