62 lines
1.8 KiB
C++
62 lines
1.8 KiB
C++
/* Copyright (c) 2022 PaddlePaddle 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. */
|
|
|
|
#pragma once
|
|
|
|
#include <string>
|
|
|
|
#include "paddle/phi/backends/all_context.h"
|
|
#include "paddle/phi/core/dense_tensor.h"
|
|
|
|
namespace phi {
|
|
namespace funcs {
|
|
|
|
template <typename DeviceContext, typename T>
|
|
class FCFunctor {
|
|
public:
|
|
void operator()(const DeviceContext& dev_ctx,
|
|
const int M,
|
|
const int N,
|
|
const int K,
|
|
const T* X,
|
|
const T* W,
|
|
T* Y,
|
|
const T* B = nullptr,
|
|
bool relu = false,
|
|
bool weight_pass = false);
|
|
};
|
|
|
|
template <typename DeviceContext, typename T>
|
|
class FCInt8Functor {
|
|
public:
|
|
void operator()(const DeviceContext& dev_ctx,
|
|
const int M,
|
|
const int N,
|
|
const int K,
|
|
const T* X,
|
|
const DenseTensor* W,
|
|
T* Y,
|
|
float scale_in,
|
|
std::vector<float> scale_weights,
|
|
int quant_round_type,
|
|
float quant_max_bound,
|
|
float quant_min_bound,
|
|
const T* B = nullptr,
|
|
bool relu = false,
|
|
bool weight_pass = false);
|
|
};
|
|
|
|
} // namespace funcs
|
|
} // namespace phi
|