Even with the fixed ATI app, I'm still getting errors on the 3s work.

"Maximum elapsed time exceeded"
"WU not compatible, falling back to a somewhat slow CPU code."

75478065
75478072
75478085

Even with the fixed ATI app, I'm still getting errors on the 3s work.

"Maximum elapsed time exceeded"
"WU not compatible, falling back to a somewhat slow CPU code."

Here is one from an Intel:

Task ID 75479248
Name ps_sgr_235_3s_4_124_1244493002_1
Workunit 74342510
Created 8 Jun 2009 20:33:36 UTC
Sent 8 Jun 2009 20:35:48 UTC
Received 8 Jun 2009 20:47:04 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 40456
Report deadline 11 Jun 2009 20:35:48 UTC
CPU time 0
stderr out

<core_client_version>6.5.0</core_client_version>
<![CDATA[
<stderr_txt>
Running Milkyway@home ATI GPU application version 0.19f by Gipsel
CPU: Intel(R) Core(TM)2 Quad CPU Q8200 @ 2.33GHz (4 cores/threads) 2.76509 GHz (146ms)

CAL Runtime: 1.3.145
Found 1 CAL device

Device 0: ATI Radeon HD 4800 (RV770) 512 MB local RAM (remote 28 MB cached + 256 MB uncached)
GPU core clock: 650 MHz, memory clock: 993 MHz
800 shader units organized in 10 SIMDs with 16 VLIW units (5-issue), wavefront size 64 threads
supporting double precision

0 WUs already running on GPU 0
Starting WU on GPU 0

main integral, 0 iterations
predicted runtime per iteration is 0 ms (33.3333 ms are allowed)
borders of the domains at 0 0
WU not compatible, falling back to a somewhat slow CPU code.
Calculated about 0 floatingpoint ops on FPU.

probability calculation (stars)
Calculated about 1.44918e+007 floatingpoint ops on FPU.

WU completed.
CPU time: 0.21875 seconds, GPU time: 0 seconds, wall clock time: 0.236 seconds, CPU frequency: 2.76515 GHz

</stderr_txt>
]]>

Validate state Invalid
Claimed credit 0
Granted credit 0
application version 0.19

---

A BLAST FROM YOUR PAST

Mine seems to have run fine:


<core_client_version>6.6.20</core_client_version>
<![CDATA[
<stderr_txt>
Running Milkyway@home ATI GPU application version 0.19f by Gipsel
CPU: Intel(R) Core(TM)2 Duo CPU E8400 @ 3.00GHz (2 cores/threads) 3.00007 GHz (241ms)

CAL Runtime: 1.3.145
Found 1 CAL device

Device 0: ATI Radeon HD 4800 (RV770) 512 MB local RAM (remote 28 MB cached + 256 MB uncached)
GPU core clock: 625 MHz, memory clock: 250 MHz
800 shader units organized in 10 SIMDs with 16 VLIW units (5-issue), wavefront size 64 threads
supporting double precision

0 WUs already running on GPU 0
Starting WU on GPU 0

main integral, 160 iterations
predicted runtime per iteration is 119 ms (33.3333 ms are allowed), dividing each iteration in 4 parts
borders of the domains at 0 400 800 1200 1600
Calculated about 2.45253e+012 floatingpoint ops on GPU, 6.34181e+007 on FPU. Approximate GPU time 20.9531 seconds.

probability calculation (stars)
Calculated about 8.83997e+008 floatingpoint ops on FPU.

WU completed.
CPU time: 1.32813 seconds, GPU time: 20.9531 seconds, wall clock time: 21.618 seconds, CPU frequency: 3.00008 GHz

</stderr_txt>
]]>


Task ID 75504556
Name ps_sgr_235_1s_4_42292_1244497065_0

---

Mine seems to have run fine:
Task ID 75504556
Name ps_sgr_235_1s_4_42292_1244497065_0

That's a 1s workunit. The issue at hand is the recently reissued 3 stream tasks that had problems on the previous version of the ATI GPU application.

All my CPU machines and the GPU one seem to have _1s_4_ and _2s_4_ WUs only.

As soon as I see a _3s_x_ WUs I will watch it with interest, and erroring out trepidation.

;))

However, after looking back to work crunched about 20.33 UTC I see I had 18 _235_3s_4_ WUs all of which showed no CPU time used, a blank claimed credit and 0 granted credit. An example can be seen here.

---

Go away, I was asleep

All my CPU machines and the GPU one seem to have _1s_4_ and _2s_4_ WUs only.

As soon as I see a _3s_x_ WUs I will watch it with interest, and erroring out trepidation.

;))

However, after looking back to work crunched about 20.33 UTC I see I had 18 _235_3s_4_ WUs all of which showed no CPU time used, a blank claimed credit and 0 granted credit. An example can be seen here.

It's weird because with every 3s WU i've seen, the application reports 0 iterations.

---

Even with the fixed ATI app, I'm still getting errors on the 3s work.

"Maximum elapsed time exceeded"
"WU not compatible, falling back to a somewhat slow CPU code."

75478065

These WUs appear to be bad. Also the CPU apps can't do anything with them. Just check the WU you linked and you will see that it got resend to a host running a CPU app (obviously even the stock app!) and returned also an error:

stderr out <core_client_version>6.4.5</core_client_version>
<![CDATA[
<message>
process got signal 8
</message>
<stderr_txt>

</stderr_txt>
]]>

Validate state Invalid
Claimed credit 0
Granted credit 0
application version 0.18

However, after looking back to work crunched about 20.33 UTC I see I had 18 _235_3s_4_ WUs all of which showed no CPU time used, a blank claimed credit and 0 granted credit. An example can be seen here.

It's weird because with every 3s WU i've seen, the application reports 0 iterations.

Yes, that's a problem. It means the main integral is empty. Most likely it is a problem with the parameter format in the WU, i.e. an WU generation error.

Edit:
Just found such a WU on my computer. I guess that part of the WU parameters can't be right ;)

convolve: 0
sgr_coordinates: 0
wedge: 0
r[min,max,steps]: 0.000000, 0.000000, 0
mu[min,max,steps]: 0.000000, 0.000000, 0
nu[min,max,steps]: 0.000000, 0.000000, 0

'bad WU! bad, bad WU!
Now go back to your kennel. :)

---

Cheers,

PeterV

.

'bad WU! bad, bad WU!
Now go back to your kennel. :)

I blame the owners myself. It's the way the WUs are brought up ;)

---

'bad WU! bad, bad WU!
Now go back to your kennel. :)

I blame the owners myself. It's the way the WUs are brought up ;)

Yea I had a bunch of bad ones yesterday.
Gave em a right good thrashing before I sent em back, I can tell you...

'bad WU! bad, bad WU!
Now go back to your kennel. :)

I blame the owners myself. It's the way the WUs are brought up ;)

Yea I had a bunch of bad ones yesterday.
Gave em a right good thrashing before I sent em back, I can tell you...

Bread and water is just too good for them...

---

WU's today, I don't know, no respect for their elders, wouldn't have happened in my day mumble mumble .....

Thank you for bringing this to my attention, it's my error (first week on BOINC, please be patient haha). Can you tell me if there is a problem with ps_sgr_235_3s_5?

Cheers,
John Vickers

'bad WU! bad, bad WU!
Now go back to your kennel. :)

Surely that should be:

Now go back to your kernel.

:)

---

Thank you for bringing this to my attention, it's my error (first week on BOINC, please be patient haha). Can you tell me if there is a problem with ps_sgr_235_3s_5?

Cheers,
John Vickers

My vista system is erroring all these right now

ps_sgr_208_3s_5_13105_1244568552_0

<core_client_version>5.10.45</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
Running Milkyway@home ATI GPU application version 0.19 by Gipsel
CPU: Intel(R) Xeon(R) CPU X5340 @ 2.40GHz (4 cores/threads) 2.39464 GHz (134ms)

0 Kernel Execution : Failed to create Program

</stderr_txt>
]]>

---

Is it also erroring on ps_sgr_210_3s_5 or ps_sgr_235_3s_5?

Thanks,
John Vickers

Is it also erroring on ps_sgr_210_3s_5 or ps_sgr_235_3s_5?

Thanks,
John Vickers

ps_sgr_210_3s_5 is running fine on ATi card here.

Also, loving the running times - 33% longer than other WUs.

---

yes

ps_sgr_210_3s_5_22215_1244570153_1

Monkee,

Do you have Cluster Physik's new ATI application .19f ?

http://milkyway.cs.rpi.edu/milkyway/forum_thread.php?id=886#24282