Message boards :
Graphics cards (GPUs) :
New workunits GPUTEST3 and new apps
Message board moderation
| Author | Message |
|---|---|
GDFSend message Joined: 14 Mar 07 Posts: 1958 Credit: 629,356 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() |
I have uploaded new work GPUTEST3 and new applications for Linux and Windows. Among other little things these are fixing a mistake I made in flops counting (sorry) which affects credits. So we were undercrediting because our estimate of the Gflops of the application was not accurate. Writing the publication presenting the application, we have noticed it. gdf |
[XTBA>XTC] ZeuZSend message Joined: 15 Jul 08 Posts: 60 Credit: 108,384 RAC: 0 Level ![]() Scientific publications
|
It's a good news :) Thanks |
|
Send message Joined: 18 Aug 08 Posts: 121 Credit: 59,836,411 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
I have uploaded new work GPUTEST3 and new applications for Linux and Windows. Among other little things these are fixing a mistake I made in flops counting (sorry) which affects credits. So we were undercrediting because our estimate of the Gflops of the application was not accurate. Writing the publication presenting the application, we have noticed it. You mean 6.43? Soon my Comp will start crunch them. What changes in application? |
koschiSend message Joined: 14 Aug 08 Posts: 127 Credit: 919,858,161 RAC: 126,373 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
I have uploaded new work GPUTEST3 and new applications for Linux and Windows. Among other little things these are fixing a mistake I made in flops counting (sorry) which affects credits. So we were undercrediting because our estimate of the Gflops of the application was not accurate. Writing the publication presenting the application, we have noticed it. One WU will receive 3,232.06 Credits on successful validation :-D |
|
Send message Joined: 18 Aug 08 Posts: 121 Credit: 59,836,411 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
Woow that is just... cool :) Maby thanx to new app :) |
|
Send message Joined: 15 Aug 08 Posts: 2 Credit: 13,004,227 RAC: 0 Level ![]() Scientific publications ![]() ![]()
|
Only errors on my system :( Win XP SP2 32Bit Boinc 6.3.10 Nvidia 177.92 Beta http://www.ps3grid.net/results.php?hostid=7713 |
GDFSend message Joined: 14 Mar 07 Posts: 1958 Credit: 629,356 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() |
Only errors on my system :( Uhmm, it should work on your system. Have you tried with normal non-beta drivers like 177.8x? Your shader frequency is slightly overclocked, it should be 1512000. Could you turn it down using Nvidia utilities. Let us know. gdf |
Krunchin-Keith [USA]Send message Joined: 17 May 07 Posts: 512 Credit: 111,288,061 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
I'm now getting 6.43 on my hosts, all seem to be running well. One host had a problem with the first one but since has been ok. The others seem to be doing ok, but I've only got 1 or 2 completed with each, still with 177.84 driver. I do not have enough completed results yet, but it appears that 6.43, at least for my 3 hosts, is about 2,000s faster than 6.41. I need to let it run some more for a few days, but then I think I can try to see if 177.92 driver works. I've got a lot going on this Holiday weekend anyway. |
KokomikoSend message Joined: 18 Jul 08 Posts: 190 Credit: 24,093,690 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
The 6.43 is here running on 3 PCs, 2 are working with a 8800GT, one with a GTX280. All are running fine. I use on all 3 PCs driver 177.84.
|
|
Send message Joined: 24 Aug 08 Posts: 45 Credit: 3,431,862 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]()
|
One host I do not have enough completed results yet, but it appears that 6.43, at least for my 3 hosts, is about 2,000s faster than 6.41. I need to let it run some more for a few days, but then I think I can try to see if 177.92 driver works. I've got a lot going on this Holiday weekend anyway. The 6.43 is not faster - the formel for the credits in 6.41 was wrong. Therefor the difference. I think the 177.92 is faster than the 177.84. The nvidia guys said it in the beta forum. |
|
Send message Joined: 17 Aug 08 Posts: 2705 Credit: 1,311,122,549 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
6.43 running fine and no difference in run times. I updated to 177.92 beta today and projected run time (after 2 hours) was about the same. MrS Scanning for our furry friends since Jan 2002 |
DoctorNowSend message Joined: 18 Aug 07 Posts: 83 Credit: 137,458,752 RAC: 81,517 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
I'm happy to announce my first finished WU on the project and this batch. :) Was about time to get rid of that Zeros... I crunched it with a Gigabyte nVidia 9600 GT card on Windows 32-Bit. Edit: Sorry for double-post. Messed up with the buttons... |
|
Send message Joined: 5 Mar 08 Posts: 5 Credit: 16,971,567 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
the support for 1.0 cuda graphics card is still not present? |
GDFSend message Joined: 14 Mar 07 Posts: 1958 Credit: 629,356 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() |
the support for 1.0 cuda graphics card is still not present? I am looking into it, but I cannot guarantee anything. gdf |
|
Send message Joined: 18 Aug 08 Posts: 121 Credit: 59,836,411 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
Is 6.43 aplication 32 or 64 bit? or are 2 diferent versions? BOINC manager is in 32 and in 64. So when it run on x64 Systems aplication 6.43 it runs it in 32 or in 64 bits mode? |
MJHSend message Joined: 12 Nov 07 Posts: 696 Credit: 27,266,655 RAC: 0 Level ![]() Scientific publications ![]()
|
Is 6.43 aplication 32 or 64 bit? or are 2 diferent versions? The Linux application is 64bit, the Windows version is 32bit. MJH. |
|
Send message Joined: 18 Aug 08 Posts: 121 Credit: 59,836,411 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
Is 6.43 aplication 32 or 64 bit? or are 2 diferent versions? Is in linux 64 much faster than 32? When will be 64 bit wersion for windows? |
koschiSend message Joined: 14 Aug 08 Posts: 127 Credit: 919,858,161 RAC: 126,373 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
I assume that it doesn't make any difference, if it is 64 or 32 bit, as the workload is processed by the GPU anyway. So the app does not profit from 64bit architectures improvements like more registers and stuff like that. Please correct me if I'm wrong :) |
|
Send message Joined: 30 Jul 08 Posts: 17 Credit: 80,343,188 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]()
|
I assume that it doesn't make any difference, if it is 64 or 32 bit, as the workload is processed by the GPU anyway. So the app does not profit from 64bit architectures improvements like more registers and stuff like that. I believe that is correct. Plus unless a CPU application is specifically optimized for 64-bit, there really is no advantage to 64-bit. |
|
Send message Joined: 18 Aug 08 Posts: 121 Credit: 59,836,411 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
I find interesting error: http://www.ps3grid.net/result.php?resultid=49857 How it happends? I have delayed on one hour computing using Boinc Manager. I uninstall 177.84 Restart I install 177.92 Restart And Boinc Manager to my suprise cancel 4 WU and download new. One of those cancel WU was after 13000/50000seconds of crunching.... Now It starts as usual new WU 2008-09-02 18:58:22||CUDA devices found 2008-09-02 18:58:22||Coprocessor: GeForce 8800 GTS 512 (1) 2008-09-02 18:58:43|PS3GRID|Starting Ka12712-GPUTEST3-0-10-acemd_0 2008-09-02 18:58:45|PS3GRID|Starting task Ka12712-GPUTEST3-0-10-acemd_0 using acemd version 643 on new 177.92 beta. I am very Curious if new drivers will be faster on WinXPS2 32bit than previous 177.84. |
©2026 Universitat Pompeu Fabra