线程调度的完整可靠解决方案（每次测试应产生完全相同的时间）是将您的程序编译为独立于操作系统并启动您的计算机，以便在无操作系统的环境中运行程序。然而，这在很大程度上是不切实际的，而且充其量也很困难。
无操作系统的一个很好的替代方法是将当前线程的亲和性设置为 1 个核心并将优先级设置为最高。这种替代方案应该提供足够一致的结果。
假设您在最终生产版本中使用-Ofast（或至少-O3）并忽略“死”代码消除问题，与-Ofast 相比，-Og 执行的优化很少;因此-Og 可能会歪曲最终产品中代码的真实速度。
进一步，所有速度测试（在某种程度上）伪证：在使用-Ofast编译的最终生产产品中，代码的每个sn-p/section/function不是孤立的；相反，每个 sn-p 代码都不断流入下一个，从而允许编译器潜在地连接、合并和优化来自各地的代码片段。
同时，如果您正在对大量使用realloc() 的代码进行基准测试，那么在内存碎片足够高的生产产品中，代码的 sn-p 可能会运行得更慢。因此，“整体大于部分之和”这一表述适用于这种情况，因为最终生产构建中的代码可能比您正在速度测试的单个 sn-p 运行得更快或更慢。
可以减少不协调的部分解决方案是使用-Ofast 进行速度测试，并将asm volatile("" :: "r"(var)) 添加到测试中涉及的变量以防止死代码/循环消除。
这是一个如何在 Windows 计算机上对平方根函数进行基准测试的示例。
// set USE_ASM_TO_PREVENT_ELIMINATION to 0 to prevent `asm volatile("" :: "r"(var))`
// set USE_ASM_TO_PREVENT_ELIMINATION to 1 to enforce `asm volatile("" :: "r"(var))`
#define USE_ASM_TO_PREVENT_ELIMINATION 1
#include <iostream>
#include <iomanip>
#include <cstdio>
#include <chrono>
#include <cmath>
#include <windows.h>
#include <intrin.h>
#pragma intrinsic(__rdtsc)
#include <cstdint>
class Timer {
public:
Timer() : beg_(clock_::now()) {}
void reset() { beg_ = clock_::now(); }
double elapsed() const {
return std::chrono::duration_cast<second_>
(clock_::now() - beg_).count(); }
private:
typedef std::chrono::high_resolution_clock clock_;
typedef std::chrono::duration<double, std::ratio<1> > second_;
std::chrono::time_point<clock_> beg_;
};
unsigned int guess_sqrt32(register unsigned int n) {
register unsigned int g = 0x8000;
if(g*g > n) {
g ^= 0x8000;
}
g |= 0x4000;
if(g*g > n) {
g ^= 0x4000;
}
g |= 0x2000;
if(g*g > n) {
g ^= 0x2000;
}
g |= 0x1000;
if(g*g > n) {
g ^= 0x1000;
}
g |= 0x0800;
if(g*g > n) {
g ^= 0x0800;
}
g |= 0x0400;
if(g*g > n) {
g ^= 0x0400;
}
g |= 0x0200;
if(g*g > n) {
g ^= 0x0200;
}
g |= 0x0100;
if(g*g > n) {
g ^= 0x0100;
}
g |= 0x0080;
if(g*g > n) {
g ^= 0x0080;
}
g |= 0x0040;
if(g*g > n) {
g ^= 0x0040;
}
g |= 0x0020;
if(g*g > n) {
g ^= 0x0020;
}
g |= 0x0010;
if(g*g > n) {
g ^= 0x0010;
}
g |= 0x0008;
if(g*g > n) {
g ^= 0x0008;
}
g |= 0x0004;
if(g*g > n) {
g ^= 0x0004;
}
g |= 0x0002;
if(g*g > n) {
g ^= 0x0002;
}
g |= 0x0001;
if(g*g > n) {
g ^= 0x0001;
}
return g;
}
unsigned int empty_function( unsigned int _input ) {
return _input;
}
unsigned long long empty_ticks=0;
double empty_seconds=0;
Timer my_time;
template<unsigned int benchmark_repetitions>
void benchmark( char* function_name, auto (*function_to_do)( auto ) ) {
register unsigned int i=benchmark_repetitions;
register unsigned long long start=0;
my_time.reset();
start=__rdtsc();
while ( i-- ) {
auto result = (*function_to_do)( i << 7 );
#if USE_ASM_TO_PREVENT_ELIMINATION == 1
asm volatile("" :: "r"(
// There is no data type in C++ that is smaller than a char, so it will
// not throw a segmentation fault error to reinterpret any arbitrary
// data type as a char. Although, the compiler might not like it.
result
));
#endif
}
if ( function_name == nullptr ) {
empty_ticks = (__rdtsc()-start);
empty_seconds = my_time.elapsed();
std::cout<< "Empty:\n" << empty_ticks
<< " ticks\n" << benchmark_repetitions << " repetitions\n"
<< std::setprecision(15) << empty_seconds
<< " seconds\n\n";
} else {
std::cout<< function_name<<":\n" << (__rdtsc()-start-empty_ticks)
<< " ticks\n" << benchmark_repetitions << " repetitions\n"
<< std::setprecision(15) << (my_time.elapsed()-empty_seconds)
<< " seconds\n\n";
}
}
int main( void ) {
void* Cur_Thread= GetCurrentThread();
void* Cur_Process= GetCurrentProcess();
unsigned long long Current_Affinity;
unsigned long long System_Affinity;
unsigned long long furthest_affinity;
unsigned long long nearest_affinity;
if( ! SetThreadPriority(Cur_Thread,THREAD_PRIORITY_TIME_CRITICAL) ) {
SetThreadPriority( Cur_Thread, THREAD_PRIORITY_HIGHEST );
}
if( ! SetPriorityClass(Cur_Process,REALTIME_PRIORITY_CLASS) ) {
SetPriorityClass( Cur_Process, HIGH_PRIORITY_CLASS );
}
GetProcessAffinityMask( Cur_Process, &Current_Affinity, &System_Affinity );
furthest_affinity = 0x8000000000000000ULL>>__builtin_clzll(Current_Affinity);
nearest_affinity = 0x0000000000000001ULL<<__builtin_ctzll(Current_Affinity);
SetProcessAffinityMask( Cur_Process, furthest_affinity );
SetThreadAffinityMask( Cur_Thread, furthest_affinity );
const int repetitions=524288;
benchmark<repetitions>( nullptr, empty_function );
benchmark<repetitions>( "Standard Square Root", standard_sqrt );
benchmark<repetitions>( "Original Guess Square Root", original_guess_sqrt32 );
benchmark<repetitions>( "New Guess Square Root", new_guess_sqrt32 );
SetThreadPriority( Cur_Thread, THREAD_PRIORITY_IDLE );
SetPriorityClass( Cur_Process, IDLE_PRIORITY_CLASS );
SetProcessAffinityMask( Cur_Process, nearest_affinity );
SetThreadAffinityMask( Cur_Thread, nearest_affinity );
for (;;) { getchar(); }
return 0;
}
另外，感谢 Mike Jarvis 的计时器。
请注意（这非常重要），如果您要运行更大的代码 sn-ps，那么您确实必须降低迭代次数以防止计算机死机。