Index  | Recent Threads  | Unanswered Threads  | Who's Active  | Guidelines  | Search
 

Quick Go »
No member browsing this thread
Thread Status: Active
Total posts in this thread: 6
[ Jump to Last Post ]
Post new Thread
Author
Previous Thread This topic has been viewed 1039 times and has 5 replies Next Thread
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Personal thoughts on BOINC-based WCG...

To me, WCG is one of the most beneficial projects around. But I would like some changes, without explaining too much, why I want them, I think most do know why wink

1. Make "My Grid"-website more BOINC-like, like all the other BOINC-project websites. To me "My Grid" is confusing/unclear!

2. Linux credit system compared to Windows credits system is unfair! (Ok, thats hearsay, but if you hear dozens of linux users saying the same...

3. Is it really necessary to distribute the same workunit to up to 20 hosts??? (Workunits starting with "la") To me thats waste of energy, time, cpu cycles...

4. More detailed workunit statistics (referring to #1: More BOINC-like!)

Dont get me wrong, I'm completely Pro-WCG! I have 25 projects running, WCG gets 1/8th in average, and I tend to increase its share.

Best regards!

(Comments welcome!)
----------------------------------------
[Edit 1 times, last edit by Former Member at Mar 17, 2007 1:49:16 AM]
[Mar 17, 2007 1:32:42 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Personal thoughts on BOINC-based WCG...

Hail to the ruler of Arrakis!
3. Is it really necessary to distribute the same workunit to up to 20 hosts??? (Workunits starting with "la") To me thats waste of energy, time, cpu cycles...

Each of the HPF2 work units is computed with a random number supplying one of the parameters. In other words, instead of 20 duplicates, each result is unique. The validation function is very complex and (I believe) works in a statistical fashion. So - - there is NO duplication in HPF2. This is the only project that WCG runs without duplication.
2. Linux credit system compared to Windows credits system is unfair! (Ok, thats hearsay, but if you hear dozens of linux users saying the same...

This is being worked on. The problem is that Windows compilers cheat when compiling benchmarks. The compiler writers competed with each other back in the 1990's by eliminating code that does not produce a result, which speeds up the benchmarks substantially.

Lawrence
[Mar 17, 2007 2:54:56 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Personal thoughts on BOINC-based WCG...

3. Is it really necessary to distribute the same workunit to up to 20 hosts??? (Workunits starting with "la") To me thats waste of energy, time, cpu cycles...


Each of the HPF2 work units is computed with a random number supplying one of the parameters. In other words, instead of 20 duplicates, each result is unique. The validation function is very complex and (I believe) works in a statistical fashion. So - - there is NO duplication in HPF2. This is the only project that WCG runs without duplication.


Thanx for explaining it! That makes sense to me!


Hail to the ruler of Arrakis!


cool
[Mar 17, 2007 11:00:35 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Personal thoughts on BOINC-based WCG...

the only comment that i have is that all work units should be small. the work units should only take up 1 and a half to 2 hours of processing time to complete. that way it is less of a hit to the project when a unit is lost. i'm sure that this isn't always possible but if it is possible to do it could increase the productivity of that project.
[Mar 22, 2007 8:33:39 PM]   Link   Report threatening or abusive post: please login first  Go to top 
retsof
Former Community Advisor
USA
Joined: Jul 31, 2005
Post Count: 6824
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: Personal thoughts on BOINC-based WCG...

It's a trade-off. Small workunits cause a larger load on the servers, since there is more time needed for transmittals and more ports needed.

My dial-up systems take a couple of hours per day to send up and download 1 hour genome comparison workunits (when they are available).

They should finish in one hour, but because of the problem, one was at 0% after 14 hours. (evening and overnight)

The longer running 5 hour FAAH have tiny files, so transmittals run quickly.

(Workunit times are on these AMD64 2.4GHz computers)
----------------------------------------
SUPPORT ADVISOR
Work+GPU i7 8700 12threads
School i7 4770 8threads
Default+GPU Ryzen 7 3700X 16threads
Ryzen 7 3800X 16 threads
Ryzen 9 3900X 24threads
Home i7 3540M 4threads50%
----------------------------------------
[Edit 2 times, last edit by retsof at Mar 23, 2007 2:32:24 AM]
[Mar 23, 2007 1:52:47 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: Personal thoughts on BOINC-based WCG...

To me, WCG is one of the most beneficial projects around. But I would like some changes, without explaining too much, why I want them, I think most do know why wink

1. Make "My Grid"-website more BOINC-like, like all the other BOINC-project websites. To me "My Grid" is confusing/unclear!

You have to remember that this is not an exclusive Boinc project, it caters for users of the Grid UD Agent as well.

To be honest I actually prefer the layout here, and find the others more unclear! laughing
[Mar 27, 2007 4:29:46 PM]   Link   Report threatening or abusive post: please login first  Go to top 
[ Jump to Last Post ]
Post new Thread