C++ 为什么元素添加在单独循环中比在组合循环中快得多?
假设C++ 为什么元素添加在单独循环中比在组合循环中快得多?,c++,performance,x86,vectorization,compiler-optimization,C++,Performance,X86,Vectorization,Compiler Optimization,假设a1,b1,c1和d1指向堆内存,我的数字代码有以下核心循环 const int n = 100000; for (int j = 0; j < n; j++) { a1[j] += b1[j]; c1[j] += d1[j]; } 在MS上编译并进行完全优化,在Duo(x64)上启用32位,第一个示例需要5.5秒,而双循环示例只需要1.9秒。我的问题是:(请参考我在底部重新表述的问题) PS:我不确定这是否有帮助: 第一个循环的反汇编基本上如下所示(该块在整个程序
a1
,b1
,c1
和d1
指向堆内存,我的数字代码有以下核心循环
const int n = 100000;
for (int j = 0; j < n; j++) {
a1[j] += b1[j];
c1[j] += d1[j];
}
在MS上编译并进行完全优化,在Duo(x64)上启用32位,第一个示例需要5.5秒,而双循环示例只需要1.9秒。我的问题是:(请参考我在底部重新表述的问题)
PS:我不确定这是否有帮助:
第一个循环的反汇编基本上如下所示(该块在整个程序中重复大约五次):
双循环示例的每个循环都会生成此代码(以下代码块重复大约三次):
这个问题与此无关,因为行为严重依赖于阵列(n)和CPU缓存的大小。因此,如果有进一步的兴趣,我将重新表述这个问题:
您能否深入了解导致不同缓存行为的细节,如下图中的五个区域所示?
通过为这些CPU提供类似的图表,指出CPU/缓存体系结构之间的差异也可能是有趣的。
PPS:这是完整的代码。它使用Tick_Count
进行更高分辨率的计时,可以通过不定义TBB_计时
宏来禁用:
#include <iostream>
#include <iomanip>
#include <cmath>
#include <string>
//#define TBB_TIMING
#ifdef TBB_TIMING
#include <tbb/tick_count.h>
using tbb::tick_count;
#else
#include <time.h>
#endif
using namespace std;
//#define preallocate_memory new_cont
enum { new_cont, new_sep };
double *a1, *b1, *c1, *d1;
void allo(int cont, int n)
{
switch(cont) {
case new_cont:
a1 = new double[n*4];
b1 = a1 + n;
c1 = b1 + n;
d1 = c1 + n;
break;
case new_sep:
a1 = new double[n];
b1 = new double[n];
c1 = new double[n];
d1 = new double[n];
break;
}
for (int i = 0; i < n; i++) {
a1[i] = 1.0;
d1[i] = 1.0;
c1[i] = 1.0;
b1[i] = 1.0;
}
}
void ff(int cont)
{
switch(cont){
case new_sep:
delete[] b1;
delete[] c1;
delete[] d1;
case new_cont:
delete[] a1;
}
}
double plain(int n, int m, int cont, int loops)
{
#ifndef preallocate_memory
allo(cont,n);
#endif
#ifdef TBB_TIMING
tick_count t0 = tick_count::now();
#else
clock_t start = clock();
#endif
if (loops == 1) {
for (int i = 0; i < m; i++) {
for (int j = 0; j < n; j++){
a1[j] += b1[j];
c1[j] += d1[j];
}
}
} else {
for (int i = 0; i < m; i++) {
for (int j = 0; j < n; j++) {
a1[j] += b1[j];
}
for (int j = 0; j < n; j++) {
c1[j] += d1[j];
}
}
}
double ret;
#ifdef TBB_TIMING
tick_count t1 = tick_count::now();
ret = 2.0*double(n)*double(m)/(t1-t0).seconds();
#else
clock_t end = clock();
ret = 2.0*double(n)*double(m)/(double)(end - start) *double(CLOCKS_PER_SEC);
#endif
#ifndef preallocate_memory
ff(cont);
#endif
return ret;
}
void main()
{
freopen("C:\\test.csv", "w", stdout);
char *s = " ";
string na[2] ={"new_cont", "new_sep"};
cout << "n";
for (int j = 0; j < 2; j++)
for (int i = 1; i <= 2; i++)
#ifdef preallocate_memory
cout << s << i << "_loops_" << na[preallocate_memory];
#else
cout << s << i << "_loops_" << na[j];
#endif
cout << endl;
long long nmax = 1000000;
#ifdef preallocate_memory
allo(preallocate_memory, nmax);
#endif
for (long long n = 1L; n < nmax; n = max(n+1, long long(n*1.2)))
{
const long long m = 10000000/n;
cout << n;
for (int j = 0; j < 2; j++)
for (int i = 1; i <= 2; i++)
cout << s << plain(n, m, j, i);
cout << endl;
}
}
#包括
#包括
#包括
#包括
//#定义TBB_定时
#ifdef TBB_定时
#包括
使用tbb::勾选计数;
#否则
#包括
#恩迪夫
使用名称空间std;
//#定义预分配\u内存新建\u cont
枚举{new_cont,new_sep};
双*a1、*b1、*c1、*d1;
无效分配(内部控制,内部n)
{
开关(续){
新个案(续)
a1=新的双精度[n*4];
b1=a1+n;
c1=b1+n;
d1=c1+n;
打破
新个案(九月)
a1=新的双精度[n];
b1=新的双精度[n];
c1=新的双精度[n];
d1=新的双精度[n];
打破
}
对于(int i=0;i cout第二个循环涉及的缓存活动要少得多,因此处理器更容易满足内存需求。这不是因为不同的代码,而是因为缓存:RAM比CPU寄存器慢,CPU内部有一个缓存,以避免每次变量更改时都写入RAM。但是缓存是RAM并没有那么大,因此,它只映射了它的一小部分
第一个代码在每个循环中交替修改远程内存地址,因此需要不断地使缓存失效
第二个代码不是交替的:它只是在相邻地址上流动两次。这使得所有的作业都在缓存中完成,只有在第二个循环开始后才会使其无效。这是因为CPU没有太多缓存未命中(它必须等待阵列数据来自RAM芯片)。您有兴趣不断调整数组的大小,使其超过CPU的大小(L1),然后是大小(L2),并根据数组的大小绘制代码执行所需的时间。图形不应像您预期的那样是一条直线。进一步分析后,我相信这是正确的(至少部分)由四个指针的数据对齐引起。这将导致某些级别的缓存组/路径冲突
如果我猜对了数组的分配方式,那么它们很可能与页面行对齐
这意味着每个循环中的所有访问都将落在相同的缓存方式上。然而,英特尔处理器已经有一段时间具有8路一级缓存关联性。但实际上,性能并不完全一致。4路访问仍然比2路访问慢
编辑:事实上,看起来您是在单独分配所有阵列。
通常,当请求如此大的分配时,分配器将从操作系统请求新的页面。因此,大的分配很有可能出现在页面边界的相同偏移量处
以下是测试代码:
int main(){
const int n = 100000;
#ifdef ALLOCATE_SEPERATE
double *a1 = (double*)malloc(n * sizeof(double));
double *b1 = (double*)malloc(n * sizeof(double));
double *c1 = (double*)malloc(n * sizeof(double));
double *d1 = (double*)malloc(n * sizeof(double));
#else
double *a1 = (double*)malloc(n * sizeof(double) * 4);
double *b1 = a1 + n;
double *c1 = b1 + n;
double *d1 = c1 + n;
#endif
// Zero the data to prevent any chance of denormals.
memset(a1,0,n * sizeof(double));
memset(b1,0,n * sizeof(double));
memset(c1,0,n * sizeof(double));
memset(d1,0,n * sizeof(double));
// Print the addresses
cout << a1 << endl;
cout << b1 << endl;
cout << c1 << endl;
cout << d1 << endl;
clock_t start = clock();
int c = 0;
while (c++ < 10000){
#if ONE_LOOP
for(int j=0;j<n;j++){
a1[j] += b1[j];
c1[j] += d1[j];
}
#else
for(int j=0;j<n;j++){
a1[j] += b1[j];
}
for(int j=0;j<n;j++){
c1[j] += d1[j];
}
#endif
}
clock_t end = clock();
cout << "seconds = " << (double)(end - start) / CLOCKS_PER_SEC << endl;
system("pause");
return 0;
}
意见:
- 6.206秒有一个循环,2.116秒有两个循环。这精确地再现了OP的结果
- 在前两个测试中,数组是分开分配的。您会注意到它们相对于页面的对齐方式都相同
- 在后两个测试中,阵列被打包在一起以进行bre
addsd xmm0,mmword ptr [eax+28h]
movsd mmword ptr [eax+28h],xmm0
movsd xmm0,mmword ptr [ecx+20h]
addsd xmm0,mmword ptr [eax+30h]
movsd mmword ptr [eax+30h],xmm0
movsd xmm0,mmword ptr [ecx+28h]
addsd xmm0,mmword ptr [eax+38h]
movsd mmword ptr [eax+38h],xmm0
movsd xmm0,mmword ptr [ecx+30h]
addsd xmm0,mmword ptr [eax+40h]
movsd mmword ptr [eax+40h],xmm0
#include <iostream>
#include <iomanip>
#include <cmath>
#include <string>
//#define TBB_TIMING
#ifdef TBB_TIMING
#include <tbb/tick_count.h>
using tbb::tick_count;
#else
#include <time.h>
#endif
using namespace std;
//#define preallocate_memory new_cont
enum { new_cont, new_sep };
double *a1, *b1, *c1, *d1;
void allo(int cont, int n)
{
switch(cont) {
case new_cont:
a1 = new double[n*4];
b1 = a1 + n;
c1 = b1 + n;
d1 = c1 + n;
break;
case new_sep:
a1 = new double[n];
b1 = new double[n];
c1 = new double[n];
d1 = new double[n];
break;
}
for (int i = 0; i < n; i++) {
a1[i] = 1.0;
d1[i] = 1.0;
c1[i] = 1.0;
b1[i] = 1.0;
}
}
void ff(int cont)
{
switch(cont){
case new_sep:
delete[] b1;
delete[] c1;
delete[] d1;
case new_cont:
delete[] a1;
}
}
double plain(int n, int m, int cont, int loops)
{
#ifndef preallocate_memory
allo(cont,n);
#endif
#ifdef TBB_TIMING
tick_count t0 = tick_count::now();
#else
clock_t start = clock();
#endif
if (loops == 1) {
for (int i = 0; i < m; i++) {
for (int j = 0; j < n; j++){
a1[j] += b1[j];
c1[j] += d1[j];
}
}
} else {
for (int i = 0; i < m; i++) {
for (int j = 0; j < n; j++) {
a1[j] += b1[j];
}
for (int j = 0; j < n; j++) {
c1[j] += d1[j];
}
}
}
double ret;
#ifdef TBB_TIMING
tick_count t1 = tick_count::now();
ret = 2.0*double(n)*double(m)/(t1-t0).seconds();
#else
clock_t end = clock();
ret = 2.0*double(n)*double(m)/(double)(end - start) *double(CLOCKS_PER_SEC);
#endif
#ifndef preallocate_memory
ff(cont);
#endif
return ret;
}
void main()
{
freopen("C:\\test.csv", "w", stdout);
char *s = " ";
string na[2] ={"new_cont", "new_sep"};
cout << "n";
for (int j = 0; j < 2; j++)
for (int i = 1; i <= 2; i++)
#ifdef preallocate_memory
cout << s << i << "_loops_" << na[preallocate_memory];
#else
cout << s << i << "_loops_" << na[j];
#endif
cout << endl;
long long nmax = 1000000;
#ifdef preallocate_memory
allo(preallocate_memory, nmax);
#endif
for (long long n = 1L; n < nmax; n = max(n+1, long long(n*1.2)))
{
const long long m = 10000000/n;
cout << n;
for (int j = 0; j < 2; j++)
for (int i = 1; i <= 2; i++)
cout << s << plain(n, m, j, i);
cout << endl;
}
}
int main(){
const int n = 100000;
#ifdef ALLOCATE_SEPERATE
double *a1 = (double*)malloc(n * sizeof(double));
double *b1 = (double*)malloc(n * sizeof(double));
double *c1 = (double*)malloc(n * sizeof(double));
double *d1 = (double*)malloc(n * sizeof(double));
#else
double *a1 = (double*)malloc(n * sizeof(double) * 4);
double *b1 = a1 + n;
double *c1 = b1 + n;
double *d1 = c1 + n;
#endif
// Zero the data to prevent any chance of denormals.
memset(a1,0,n * sizeof(double));
memset(b1,0,n * sizeof(double));
memset(c1,0,n * sizeof(double));
memset(d1,0,n * sizeof(double));
// Print the addresses
cout << a1 << endl;
cout << b1 << endl;
cout << c1 << endl;
cout << d1 << endl;
clock_t start = clock();
int c = 0;
while (c++ < 10000){
#if ONE_LOOP
for(int j=0;j<n;j++){
a1[j] += b1[j];
c1[j] += d1[j];
}
#else
for(int j=0;j<n;j++){
a1[j] += b1[j];
}
for(int j=0;j<n;j++){
c1[j] += d1[j];
}
#endif
}
clock_t end = clock();
cout << "seconds = " << (double)(end - start) / CLOCKS_PER_SEC << endl;
system("pause");
return 0;
}
for(int j=0;j<n;j++){
a[j] += b[j];
}
for(int j=0;j<n;j++){
c[j] += d[j];
}
for(int j=0;j<n;j++){
a[j] += b[j];
c[j] += d[j];
}
for(int j=0;j<n;j++){
a[j] += b[j];
}
for(int j=0;j<n;j++){
c[j] += d[j];
}
for(int j=0;j<n;j++){
a[j] += b[j];
c[j] += d[j];
}
// MemBufferMystery.cpp : Defines the entry point for the console application.
//
#include "stdafx.h"
#include <iostream>
#include <cmath>
#include <string>
#include <time.h>
#define dbl double
#define MAX_ARRAY_SZ 262145 //16777216 // AKA (2^24)
#define STEP_SZ 1024 // 65536 // AKA (2^16)
int _tmain(int argc, _TCHAR* argv[]) {
long i, j, ArraySz = 0, LoopKnt = 1024;
time_t start, Cumulative_Combined = 0, Cumulative_Separate = 0;
dbl *a = NULL, *b = NULL, *c = NULL, *d = NULL, *InitToOnes = NULL;
a = (dbl *)calloc( MAX_ARRAY_SZ, sizeof(dbl));
b = (dbl *)calloc( MAX_ARRAY_SZ, sizeof(dbl));
c = (dbl *)calloc( MAX_ARRAY_SZ, sizeof(dbl));
d = (dbl *)calloc( MAX_ARRAY_SZ, sizeof(dbl));
InitToOnes = (dbl *)calloc( MAX_ARRAY_SZ, sizeof(dbl));
// Initialize array to 1.0 second.
for(j = 0; j< MAX_ARRAY_SZ; j++) {
InitToOnes[j] = 1.0;
}
// Increase size of arrays and time
for(ArraySz = STEP_SZ; ArraySz<MAX_ARRAY_SZ; ArraySz += STEP_SZ) {
a = (dbl *)realloc(a, ArraySz * sizeof(dbl));
b = (dbl *)realloc(b, ArraySz * sizeof(dbl));
c = (dbl *)realloc(c, ArraySz * sizeof(dbl));
d = (dbl *)realloc(d, ArraySz * sizeof(dbl));
// Outside the timing loop, initialize
// b and d arrays to 1.0 sec for consistent += performance.
memcpy((void *)b, (void *)InitToOnes, ArraySz * sizeof(dbl));
memcpy((void *)d, (void *)InitToOnes, ArraySz * sizeof(dbl));
start = clock();
for(i = LoopKnt; i; i--) {
for(j = ArraySz; j; j--) {
a[j] += b[j];
c[j] += d[j];
}
}
Cumulative_Combined += (clock()-start);
printf("\n %6i miliseconds for combined array sizes %i and %i loops",
(int)(clock()-start), ArraySz, LoopKnt);
start = clock();
for(i = LoopKnt; i; i--) {
for(j = ArraySz; j; j--) {
a[j] += b[j];
}
for(j = ArraySz; j; j--) {
c[j] += d[j];
}
}
Cumulative_Separate += (clock()-start);
printf("\n %6i miliseconds for separate array sizes %i and %i loops \n",
(int)(clock()-start), ArraySz, LoopKnt);
}
printf("\n Cumulative combined array processing took %10.3f seconds",
(dbl)(Cumulative_Combined/(dbl)CLOCKS_PER_SEC));
printf("\n Cumulative seperate array processing took %10.3f seconds",
(dbl)(Cumulative_Separate/(dbl)CLOCKS_PER_SEC));
getchar();
free(a); free(b); free(c); free(d); free(InitToOnes);
return 0;
}
const int n=100000;
for(int j=0;j<n;j++){
a1[j] += b1[j];
c1[j] += d1[j];
}
for(int j=0;j<n;j++){
a1[j] += b1[j];
}
for(int j=0;j<n;j++){
c1[j] += d1[j];
}
Sum n=1 : [1,100000] = F1(), F2();
F1() = { f(a) = f(a) + f(b); }
F2() = { f(c) = f(c) + f(d); }
Sum1 n=1 : [1,100000] = F1();
F1() = { f(a) = f(a) + f(b); }
Sum2 n=1 : [1,100000] = F1();
F1() = { f(c) = f(c) + f(d); }
const n = 100000
distTraveledOfFirst = (100 + 500) + ((n-1)*(500 + 500);
// Simplify
distTraveledOfFirst = 600 + (99999*100);
distTraveledOfFirst = 600 + 9999900;
distTraveledOfFirst = 10000500;
// Distance Traveled On First Algorithm = 10,000,500ft
distTraveledOfSecond = 100 + 500 = 600;
// Distance Traveled On Second Algorithm = 600ft;
DeltaTimeDifference approximately = Loop1(time) - Loop2(time)
//where
Loop1(time) = Loop2(time) + (Loop2(time)*[0.6,0.7]) // approximately
// So when we substitute this back into the difference equation we end up with
DeltaTimeDifference approximately = (Loop2(time) + (Loop2(time)*[0.6,0.7])) - Loop2(time)
// And finally we can simplify this to
DeltaTimeDifference approximately = [0.6,0.7]*Loop2(time)
struct A {
int data;
A() : data{0}{}
A(int a) : data{a}{}
};
struct B {
int data;
B() : data{0}{}
A(int b) : data{b}{}
}
template<typename T>
void Foo( T& t ) {
// Do something with t
}
// Some looping operation: first stack then heap.
// Stack data:
A dataSetA[10] = {};
B dataSetB[10] = {};
// For stack operations this is okay and efficient
for (int i = 0; i < 10; i++ ) {
Foo(dataSetA[i]);
Foo(dataSetB[i]);
}
// If the above two were on the heap then performing
// the same algorithm to both within the same loop
// will create that bottleneck
A* dataSetA = new [] A();
B* dataSetB = new [] B();
for ( int i = 0; i < 10; i++ ) {
Foo(dataSetA[i]); // dataSetA is on the heap here
Foo(dataSetB[i]); // dataSetB is on the heap here
} // this will be inefficient.
// To improve the efficiency above, put them into separate loops...
for (int i = 0; i < 10; i++ ) {
Foo(dataSetA[i]);
}
for (int i = 0; i < 10; i++ ) {
Foo(dataSetB[i]);
}
// This will be much more efficient than above.
// The code isn't perfect syntax, it's only psuedo code
// to illustrate a point.