Index  | Recent Threads  | Unanswered Threads  | Who's Active  | Guidelines  | Search
 
World Community Grid Forums
  Category: Beta Testing
  Forum: Beta Test Support Forum
  Thread: HCC GPU Beta (July 9, 2012)

Quick Go »
No member browsing this thread
Thread Status: Active
Total posts in this thread: 68
Posts: 68   Pages: 7   [ Previous Page | 1 2 3 4 5 6 7 | Next Page ]
[ Jump to Last Post ]
Post new Thread
Author
Previous Thread This topic has been viewed 15814 times and has 67 replies Next Thread
nanoprobe
Master Cruncher
Classified
Joined: Aug 29, 2008
Post Count: 2998
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
After having 0 errors on the last run I had 27 on this run.

11 were

Result Log

Result Name: BETA_ X0000038190343200409181627_ 2--
<core_client_version>7.0.28</core_client_version>
<![CDATA[
<message>
- exit code 293 (0x125)
</message>
<stderr_txt>
Commandline: projects/www.worldcommunitygrid.org/wcg_beta3_img_6.46_windows_intelx86__ati14_opencl X0000038190343200409181627.jp2
ERROR: GPU device not specified. Exiting.
17:02:51 (4464): called boinc_finish

</stderr_txt>
]]>
That has to be an app problem. Saw many of my resends with the same error.

16 were this:

Result Log

Result Name: BETA_ X0000038191170200409181614_ 1--
<core_client_version>7.0.28</core_client_version>
<![CDATA[
<stderr_txt>
Commandline: projects/www.worldcommunitygrid.org/wcg_beta3_img_6.46_windows_intelx86__ati14_opencl X0000038191170200409181614.jp2 --device 0
Boinc requested ATI gpu device number0
Found compute platform Advanced Micro Devices, Inc.
Selecting this platform
CL_DEVICE_NAME: Cypress
CL_DEVICE_VENDOR: Advanced Micro Devices, Inc.
CL_DEVICE_VERSION: CAL 1.4.1720 (VM)
CL_DEVICE_MAX_COMPUTE_UNITS: 
CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS: 3
CL_DEVICE_MAX_WORK_ITEM_SIZES: 256 / 256 / 256
CL_DEVICE_MAX_WORK_GROUP_SIZE: 256
CL_DEVICE_MAX_CLOCK_FREQUENCY: 880 MHz
CL_DEVICE_ADDRESS_BITS: 32
CL_DEVICE_MAX_MEM_ALLOC_SIZE: 512 MByte
CL_DEVICE_GLOBAL_MEM_SIZE: 2048 MByte
CL_DEVICE_ERROR_CORRECTION_SUPPORT: no
CL_DEVICE_LOCAL_MEM_TYPE: local
CL_DEVICE_LOCAL_MEM_SIZE: 32 KByte
CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE: 64 KByte
CL_DEVICE_QUEUE_PROPERTIES: CL_QUEUE_PROFILING_ENABLE
CL_DEVICE_EXTENSIONS:
cl_khr_fp64
cl_amd_fp64
cl_khr_global_int32_base_atomics
cl_khr_global_int32_extended_atomics
cl_khr_local_int32_base_atomics
cl_khr_local_int32_extended_atomics
cl_khr_3d_image_writes
cl_khr_byte_addressable_store
cl_khr_gl_sharing
cl_ext_atomic_counters_32
cl_amd_device_attribute_query
cl_amd_vec3
cl_amd_printf
cl_amd_media_ops
cl_amd_popcnt
cl_khr_d3d10_sharing
Estimated kernel execution time = 0.37515 [sec]
Starting analysis of ../../projects/www.worldcommunitygrid.org/BETA_X0000038191170200409181614_X0000038191170200409181614.jp2...
Extracting GLCM features...
17:34:09 (3484): called boinc_finish

</stderr_txt>
<message>
upload failure: <file_xfer_error>
<file_name>BETA_X0000038191170200409181614_1_0</file_name>
<error_code>-161</error_code>
</file_xfer_error>

</message>
]]>

I also noticed on 1 machine that if i tried to do a manual update while a GPU task was running that the task would immediately error out. Tried it 3 times on 1 machine and it happened all 3 times. Saw this in the event log after the error. Output file BETA_X0000038270367200409250024_0_0 for task BETA_X0000038270367200409250024_0 absent


I also had the same issue as skgiven on 1 machine. I had to go into BM and set allow 0% of the CPUs to get the GPU tasks to run.
----------------------------------------
In 1969 I took an oath to defend and protect the U S Constitution against all enemies, both foreign and Domestic. There was no expiration date.


----------------------------------------
[Edit 1 times, last edit by nanoprobe at Jul 9, 2012 11:56:11 PM]
[Jul 9, 2012 11:52:18 PM]   Link   Report threatening or abusive post: please login first  Go to top 
nanoprobe
Master Cruncher
Classified
Joined: Aug 29, 2008
Post Count: 2998
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
Suspended Einstein and HCC GPU tasks would not start (no other GPU project attached, 3 HCC GPU tasks in the queue)!
Allowed Einstein to run and it ran an Einstein task.
Suspended and no HCC GPU task started.

Could be a Boinc flaw (7.0.28), but perhaps not.

FWIW I don't think it's a 7.0.28 issue alone. The computer that did the same thing to me is running 7.0.27.
----------------------------------------
In 1969 I took an oath to defend and protect the U S Constitution against all enemies, both foreign and Domestic. There was no expiration date.
[Jul 10, 2012 12:10:59 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Bearcat
Master Cruncher
USA
Joined: Jan 6, 2007
Post Count: 2803
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
Received 52 between two crunchers. 43 valid, 9 pending validation. ATI 6950 and a ATI 5670. Both pc's are on Win7 64 and boinc 6.12.34. No OCing on my rigs.
----------------------------------------
Crunching for humanity since 2007!
[Jul 10, 2012 2:13:01 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Dana Helgeson
Cruncher
USA
Joined: Dec 2, 2005
Post Count: 15
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
I got four w/u's and all seem to have completed successfully and uploaded the results. Win7 64-bit, Nvidia GTX590, driver 301.42, CPU Intel X990, BOINC 7.0.28. Had BOINC set to suspend GPU processing so I could actually watch it this time (last GPU beta [not sure which one] ran while I was at work and I only noticed because my ETA's were all goofy). Got home tonight, saw the betas patiently waiting, released GPU suspend and the card processed two at a time. While the GPU was running, BOINC put one of the CPU CEP2 in waiting to run mode. .799 CPU usage per GPU work unit, which is higher than running SETI GPU at something like .48 CPU usage. Time to completion on all was around 3.44 minutes. No problems noticed with ETA on CPU tasks running like the last BETA. GTX590 ran up to 125.4F (water cooled) which is normal in this room in the summer with it being 82F in here. Only oddity I could see was that when the time to completion was at 00.00 the elapsed time was still ticking away, then time to completion went to 00.01 then it finally fully finished and uploaded after about 5-10 seconds.
----------------------------------------
[Edit 1 times, last edit by Dana Helgeson at Jul 10, 2012 2:17:14 AM]
[Jul 10, 2012 2:15:13 AM]   Link   Report threatening or abusive post: please login first  Go to top 
deltavee
Ace Cruncher
Texas Hill Country
Joined: Nov 17, 2004
Post Count: 4894
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
20 WUs. All valid except two still PV. No errors. 6870, i7, W7.
[Jul 10, 2012 2:20:33 AM]   Link   Report threatening or abusive post: please login first  Go to top 
slakin
Advanced Cruncher
Joined: Jul 4, 2008
Post Count: 79
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
I was excited to see that I had my first GPU BETA's but all 16 failed running on an ATI R7950.

The first 12 had this error:

Result Log

Result Name: BETA_ X0000038270299200409250025_ 1--
<core_client_version>6.10.58</core_client_version>
<![CDATA[
<message>
- exit code 293 (0x125)
</message>
<stderr_txt>
Commandline: projects/www.worldcommunitygrid.org/wcg_beta3_img_6.46_windows_intelx86__ati14_opencl X0000038270299200409250025.jp2
ERROR: GPU device not specified. Exiting.
18:42:51 (6128): called boinc_finish

</stderr_txt>
]]>


the last 4 had this error:


Result Log

Result Name: BETA_ X0000038270845200409250015_ 3--
<core_client_version>6.10.58</core_client_version>
<![CDATA[
<message>
The pipe is being closed. (0xe8) - exit code 232 (0xe8)
</message>
<stderr_txt>
Commandline: projects/www.worldcommunitygrid.org/wcg_beta3_img_6.46_windows_intelx86__ati14_opencl X0000038270845200409250015.jp2 --device 0
Boinc requested ATI gpu device number0
ERROR: .\VerifyGPU.cpp:65 Unknown
18:28:53 (5504): called boinc_finish

</stderr_txt>
]]>

Message log entries appear similar to what others have seen ..here is a sample:

09/07/2012 6:33:43 PM World Community Grid Starting BETA_X0000038270789200409250016_2
09/07/2012 6:33:43 PM World Community Grid Starting task BETA_X0000038270789200409250016_2 using beta3 version 646
09/07/2012 6:33:43 PM World Community Grid Starting BETA_X0000038271221200409250008_1
09/07/2012 6:33:43 PM World Community Grid Starting task BETA_X0000038271221200409250008_1 using beta3 version 646
09/07/2012 6:33:44 PM World Community Grid Finished download of BETA_X0000038270023200409250030_X0000038270023200409250030.jp2
09/07/2012 6:33:44 PM World Community Grid Starting BETA_X0000038270023200409250030_1
09/07/2012 6:33:44 PM World Community Grid Starting task BETA_X0000038270023200409250030_1 using beta3 version 646
09/07/2012 6:33:45 PM World Community Grid Computation for task BETA_X0000038270789200409250016_2 finished
09/07/2012 6:33:45 PM World Community Grid Output file BETA_X0000038270789200409250016_2_0 for task BETA_X0000038270789200409250016_2 absent
09/07/2012 6:33:45 PM World Community Grid Computation for task BETA_X0000038271221200409250008_1 finished
09/07/2012 6:33:45 PM World Community Grid Output file BETA_X0000038271221200409250008_1_0 for task BETA_X0000038271221200409250008_1 absent
09/07/2012 6:33:45 PM World Community Grid Resuming task CMD2_2500-MYH6.clustersOccur-PYGM.clustersOccur_1345_1188122_1188319_0 using hcmd2 version 640
09/07/2012 6:33:45 PM World Community Grid Resuming task CMD2_2500-IF4A2A.clustersOccur-MYH1.clustersOccur_126_410872_411860_0 using hcmd2 version 640
09/07/2012 6:33:46 PM World Community Grid Computation for task BETA_X0000038270023200409250030_1 finished
09/07/2012 6:33:46 PM World Community Grid Output file BETA_X0000038270023200409250030_1_0 for task BETA_X0000038270023200409250030_1 absent
09/07/2012 6:33:46 PM World Community Grid Resuming task CMD2_2500-RADIA.clustersOccur-TPM1A.clustersOccur_399_3979295_3980235_1 using hcmd2 version 640
09/07/2012 6:34:50 PM World Community Grid Sending scheduler request: To report completed tasks.
09/07/2012 6:34:50 PM World Community Grid Reporting 3 completed tasks, requesting new tasks for GPU

Disappointed in no successful results but will hope for better luck next round. Let me know if there are any suggestions for changed settings.
[Jul 10, 2012 2:33:14 AM]   Link   Report threatening or abusive post: please login first  Go to top 
BSD
Senior Cruncher
Joined: Apr 27, 2011
Post Count: 224
Status: Offline
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
I've received 7 so far, 6 "Invalid" and 1 "Pending Validation".

Intresting, since I'm not getting errors I'm presuming the validator is looking at comparable CPU completion times before granting "Valid".

He's one of mine:

BETA_ X0000038270746200409250017_ 3-- 646 Valid 7/9/12 23:07:22 7/9/12 23:11:48 0.03 53.4 / 53.4
BETA_ X0000038270746200409250017_ 2-- 646 Error 7/9/12 23:05:55 7/9/12 23:07:08 0.00 53.4 / 0.0
BETA_ X0000038270746200409250017_ 1-- 646 Valid 7/9/12 21:58:48 7/9/12 22:45:29 0.03 53.5 / 53.4
BETA_ X0000038270746200409250017_ 0-- 646 Invalid 7/9/12 21:58:20 7/9/12 23:05:20 0.35 53.4 / 53.4 <-- Me

Looks like I need to get a mid to high end GPU card and higher wattage PSU just to get a chance for "Valid" results. Hey honey, can I spend more money on computer parts and electricity? money eyes
[Jul 10, 2012 3:04:53 AM]   Link   Report threatening or abusive post: please login first  Go to top 
wplachy
Senior Cruncher
Joined: Sep 4, 2007
Post Count: 423
Status: Offline
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
Mixed bag for me as well. Same device had both Valids and Errors. Errors were all exit code 293 (0x125)|ERROR: GPU device not specified. Exiting

All the devices were running only BOINC since everyone was out of the house all day. Power options have "Turn Off Display=Never" and "Screen Saver=none".

My ETA's are really out of wack as well, 6 hour HCMD2's reporting from 62-133 hours to completion.

		Nb	PV	Vld	Err
		---	---	---	---
GTX 460 (3)	57	3	46	8
GTX 465	(1)	48	2	25	21
HD 5770	(1)	14	1	9	4
		---	---	---	---
		119	6	80	33

----------------------------------------
Bill P
[Jul 10, 2012 3:23:14 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Former Member
Cruncher
Joined: May 22, 2018
Post Count: 0
Status: Offline
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
I am wondering why the CPU tasks were stopping , especially when I already had 2 CPU threads free ?
I am hoping this is a Bug and not a Feature rolling eyes
If it is intended to act this way this is a bad idea.
The user should be in control of the CPU usage , not the GPU task.
Maybe at some point someone will make an app_info.xml , otherwise it should be up to each user to decide to free up a CPU thread or 2 , or 3 , etc... or not.
[Jul 10, 2012 3:50:14 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Bugg
Senior Cruncher
USA
Joined: Nov 19, 2006
Post Count: 271
Status: Offline
Project Badges:
Reply to this Post  Reply with Quote 
Re: HCC GPU Beta (July 9, 2012)
I received 31 beta work units, all are valid first time through. I was at work when they came around.

However, I also saw this in my log:

7/9/2012 2:52:27 PM | World Community Grid | Sending scheduler request: To fetch work.
7/9/2012 2:52:27 PM | World Community Grid | Requesting new tasks for CPU
7/9/2012 2:52:28 PM | World Community Grid | Temporarily failed upload of c4cw_target06_075850701_0_0: HTTP error
7/9/2012 2:52:28 PM | World Community Grid | Backing off 13 min 42 sec on upload of c4cw_target06_075850701_0_0
7/9/2012 2:52:43 PM | | Project communication failed: attempting access to reference site
7/9/2012 2:52:45 PM | | Internet access OK - project servers may be temporarily down.
7/9/2012 2:52:49 PM | World Community Grid | Scheduler request failed: Couldn't connect to server
7/9/2012 2:52:52 PM | | Project communication failed: attempting access to reference site
7/9/2012 2:52:53 PM | | Internet access OK - project servers may be temporarily down.
7/9/2012 2:54:00 PM | World Community Grid | Sending scheduler request: To fetch work.
7/9/2012 2:54:00 PM | World Community Grid | Requesting new tasks for CPU
7/9/2012 2:54:22 PM | World Community Grid | Scheduler request failed: Couldn't connect to server
7/9/2012 2:54:37 PM | | Project communication failed: attempting access to reference site
7/9/2012 2:54:38 PM | | Internet access OK - project servers may be temporarily down.
7/9/2012 2:55:19 PM | World Community Grid | Computation for task c4cw_target06_075840594_0 finished
7/9/2012 2:55:19 PM | World Community Grid | Starting task c4cw_target06_075854098_0 using c4cw version 641
7/9/2012 2:55:21 PM | World Community Grid | Started upload of c4cw_target06_075840594_0_0
7/9/2012 2:55:24 PM | World Community Grid | [error] Error reported by file upload server: Maintenance underway: file uploads are temporarily disabled.
7/9/2012 2:55:24 PM | World Community Grid | Temporarily failed upload of c4cw_target06_075840594_0_0: transient upload error
7/9/2012 2:55:24 PM | World Community Grid | Backing off 10 min 30 sec on upload of c4cw_target06_075840594_0_0

I included the info from the initial request to where the error occurred, so you can see that the rest that were also requested at the same time downloaded just fine. Perhaps it's something that needs to be looked into, perhaps not. But that's for you all to decide. :)
----------------------------------------

i5-12600K (3.7GHz), 32GB DDR5, Win11 64bit Home
[Jul 10, 2012 4:29:21 AM]   Link   Report threatening or abusive post: please login first  Go to top 
Posts: 68   Pages: 7   [ Previous Page | 1 2 3 4 5 6 7 | Next Page ]
[ Jump to Last Post ]
Post new Thread