They were test_2's ...

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=60876213

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=60876213

Error message the same:

<core_client_version>6.12.33</core_client_version>
<![CDATA[
<message>
- exit code -1073740940 (0xc0000374)
</message>
<stderr_txt>
Using SSE3 path
Found 4 CAL devices
Chose device 3

Regards
Zy

Another test2 fell over:

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=60894748

<core_client_version>6.12.33</core_client_version>
<![CDATA[
<message>
- exit code -1073740940 (0xc0000374)
</message>
<stderr_txt>
Using SSE3 path
Found 4 CAL devices
Chose device 1

EDIT: Got two more test2's coming up, be thro in about 5 mins or so

Regards
Zy

Those two test2's fell over, same as before, went to 100% and fell over in the last two seconds.

I have got a batch of 25 test2's coming up in another 5 mins, I wont clog thread with results for each - they are being run on my 2X5970 box.

EDIT: looks like they will all be failures, first one coming thro now.

EDIT2: Different ..... when the test2's fall over, the delay counter for next update resets immediately to 5 mins. Normally the counter resets to 1 min on succesful ones. Normal 10_3s & 13_3s are still going through ok.

EDIT3: Still about a dozen left of the test2 batch, but its vertuallty certain all will fall over, the others have. Test2 batch will be finished in about 6 mins

EDIT4: Batch of 25 test2's all been through, all failed, all went to 100% and fell over in the last two seconds of processing. I have been running low clocks to eliminate o/c as an error source (725/300). All now back to normal 13_3s and 10_3s going through ok.

Regards
Zy

test 2's getting errors for me, too (2 X HD 5870 system):
Stderr output

<core_client_version>6.12.12</core_client_version>
<![CDATA[
<message>
- exit code -1073740940 (0xc0000374)
</message>
<stderr_txt>
Using SSE3 path
Found 2 CAL devices
Chose device 1

Device target: CAL_TARGET_CYPRESS
Revision: 2
CAL Version: 1.4.1332
Engine clock: 900 Mhz
Memory clock: 1150 Mhz
GPU RAM: 1024
Wavefront size: 64
Double precision: CAL_TRUE
Compute shader: CAL_TRUE
Number SIMD: 20
Number shader engines: 2
Pitch alignment: 256
Surface alignment: 4096
Max size 2D: { 16384, 16384 }

Estimated iteration time 137.700694 ms
Target frequency 30.000000 Hz, polling mode 1
Dividing into 4 chunks, initially sleeping for 0 ms
Integration range: { nu_steps = 640, mu_steps = 1600, r_steps = 1400 }
Using 4 chunk(s) with sizes: 400 400 400 400
Integration time = 79.364041 s, average per iteration = 124.006313 ms
Integral 0 time = 80.163489 s
Estimated iteration time 34.425174 ms
Target frequency 30.000000 Hz, polling mode 1
Dividing into 1 chunks, initially sleeping for 0 ms
Integration range: { nu_steps = 640, mu_steps = 400, r_steps = 1400 }
Using 1 chunk(s) with sizes: 400
Integration time = 19.841472 s, average per iteration = 31.002300 ms
Integral 1 time = 20.019790 s
Estimated iteration time 34.425174 ms
Target frequency 30.000000 Hz, polling mode 1
Dividing into 1 chunks, initially sleeping for 0 ms
Integration range: { nu_steps = 640, mu_steps = 400, r_steps = 1400 }
Using 1 chunk(s) with sizes: 400
Integration time = 19.841110 s, average per iteration = 31.001734 ms
Integral 2 time = 20.054719 s
Likelihood time = 1.054170 s
<background_integral> 0.000673015677022 </background_integral>
<stream_integral> 59.061583544896259 272.845369636376460 2039.111403984195900 </stream_integral>
<background_likelihood> -3.360251053254806 </background_likelihood>
<stream_only_likelihood> -25.175042984847199 -3.662134961229784 -4.299719395742361 </stream_only_likelihood>
<search_likelihood> -2.987678865754052 </search_likelihood>

</stderr_txt>
]]>

---

Seams to run just fine but ends up as 'Invalid'


Task 60910482

Name
ps_separation_17_test2_1538_2

Workunit
41511331

Created
28 Jun 2011 | 21:02:42 UTC

Sent
28 Jun 2011 | 21:07:33 UTC

Received
28 Jun 2011 | 21:24:59 UTC

Server state
Over

Outcome
Computation error

Client state
Compute error

Exit status
-1073740940 (0xffffffffc0000374)

Computer ID
83808

Report deadline
10 Jul 2011 | 21:07:33 UTC

Run time
212.24

CPU time
5.04

Validate state
Invalid

Credit
0.00

Application version

MilkyWay@Home
Anonymous platform (ATI GPU)

And one more, time to go to sleep, good luck guy's

Name
ps_separation_17_test2_217_1

Workunit
41502110

Created
28 Jun 2011 | 21:07:55 UTC

Sent
28 Jun 2011 | 21:09:49 UTC

Received
28 Jun 2011 | 21:26:22 UTC

Server state
Over

Outcome
Computation error

Client state
Compute error

Exit status
-1073740940 (0xffffffffc0000374)

Computer ID
83808

Report deadline
10 Jul 2011 | 21:09:49 UTC

Run time
196.23

CPU time
4.79

Validate state
Invalid

Credit
0.00

Application version

MilkyWay@Home
Anonymous platform (ATI GPU)

Sorry, the ps_separation_17_test2 all fail

one example:
Stderr output

<core_client_version>6.12.33</core_client_version>
<![CDATA[
<message>
- exit code -1073740940 (0xc0000374)
</message>
<stderr_txt>
Using SSE3 path
Found 2 CAL devices
Chose device 1

Device target: CAL_TARGET_CYPRESS
Revision: 2
CAL Version: 1.4.1417
Engine clock: 810 Mhz
Memory clock: 1000 Mhz
GPU RAM: 1024
Wavefront size: 64
Double precision: CAL_TRUE
Compute shader: CAL_TRUE
Number SIMD: 18
Number shader engines: 2
Pitch alignment: 256
Surface alignment: 4096
Max size 2D: { 16384, 16384 }

Estimated iteration time 170.000857 ms
Target frequency 30.000000 Hz, polling mode 1
Dividing into 5 chunks, initially sleeping for 0 ms
Integration range: { nu_steps = 640, mu_steps = 1600, r_steps = 1400 }
Using 5 chunk(s) with sizes: 320 320 320 320 320
Integration time = 106.699875 s, average per iteration = 166.718554 ms
Integral 0 time = 108.986705 s
Estimated iteration time 42.500214 ms
Target frequency 30.000000 Hz, polling mode 1
Dividing into 1 chunks, initially sleeping for 0 ms
Integration range: { nu_steps = 640, mu_steps = 400, r_steps = 1400 }
Using 1 chunk(s) with sizes: 400
Integration time = 25.863625 s, average per iteration = 40.411913 ms
Integral 1 time = 26.503867 s
Estimated iteration time 42.500214 ms
Target frequency 30.000000 Hz, polling mode 1
Dividing into 1 chunks, initially sleeping for 0 ms
Integration range: { nu_steps = 640, mu_steps = 400, r_steps = 1400 }
Using 1 chunk(s) with sizes: 400
Integration time = 26.804972 s, average per iteration = 41.882768 ms
Integral 2 time = 27.302759 s
Likelihood time = 2.087996 s
<background_integral> 0.000770135254185 </background_integral>
<stream_integral> 62.761162507748544 288.445782413720790 1352.138826459207400 </stream_integral>
<background_likelihood> -3.374819196264162 </background_likelihood>
<stream_only_likelihood> -64.678060075875237 -3.655177048250085 -4.159493312194440 </stream_only_likelihood>
<search_likelihood> -2.980101126510245 </search_likelihood>

</stderr_txt>
]]>

I started a new ps_separation_17 run using the old parameter file. Matt A. needs to update the applications before we can go back to trying the new one. I'm hoping the new 17 workunits should work fine.

---

Got a batch of around 50 of the 17_test2, first four errored out same issue, went to 100%, errored in last 2 seconds.

They are on my 2X5970 box

EDIT: Next four fell over as well - I will post if they succeed, otherwise assume the 50 failed.

EDIT2: 11 more "retreads test2's" are in plus around 10 normal. Assume the retreads failed, and normal ones (10_3s) succeeded unless I post.

EDIT3: I had a 17_3s_fix failed, that was unusual so highlighted it:
http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=60962051
(WU: ps_separation_17_3s_fix_5_930_3, workunit number: 41420623 Computer ID
216948 )

Regards
Zy

Hello!

Have a computation errors and errors of verification with my hosts 103082 (Radeon HD 4890) and 215277 (Radeon HD 4850).

Just started for today and got a few ps_separation_17_3s_fix_2_.....

and they seams to work just fine.

I posted to the wrong thread yesterday here. That was after resetting the project on two machines. So it would seem that the updated parameter file didn't help.

---

"Those who would give up essential Liberty, to purchase a little temporary Safety, deserve neither Liberty nor Safety." (Benjamin Franklin)

All "ps_separation_17_test2" work units on one computer failed and froze on completion (reported as 100% but just sat on the the gpu without uploading) these workunits had to be manually aborted as they did not release the the GPU. Interestingly boincview reported the estimated speed to be 12.01 TFlops even though they were 100% completed

See screenprint below of properties box note elapsed time

Try this app_info.xml File in the Milkyway Data DIR

(C:\ProgramData\BOINC\projects\milkyway.cs.rpi.edu_milkyway)

This wored in some cases.

If you don't want to run 2 WU's parallel(which is e little more efficient) replace:
<count>0.5</count>
->
<count>1</count>

<app_info>
<app>
<name>milkyway</name>
</app>
<file_info>
<name>milkyway_separation_0.82_windows_x86_64__ati14.exe</name>
<executable/>
</file_info>
<app_version>
<app_name>milkyway</app_name>
<version_num>82</version_num>
<flops>1.0e11</flops>
<avg_ncpus>0.05</avg_ncpus>
<max_ncpus>1</max_ncpus>
<plan_class>ati14ati</plan_class>
<coproc>
<type>ATI</type>
<count>0.5</count>
</coproc>
<cmdline>--gpu-target-frequency 60 --gpu-disable-checkpointing</cmdline>
<file_ref>
<file_name>milkyway_separation_0.82_windows_x86_64__ati14.exe</file_name>
<main_program/>
</file_ref>
</app_version>
</app_info>