CPU Time ? System time ? Wallclock ?

[eroque]

Hello,

Can anyone tell me the diference between User, System, Total Cpu and Wallclok time ?

I want to compare the time wich my computer takes to run a job and preform results, for the same model, just differing the mesh size (seeds). What is the most appropriate time to do this ?

Thaaankss !!!

 

[IRstuff]

Does it matter? You're talking about relative time, which doesn't care about absolute time.

TTFN
I can do absolutely anything. I'm an expert!
faq731-376 forum1529

 

[Dave442]

The .log file will tell you the dates/times your analyses began and completed. I'd just use these for your comparison.

 

[eroque]

Hello,

Thank You for your answers.

How do u suggest to compare the computer effort performing the job ?

I have some models, they only differ in the mesh size. I want to acess processing time to do a reletion between results accuracy/ time spent running the job.

Thanks !!!

 

[IceBreakerSours]

Those are fairly standard terms commonly used by developers. Read this.

I am not sure how granular you want to get but just so you know a truly fair comparison isn't as straightforward as you might imagine. Domain decomposition, system background load, hardware load balancing parameters, etc. are variables that end-users are blinded to.

*********************************************************
Are you new to this forum? If so, please read these FAQs:

http://www.eng-tips.com/faqs.cfm?fid=376

http://www.eng-tips.com/faqs.cfm?fid=1083

 

[eroque]

Thank you for your answers !

So, what is the best way/ parameters to compare PC effort regarding to different seed sizes ?

I really want to compare the effort related to differnt seed sizes to do a relation accuracy/ processing time.

Thanks