我正在优化这个功能，我尝试各种方式甚至sse，并修改代码从不同的位置返回以查看计算时间跨度，但最后我发现大部分时间花费在bool判断上。即使我用if中的简单添加操作替换if语句中的所有代码，它仍然需要6000毫秒。
我的平台是gcc 4.7.1 e5506 cpu。它的输入'a'和'b'是一个1000size的int数组，'asize'，'bsize'是相应的数组大小。 MATCH_MASK = 16383，我运行100000次函数来统计一个时间跨度。这个问题有什么好主意吗？谢谢！
if (aoffsets[i] && boffsets[i]) // this line costs most time
代码：
uint16_t aoffsets[DOUBLE_MATCH_MASK] = {0}; // important! or it will only be right on the first time
uint16_t* boffsets = aoffsets + MATCH_MASK;
uint8_t* seen = (uint8_t *)aoffsets;
auto fn_init_offsets = [](const int32_t* x, int n_size, uint16_t offsets[])->void
{
for (int i = 0; i < n_size; ++i)
offsets[MATCH_STRIP(x[i])] = i;
};
fn_init_offsets(a, asize, aoffsets);
fn_init_offsets(b, bsize, boffsets);
uint8_t topcount = 0;
int topoffset = 0;
{
std::vector<uint8_t> count_vec(asize + bsize + 1, 0); // it's the fastest way already, very near to tls
uint8_t* counts = &(count_vec[0]);
//return aoffsets[0]; // cost 1375 ms
for (int i = 0; i < MATCH_MASK; ++i)
{
if (aoffsets[i] && boffsets[i]) // this line costs most time
{
//++affsets[i]; // for test
int offset = (aoffsets[i] -= boffsets[i]);
if ((-n_maxoffset <= offset && offset <= n_maxoffset))
{
offset += bsize;
uint8_t n_cur_count = ++counts[offset];
if (n_cur_count > topcount)
{
topcount = n_cur_count;
topoffset = offset;
}
}
}
}
}
return aoffsets[0]; // cost 6000ms
答案 0 :(得分：4)
首先，memaligned缓冲区的memset(count_vec,0, N);胜过std :: vector 30％。
您可以尝试使用无分支表达式（aoffsets [i] * boffsets [i]）并同时计算一些不使用的表达式：offset = aoffset[i]-boffset[i]; offset+bsize; offset+n_maxoffset;。
根据 offset 的典型范围，可以尝试计算（offset + bsize）的最小值/最大值以限制下一次迭代时所需的memset（count_vec）：无需已清零值。
正如菲利普指出的那样，交错操作是好的 - 然后再次，可以从uint32_t aboffset [N]同时读取aoffset [i]和boffset [i];通过一些聪明的位掩码（生成更改掩码：aoffset [i]，aoffset [i + 1]），可以使用纯c中的64位模拟SIMD并行处理2组（直到直方图累积部分）。
答案 1 :(得分：3)
您可以通过减少缓存未命中来提高程序的速度：aoffsets[i]和boffsets[i]在内存中相对较远。通过将它们放在一起，可以显着加快程序的运行速度。在我的机器上（e5400 cpu，VS2012），执行时间从3.0秒减少到2.3秒：
#include <vector>
#include <windows.h>
#include <iostream>
typedef unsigned short uint16_t;
typedef int int32_t;
typedef unsigned int uint32_t;
typedef unsigned char uint8_t;
#define MATCH_MASK 16383
#define DOUBLE_MATCH_MASK (MATCH_MASK*2)
static const int MATCH_BITS = 14;
static const int MATCH_LEFT = (32 - MATCH_BITS);
#define MATCH_STRIP(x) ((uint32_t)(x) >> MATCH_LEFT)
static const int n_maxoffset = 1000;
uint16_t test(int32_t* a, int asize, int32_t* b, int bsize)
{
uint16_t offsets[DOUBLE_MATCH_MASK] = {0};
auto fn_init_offsets = [](const int32_t* x, int n_size, uint16_t offsets[])->void
{
for (int i = 0; i < n_size; ++i)
offsets[MATCH_STRIP(x[i])*2 /*important. leave space for other offsets*/] = i;
};
fn_init_offsets(a, asize, offsets);
fn_init_offsets(b, bsize, offsets+1);
uint8_t topcount = 0;
int topoffset = 0;
{
std::vector<uint8_t> count_vec(asize + bsize + 1, 0);
uint8_t* counts = &(count_vec[0]);
for (int i = 0; i < MATCH_MASK; i+=2)
{
if (offsets[i] && offsets[i+1])
{
int offset = (offsets[i] - offsets[i+1]); //NOTE: I removed
if ((-n_maxoffset <= offset && offset <= n_maxoffset))
{
offset += bsize;
uint8_t n_cur_count = ++counts[offset];
if (n_cur_count > topcount)
{
topcount = n_cur_count;
topoffset = offset;
}
}
}
}
}
return offsets[0];
}
int main(int argc, char* argv[])
{
const int sizes = 1000;
int32_t* a = new int32_t[sizes];
int32_t* b = new int32_t[sizes];
for (int i=0;i<sizes;i++)
{
a[i] = rand()*rand();
b[i] = rand()*rand();
}
//Variablen
LONGLONG g_Frequency, g_CurentCount, g_LastCount;
QueryPerformanceFrequency((LARGE_INTEGER*)&g_Frequency);
QueryPerformanceCounter((LARGE_INTEGER*)&g_CurentCount);
int sum = 0;
for (int i=0;i<100000;i++)
{
sum += test(a,sizes,b,sizes);
}
QueryPerformanceCounter((LARGE_INTEGER*)&g_LastCount);
double dTimeDiff = (((double)(g_LastCount-g_CurentCount))/((double)g_Frequency));
std::cout << "Result: " << sum << std::endl <<"time: " << dTimeDiff << std::endl;
delete[] a;
delete[] b;
return 0;
}
与您的test()版本进行比较。
#include <vector>
#include <windows.h>
#include <iostream>
typedef unsigned short uint16_t;
typedef int int32_t;
typedef unsigned int uint32_t;
typedef unsigned char uint8_t;
#define MATCH_MASK 16383
#define DOUBLE_MATCH_MASK (MATCH_MASK*2)
static const int MATCH_BITS = 14;
static const int MATCH_LEFT = (32 - MATCH_BITS);
#define MATCH_STRIP(x) ((uint32_t)(x) >> MATCH_LEFT)
static const int n_maxoffset = 1000;
uint16_t test(int32_t* a, int asize, int32_t* b, int bsize)
{
uint16_t aoffsets[DOUBLE_MATCH_MASK] = {0}; // important! or it will only be right on the first time
uint16_t* boffsets = aoffsets + MATCH_MASK;
auto fn_init_offsets = [](const int32_t* x, int n_size, uint16_t offsets[])->void
{
for (int i = 0; i < n_size; ++i)
offsets[MATCH_STRIP(x[i])] = i;
};
fn_init_offsets(a, asize, aoffsets);
fn_init_offsets(b, bsize, boffsets);
uint8_t topcount = 0;
int topoffset = 0;
{
std::vector<uint8_t> count_vec(asize + bsize + 1, 0);
uint8_t* counts = &(count_vec[0]);
for (int i = 0; i < MATCH_MASK; ++i)
{
if (aoffsets[i] && boffsets[i])
{
int offset = (aoffsets[i] - boffsets[i]); //NOTE: I removed the -= because otherwise offset would always be positive!
if ((-n_maxoffset <= offset && offset <= n_maxoffset))
{
offset += bsize;
uint8_t n_cur_count = ++counts[offset];
if (n_cur_count > topcount)
{
topcount = n_cur_count;
topoffset = offset;
}
}
}
}
}
return aoffsets[0];
}
int main(int argc, char* argv[])
{
const int sizes = 1000;
int32_t* a = new int32_t[sizes];
int32_t* b = new int32_t[sizes];
for (int i=0;i<sizes;i++)
{
a[i] = rand()*rand();
b[i] = rand()*rand();
}
LONGLONG g_Frequency, g_CurentCount, g_LastCount;
QueryPerformanceFrequency((LARGE_INTEGER*)&g_Frequency);
QueryPerformanceCounter((LARGE_INTEGER*)&g_CurentCount);
int sum = 0;
for (int i=0;i<100000;i++)
{
sum += test(a,sizes,b,sizes);
}
QueryPerformanceCounter((LARGE_INTEGER*)&g_LastCount);
double dTimeDiff = (((double)(g_LastCount-g_CurentCount))/((double)g_Frequency));
std::cout << "Result: " << sum << std::endl <<"time: " << dTimeDiff << std::endl;
delete[] a;
delete[] b;
return 0;
}