我需要对元组数组进行排序,因此我为元组定义一个运算符并使用 thrust::sort
进行排序。
所以我发现对元组数组进行排序比对数字数组进行排序要慢得多。这是我的代码:
#include <thrust/device_vector.h>
#include <thrust/host_vector.h>
#include <thrust/set_operations.h>
#include <thrust/reduce.h>
#include <thrust/unique.h>
#include <thrust/binary_search.h>
#include <thrust/gather.h>
#include <thrust/transform.h>
#include <thrust/functional.h>
#include <thrust/sort.h>
#include <thrust/execution_policy.h>
#include <iostream>
static const int size = 100000;
#define mzi(x) thrust::make_zip_iterator(x)
#define mt(...) thrust::make_tuple(__VA_ARGS__)
typedef thrust::tuple<int, int> IntTuple;
typedef thrust::device_vector<IntTuple>::iterator TupleIterator;
typedef thrust::device_vector<int>::iterator IntIterator;
typedef thrust::tuple<IntIterator, IntIterator> IteratorTuple;
typedef thrust::zip_iterator<IteratorTuple> ZipIterator;
struct TupleComp
{
__host__ __device__
bool operator()(const IntTuple& t1, const IntTuple& t2)
{
return t1.get<0>() != t2.get<0>() ? t1.get<0>() < t2.get<0>() : t1.get<1>() > t2.get<1>();
}
};
int main()
{
timespec start;
clock_gettime(0, &start);
thrust::device_vector<int> dataA1(size);
thrust::device_vector<int> dataA2(size);
thrust::device_vector<int> dataB1(size);
thrust::device_vector<int> dataB2(size);
srand(time(NULL));
for (int i = 0; i < size; i++)
{
//dataA[i] = dataA[i - 1] + (rand() % 100);
dataA1[i] = (rand() % 100);
dataA2[i] = (rand() % 100);
dataB1[i] = (rand() % 100);
dataB2[i] = (rand() % 100);
std::cout << dataA1[i] << "\t" << dataA2[i] << "\t" << dataB1[i] << "\t" << dataB2[i];
std::cout << std::endl;
}
timespec end;
clock_gettime(0, &end);
std::cout << "gendb took: " << end.tv_sec - start.tv_sec << "s" << end.tv_nsec - start.tv_nsec << "ns" << std::endl;
ZipIterator beginA = mzi(mt(dataA1.begin(), dataA2.begin()));
ZipIterator beginB = mzi(mt(dataB1.begin(), dataB2.begin()));
ZipIterator endA = mzi(mt(dataA1.end(), dataA2.end()));
ZipIterator endB = mzi(mt(dataB1.end(), dataB2.end()));
thrust::device_vector<IntTuple> A(size);
thrust::device_vector<IntTuple> B(size);
clock_gettime(0, &start);
thrust::copy(beginA, endA, A.begin());
thrust::copy(beginB, endB, B.begin());
clock_gettime(0, &end);
std::cout << "thrust::copy took: " << end.tv_sec - start.tv_sec << "s" << end.tv_nsec - start.tv_nsec << "ns" << std::endl;
clock_gettime(0, &start);
thrust::sort(A.begin(), A.end());
clock_gettime(0, &end);
std::cout << "A thrust::sort took: " << end.tv_sec - start.tv_sec << "s" << end.tv_nsec - start.tv_nsec << "ns" << std::endl;
clock_gettime(0, &start);
thrust::sort(B.begin(), B.end(), TupleComp());
clock_gettime(0, &end);
std::cout << "B thrust::sort took: " << end.tv_sec - start.tv_sec << "s" << end.tv_nsec - start.tv_nsec << "ns" << std::endl;
clock_gettime(0, &start);
thrust::sort(dataA1.begin(), dataA1.end());
clock_gettime(0, &end);
std::cout << "regular thrust::sort took: " << end.tv_sec - start.tv_sec << "s" << end.tv_nsec - start.tv_nsec << "ns" << std::endl;
clock_gettime(0, &start);
thrust::sort(beginA, endA, TupleComp());
thrust::sort(beginB, endB, TupleComp());
clock_gettime(0, &end);
std::cout << "thrust::sort took: " << end.tv_sec - start.tv_sec << "s" << end.tv_nsec - start.tv_nsec << "ns" << std::endl;
}
我发现元组排序比常规排序慢~10X倍。
我不明白为什么。推力中排序的复杂度是否直接受操作符影响?尽管如此,我的运算符并不比常规比较器慢 10 倍。
注意: 它不只是慢了 10 倍: 对于 100000 来说,速度慢了约 10 倍 对于 1000000 来说,速度慢了约 20 倍
我还发现,将两个数组复制到元组数组中并对该数组进行排序大约快 150%,而 Thrust::copy 几乎不需要任何操作(1M 需要 0.3)。
注2:
我将运算符更改为:
struct TupleComp
{
__host__ __device__
bool operator()(const IntTuple& t1, const IntTuple& t2)
{
if(t1.get<0>() < t2.get<0>())
return true;
if(t1.get<0>() > t2.get<0>())
return false;
return t1.get<1>() > t2.get<1>();
}
};
现在排序速度快了大约 112.5%,这可能是因为第一个值上的 equals
很少发生,这样就需要检查更少的 if
一般在运算符中。
最佳答案
抱歉,Nsight 完全让我困惑,一直以来我都相信自己处于 Release模式,但它本身的运行配置被设置为运行 Debug模式。
现在我已经确保一切都准备好发布,而且效果好多了。
整型排序和元组排序之间的差异仅约 150%,这更有意义。不确定我还能做些什么来提高性能,但它已经足够好了。
结论是:要小心 Eclipse 首选项,尤其是在 Linux 上。
关于c++ - 元组上的推力排序非常慢,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/21109582/