| 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) |
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 68
|
|
| Author |
|
|
armstrdj
Former World Community Grid Tech Joined: Oct 21, 2004 Post Count: 695 Status: Offline Project Badges: 
|
Some information and questions for users who consistently get error code 232. The error is occurring on the first OpenCL call, clGetPlatformIDs, which should return the available platforms. If this fails it could be that there is an issue with the OpenCL ICD. One thing to check is that you have the latest video driver installed and if so you might try to reinstall. And some questions for users who get this error.
Thanks, armstrdj |
||
|
|
nanoprobe
Master Cruncher Classified Joined: Aug 29, 2008 Post Count: 2998 Status: Offline Project Badges: 
|
@nanoprobe - can you paste the details from the client_state.xml about the app version? Here's the details you asked for Kevin. I now have 16 of these errors. <app_version> <app_name>beta3</app_name> <version_num>647</version_num> <platform>windows_intelx86</platform> <avg_ncpus>1.000000</avg_ncpus> <max_ncpus>0.271853</max_ncpus> <flops>7650652590.969408</flops> <plan_class>ati14_hcc1</plan_class> <api_version>7.1.0</api_version> <file_ref> <file_name>wcg_beta3_img_6.47_windows_intelx86__ati14_hcc1</file_name> <main_program/> </file_ref> <file_ref> <file_name>hcckernel.cl.6.47</file_name> <open_name>hcckernel.cl</open_name> </file_ref> <file_ref> <file_name>beta3_image01_6.47.tga</file_name> <open_name>boinc_wcg_skin_w-logo.tga</open_name> </file_ref> <file_ref> <file_name>beta3_image02_6.47.tga</file_name> <open_name>pbibmablk.tga</open_name> </file_ref> <file_ref> <file_name>beta3_image03_6.47.tga</file_name> <open_name>UHN_stacked2.tga</open_name> </file_ref> <file_ref> <file_name>beta3_image04_6.47.tga</file_name> <open_name>HCC_LOGO.tga</open_name> </file_ref> <coproc> <type>ATI</type> <count>1.000000</count> </coproc> <gpu_ram>262144000.000000</gpu_ram> </app_version>
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.
  |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
3 pages of valids between my 2 680s and my 570 and counting.
|
||
|
|
mwgiii
Advanced Cruncher United States Joined: Aug 17, 2006 Post Count: 131 Status: Offline Project Badges: 
|
25 betas Valid 12 PV with my Nvidia 570. Still running a full load as my previous post.
----------------------------------------I may be in the minority here, but I am not a fan of using a full core for GPU tasks as my main machine is a non-HT Quad.   [Edit 1 times, last edit by mwgiii at Jul 12, 2012 9:01:06 PM] |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
Gpus will always need some help from the CPU, so this cannot be avoided. Not my favorite method they have chosen but I understand the reasoning and am glad things are moving forward again.
|
||
|
|
mwgiii
Advanced Cruncher United States Joined: Aug 17, 2006 Post Count: 131 Status: Offline Project Badges:
|
I know GPUs need to use part of a core. I'm just not a fan of them taking a full core. But as you said, if this is the only way for WCG to expedite GPU processing, so be it. Hopefully they can fix the code somewhere down the line to help out those of us with non-HT processors.
---------------------------------------- |
||
|
|
Jim1348
Veteran Cruncher USA Joined: Jul 13, 2009 Post Count: 1066 Status: Offline Project Badges: 
|
I may be in the minority here, but I am not a fan of using a full core for GPU tasks as my main machine is a non-HT Quad. I am wondering whether HCC1 plays well with hyper-threading, or whether you need a full physical core. I would ideally like two HD 7770s supported by two virtual cores (one physical core) on my next build, which will be Haswell. |
||
|
|
ICG Studio
Cruncher Joined: Jan 17, 2011 Post Count: 12 Status: Offline Project Badges: 
|
Yes so far when poem@home move with new compiler (they saying with sse) was exacly like that i run without crossfire two radeon one its 5830 second is 5870, so far not problem with following projects:
milkyway@home (opencl version), einstein@home, poem@home, seti@home beta. Vaious mixture... sometimes with all 6 cores feeded to the max I didn't get any errors at all. Please maybe ask Timo from poem@home he what i remember after 2 nights realize where was a problem. My drivers its: Catalyst Version 12.6, Packing version: 8.98-120611a-141402C-ATI. |
||
|
|
nanoprobe
Master Cruncher Classified Joined: Aug 29, 2008 Post Count: 2998 Status: Offline Project Badges:
|
I know GPUs need to use part of a core. I'm just not a fan of them taking a full core. But as you said, if this is the only way for WCG to expedite GPU processing, so be it. Hopefully they can fix the code somewhere down the line to help out those of us with non-HT processors. The problem is not the code, it's the Nvidia drivers. They have very poor OpenCl support and that is not likely to change any time soon.
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.
|
||
|
|
nanoprobe
Master Cruncher Classified Joined: Aug 29, 2008 Post Count: 2998 Status: Offline Project Badges:
|
I may be in the minority here, but I am not a fan of using a full core for GPU tasks as my main machine is a non-HT Quad. I am wondering whether HCC1 plays well with hyper-threading, or whether you need a full physical core. I would ideally like two HD 7770s supported by two virtual cores (one physical core) on my next build, which will be Haswell.It plays well with my i7-2600k with HT on.
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.
|
||
|
|
|