[英]how to avoid copying when using std::transform_reduce(par,…)
[英]How to eliminate intermediate container for parallel std::transform_reduce()?
通常,我必須找到Sum( f(i), 1, N )
或Product( f(i), 1, N )
,其中f(i)
在計算上是 CPU 密集型的,而積分 i 來自順序范圍但很大.
使用 C++20 編譯器,我可以編寫 function:
uint64_t solution(uint64_t N)
{
std::vector<uint64_t> v(N);
std::iota(v.begin(), v.end(), 1ULL);
return std::transform_reduce(
std::execution::par,
v.cbegin(), v.cend(),
0ull,
std::plus<>(),
[]f(const uint64_t& i)->uint64_t {
uint64_t result(0);
// expensive computation of result=f(i) goes here
// ...
return result;
});
}
但這將受到 RAM 的限制。
如何在運行時僅使用 C++20 STL (即沒有特定於供應商的庫或第 3 方庫)完全消除中間 memory 操作與輸入向量,但仍具有高效的並行執行?
免責聲明:我之前沒有實現迭代器或 C++20 的經驗
這似乎對我有用 gcc 10.1 和-std=c++2a
。 我在很短的時間內把它放在一起,沒有花太多心思,所以實現肯定可以改進,如果只是通過模板化它。 如果將operator<=>
替換為舊的雙向比較運算符,這也應該與 C++17 一起運行,但我還沒有測試過。 如果您發現任何錯誤或易於糾正的設計缺陷,歡迎您在下面發表評論,以便改進此答案。
#include <cstddef>
#if __cplusplus > 201703L
#include <compare>
#endif
#include <execution>
#include <iostream>
#include <iterator>
#include <numeric>
class counting_iterator {
public:
typedef std::ptrdiff_t difference_type;
typedef std::ptrdiff_t value_type;
typedef void pointer;
typedef void reference;
typedef std::random_access_iterator_tag iterator_category;
private:
value_type val_{0};
public:
counting_iterator() = default;
explicit counting_iterator(value_type init) noexcept : val_{init} {}
value_type operator*() const noexcept { return val_; }
value_type operator[](difference_type index) const noexcept {
return val_ + index;
}
counting_iterator &operator++() noexcept {
++val_;
return *this;
}
counting_iterator operator++(int) noexcept {
counting_iterator res{*this};
++(*this);
return res;
}
counting_iterator &operator--() noexcept {
--val_;
return *this;
}
counting_iterator operator--(int) noexcept {
counting_iterator res{*this};
--(*this);
return res;
}
friend counting_iterator operator+(counting_iterator const &it,
difference_type const &offset) noexcept;
friend counting_iterator operator+(difference_type const &offset,
counting_iterator const &it) noexcept;
friend counting_iterator operator-(counting_iterator const &it,
difference_type const &offset) noexcept;
friend difference_type operator-(counting_iterator const &a,
counting_iterator const &b) noexcept;
counting_iterator &operator+=(difference_type offset) noexcept {
val_ += offset;
return *this;
}
counting_iterator &operator-=(difference_type offset) noexcept {
val_ -= offset;
return *this;
}
friend bool operator==(counting_iterator const &a,
counting_iterator const &b) noexcept;
#if __cplusplus > 201703L
friend std::strong_ordering operator<=>(counting_iterator const &a,
counting_iterator const &b);
#else
friend bool operator!=(counting_iterator const &a,
counting_iterator const &b) noexcept;
friend bool operator<=(counting_iterator const &a,
counting_iterator const &b) noexcept;
friend bool operator>=(counting_iterator const &a,
counting_iterator const &b) noexcept;
friend bool operator<(counting_iterator const &a,
counting_iterator const &b) noexcept;
friend bool operator>(counting_iterator const &a,
counting_iterator const &b) noexcept;
#endif
};
counting_iterator
operator+(counting_iterator const &it,
counting_iterator::difference_type const &offset) noexcept {
return counting_iterator{it.val_ + offset};
}
counting_iterator operator+(counting_iterator::difference_type const &offset,
counting_iterator const &it) noexcept {
return counting_iterator{it.val_ + offset};
}
counting_iterator
operator-(counting_iterator const &it,
counting_iterator::difference_type const &offset) noexcept {
return counting_iterator{it.val_ - offset};
}
counting_iterator::difference_type
operator-(counting_iterator const &a, counting_iterator const &b) noexcept {
return a.val_ - b.val_;
}
bool operator==(counting_iterator const &a,
counting_iterator const &b) noexcept {
return a.val_ == b.val_;
}
#if __cplusplus > 201703L
std::strong_ordering operator<=>(counting_iterator const &a,
counting_iterator const &b) {
return a.val_ <=> b.val_;
}
#else
bool operator!=(counting_iterator const &a,
counting_iterator const &b) noexcept {
return a.val_ != b.val_;
}
bool operator<=(counting_iterator const &a,
counting_iterator const &b) noexcept {
return a.val_ <= b.val_;
}
bool operator>=(counting_iterator const &a,
counting_iterator const &b) noexcept {
return a.val_ >= b.val_;
}
bool operator<(counting_iterator const &a,
counting_iterator const &b) noexcept {
return a.val_ < b.val_;
}
bool operator>(counting_iterator const &a,
counting_iterator const &b) noexcept {
return a.val_ > b.val_;
}
#endif
int main() {
auto res = std::transform_reduce(
std::execution::par,
counting_iterator(0), counting_iterator(10),
0L,
std::plus<>(),
[](const std::ptrdiff_t& i) { return i * i; });
std::cout << res << std::endl;
}
編輯:我在 class 上工作,使其也可以與 C++17 一起使用。 現在它還顯式地定義了std::random_access_iterator_tag
。 我仍然沒有使用該執行策略進行任何並行計算,無論是使用迭代器還是使用向量,所以我不知道 class 本身是否會抑制並行執行。
經過一些按摩和實驗,我確認雙向迭代器,基於上面 Paul 的示例,已經工作:
class counting_iterator {
public:
using iterator_category = std::bidirectional_iterator_tag;
using difference_type = std::ptrdiff_t;
using value_type = std::ptrdiff_t;
private:
value_type val_;
public:
counting_iterator() : val_(0) {}
explicit counting_iterator(value_type init) : val_(init) {}
value_type operator*() noexcept { return val_; }
const value_type& operator*() const noexcept { return val_; }
counting_iterator& operator++() noexcept { ++val_; return *this; }
counting_iterator operator++(int) noexcept { counting_iterator res{ *this }; ++(*this); return res; }
counting_iterator& operator--() noexcept { --val_; return *this; }
counting_iterator operator--(int) noexcept { counting_iterator res{ *this }; --(*this); return res; }
value_type operator[](difference_type index) noexcept { return val_ + index; }
counting_iterator& operator+=(difference_type offset) noexcept { val_ += offset; return *this; }
counting_iterator& operator-=(difference_type offset) noexcept { val_ -= offset; return *this; }
counting_iterator operator+(difference_type offset) const noexcept { return counting_iterator{ *this } += offset; };
/*counting_iterator& operator+(difference_type offset) noexcept { return operator+=(offset); }*/
counting_iterator operator-(difference_type offset) const noexcept { return counting_iterator{ *this } -= offset; };
/*counting_iterator& operator-(difference_type offset) noexcept { return operator-=(offset); }*/
difference_type operator-(counting_iterator const& other) noexcept { return val_ - other.val_; }
bool operator<(counting_iterator const& b) const noexcept { return val_ < b.val_; }
bool operator==(counting_iterator const& b) const noexcept { return val_ == b.val_; }
bool operator!=(counting_iterator const& b) const noexcept { return !operator==(b); }
std::strong_ordering operator<=>(counting_iterator const& b) const noexcept { return val_ <=> b.val_; }
};
盡管std::transform_reduce
與iterator_category = std::random_access_iterator_tag
並行工作,但我無法使其工作,我相信這是性能下降的原因。
UPD:在上面的代碼中,注釋行使 MS 編譯器選擇它們而不是復制版本替代方案,如果迭代器被標記為 random_access_category_tag,則會在並行執行期間造成嚴重破壞。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.