Advanced search

Message boards : Number crunching : BOINC Supercomputer

Author Message
PappaLitto
Send message
Joined: 21 Mar 16
Posts: 508
Credit: 4,607,207,341
RAC: 0
Level
Arg
Scientific publications
watwatwatwatwatwatwatwat
Message 45937 - Posted: 28 Dec 2016 | 0:15:46 UTC

If all of BOINC with all of its projects were combined into one supercomputer, how many PetaFLOPs do you think it would have? An estimate on the power usage?

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2305
Credit: 16,131,308,517
RAC: 2,393,918
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 45940 - Posted: 28 Dec 2016 | 2:40:23 UTC - in response to Message 45937.
Last modified: 28 Dec 2016 | 2:42:49 UTC

According to http://boincstats.com/en/stats/-5/project/detail/ the average floating point operations per second is 13,092,496.5 GigaFLOPS / 13,092.497 TeraFLOPS (that is 13.1 PetaFLOPS)

It is very hard to even estimate the overall power usage, as there are many obsolete CPUs and GPUs used.

JoergF
Avatar
Send message
Joined: 20 Apr 15
Posts: 285
Credit: 1,102,216,607
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwat
Message 45941 - Posted: 28 Dec 2016 | 10:11:17 UTC

Frankly I wish all that computing power would exclusively go to projects like GPUGRID, Folding@Home, WCG or Rosetta. Those alleviate suffering and move mankind more forward than e.g. decoding meaningless Enigma transmissions from WW2.

Just my two Cents. So may the shitstorm fall on me.
____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

Bedrich Hajek
Send message
Joined: 28 Mar 09
Posts: 404
Credit: 5,832,269,764
RAC: 1,788,981
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 45945 - Posted: 29 Dec 2016 | 1:45:57 UTC - in response to Message 45940.

According to http://boincstats.com/en/stats/-5/project/detail/ the average floating point operations per second is 13,092,496.5 GigaFLOPS / 13,092.497 TeraFLOPS (that is 13.1 PetaFLOPS)

It is very hard to even estimate the overall power usage, as there are many obsolete CPUs and GPUs used.




And this project has currently 1,680,460 GigaFLOPs, which is almost 13% of the total. Amazing, what a few hundred crunchers can accomplish!

A few weeks ago, we were at over 2,000,000 GigaFLOPs.



Profile skgiven
Volunteer moderator
Project tester
Volunteer tester
Avatar
Send message
Joined: 23 Apr 09
Posts: 3968
Credit: 1,995,359,260
RAC: 0
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46010 - Posted: 30 Dec 2016 | 23:15:33 UTC - in response to Message 45941.

Firstly, Boinc is not a supercomputer!
Nor does 'Boinc' have a supercomputer. It's a tool for a very broad spectrum of (and I use the word very loosely) 'scientific' research. People don't connect to Boinc, they use Boinc to connect to many different research projects. Sometimes their only affiliation/commonality is their use of Boinc.

Frankly I wish all that computing power would exclusively go to projects like GPUGRID, Folding@Home, WCG or Rosetta. Those alleviate suffering and move mankind more forward than e.g. decoding meaningless Enigma transmissions from WW2.

Just my two Cents. So may the shitstorm fall on me.

People chose to crunch for numerous different projects for combinations of many different reasons; some logical, some irrational, some sad, some funny... IMO you're ~99% correct, but I could be wrong, right or somewhere in between. What I've learnt from experience is that some of the less thought of projects have helped push the boundary's of what Boinc can do/facilitates. Indirectly, the lesser accepted projects have helped enhance Boinc as a research tool and just because you don't think highly of a project doesn't mean you can't learn from their mistakes or take advantage of their success. If person A didn't develop a tool to allow distributed computers to help search for aliens then it's likely someone else would have. I've learnt a lot form other Boinc projects, especially their forums (so it's there for all to access). TN-Grid Platform is probably a project you've never heard of, but they are doing some good cutting edge CPU research. It's not as big as here & their science isn't readily accessible (you need to be well read) but it's not to be sniffed at. Back in Oct they were interested in some help porting their app to cuda (G, M, T, Dr's...).

____________
FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Profile Beyond
Avatar
Send message
Joined: 23 Nov 08
Posts: 1112
Credit: 6,162,416,256
RAC: 0
Level
Tyr
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46044 - Posted: 2 Jan 2017 | 23:25:41 UTC - in response to Message 46010.

What I've learnt from experience is that some of the less thought of projects have helped push the boundary's of what Boinc can do/facilitates. Indirectly, the lesser accepted projects have helped enhance Boinc as a research tool and just because you don't think highly of a project doesn't mean you can't learn from their mistakes or take advantage of their success. If person A didn't develop a tool to allow distributed computers to help search for aliens then it's likely someone else would have. I've learnt a lot form other Boinc projects, especially their forums (so it's there for all to access). TN-Grid Platform is probably a project you've never heard of, but they are doing some good cutting edge CPU research. It's not as big as here & their science isn't readily accessible (you need to be well read) but it's not to be sniffed at. Back in Oct they were interested in some help porting their app to cuda (G, M, T, Dr's...).

I agree for the most part. There's too much judgment about what people choose to do with their own computers. Personally I feel good about crunching WUs for GPUGrid, so that's what I mostly do. However I don't feel that it's of any use to judge others based on what they choose to do with their own equipment and their own money. I don't hear anyone complaining about the VAST amount of money that could be regarded as wasted running games, etc. For many people BOINC is also a competition and a game, and I would submit that no matter what project someone runs it's most likely more useful than running world of warcraft, etc. etc. etc...

Profile Logan Carr
Send message
Joined: 12 Aug 15
Posts: 240
Credit: 64,069,811
RAC: 0
Level
Thr
Scientific publications
watwatwatwat
Message 46046 - Posted: 3 Jan 2017 | 2:47:33 UTC - in response to Message 46044.

What I've learnt from experience is that some of the less thought of projects have helped push the boundary's of what Boinc can do/facilitates. Indirectly, the lesser accepted projects have helped enhance Boinc as a research tool and just because you don't think highly of a project doesn't mean you can't learn from their mistakes or take advantage of their success. If person A didn't develop a tool to allow distributed computers to help search for aliens then it's likely someone else would have. I've learnt a lot form other Boinc projects, especially their forums (so it's there for all to access). TN-Grid Platform is probably a project you've never heard of, but they are doing some good cutting edge CPU research. It's not as big as here & their science isn't readily accessible (you need to be well read) but it's not to be sniffed at. Back in Oct they were interested in some help porting their app to cuda (G, M, T, Dr's...).

I agree for the most part. There's too much judgment about what people choose to do with their own computers. Personally I feel good about crunching WUs for GPUGrid, so that's what I mostly do. However I don't feel that it's of any use to judge others based on what they choose to do with their own equipment and their own money. I don't hear anyone complaining about the VAST amount of money that could be regarded as wasted running games, etc. For many people BOINC is also a competition and a game, and I would submit that no matter what project someone runs it's most likely more useful than running world of warcraft, etc. etc. etc...


Haha, Took the words out of my mouth!

My only concern about this project is how long it will be running. Before I put more money to it, I'd like to feel at ease that it won't end any time soon(possibly a time estimate on how long it will run?). Might seem foolish but I see these other projects closing down. I don't want to go out and buy something and then have this project be done. This is pretty much the only project on Boinc I run, so I'm a bit cautious. Thanks



____________
Cruncher/Learner in progress.

JoergF
Avatar
Send message
Joined: 20 Apr 15
Posts: 285
Credit: 1,102,216,607
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwat
Message 46069 - Posted: 4 Jan 2017 | 20:06:41 UTC
Last modified: 4 Jan 2017 | 20:07:28 UTC

I don't hear anyone complaining about the VAST amount of money that could be regarded as wasted running games, etc.


Oh yes ... me, if I may. Wasted entirely!

Except for Mass Effect Andromeda next year ...... that is a must and I can't miss out on all the fun..... I apologize for my characterlessness and ... X-D
____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

PappaLitto
Send message
Joined: 21 Mar 16
Posts: 508
Credit: 4,607,207,341
RAC: 0
Level
Arg
Scientific publications
watwatwatwatwatwatwatwat
Message 46071 - Posted: 4 Jan 2017 | 22:41:40 UTC

Don't hate on games, they are a large reason these companies like nvidia have the R&D money to make GPUs this fast and a very large reason why so many people have high power GPUs at all. BOINC wouldn't even be possible without these people.

Jim1348
Send message
Joined: 28 Jul 12
Posts: 790
Credit: 1,561,693,721
RAC: 39,552
Level
His
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46072 - Posted: 4 Jan 2017 | 23:20:45 UTC

Biomedical projects help you live longer, but the purpose of life is not just to live longer but to learn something in the process. That is why I also support the CERN projects (ATLAS, LHC), Cosmology and Universe at the moment. They are pushing the boundaries of science, which is one way of expanding knowledge, though not the only one.

JoergF
Avatar
Send message
Joined: 20 Apr 15
Posts: 285
Credit: 1,102,216,607
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwat
Message 46073 - Posted: 5 Jan 2017 | 0:26:22 UTC

All of you are correct ... and I like playing games too.

But I admit to be biased in this regard. Because my little son suffers from muscle weakness and that is one reason for my Boinc participation. Yes, either of us must perish some day, but nobody shall be shunned by the world and in torment until his last breath. Especially not our little ones. Those of us who have children in chronic pain, suffering from Muscular Dystrophy, COAD, Autism, epilepsy, FXS or Rett know how I feel...

Can you imagine, what if all the gamers worldwide would spend their GPU power for a week ... just a single week...
____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

James
Send message
Joined: 22 Dec 16
Posts: 3
Credit: 88,212,575
RAC: 0
Level
Thr
Scientific publications
watwat
Message 46170 - Posted: 14 Jan 2017 | 3:50:55 UTC

1.21 Jigawatts

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2305
Credit: 16,131,308,517
RAC: 2,393,918
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46181 - Posted: 14 Jan 2017 | 21:57:24 UTC - in response to Message 46170.

1.21 Jigawatts


That's funny, I call one of my computers flux-capacitor :)

JoergF
Avatar
Send message
Joined: 20 Apr 15
Posts: 285
Credit: 1,102,216,607
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwat
Message 46184 - Posted: 15 Jan 2017 | 0:37:58 UTC

That definitely is not enough!


____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

PappaLitto
Send message
Joined: 21 Mar 16
Posts: 508
Credit: 4,607,207,341
RAC: 0
Level
Arg
Scientific publications
watwatwatwatwatwatwatwat
Message 46222 - Posted: 18 Jan 2017 | 11:51:33 UTC

Up to 2.4 PetaFLOPS now!

PappaLitto
Send message
Joined: 21 Mar 16
Posts: 508
Credit: 4,607,207,341
RAC: 0
Level
Arg
Scientific publications
watwatwatwatwatwatwatwat
Message 46224 - Posted: 18 Jan 2017 | 14:05:13 UTC

Does anyone know the highest its even been?

Betting Slip
Send message
Joined: 5 Jan 09
Posts: 670
Credit: 2,498,095,550
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46226 - Posted: 18 Jan 2017 | 14:35:09 UTC - in response to Message 46224.

2.5xx Peta Flops in recent times when there is a constant flow of work. Obviously any interuption in work flow will reduce it quickly and takes a while to recover.

Profile God is Love, JC proves it...
Avatar
Send message
Joined: 24 Nov 11
Posts: 30
Credit: 188,758,560
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwat
Message 46377 - Posted: 28 Jan 2017 | 22:33:27 UTC - in response to Message 46046.
Last modified: 28 Jan 2017 | 22:39:09 UTC

Not sure if there might be a better thread for this question, especially as it has been ignored for nearly four weeks, but I concur (mostly):

"My only concern about this project is how long it will be running. Before I put more money to it, I'd like to feel at ease that it won't end any time soon(possibly a time estimate on how long it will run?). Might seem foolish but I see these other projects closing down. I don't want to go out and buy something and then have this project be done."

While I do run quite a few other projects, I (try to) use my GPU exclusively for GpuGrid. (A reasonable alternative was POEM, but that has now folded [pun intended]). I have in the past (about 3-4 years ago) invested in a (+- small) upgrade. I am pondering doing so again. As I've posted before: I am NOT a gamer. I have a GPU solely to support scientific computing projects.

SO, some moderator,... any moderator... any idea how long GPU might keep rolling along?
I presume this really is a question not for a moderator, but for some of the academic faculty doing research which feeds the computing needs for this project.

Thanks,
LLP PhD PE
____________
I think ∴ I THINK I am
My thinking neither is the source of my being
NOR proves it to you
God Is Love, Jesus proves it! ∴ we are

JoergF
Avatar
Send message
Joined: 20 Apr 15
Posts: 285
Credit: 1,102,216,607
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwat
Message 46378 - Posted: 29 Jan 2017 | 8:43:05 UTC
Last modified: 29 Jan 2017 | 8:43:57 UTC

This department has half a dozen of researchers and therefore the termination of all their investigations on short notice is VERY unlikely. They would have to cancel some labour contracts, lectures and dissertations otherwise. Of course life is not 100% safe and predictable, but even if they would stop all the simulations you can anytime move to Folding@Home and let your GPU help there.

Besides, 'unemployed' GPUs can be sold again. Assuming that you don't want to spend a lot of money for the card (as you do not play games with it) and the electricity cost I guess the gtx 1050 (or 1050ti) for 120-160€ is a good idea. Most of those don't even require a 6-pin supply from the PSU. So the amount invested and the risk of capital loss seem not hypercritical to me...
____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

Post to thread

Message boards : Number crunching : BOINC Supercomputer