Intel® High Level Design
Support for Intel® High Level Synthesis Compiler, DSP Builder, OneAPI for Intel® FPGAs, Intel® FPGA SDK for OpenCL™

Kernel execution time

Vishvas
Novice
1,585 Views

In my program the execution time of the kernel is more than the execution time of the entire program

In the output screen (Attached Screenshot) 'Execution time of kernel' is measured using 'clGetEventProfilingInfo' 

and 'Execution time' is measured using clock_t, similar to this link and it measures the total time taken by the main function

This issue occurs only when I run my code on DevCloud, if I run it on my PC then Execution time > Kernel Execution time

Why is this happening? 

 

 

int main()
{
        .
        .
        .
	start = clock();
        .
        .
	err = clEnqueueNDRangeKernel(queue, multiply_ker, 1, NULL, &global, &local, 0, NULL, &event);
	clWaitForEvents(1, &event);
	clFinish(queue);
        .
        .
        .

	end = clock();

}

 

0 Kudos
1 Solution
HRZ
Valued Contributor III
1,523 Views

It is possible that the OS is reading the CPU clock incorrectly and setting the wrong value for "CLOCKS_PER_SEC". You can try with the high-precision "clock_gettime" function to see if it makes a difference. You can find the function information here:

https://linux.die.net/man/3/clock_gettime

 

And an example implementation here:

https://github.com/zohourih/FPGAMemBench/blob/master/common/timer.h

View solution in original post

0 Kudos
6 Replies
ChithraJ_Intel
Moderator
1,569 Views

Hi Vishvas,


Thanks for reaching out us.

Could you please let us know the node in which you are running the application, Is it in FPGA nodes of Devcloud?


Regards,

Chithra


0 Kudos
Vishvas
Novice
1,564 Views

The node is : s001-n139 

And Device is Arria 10  Platform as shown in the screenshot
I compiled the OpenCL code into RTL and ran it on FPGA. 

The issue I mentioned only occurs on FPGA, if I simulate it on CPU the timings are proper

0 Kudos
ChithraJ_Intel
Moderator
1,556 Views

Hi Vishvas,


 Thanks for the information. Since your issue is related to FPGA, we are moving this query to FPGA forum for a faster response.


Regards,

Chithra


0 Kudos
HRZ
Valued Contributor III
1,524 Views

It is possible that the OS is reading the CPU clock incorrectly and setting the wrong value for "CLOCKS_PER_SEC". You can try with the high-precision "clock_gettime" function to see if it makes a difference. You can find the function information here:

https://linux.die.net/man/3/clock_gettime

 

And an example implementation here:

https://github.com/zohourih/FPGAMemBench/blob/master/common/timer.h

0 Kudos
AnilErinch_A_Intel
1,486 Views

Hi ,

Please let us know whether the issue is resolved using clock_gettime. If not we can look in to further possibilities.

Thanks and Regards

Anil


0 Kudos
Vishvas
Novice
1,467 Views

I had some issues implementing it,  but I was able to complete it now

Thanks a lot for your help!

0 Kudos
Reply