Are there any issue with the CUDA3.1 beta applications?

gdf

Hi GDF im on linux 64 Ubuntu 10.10 6.12 dident work well on my setup 100hrs per unit so i aborted but 6.37 worked well sadly low points.

Keep up the good work:)

ID 31329 XP x_64 GTX260 65nm rev A.2 one tasks errored out, one finished in 483s.
ID 64724 Ubuntu 10.04.1 64bit 9600GT 4 tasks errored out. Maybe issue of my configuration, I am running there Folding GPU3 via Wine with 32bit drivers. I am not sure which drivers is GPUGRID using as I am Linux noob.

We are interested in knowing, in order of importance.
1) Does it run?
2) If the speed is fine.

The speed of the beta test on a Fermi GTX480, run with SWAN_SYNC=0, should be around 5ms/step, on a GTX275 around 9ms/step. To check look at the result output.

gdf

Another two beta tasks Win XP x_64 GTX260 65 nm rev A2, no SWAN_SYC set.
1. 522s, 2. 534s - I turned back OC to factory settings.

Win XP x86, 9600GT, no SWAN_SYC set - 2,533s. Factory clock.

All beta tasks finished after turning clock back on both XP x_64/GTX260 and XP x_86/9600GT.

The 260 is about 10ms/step. Quite nice.

gdf

Unfortunately nothing but crashes on my Ubuntu 10.10 with GTX470 driver 260.19.12. With 6.06 version everything was fine.

My GT240 on Vista 32 with driver 260.99 though seems to be doing fine.

Happy crunching

Alain

This is odd.
../../projects/www.gpugrid.net/acemdbeta_6.37_x86_64-pc-linux-gnu__cuda31: error while loading shared libraries: libcufft.so.3: cannot open shared object file: No such file or directory


try to reset project.

gdf

Unfortunately nothing but crashes on my Ubuntu 10.10 with GTX470 driver 260.19.12. With 6.06 version everything was fine.

My GT240 on Vista 32 with driver 260.99 though seems to be doing fine.

Happy crunching

Alain

Thanks for your fast reply.

Interesting is that after reset the file libcufft.so.3.0 is being uploaded togheter with all the rest.

But for now I am back to 6.06 type WUs.

Will report as soon as I get a new 6.37 type.

kind regards

Alain

This is odd.
../../projects/www.gpugrid.net/acemdbeta_6.37_x86_64-pc-linux-gnu__cuda31: error while loading shared libraries: libcufft.so.3: cannot open shared object file: No such file or directory


try to reset project.

gdf

Unfortunately nothing but crashes on my Ubuntu 10.10 with GTX470 driver 260.19.12. With 6.06 version everything was fine.

My GT240 on Vista 32 with driver 260.99 though seems to be doing fine.

Happy crunching

Alain

NVidia's Linux drivers are wantant.

Good Luck,

core_client_version>6.10.58</core_client_version>
<![CDATA[
<stderr_txt>
# Using device 0
# There are 2 devices supporting CUDA
# Device 0: "GeForce GTX 295"
# Clock rate: 1.24 GHz
# Total amount of global memory: 939327488 bytes
# Number of multiprocessors: 30
# Number of cores: 240
# Device 1: "GeForce GTX 295"
# Clock rate: 1.24 GHz
# Total amount of global memory: 939196416 bytes
# Number of multiprocessors: 30
# Number of cores: 240
MDIO ERROR: cannot open file "restart.coor"
# Time per step (avg over 50000 steps): 12.679 ms
# Approximate elapsed time for entire WU: 633.938 s
called boinc_finish

</stderr_txt>
]]>

Received two beta's - one cancelled after 10 seconds and one OK in 10 minutes.
Windows XP-pro 260.99 driver gtx295

Good luck!

---

Ton (ftpd) Netherlands

Name 111-GIANNI_TESTDHFR9-2-5-RND8139_0
Workunit 2059454
Created 10 Nov 2010 8:52:51 UTC
Sent 10 Nov 2010 9:00:13 UTC
Received 10 Nov 2010 11:47:14 UTC
Server state Over
Outcome Client error
Client state Compute error
Exit status 1 (0x1)
Computer ID 71363
Report deadline 15 Nov 2010 9:00:13 UTC
Run time 15.28125
CPU time 13.14063
stderr out

<core_client_version>6.10.58</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
# Using device 0
# There are 2 devices supporting CUDA
# Device 0: "GeForce GTX 470"
# Clock rate: 1.43 GHz
# Total amount of global memory: 1341849600 bytes
# Number of multiprocessors: 14
# Number of cores: 112
# Device 1: "GeForce GTX 470"
# Clock rate: 1.43 GHz
# Total amount of global memory: 1341718528 bytes
# Number of multiprocessors: 14
# Number of cores: 112
SWAN: Using synchronization method 0
MDIO ERROR: cannot open file "restart.coor"

</stderr_txt>
]]>

Validate state Invalid
Claimed credit 187.279513888889
Granted credit 0
application version ACEMD beta version v6.37 (cuda31)

http://www.gpugrid.net/result.php?resultid=3266818

Not running for me. Ubuntu 10.4 GTX 470 driver 260.19.12

Name 138-GIANNI_TESTDHFR9-3-5-RND1365_0
Workunit 2060131
Created 10 Nov 2010 14:00:31 UTC
Sent 10 Nov 2010 14:01:15 UTC
Received 10 Nov 2010 17:21:17 UTC
Server state Over
Outcome Client error
Client state Compute error
Exit status 127 (0x7f)
Computer ID 75881
Report deadline 15 Nov 2010 14:01:15 UTC
Run time 0
CPU time 0
stderr out

<core_client_version>6.10.56</core_client_version>
<![CDATA[
<message>
process exited with code 127 (0x7f, -129)
</message>
<stderr_txt>

</stderr_txt>
]]>

Validate state Invalid
Claimed credit 0
Granted credit 0
application version ACEMD beta version v6.37 (cuda31)

A bit late, but Worked OK here, Win7 Pro, GTX260.

Name 80-GIANNI_TESTDHFR9-1-5-RND0853_0
Workunit 2042787
Created 4 Nov 2010 3:15:47 UTC
Sent 4 Nov 2010 10:45:47 UTC
Received 4 Nov 2010 13:08:03 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 79450
Report deadline 9 Nov 2010 10:45:47 UTC
Run time 591.927441
CPU time 545.6447
stderr out <core_client_version>6.10.58</core_client_version>
<![CDATA[
<stderr_txt>
# Using device 0
# There are 2 devices supporting CUDA
# Device 0: "GeForce GTX 260"
# Clock rate: 1.47 GHz
# Total amount of global memory: 915800064 bytes
# Number of multiprocessors: 27
# Number of cores: 216
# Device 1: "GeForce GTX 260"
# Clock rate: 1.47 GHz
# Total amount of global memory: 915931136 bytes
# Number of multiprocessors: 27
# Number of cores: 216
SWAN: Using synchronization method 0
MDIO ERROR: cannot open file "restart.coor"
# Time per step (avg over 50000 steps): 11.795 ms
# Approximate elapsed time for entire WU: 589.775 s
called boinc_finish

</stderr_txt>
]]>


Validate state Valid
Claimed credit 187.279513888889
Granted credit 280.919270833333
application version ACEMD beta version v6.37 (cuda31)

http://www.gpugrid.net/result.php?resultid=3237311

Hello!
I would like to provide feedback on "ACEMDBETA 6:37", and my system setup.

I got 29 WU's and all of them are complete and validated.

Information about the system:
Motherboard: ASUS AT3IONT-I
Graphics card: GeForce GTX460 (1024MB) Sparkle
OS: Ubuntu 10:04 (64bit)
Nvidia Driver: NVIDIA-Linux-x86_64-260.19.12 and cudatoolkit_3.2.12_linux_64_ubuntu10.04
Boinc: boinc_6.10.58_x86_64-pc-linux-gnu

Here is one of the Beta results.
http://www.gpugrid.net/result.php?resultid=3269099
-----
<core_client_version> 6:10:58 </ core_client_version>
<! [CDATA [
<stderr_txt>
# Using device 0
# There ARE two devices Supporting CUDA
# Device 0: "GeForce GTX 460"
# Clock rate: 1.40 GHz
# Total Amount of global memory: 1073414144 bytes
# Number of multiprocessors: 7
# Number of cores: 56
Device # 1: "ION"
# Clock rate: 1.10 GHz
# Total Amount of global memory: 265617408 bytes
# Number of multiprocessors: 2
# Number of cores: 16
MDIO ERROR: can not open file "restart.coor"
# Time per step (avg over 50 000 steps): 20 963 ms
# Approximate elapsed time for Entire WU: 1048.166 s
20:27:50 (5410): Called boinc_finish

</ Stderr_txt>
]]>

Valid
Claimed credit 187.279513888889
Granted credit 280.919270833333
application version ACEMD beta version v6.37 (cuda31)
-----

Maybe it's too late to give feedback.
Greetings Anders

I was attempting to get some beta WUs for my systems with the GTX260.

11/15/2010 5:23:02 PM | GPUGRID | Message from GPUGRID: ACEMD beta version is not available for your type of computer.

Is there a way to get around this?

No and there would be no point; if the team is testing tasks or apps on Fermi cards they don't want to run them on non-Fermi cards, otherwise they would already be available for your card.