|
1)
Message boards :
Graphics cards (GPUs) :
Which graphic card
(Message 30287)
Posted 8 hours ago by  Retvari Zoltan*
Going back a year to when the top GPU's were CC2.0, a GTX470 did 29% more work than a GTX560Ti. I think it's because the newer apps are made with CUDA4.2. With super-scaler cards you can never utilize all the shaders fully, ... It's true even for a non super-scalar card :) I would say that the non-super-scalar cards (still) have a significant advantage over the super-scalar cards in the shader utilizaiton. ... but I think its went up from 66% to around 80%. This advantage is less than it was with the CUDA3.1 apps (it was around 33%) It's too bad from the cruncher's perspective that nVidia doesn't make non-super-scalar GPUs anymore, but (as kind of compensation) the good news is that the CUDA4.2 can better utilize the super-scalar architecture than the CUDA3.1. This discussion is difficult, because we're talking about the performance of a system consisting many parts, all of these parts continuously changing over time, and this change could alter (like it did in the past) their order of significance: 1. I/a The GPU 2. I/b The code running on the GPU 3. II - The computer (also a system consisting many parts) 4. II/a The operating system of the computer 5. II/b The optimization of the BOINC client for the hardware it's running on 6. II/c The hardware components of the computer (beside the GPU) This is the actual order. Except for item 2, the participants can optimize this system. But item 2 is the fundamental of this optimization: I've changed my Core 2 Quad systems to Core i7 systems to achieve better overall performance by eliminating the PCIe bandwith bottleneck which reduced the performance of the CUDA3.1 client. The CUDA 4.2 client is better in regards of this issue also, so no such change (read it as investment) is needed now from the participants. But you still have to spare a CPU thread per GPU (item 5) |
|
2)
Message boards :
Number crunching :
NOELIAs are back!
(Message 29854)
Posted 12 days ago by Retvari Zoltan*
Problem for me: much too long, won't finish on time on my 470GTX. :( Your GTX 470 should be fast enough to complete a NOELIA_klebe workunit in time (about 12 hours). It takes 10h45m ~ 11h45m to process them on my (slightly overclocked) GTX 480. So the problem is at your end, try to restart your host, or try not to crunch any CPU tasks on your P4. |
|
3)
Message boards :
Number crunching :
A trick (for the scientists) to fold proteins more quickly
(Message 29754)
Posted 16 days ago by Retvari Zoltan*
Quote from http://phys.org/news/2013-05-proteins-quickly.html "We exploit the experimental data obtained observing the proteins through nuclear magnetic resonance, and use them to create restraints to be applied to the model", explained Laio, who has coordinated the research published in Proceedings of the National Academy of Sciences (PNAS). This reads to me like "If we know the shape of the protein, we can create restraints to make the model fold more quickly". That's ok. But usually we fold proteins with computers because we can't obtain the shape of a given protein by different methods. If we could obtain the shape of all proteins by measurements, the rules of their folding still would be unknown. The real question is not their shape, but the rules make them form to their shape. Or am I missing something here? |
|
4)
Message boards :
Number crunching :
NOELIAs are back!
(Message 29745)
Posted 16 days ago by Retvari Zoltan*
These new units are using really low CPU power. The gpus are way cooler aswell, and the processing times seems to be very high. Not using all the hardware. +1 |
|
5)
Message boards :
Number crunching :
NOELIAs are back!
(Message 29744)
Posted 16 days ago by Retvari Zoltan*
I had two failures, and many successful 'NOELIA_klebe_run-0-3's. The first one was stuck for 8 hours before I noticed it, but after a system restart it immediately ran into an error "Kernel not foundAssertion failed: a, file swanlibnv2.cpp, line 59". The second one ran for 3 hours, then ran into an "ERROR: file deven.cpp line 1743: deven_Cellresize(): invalid dimensions" - it's probably due to overclocking. |
|
6)
Message boards :
GPUGRID CAFE :
The milestone thread
(Message 29605)
Posted 24 days ago by Retvari Zoltan*
I've earned 1,830,236,455 credits in GPUGrid so far. According to Boincstats, today I've reached 1,853,492,168 credits combined of all projects. I think you might wonder why this hard-to-read number is so important for me, that I pay tribute to it? Well, I'm not drunk (maybe I should be), and I don't know if it's a prime number either - it doesn't matter anyway -, but it's important because it makes me the 60th BOINC cruncher in the world. Now, this is a much easier readable number (surely not a prime), but you can still wonder, why exactly the 60th place is so important to me? The importance is that the 60th place makes me the highest ever Hungarian cruncher on the combined toplist. The previous record holder is this guy. He was 61st on 14. september 2004. I wonder how much credit he had on that day? Today he has 13,425,857 credits (combined). When everything runs smoothly, my 10 GPUs earn this much credit in 3 days. That's quite a development in computing technology. So today I just broke an 8 and a half year old national record, and it makes me quite proud of myself :) I've started hardcore crunching in May 2010, so it took me (and for my girlfriend) almost 3 years. It wouldn't be possible without Her constant support, so I would like to thank Her for that! Now that I could say I've reached my goal, I wonder how long my record will last? One thing is sure: my future competitors will have a much harder time in getting above the 60th place than I had. I had to post this because I think that the best audience to share my delight is all of you here in GPUGrid. Don't worry - I'll keep on crunching. :) I wish you to enjoy crunching as much as I enjoy it! Regardless of your goals or competitors, always keep in mind that in crunching we're not competitors at all: we're partners. I will think of that when I begin to fall back on the toplist. |
|
7)
Message boards :
Graphics cards (GPUs) :
A little warning to GTX690 owners
(Message 29592)
Posted 26 days ago by Retvari Zoltan*
what was the cause of the error? The workunits didn't fail, only the card. The GTX670 finished the two workunits which the GTX 690 could process only partially. |
|
8)
Message boards :
Graphics cards (GPUs) :
A little warning to GTX690 owners
(Message 29584)
Posted 26 days ago by Retvari Zoltan*
The temperatures of the GTX 690 were 62°C and 65°C. Everything was OK. This host had a GTX 670 beside the GTX 690. The GTX 670 kept on crunching fine after the GTX 690 had failed. I didn't overclocked the GTX 690. It simply broke down in the middle of crunching. This host has an Enermax MaxRevo 1500W power supply, and an ASUS Rampage III Extreme motherboard. |
|
9)
Message boards :
Graphics cards (GPUs) :
A little warning to GTX690 owners
(Message 29575)
Posted 27 days ago by Retvari Zoltan*
My only GTX 690 (with the failed then changed cooling) has failed yesterday while it was crunching. There was no environmental hazard of any kind. |
|
10)
Message boards :
Number crunching :
NATHAN_dhfr36 problems
(Message 29545)
Posted 30 days ago by Retvari Zoltan*
I've got another one of this. I've spotted it after 74 hours... After a system restart it's ran into an application error. |
Next 10