How can we get the system time in microseconds? Gracian (Mylee) 15:08:30 on
C/C ++/
C LanguageQuestion? Number of questions: 20. replies: 6
On the first floor, chillman (the talented old man) replied to 15:16:59, with a score of 8.
The number of pulses of the crystal oscillator.
You can refer to similar programs
_ ASM mov ax, icount
_ ASM mov dx, tmr1_maxa
_ ASM out dx, Al
_ Asm xor ax, ax
_ ASM mov dx, tmr1_cnt // t1cnt
_ ASM out dx, Al
_ ASM mov dx, tmr1_ctl // t1con
_ ASM in ax, DX
_ ASM mov savedt1, ax
_ ASM mov ax, 0xe001
_ ASM out dx, Al
Top
Keiy () on the second floor replied to the score of 10 at 15:33:26
Here
Http://expert.csdn.net/Expert/topic/1990/1990344.xml? Temp =. 7977564.
Top
On the third floor, keiy () replied to 15:38:04, with a score of 0.
A method for making a microsecond-level precision timer (transpose)
When a timer is used, in many cases, only the interval of milliseconds is used. Therefore, you only need to use the following two common methods to meet the requirements. First, after a timer is created using the settimer function, the timer is sent to the wm_timer message in the thread Message Queue through the reason in the process, and get the scheduled effect (do not forget to call the killtimer function paired with settimer when you exit the program ). The second is to use the gettickcount function to return the start time of the computer, call the gettickcount function twice, and then control the difference between them to achieve the scheduled effect. This method is the same as the first method, precision is also in milliseconds.
Although the timing effect obtained using these two methods has already met the actual requirements in many cases, their precision is only millisecond-level, and the time interval is required for the hour, the actual timing error is large. The following describes a method for obtaining high-precision timing.
In some computer hardware systems, high-precision operation counters (high-resolution Performance Counter) can be used to obtain high-precision timing intervals, and their accuracy is related to the clock frequency of the CPU. The steps for using this method are as follows:
1. First, call the queryperformancefrequency function to obtain the frequency f of the high-precision running counter. The Unit is the number of times per second (N/S), which is generally large.
2. Call queryperformancecounter at both ends of the Code that requires timing to obtain the values N1 and N2 of the high-precision running counter. The difference between the two values is converted to the time interval by F, t = (n2-n1)/F.
The following example shows how to use this method and its accuracy.
In VC 6.0, use MFC to create a dialog box project named highttimer. The layout of the control in the dialog box panel is as follows:
It contains two static text boxes, two editing boxes, and two buttons. The ID of the edit box above and below is idc_e_test and idc_e_actual, respectively. The member variables added through MFC classwizard also correspond to DWORD m_dwtest and DWORD m_dwact respectively. the ID of the "exit" button is idok, and the "Start test" button ID is idc_ B _test. To add this button with MFC classwizard, click the message processing function as follows:
Void chighttimerdlg: onbtest ()
{
// Todo: add your control notification handler code here
Updatedata (true); // obtain the input test time value to the member variable m_dwtest associated with the edit box.
Large_integer frequence;
If (! Queryperformancefrequency (& frequence) // gets the frequency of the high-precision running counter. If the hardware does not support this function, false is returned.
MessageBox ("your computer hardware doesn't support the high-resolution performance counter ",
"Not support", mb_iconexclamation | mb_ OK );
Large_integer test, RET;
Test. quadpart = frequence. quadpart * m_dwtest/1000000; // converts the number of microseconds to the corresponding number (related to the CPU clock) by frequency, 1 second = 1000000 microseconds
Ret = mysleep (TEST); // call this function to start the delay and return the actual cost.
M_dwact = (DWORD) (1000000 * ret. quadpart/frequence. quadpart); // converts to the number of microseconds
Updatedata (false); // displayed on the dialog box panel
}
The mysleep function called above is as follows:
Large_integer chighttimerdlg: mysleep (large_integer interval)
//////////////////////////////////////// //////////////////////////////////////// /////////////////////////////
// Function: perform the actual latency Function
// Parameter: The interval parameter is the number of time-related delays to be executed.
// Return value: returns the number of time-related values after the function is executed.
//////////////////////////////////////// //////////////////////////////////////// ///////////////////////////
{
Large_integer privious, current, elapse;
Queryperformancecounter (& privious );
Current = privious;
While (current. quadpart-privious. quadpart <interval. quadpart)
Queryperformancecounter (counter t );
Elapse. quadpart = current. quadpart-privious. quadpart;
Return elapse;
}
Note: Do not forget to add a function declaration for this function in the header file.
Now, you can compile and execute this project. The results are shown in. In my own machine (Pentium 366, 64 M memory) testing, when the test time exceeds 3 microseconds, the accuracy is already very high, at this time, the time when the machine executes its own latency Function Code has little impact on the time needed for latency.
The above functions are not encapsulated at the function level due to the needs of the demonstration test. The functions provided below can basically be copied to other programs in the form of global functions.
Bool mysleep (DWORD dwinterval)
//////////////////////////////////////// //////////////////////////////////////// /////////////////////////////
// Function: executes the latency function in microseconds.
// Parameter: The interval parameter is the number of required latencies (unit: microseconds)
// Return value: if the computer hardware does not support this function, false is returned. If the function is successfully executed, true is returned.
//////////////////////////////////////// //////////////////////////////////////// ///////////////////////////
{
Bool bnormal = true;
Large_integer frequence, privious, current, interval;
If (! Queryperformancefrequency (& frequence ))
{
: MessageBox (null, "your computer hardware doesn't support the high-resolution performance counter ",
"Not support", mb_iconexclamation | mb_ OK); // or other prompts
Return false;
}
Interval. quadpart = frequence. quadpart * dwinterval/1000000;
Bnormal = bnormal & queryperformancecounter (& privious );
Current = privious;
While (current. quadpart-privious. quadpart <interval. quadpart)
Bnormal = bnormal & queryperformancecounter (counter t );
Return bnormal;
}
It should be noted that, because there are a lot of code in this function, it takes a long time for the machine to execute the code, so the accuracy will be affected when the latency is several microseconds. In fact, when you are familiar with this method, you only need to use the queryperformancefrequency and queryperformancecounter functions to write your own latency code as needed.
Top
On the fourth floor, keiy () replied to 16:15:44, with a score of 0.
Paste another
High-precision timing using CPU timestamps
13:14:11 gameres zhangyan_qd views: 764
For performance-focused program developers, a good timing component is both a mentor and a mentor. Timers can be used as program components to help programmers precisely control program processes, and are also a powerful debugging weapon. experienced programmers can determine program performance bottlenecks as soon as possible, or make a convincing performance comparison for different algorithms.
On Windows, there are two commonly used Timers: timegettime multimedia timer, which provides millisecond-level timer. However, this accuracy is too rough for many applications. The other is the queryperformancecount counter, which provides a microsecond-level count as the system differs. For real-time graphics processing, multimedia data stream processing, or real-time system construction programmers, using queryperformancecount/queryperformancefrequency is a basic skill.
This article introduces another high-precision timing method that uses the internal timestamp of the Pentium CPU directly. The following discussion mainly benefited from the book Windows graphic programming, page 1-page 17. Interested readers can directly refer to the book. For more information about the rdtsc commands, see the Intel product manual. This article is only used for throwing bricks.
Among Intel Pentium-level CPUs, there is a part called "Time Stamp", which is in the format of a 64-bit unsigned integer, records the number of clock cycles that have elapsed since CPU power-on. Because the current CPU clock speed is very high, this component can achieve the time precision of the nanosecond level. This accuracy is incomparable to the above two methods.
In a CPU above Pentium, a machine command rdtsc (read time stamp counter) is provided to read the timestamp number and save it in The edX: eax register pair. Since the edX: eax register is the register that stores the function return value in the C ++ language on the Win32 platform, we can regard this instruction as a common function call. Like this:
Inline unsigned _ int64 getcyclecount ()
{
_ ASM rdtsc
}
But no, because rdtsc is not directly supported by the C ++ Embedded Assembler, we need to use the _ emit pseudo command to directly embed the machine code form 0x0f, 0x31 of the command, as shown below:
Inline unsigned _ int64 getcyclecount ()
{
_ ASM _ emit 0x0f
_ ASM _ emit 0x31
}
In the future, when a counter is required, you can call the getcyclecount function twice like using a common Win32 API to compare the difference between the two return values, as shown in the following code:
Unsigned long T;
T = (unsigned long) getcyclecount ();
// Do Something time-intensive...
T-= (unsigned long) getcyclecount ();
On page 15th of Windows graphic programming, a class is written to encapsulate this counter. Interested readers can refer to the code of that class. For more precise timing, the author makes a small improvement by calculating and saving the time for executing the rdtsc command by calling the getcyclecount function twice in a row, after each timer is completed, the short time is subtracted from the actual count to get a more accurate timing number. But I personally think this improvement is of little significance. According to the test on my machine, this command took about dozens to 100 cycles. It was only a tenth of microsecond in the time on the celon MHZ machine. For most applications, this time is completely negligible, and for those applications that are indeed accurate to the order of nanoseconds, this compensation is too rough.
The advantages of this method are:
1. High precision. The timing accuracy can be achieved directly in nanoseconds (each clock cycle on a 1 GHz CPU is One nanosecond), which is hard to achieve by other timing methods.
2. low cost. The timegettime function needs to be linked to the multi-media library winmm. the Lib and queryperformance * functions are supported by hardware (although I have not seen any machines that are not supported) and the kernel library according to msdn instructions, therefore, both of them can only be used on the Windows platform (for precise timing on the DOS platform, refer to the graphic program developer Guide, which provides detailed instructions on the control timer 8253 ). However, the rdtsc command is a CPU command, which is supported by any machine above the Pentium on the i386 platform, or even without platform restrictions (I believe that the i386 UNIX and Linux methods are also applicable, but there is no conditional test), and the function call overhead is the smallest.
3. There is a direct rate relationship with the CPU clock speed. One count is equivalent to 1/second (CPU clock speed Hz), so that as long as you know the CPU clock speed, you can directly calculate the time. This is different from queryperformancecount. The latter needs to use queryperformancefrequency to obtain the count times of the current counter per second to convert it to time.
The disadvantage of this method is:
1. Most of the existing C/C ++ compilers do not directly support the use of rdtsc commands. You need to program the code by embedding the machine code directly, which is troublesome.
2. High Data jitter. In fact, accuracy and stability are always a conflict for any measurement method. If low-precision timegettime is used for timing, the results are basically the same each time. The rdtsc command has different results each time, with hundreds or even thousands of gaps. This is a contradiction inherent in this method of high precision.
We can use the following formula to calculate the maximum length of timing in this method:
Number of seconds since CPU power-on = number of cycles read by rdtsc/CPU clock speed (HZ)
The maximum number that a 64-bit unsigned integer can express is 1.8 × 10 ^ 19. On my celon 800, it can be timed around (the book says it can be timed on a MHz Pentium in, I don't know how this number is obtained, but it is different from my calculations ). No matter what it is, we don't have to worry about overflow.
The following is a few small examples, which briefly compares the usage and accuracy of the three timing methods.
// Timer1.cpp Timer class that uses the rdtsc command // ktimer class definition can be found in Windows graphic programming p15
// Compilation line: CL timer1.cpp/link user32.lib
# Include <stdio. h>
# Include "ktimer. H"
Main ()
{
Unsigned T;
Ktimer timer;
Timer. Start ();
Sleep (1000 );
T = timer. Stop ();
Printf ("lasting time: % d/N", t );
}
// Timer2.cpp uses the timegettime Function
// <Mmsys. h> must be included, but the Windows header file is complex.
// Simple inclusion <windows. h> is relatively lazy :)
// Compilation line: CL timer2.cpp/link winmm. Lib
# Include <windows. h>
# Include <stdio. h>
Main ()
{
DWORD T1, T2;
T1 = timegettime ();
Sleep (1000 );
T2 = timegettime ();
Printf ("begin time: % u/N", T1 );
Printf ("End Time: % u/N", T2 );
Printf ("lasting time: % u/N", (t2-t1 ));
}
// Timer3.cpp uses the queryperformancecounter Function
// Compilation line: CL timer3.cpp/link kernel32.lib
# Include <windows. h>
# Include <stdio. h>
Main ()
{
Large_integer T1, T2, TC;
Queryperformancefrequency (& TC );
Printf ("frequency: % u/N", TC. quadpart );
Queryperformancecounter (& T1 );
Sleep (1000 );
Queryperformancecounter (& T2 );
Printf ("begin time: % u/N", t1.quadpart );
Printf ("End Time: % u/N", t2.quadpart );
Printf ("lasting time: % u/N", (t2.quadpart-t1.quadpart ));
}
//////////////////////////////////////// ////////
// The above three examples are the time required to test the sleep for 1 second.
File: // test/test environment: celeon 800 MHz/256 M SDRAM
// Windows 2000 Professional SP2
// Microsoft Visual C ++ 6.0 SP5
//////////////////////////////////////// ////////
The following are the running results of timer1, using the high-precision rdtsc command.
Lasting Time: 804586872
The following is the running result of timer2, using the rough timegettime API
Begin time: 20254254
Endtime: 20255255
Lasting Time: 1001
The following is the running result of timer3, using the queryperformancecount API
Frequency: 3579545
Begin time: 3804729124
Endtime: 3808298836
Lasting Time: 3569712
The ancients said that the class was accessible. I am very happy to get such a useful real-time processing knowledge from this introduction to Graphic programming. I hope everyone will like this light and effective timer like me.
Top
Fenglove (I am actually an actor) on the fifth floor replied to the question: 17:42:55, score 2
Learning from Daniel ~~~~~~~~~~~~~~~~~
Top
On the 6th floor, gracian (Mylee) replied with a score of 0 from 09:49:40.
Well, I have benefited a lot.
