Similarly when the machine changes significantly.
jm7
"Lynn W. Taylor"
<[email protected]>
Sent by: To
<boinc_dev-bounce Martin <[email protected]>
[email protected] cc
u> BOINC Developers Mailing List
<[email protected]>
Subject
09/29/2009 01:33 Re: [boinc_dev] [boinc_alpha] Card
PM Gflops in BOINC 6.10
There is a small catch-22.
If you base cache size on speed, and you measure speed using only the
live application, then you can't fill the cache until you've done some
work.
If you assume the machine is fairly fast, and it isn't, you run the risk
of grabbing an initial task that couldn't possibly finish on time.
If you assume the machine is slow, and it's really fast, you run the
risk of being denied work because BOINC thinks the machine is too slow.
So you need the benchmark as a rough initial measurement of speed.
Emphasis on the word "rough." It can be off by a factor of five and
still work.
Martin wrote:
> [email protected] wrote:
>> The point was that a few seconds or a few minutes every week is much
more
>> palatable than running a benchmark that takes a few hours every week.
>
> And real work that is calibrated against a reference that then is used
> to calibrate that particular host is better still.
>
> No wasteful benchmarking on the clients needed!
>
> Regards,
> Martin
>
_______________________________________________
boinc_dev mailing list
[email protected]
http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev
To unsubscribe, visit the above URL and
(near bottom of page) enter your email address.
_______________________________________________
boinc_dev mailing list
[email protected]
http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev
To unsubscribe, visit the above URL and
(near bottom of page) enter your email address.
