I just got another WU ..but it also resulted in an error. Slightly different from my last results. This is on ATI R7950 running on intel i5-3570K cpu with 8 GB RAM. 64 bit OS Windows 7 Home Premium ---- All 4 processors committed to WCG at 80% Here is the Result log"
Result Log

Result Name: BETA_ X0000038190872200409181619_ 4--
<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 X0000038190872200409181619.jp2 --device 0
Boinc requested ATI gpu device number0
ERROR: .\VerifyGPU.cpp:65 Unknown
17:24:55 (6164): called boinc_finish

</stderr_txt>
]]>
and the message log entries.

11/07/2012 5:24:54 PM World Community Grid Started download of BETA_X0000038190872200409181619_X0000038190872200409181619.jp2
11/07/2012 5:24:55 PM World Community Grid Finished download of BETA_X0000038190872200409181619_X0000038190872200409181619.jp2
11/07/2012 5:24:55 PM World Community Grid Starting BETA_X0000038190872200409181619_4
11/07/2012 5:24:55 PM World Community Grid Starting task BETA_X0000038190872200409181619_4 using beta3 version 646
11/07/2012 5:24:58 PM World Community Grid Computation for task BETA_X0000038190872200409181619_4 finished
11/07/2012 5:24:58 PM World Community Grid Output file BETA_X0000038190872200409181619_4_0 for task BETA_X0000038190872200409181619_4 absent
11/07/2012 5:26:02 PM World Community Grid Sending scheduler request: To report completed tasks.

Hope this helps ..I would love to successfully complete one of these WU's.

Sound like folks maxing out all threads are having issues and those leaving at least one thread free is not having issues. For those who are maxing out your threads, when the gpu finishes a wu and passes to the CPU, either one of those threads will have to pause to finish the gpu wu, or the gpu work unit getting passed back to the CPU will most likely error out due to nothing available to finish the job. Could be OCing issues to. I don't OC but do leave one thread free and didnt get any errors. Just a theory on my part.

We have been discussing some of the observed items with David Anderson and there is a fact that we didn't understand. If the estimated cpu use for a GPU application version < 1 full core, then the BOINC client starts the research application at normal priority. Given the 30-45 seconds at the start and end of each workunit, this can interfere with user interaction on their machine. As a result, the next beta test we run will have it set to use 1 full core + 1 gpu. Those users who have set their machines to have an extra cpu slot available for this gpu app do not need to do that anymore.

It would be helpful to get a heads-up on when the next beta will come, so that I can free up my video card from other duties (i.e., POEM). I am sure that other people have various GPU projects running too in the interim. I would not want to get errors or whatever happens when two projects compete for the same card. A 12-hour warning would be good, and 24-hours better.

Despite leaving one processor free (which sounds like it should not be a requirement if I understood correctly) I still failed with RC232 ...
12/07/2012 2:03:19 PM World Community Grid General prefs: using your defaults
12/07/2012 2:03:19 PM Reading preferences override file
12/07/2012 2:03:19 PM Preferences:
12/07/2012 2:03:19 PM max memory usage when active: 6115.33MB
12/07/2012 2:03:19 PM max memory usage when idle: 7338.40MB
12/07/2012 2:03:19 PM max disk usage: 10.00GB
12/07/2012 2:03:19 PM max CPUs used: 3
12/07/2012 2:03:19 PM (to change preferences, visit the web site of an attached project, or select Preferences in the Manager)
12/07/2012 2:03:31 PM Benchmark results:
12/07/2012 2:03:31 PM Number of CPUs: 3
12/07/2012 2:03:31 PM 3757 floating point MIPS (Whetstone) per CPU
12/07/2012 2:03:31 PM 9205 integer MIPS (Dhrystone) per CPU

12/07/2012 2:05:30 PM World Community Grid Requesting new tasks for GPU
12/07/2012 2:05:32 PM World Community Grid Scheduler request completed: got 2 new tasks
12/07/2012 2:05:34 PM World Community Grid Started download of BETA_X0000038191070200409181615_X0000038191070200409181615.jp2
12/07/2012 2:05:34 PM World Community Grid Started download of BETA_X0000038191308200409181611_X0000038191308200409181611.jp2
12/07/2012 2:05:35 PM World Community Grid Finished download of BETA_X0000038191070200409181615_X0000038191070200409181615.jp2
12/07/2012 2:05:35 PM World Community Grid Finished download of BETA_X0000038191308200409181611_X0000038191308200409181611.jp2
12/07/2012 2:05:35 PM World Community Grid Starting BETA_X0000038191308200409181611_0
12/07/2012 2:05:35 PM World Community Grid Starting task BETA_X0000038191308200409181611_0 using beta3 version 647
12/07/2012 2:05:39 PM World Community Grid Computation for task BETA_X0000038191308200409181611_0 finished
12/07/2012 2:05:39 PM World Community Grid Output file BETA_X0000038191308200409181611_0_0 for task BETA_X0000038191308200409181611_0 absent
12/07/2012 2:05:39 PM World Community Grid Starting BETA_X0000038191070200409181615_1
12/07/2012 2:05:39 PM World Community Grid Starting task BETA_X0000038191070200409181615_1 using beta3 version 647
12/07/2012 2:05:42 PM World Community Grid Computation for task BETA_X0000038191070200409181615_1 finished
12/07/2012 2:05:42 PM World Community Grid Output file BETA_X0000038191070200409181615_1_0 for task BETA_X0000038191070200409181615_1 absent
12/07/2012 2:05:42 PM World Community Grid Resuming task CMD2_2503-1HCI_A.clustersOccur-1NCJ_A.clustersOccur_254_2566185_2567151_1 using hcmd2 version 640

Let me know if there is something else I can supply