Advanced search

Message boards : Number crunching : Version 9.18 Takes longer

Author Message
PappaLitto
Send message
Joined: 21 Mar 16
Posts: 262
Credit: 1,192,238,406
RAC: 4,709,215
Level
Met
Scientific publications
watwat
Message 47073 - Posted: 24 Apr 2017 | 10:40:38 UTC

App 9.18 seems to take way longer to get the same WUs done than 9.15, is there an explanation behind this? Upwards of 20-30% longer

John C MacAlister
Send message
Joined: 17 Feb 13
Posts: 178
Credit: 132,357,411
RAC: 24,273
Level
Cys
Scientific publications
watwatwatwatwatwatwatwat
Message 47074 - Posted: 24 Apr 2017 | 12:58:37 UTC

My WUs are running for around 27h on my GTX 660 Ti cards. I cannot use my 650 Ti cards as the run time is much higher. I guess my days at GPUGrid may be drawing to a close as these cards can't keep up.
____________
John

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47075 - Posted: 24 Apr 2017 | 15:08:12 UTC

If I compare the crunching times of 918-80 with what they were before with 847-65 / 848-65, I, too, notice a considerable increase.
This is true for my GTX750ti on Windows10 and the GTX970 on Windows 10 - they now need about 30% longer :-(

Since at the same time I had to update the drivers to 381.65, it's hard to say whether the raise in crunching time is mainly due to the new acemd version, or mainly due to the new driver, or both.
What could also be the case is that, for what reason ever, the WDDM overhead now has a much more negative effect.

Hence, the main question seems to be whether anything can be done in order to get the former speed back.

What concerns the change from 847-65 / 848-65 to 849-65 for Windows XP, no WDDM overhead, (one GTX750ti and two GTX980ti), the crunching times seem to be only slightly higher than before.

Would be interesting to hear how the situation is with Linux.

Jim1348
Send message
Joined: 28 Jul 12
Posts: 455
Credit: 1,130,760,908
RAC: 182,632
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwat
Message 47076 - Posted: 24 Apr 2017 | 15:58:02 UTC - in response to Message 47075.

Would be interesting to hear how the situation is with Linux.

Linux has stayed on the 9.14 application for the past few months, at least for my GTX 960/970 and I think the Pascal cards too. It was originally the usual 15% or so speed improvement over Windows, though that may have now increased.

But I don't see the page listing the applications at the moment. Either I am not looking in the right place, or maybe they are updating it.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47077 - Posted: 24 Apr 2017 | 16:52:46 UTC - in response to Message 47076.

But I don't see the page listing the applications at the moment. Either I am not looking in the right place, or maybe they are updating it.

Jim, are you talking about this:
http://gpugrid.net/forum_thread.php?id=4551&nowrap=true#46981

Jim1348
Send message
Joined: 28 Jul 12
Posts: 455
Credit: 1,130,760,908
RAC: 182,632
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwat
Message 47078 - Posted: 24 Apr 2017 | 17:59:48 UTC - in response to Message 47077.
Last modified: 24 Apr 2017 | 18:01:24 UTC

Didn't they have a separate page listing all the apps for Window, Linux, etc, along with the dates? I thought so, and I saw that the Linux 9.14 version came out last year. Or else I am just imagining it; maybe I got it right? Who knows.

PappaLitto
Send message
Joined: 21 Mar 16
Posts: 262
Credit: 1,192,238,406
RAC: 4,709,215
Level
Met
Scientific publications
watwat
Message 47079 - Posted: 24 Apr 2017 | 18:02:05 UTC

With the lack of Pascal Windows XP support, and now with the dramatic slowdown of WDDM modern windows OS's. It looks like we must change our crunching rigs to linux as it is still running the 9.14 app, with no WDDM and no 9.18 slowdown.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47080 - Posted: 24 Apr 2017 | 18:07:04 UTC - in response to Message 47079.

... It looks like we must change our crunching rigs to linux as it is still running the 9.14 app, with no WDDM and no 9.18 slowdown.

but who can tell how long Linux will be running the 9.14 app - before changing to 9.18 or any newer (and also slower) app maybe in the near future?

PappaLitto
Send message
Joined: 21 Mar 16
Posts: 262
Credit: 1,192,238,406
RAC: 4,709,215
Level
Met
Scientific publications
watwat
Message 47081 - Posted: 24 Apr 2017 | 18:12:12 UTC - in response to Message 47080.

but who can tell how long Linux will be running the 9.14 app - before changing to 9.18 or any newer (and also slower) app maybe in the near future?

Clearly it's a bug of 9.18 so they definitely would not hinder themselves any further until 9.19 comes out hopefully fixing the problem. Scientists are some of the most impatient people, so I'm sure they want this fixed faster than any of us

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 1836
Credit: 10,414,223,794
RAC: 8,653,992
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 47083 - Posted: 24 Apr 2017 | 18:35:08 UTC - in response to Message 47076.
Last modified: 24 Apr 2017 | 18:36:14 UTC

But I don't see the page listing the applications at the moment. Either I am not looking in the right place, or maybe they are updating it.
You can find them here. This page is not linked from the GPUGrid pages, so it's no wonder that you didn't see it.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47087 - Posted: 24 Apr 2017 | 19:14:28 UTC - in response to Message 47083.

You can find them here.

although this information is somewhat misleading what concerns 64bit Windows. Because if the 64bit Windows is a Windows XP, it runs with 8.49 (cuda65)

Microsoft Windows (98 or later) running on an Intel x86-compatible CPU 8.49 (cuda65) 17 Apr 2017 | 19:06:31 UTC
Microsoft Windows (98 or later) running on an Intel x86-compatible CPU 9.18 (cuda80) 16 Apr 2017 | 0:40:05 UTC
Linux running on an AMD x86_64 or Intel EM64T CPU 9.14 (cuda80) 1 Nov 2016 | 21:27:32 UTC
64bit Windows 9.18 (cuda80)

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47204 - Posted: 13 May 2017 | 15:14:21 UTC - in response to Message 47075.

If I compare the crunching times of 918-80 with what they were before with 847-65 / 848-65, I, too, notice a considerable increase.
This is true for my GTX750ti on Windows10 and the GTX970 on Windows 10 - they now need about 30% longer :-(

Since at the same time I had to update the drivers to 381.65, it's hard to say whether the raise in crunching time is mainly due to the new acemd version, or mainly due to the new driver, or both.
What could also be the case is that, for what reason ever, the WDDM overhead now has a much more negative effect.

Hence, the main question seems to be whether anything can be done in order to get the former speed back.

What concerns the change from 847-65 / 848-65 to 849-65 for Windows XP, no WDDM overhead, (one GTX750ti and two GTX980ti), the crunching times seem to be only slightly higher than before.

Would be interesting to hear how the situation is with Linux.

In view of the above-said, plus my experience from the last three weeks, I strongly suggest that in the preferences for download of tasks, beside "short runs" and "long runs", a third category like "extra long runs" or similar, should be introduced.

A typical candidate for such an "extra long runs" would be "ADRIA_FOLDGREED90_crystal_ss_contacts_100_ubiquitin..."
which on my GTX750Ti in the Windows10 machine takes close to 60 hours (on Windows XP with software 849-65 and an older driver, crunching time is considerably shorter).

Beside the extremely, if not rediculously long crunching time, crunching these sort of tasks with the GTX750Ti on Windows10 is rather unstable. Even the slightest overclocking can lead to immediate halts - the only thing one then can do (as soon as one finds out, which might take a while - for example over night) is to suspend and restart the task. So it's been the case here that the total time for such a task was 3 days! Forget about it! A GTX750ti on Windows10 is definitely overtaxed with such a task.

Hence, crunchers with smaller/older cards would definitely wish to exclude tasks like the "_100_ubiquitin..." from download.
Be it coinsidence or not: what I have watched all time long was that my two GTX750Ti tend to receive such long tasks almost all the time, whereas my GTX980Ti's get smaller tasks (like the "Adria") as well. No idea why, it just seems worth to be mentioned (maybe someone knows more about this phenomen).

Anyway, at the bottom line: while it's clear that we crunchers should not be allowed to choose a specific type of task (this clearly remains in the priority determination of the GPUGRID people), a third category "extra long runs" would help quite a lot.
As everyone can imagine: total running time of nearly 3 days is rather frustrating, besides that it does not make a whole lot of sense :-(

Jim1348
Send message
Joined: 28 Jul 12
Posts: 455
Credit: 1,130,760,908
RAC: 182,632
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwat
Message 47205 - Posted: 13 May 2017 | 15:27:24 UTC - in response to Message 47204.
Last modified: 13 May 2017 | 15:30:17 UTC

I think you have it backwards. The "long" category is for the latest cards, which the GTX 750 Ti is not. It is wonderful for efficiency (I have several), but it is not a powerhouse. So use it on "shorts", where it can do its thing.

I know, there are not enough shorts to keep it busy. That is a consequence of the science they need to do. Rule #1 for me is that we are here to help them. They are not here to provide us something to do with our cards.

PS: An extra category for "extra longs" is a good idea, but it won't save the GTX 750 Ti.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47207 - Posted: 13 May 2017 | 17:30:00 UTC - in response to Message 47205.

PS: An extra category for "extra longs" is a good idea, but it won't save the GTX 750 Ti.

But it would help to assign to the GTX750ti those "longruns" which are not that much of a problem for it :-) (and there are still many of such task around)

Jim1348
Send message
Joined: 28 Jul 12
Posts: 455
Credit: 1,130,760,908
RAC: 182,632
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwat
Message 47208 - Posted: 13 May 2017 | 17:49:59 UTC - in response to Message 47207.
Last modified: 13 May 2017 | 18:04:13 UTC

PS: An extra category for "extra longs" is a good idea, but it won't save the GTX 750 Ti.

But it would help to assign to the GTX750ti those "longruns" which are not that much of a problem for it :-) (and there are still many of such task around)

I guess you are saying that they could then exclude those extra long runs. So it could be a good idea with that in mind.

PS - I just pulled a GTX 750 Ti out and replaced it with a GTX 1060 on my Win7 64-bit machine. Too bad the app is not optimized for it now, but I will try it later. And anything to extend the life of the GTX 750 Ti is a good idea if you don't insist on the 50% bonus, which is not that important anyway.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47209 - Posted: 13 May 2017 | 18:06:27 UTC - in response to Message 47208.
Last modified: 13 May 2017 | 18:08:50 UTC

I guess you are saying that they could then exclude those extra long runs. So it could be a good idea with that in mind.

yes, this is exactly what I am saying :-) Would make a lot of sense.

Of course, like in many other areas, things are progressing. So at GPUGRID, too.
When some 15 months ago, I started adding two GTX980ti to my crunching hardware (which had been very modest until then), no "longruns" took longer than 6-7 hours.
And with the GTX750ti, I could finish almost any "longruns" within the 24-hours-bonus-period.

But things have changed, obviously.
Nowadays, for some "longruns" it takes my GTX980ti's almost double time than a year ago.
And the GTX750ti's are brought to the verge of their capibilities with those extreme "longruns" like, as already mentioned, the "ADRIA_FOLDGREED90_crystal_ss_contacts_100_ubiquitin" - for example.
Besides that, as also said above, the latest crunching software increases the crunching time markedly, up to 30% (any idea at all why this is so?)

Hence, as said before, the introduction of 2 types of "longruns" would be very useful. I would guess that quite a number of crunchers are still using the GTX750ti, which definitely is a perfect card for mid-range tasks.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47312 - Posted: 23 May 2017 | 6:56:32 UTC - in response to Message 47208.

PS - I just pulled a GTX 750 Ti out and replaced it with a GTX 1060 on my Win7 64-bit machine. Too bad the app is not optimized for it now, but I will try it later.

I also was playing with the same idea. However, I am unsure now, particularly after you are saying "the app is not optimized for it now" - what exactly do you mean?

Another setback would be that, at least from what I read somewhere here in the Forum, the Pascals dont's work with the NVIDIA Inspector, which is too bad.

Jim1348
Send message
Joined: 28 Jul 12
Posts: 455
Credit: 1,130,760,908
RAC: 182,632
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwat
Message 47314 - Posted: 23 May 2017 | 10:14:48 UTC - in response to Message 47312.

I also was playing with the same idea. However, I am unsure now, particularly after you are saying "the app is not optimized for it now" - what exactly do you mean?

I just mean that 9.18 is not as fast as 9.15, at least from the reports, though I never tried the GTX 1060 on 9.15 so I don't know directly.

But here it is:
http://www.gpugrid.net/results.php?hostid=177999

That is still efficient, but not as much as it could be.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47331 - Posted: 27 May 2017 | 19:15:45 UTC - in response to Message 47204.

If I compare the crunching times of 918-80 with what they were before with 847-65 / 848-65, I, too, notice a considerable increase.
This is true for my GTX750ti on Windows10 and the GTX970 on Windows 10 - they now need about 30% longer :-(

Since at the same time I had to update the drivers to 381.65, it's hard to say whether the raise in crunching time is mainly due to the new acemd version, or mainly due to the new driver, or both.
What could also be the case is that, for what reason ever, the WDDM overhead now has a much more negative effect.

Hence, the main question seems to be whether anything can be done in order to get the former speed back.

What concerns the change from 847-65 / 848-65 to 849-65 for Windows XP, no WDDM overhead, (one GTX750ti and two GTX980ti), the crunching times seem to be only slightly higher than before.

Would be interesting to hear how the situation is with Linux.

In view of the above-said, plus my experience from the last three weeks, I strongly suggest that in the preferences for download of tasks, beside "short runs" and "long runs", a third category like "extra long runs" or similar, should be introduced.

A typical candidate for such an "extra long runs" would be "ADRIA_FOLDGREED90_crystal_ss_contacts_100_ubiquitin..."
which on my GTX750Ti in the Windows10 machine takes close to 60 hours (on Windows XP with software 849-65 and an older driver, crunching time is considerably shorter).

Beside the extremely, if not rediculously long crunching time, crunching these sort of tasks with the GTX750Ti on Windows10 is rather unstable. Even the slightest overclocking can lead to immediate halts - the only thing one then can do (as soon as one finds out, which might take a while - for example over night) is to suspend and restart the task. So it's been the case here that the total time for such a task was 3 days! Forget about it! A GTX750ti on Windows10 is definitely overtaxed with such a task.

Hence, crunchers with smaller/older cards would definitely wish to exclude tasks like the "_100_ubiquitin..." from download.
Be it coinsidence or not: what I have watched all time long was that my two GTX750Ti tend to receive such long tasks almost all the time, whereas my GTX980Ti's get smaller tasks (like the "Adria") as well. No idea why, it just seems worth to be mentioned (maybe someone knows more about this phenomen).

Anyway, at the bottom line: while it's clear that we crunchers should not be allowed to choose a specific type of task (this clearly remains in the priority determination of the GPUGRID people), a third category "extra long runs" would help quite a lot.
As everyone can imagine: total running time of nearly 3 days is rather frustrating, besides that it does not make a whole lot of sense :-(

any thoughts from GPUGRID side on my suggestion above ?
Good idea - bad idea ?
Feasible - not feasible ?

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47360 - Posted: 3 Jun 2017 | 20:00:35 UTC - in response to Message 47331.

...
any thoughts from GPUGRID side on my suggestion above ?
Good idea - bad idea ?
Feasible - not feasible ?

still no reaction whatsoever from the GPUGRID team - why so?

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47420 - Posted: 13 Jun 2017 | 6:44:46 UTC - in response to Message 47360.

...
any thoughts from GPUGRID side on my suggestion above ?
Good idea - bad idea ?
Feasible - not feasible ?

still no reaction whatsoever from the GPUGRID team - why so?


is my idea/suggestion that bad that it's not even worth being considered to be implemented?

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2670
Credit: 739,666,324
RAC: 660,949
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 47448 - Posted: 15 Jun 2017 | 21:57:07 UTC - in response to Message 47312.

the Pascals dont's work with the NVIDIA Inspector

Wrong, worked just fine with my GTX1060 and nwo with my GTX1070.

is my idea/suggestion that bad that it's not even worth being considered to be implemented?

Well.. the current project team is not the most active in the forums, so I suspect they didn't even notice your request. Personally I agree that it's strange to alost not use the short runs queue at all and have long runs which differ by more than a factor of 2 in the runtime. That's clearly two different WU categories, so if they don't want to introduce a 3rd tier they coulöd at least use the 2 which they already have.

MrS
____________
Scanning for our furry friends since Jan 2002

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47450 - Posted: 16 Jun 2017 | 14:18:51 UTC - in response to Message 47448.

the Pascals dont's work with the NVIDIA Inspector
Wrong, worked just fine with my GTX1060 and nwo with my GTX1070.
hm, this sounds interesting. A few months ago, I read somewhere here in the forum that the NVIDIA Inspector does not work with Pascals.
Maybe that guy had an older version in use - which version is your's?

is my idea/suggestion that bad that it's not even worth being considered to be implemented?

Well.. the current project team is not the most active in the forums, so I suspect they didn't even notice your request.
This is the problem with this project, in general.
As I already said, with a project of this magnitude, a certain amount of "customer care" is a vital component. They need to receive and to understand the feedback from the crunchers. If this doesn't happen, much will get worse.

Personally I agree that it's strange to alost not use the short runs queue at all and have long runs which differ by more than a factor of 2 in the runtime. That's clearly two different WU categories, so if they don't want to introduce a 3rd tier they could at least use the 2 which they already have.
For some of the recent tasks, like the "ADRIA_FOLDGREED90_crystal_ss_contacts_100_ubiquitin", a GTX750Ti under Windows10 is clearly overtaxed. It can take up to 3 days to get such a monstreous task finished (with several stops inbetween, caused by one if the bugs of the current crunching software).
So, it would definitely be important to implement a 3rd tier for such types of task.
And I am pretty sure that many crunchers are still using one or more GTX750Ti.

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2670
Credit: 739,666,324
RAC: 660,949
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 47456 - Posted: 16 Jun 2017 | 20:24:27 UTC - in response to Message 47450.
Last modified: 16 Jun 2017 | 20:25:28 UTC

I'm using NV Inspector 1.9.7.8. On afterthought: amybe he meant a certain feature was not working, or not working as intended. Setting the CUDA memory clock for Maxwell and Pascal is a bit weird.

BTW: on topic.. has there been any change notification from 9.15 to 9.18? Maybe they fixed some bug or added a feature, which resulted in more work being needed?

MrS
____________
Scanning for our furry friends since Jan 2002

Jim1348
Send message
Joined: 28 Jul 12
Posts: 455
Credit: 1,130,760,908
RAC: 182,632
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwat
Message 47457 - Posted: 16 Jun 2017 | 22:16:48 UTC - in response to Message 47456.

BTW: on topic.. has there been any change notification from 9.15 to 9.18? Maybe they fixed some bug or added a feature, which resulted in more work being needed?

I am really out of my depths here, and I apologize to Richard Haselgrove if I am referencing him out of context. But there is an interesting discussion on the BOINC forum between him and boboviz (among others) that touches on some of these issues.
http://boinc.berkeley.edu/dev/forum_thread.php?id=11647&postid=79043#79043

I think improvement in all areas would not hurt, but getting it done with the present limitations on both BOINC and GPUGrid (not to mention the Nvidia drivers) is another matter.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47458 - Posted: 17 Jun 2017 | 6:40:27 UTC - in response to Message 47457.

But there is an interesting discussion on the BOINC forum between him and boboviz (among others) that touches on some of these issues.
http://boinc.berkeley.edu/dev/forum_thread.php?id=11647&postid=79043#79043

I just read an interesting statement in the discussion there:

"gpugrid admins don't listen their volunteers. :-P"

which for me is best proof that I am not the only one who feels this.


Jim1348
Send message
Joined: 28 Jul 12
Posts: 455
Credit: 1,130,760,908
RAC: 182,632
Level
Met
Scientific publications
watwatwatwatwatwatwatwatwat
Message 47459 - Posted: 17 Jun 2017 | 11:47:55 UTC - in response to Message 47458.

No, I don't read it that way at all. They don't have the people (particularly with the BOINC expertise) to fix it. But on the other hand, why not go back to the old app for Windows? Maybe that would provide more output, or maybe just more confusion at this point.

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47460 - Posted: 17 Jun 2017 | 13:56:04 UTC - in response to Message 47459.

They don't have the people (particularly with the BOINC expertise) to fix it.

I guess it's not a matter of BOINC.
Fact is, that the new crunching software 918.80 was put together in a hurry and obviously not testet well enough; hence, it's buggy.

So, in order to eliminate the bugs, it would just need to re-work the software including thorough testing, and then releasing it.

ExtraTerrestrial Apes
Volunteer moderator
Volunteer tester
Avatar
Send message
Joined: 17 Aug 08
Posts: 2670
Credit: 739,666,324
RAC: 660,949
Level
Lys
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 47465 - Posted: 17 Jun 2017 | 21:26:45 UTC - in response to Message 47458.

which for me is best proof that I am not the only one who feels this.

No doubt about that. However, I see it this way: they're mainly scientist interested in doing good science. The number crunching is an essential part of it, but it's neither the only nor the most important one. For more important is what simulations they run and to analyse what the results actually mean. Apparently they're quite busy doing just that, as the project ran out of work several times in the last months.

I understand this as "We're limited by manpower to setup and process simulations and results. Having even more GPUs available or making them a few % faster wouldn't help us much."

Mind you, I'm not talking officially for the project and don't endorse an almost complete lack of communication. But it's something I keep in mind and lets me lay back relaxed, thinking that overall we're doing quite well (giving them a bit more power than they can handle). If they would have to wait for results we may see them more often in the forums, chatting and pushing for performance improvements and new users.

MrS
____________
Scanning for our furry friends since Jan 2002

Erich56
Send message
Joined: 1 Jan 15
Posts: 369
Credit: 1,605,761,327
RAC: 2,747,957
Level
His
Scientific publications
watwatwat
Message 47468 - Posted: 18 Jun 2017 | 5:57:43 UTC - in response to Message 47465.

they're mainly scientist interested in doing good science.
yes, this is perfectly right. I am not saying at all that it's the job of the the scientists to take care of the infrastructure. This needs to be done by someone specialized in this. However, as it seems, they person in charge of this is available only very rarely, if at all.

an almost complete lack of communication
for sure rather frustrating for many crunchers, believe me.
I am reading in the forum quite much, and too often I see people bringing up the same kind of problem or question, over and over. However, no reaction whatsoever.

Having said that, I can only repeat what one of the admins from another project under BOINC has published recently:
"Of course have happy volunteers is very important for the health of a project so it is something that should be addressed"
So let's hope that at some time the GPUGRID people will realize this.

Post to thread

Message boards : Number crunching : Version 9.18 Takes longer