According to the German computer magazine "c't computertechnik" the 90000 PC's working for einstein@home are no longer effective enough to get the job done.
Why is my PC (Q9330 Quadcore, 4096 MB RAM, Vista Ultimate 64 bit) too poor for that? Does it make sense any longer to support the project?
Intel Q9300 Quadcore, 2500 Mhz, 4096 MB RAM, GeForce 9800 GT, Vista Ultimate 64-bit, Ubuntu 10.10 64 bit
According to the German computer magazine "c't computertechnik" the 90000 PC's working for einstein@home are no longer effective enough to get the job done.
Why is my PC (Q9330 Quadcore, 4096 MB RAM, Vista Ultimate 64 bit) too poor for that? Does it make sense any longer to support the project?
They perhaps need additional computing power is my take on this. I would imagine if we were no longer needed they would close up this web site! ;)
Sounds like the SSE/SSE2 app will need to be pushed to the Windows clients, then. That would add a significant speedup, but not like a GPU client would. It would probably take the building and optimizing of several applications to add significant processing to the project as I don't think that there would be a notable increase in the number of users or hosts since this project is getting mature now.
According to the German computer magazine "c't computertechnik" the 90000 PC's working for einstein@home are no longer effective enough to get the job done.
Were they quoting anyone from the project management? Had they done some detailed analysis of the project?
Quote:
Why is my PC (Q9330 Quadcore, 4096 MB RAM, Vista Ultimate 64 bit) too poor for that?
Certainly isn't!
Quote:
Does it make sense any longer to support the project?
Makes good sense, if that floats your boat.
The only sensible take I can think of is that one can always exceed computing power for signal analysis tasks. It depends what you are looking for and to what desired level of sensitivity. It can be a bottomless pit. The reason we have E@H is to examine long stretches of data for some regularities, generated from a detector which is on a platform moving with respect to the source. This motion complicates the pickup of even 'simple' waveforms.
I've always taken the view that even if our current work yields no positive signal detection in the near term, then at least it hones the whole processing/pipeline shebang. So that gives specific benefits - obviously actual detections at some time, but also confidence in their reliability, and in an efficient manner without misses. If there's smoke you want to be sure it's a fire, and if there's no smoke then where did the fire go?
It is hard to find an exact analogy in history ( for anything ), but I'd liken matters to the invention of the telescope: some guy in Holland grinds a bit of glass and looks at Paramecia, another guy in Poland attaches these ground glass pieces together, points it at the sky and finds .... oh gosh .... lots of stars and stuff, yet another fellow in Italy improves upon it and then looks closely at planets ..... finds some moons .... gets in trouble with the Pope .... etc.
Would "c't computertechnik" have said Leeuwenhoek was going to be too overwhelmed with things to look at, so why bother?
Not that you could tell, but I'm rather biased in this. :-)
It sounds like yet more rubbish from media outlets which can do little beyond making noise to sell copy. But please correct me if that's not the tenor of the article.
Cheers, Mike.
I have made this letter longer than usual because I lack the time to make it shorter ...
... and my other CPU is a Ryzen 5950X :-) Blaise Pascal
>"I've always taken the view that even if our current work yields no positive signal detection in the near term, then at least it hones the whole processing/pipeline shebang. So that gives specific benefits - obviously actual detections at some time, but also confidence in their reliability, and in an efficient manner without misses. If there's smoke you want to be sure it's a fire, and if there's no smoke then where did the fire go?"<
Right on. Sometimes negative results are just as important as positive ones. Physicists once thought "aether" permeated space. Along came Michelson and Morley and ran their experiment - negative results - new theory required. Probably was grist for Einstein's mill.
edit - P.S. They used an early version of the devices we're using in the search for gravity waves.
... Why is my PC (Q9330 Quadcore, 4096 MB RAM, Vista Ultimate 64 bit) too poor for that? ...
Because of vista. ;D
(Couldn't resist)
Greetings,
Hey, buddy, the first gravitational wave will be detected by a PC running Vista 64bit SP 1, believe me!
Mike:
Thanks for your posting. Two cores of my cpu will go on working 6/24 for einstein@home and analysing signals from "black suns", while the other two are playing around with seti@home and astropulse. The electricity bill will be interesting too -- uups!
Intel Q9300 Quadcore, 2500 Mhz, 4096 MB RAM, GeForce 9800 GT, Vista Ultimate 64-bit, Ubuntu 10.10 64 bit
According to the German computer magazine "c't computertechnik" the 90000 PC's working for einstein@home are no longer effective enough to get the job done.
Were they quoting anyone from the project management? Had they done some detailed analysis of the project?
Do you refer to c't 13/2008, S. 18: Supercomputer? There Andreas Stiller points out that the average Einstein@home host doesn't have the necessary "local capacity" ("lokale Speicherkapazität"). This is a bit misleading; actually the limiting factor for the searches we can run on Einstein@home is not so much the local power of the participant's machines, but the bandwidth with which we can transfer data between these and our servers. If we'd have a network to the Einstein@home participants as powerful as that we have on ATLAS - non-blocking "wire-speed" Gigabit-Ethernet between 1342 Nodes (4 cores per node, not 671 with 8 cores as Andreas wrote), we wouldn't need ATLAS.
ATLAS will run different types of searches for gravitational waves that are not suitable for Einstein@home, e.g. because you can't easily split the required data into such small pieces as we do for the continuous wave search. Probably similar to what Nemo does now (the "nice" CPU is usually Einstein@home).
Edit: ATLAS will probably contribute its idle time to Einstein@home from S5R4 on.
Shadoks .... my kinda guys,
)
Shadoks .... my kinda guys, what an unbeatable philosophy! :-)
Cheers, Mike.
I have made this letter longer than usual because I lack the time to make it shorter ...
... and my other CPU is a Ryzen 5950X :-) Blaise Pascal
According to the German
)
According to the German computer magazine "c't computertechnik" the 90000 PC's working for einstein@home are no longer effective enough to get the job done.
Why is my PC (Q9330 Quadcore, 4096 MB RAM, Vista Ultimate 64 bit) too poor for that? Does it make sense any longer to support the project?
Intel Q9300 Quadcore, 2500 Mhz, 4096 MB RAM, GeForce 9800 GT, Vista Ultimate 64-bit, Ubuntu 10.10 64 bit
RE: According to the German
)
They perhaps need additional computing power is my take on this. I would imagine if we were no longer needed they would close up this web site! ;)
is it possible that in the
)
is it possible that in the near future (s5r4) a GPU aplication will be developed?
Sounds like the SSE/SSE2 app
)
Sounds like the SSE/SSE2 app will need to be pushed to the Windows clients, then. That would add a significant speedup, but not like a GPU client would. It would probably take the building and optimizing of several applications to add significant processing to the project as I don't think that there would be a notable increase in the number of users or hosts since this project is getting mature now.
RE: According to the German
)
Were they quoting anyone from the project management? Had they done some detailed analysis of the project?
Certainly isn't!
Makes good sense, if that floats your boat.
The only sensible take I can think of is that one can always exceed computing power for signal analysis tasks. It depends what you are looking for and to what desired level of sensitivity. It can be a bottomless pit. The reason we have E@H is to examine long stretches of data for some regularities, generated from a detector which is on a platform moving with respect to the source. This motion complicates the pickup of even 'simple' waveforms.
I've always taken the view that even if our current work yields no positive signal detection in the near term, then at least it hones the whole processing/pipeline shebang. So that gives specific benefits - obviously actual detections at some time, but also confidence in their reliability, and in an efficient manner without misses. If there's smoke you want to be sure it's a fire, and if there's no smoke then where did the fire go?
It is hard to find an exact analogy in history ( for anything ), but I'd liken matters to the invention of the telescope: some guy in Holland grinds a bit of glass and looks at Paramecia, another guy in Poland attaches these ground glass pieces together, points it at the sky and finds .... oh gosh .... lots of stars and stuff, yet another fellow in Italy improves upon it and then looks closely at planets ..... finds some moons .... gets in trouble with the Pope .... etc.
Would "c't computertechnik" have said Leeuwenhoek was going to be too overwhelmed with things to look at, so why bother?
Not that you could tell, but I'm rather biased in this. :-)
It sounds like yet more rubbish from media outlets which can do little beyond making noise to sell copy. But please correct me if that's not the tenor of the article.
Cheers, Mike.
I have made this letter longer than usual because I lack the time to make it shorter ...
... and my other CPU is a Ryzen 5950X :-) Blaise Pascal
RE: ... Why is my PC (Q9330
)
Because of vista. ;D
(Couldn't resist)
Greetings,
>"I've always taken the view
)
>"I've always taken the view that even if our current work yields no positive signal detection in the near term, then at least it hones the whole processing/pipeline shebang. So that gives specific benefits - obviously actual detections at some time, but also confidence in their reliability, and in an efficient manner without misses. If there's smoke you want to be sure it's a fire, and if there's no smoke then where did the fire go?"<
Right on. Sometimes negative results are just as important as positive ones. Physicists once thought "aether" permeated space. Along came Michelson and Morley and ran their experiment - negative results - new theory required. Probably was grist for Einstein's mill.
edit - P.S. They used an early version of the devices we're using in the search for gravity waves.
http://hyperphysics.phy-astr.gsu.edu/hbase/Relativ/mmhist.html#c1
Joe B
RE: RE: ... Why is my PC
)
Hey, buddy, the first gravitational wave will be detected by a PC running Vista 64bit SP 1, believe me!
Mike:
Thanks for your posting. Two cores of my cpu will go on working 6/24 for einstein@home and analysing signals from "black suns", while the other two are playing around with seti@home and astropulse. The electricity bill will be interesting too -- uups!
Intel Q9300 Quadcore, 2500 Mhz, 4096 MB RAM, GeForce 9800 GT, Vista Ultimate 64-bit, Ubuntu 10.10 64 bit
RE: RE: According to the
)
Do you refer to c't 13/2008, S. 18: Supercomputer? There Andreas Stiller points out that the average Einstein@home host doesn't have the necessary "local capacity" ("lokale Speicherkapazität"). This is a bit misleading; actually the limiting factor for the searches we can run on Einstein@home is not so much the local power of the participant's machines, but the bandwidth with which we can transfer data between these and our servers. If we'd have a network to the Einstein@home participants as powerful as that we have on ATLAS - non-blocking "wire-speed" Gigabit-Ethernet between 1342 Nodes (4 cores per node, not 671 with 8 cores as Andreas wrote), we wouldn't need ATLAS.
ATLAS will run different types of searches for gravitational waves that are not suitable for Einstein@home, e.g. because you can't easily split the required data into such small pieces as we do for the continuous wave search. Probably similar to what Nemo does now (the "nice" CPU is usually Einstein@home).
Edit: ATLAS will probably contribute its idle time to Einstein@home from S5R4 on.
BM
BM