wehub-resource-sync
48 lines
1.5 KiB
C++
48 lines
1.5 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 <algorithm>
|
|
|
|
#include "paddle/common/hostdevice.h"
|
|
#include "paddle/phi/backends/gpu/gpu_context.h"
|
|
#include "paddle/phi/backends/gpu/gpu_helper.h"
|
|
#include "paddle/phi/core/kernel_registry.h"
|
|
#include "paddle/phi/core/tensor_utils.h"
|
|
#include "paddle/phi/kernels/funcs/cub.h"
|
|
#include "paddle/phi/kernels/funcs/elementwise_base.h"
|
|
#include "paddle/phi/kernels/funcs/math.h"
|
|
#include "paddle/phi/kernels/gpu/reduce.h"
|
|
|
|
namespace phi {
|
|
|
|
static constexpr int kNumCUDAThreads = 512;
|
|
static constexpr int kNumMaximumNumBlocks = 4096;
|
|
|
|
static inline int NumBlocks(const int N) {
|
|
return std::min((N + kNumCUDAThreads - 1) / kNumCUDAThreads,
|
|
kNumMaximumNumBlocks);
|
|
}
|
|
|
|
template <typename T>
|
|
struct NonzeroFunctor {
|
|
HOSTDEVICE explicit inline NonzeroFunctor() {}
|
|
HOSTDEVICE inline T operator()(const T x) const {
|
|
return static_cast<T>(static_cast<double>(x) != 0);
|
|
}
|
|
};
|
|
|
|
} // namespace phi
|