Task 132473914  
Name de_s222_3s_random_3p_10r_24_6612327_1255415842_0 
Workunit 129567207 
Created 13 Oct 2009 6:37:24 UTC 
Sent 13 Oct 2009 6:38:14 UTC 
Received 13 Oct 2009 6:39:22 UTC 
Server state Over 
Outcome Success 
Client state Done 
Exit status 0 (0x0) 
Computer ID 107881 
Report deadline 16 Oct 2009 6:38:14 UTC 
Run time 3.686209 
stderr out <core_client_version>6.10.7</core_client_version>
<![CDATA[
<stderr_txt>
Running Milkyway@home ATI GPU application version 0.20 (Win64) by Gipsel
ignoring unknown input argument in app_info.xml: --device
ignoring unknown input argument in app_info.xml: 1
CPU: Intel(R) Core(TM)2 Duo CPU     E8400  @ 3.00GHz (2 cores/threads) 2.99968 GHz (285ms)

CAL Runtime: 1.4.344
Found 2 CAL devices

Device 0: ATI Radeon HD 3800 (RV670) 512 MB local RAM (remote 1855 MB cached + 1855 MB uncached)
GPU core clock: 850 MHz, memory clock: 901 MHz
320 shader units organized in 4 SIMDs with 16 VLIW units (5-issue), wavefront size 64 threads
supporting double precision

Device 1: ATI Radeon HD 3800 (RV670) 512 MB local RAM (remote 1855 MB cached + 1855 MB uncached)
GPU core clock: 850 MHz, memory clock: 901 MHz
320 shader units organized in 4 SIMDs with 16 VLIW units (5-issue), wavefront size 64 threads
supporting double precision

1 WUs already running on GPU 0
0 WUs already running on GPU 1
Starting WU on GPU 1

main integral, 100 iterations
predicted runtime per iteration is 27 ms (33.3333 ms are allowed)
borders of the domains at 0 1000
Calculated about 2.29421e+011 floatingpoint ops on GPU, 2.39676e+007 on FPU. Approximate GPU time 3.68621 seconds.

probability calculation (stars)
Calculated about 3.34818e+009 floatingpoint ops on FPU.

WU completed.
CPU time: 1.60681 seconds,  GPU time: 3.68621 seconds,  wall clock time: 5.558 seconds,  CPU frequency: 2.99969 GHz

</stderr_txt>
]]>
 
Validate state Valid 
Claimed credit 0.0245001684629481 
Granted credit 53.45337 
application version 0.20 

Configuration of the number of concurrent WUs with new BOINC clients (6.10.3 and up):

The included app_info.xml declares the app as GPU app for the new 6.10.x clients. This is done
with a <coproc></coproc> statement. This statement also determines how much of a GPU the
application is upposed to use. If it uses less than a full GPU the client will start several WUs
for each detected GPU. Search for the following lines in the app_info.xml:
 <coproc>
   <type>ATI</type>
   <count>1</count>
 </coproc>
Changing the count value to 0.5 will run two WUs per GPU, a value of 0.33 three WUs.

<core_client_version>6.10.13</core_client_version>
<![CDATA[
<stderr_txt>
Running Milkyway@home ATI GPU application version 0.20b (Win64, CAL 1.4) by Gipsel
instructed by BOINC client to use device 0
CPU: Intel(R) Core(TM)2 Quad  CPU   Q8200  @ 2.33GHz (4 cores/threads) 2.8701 GHz (234ms)

CAL Runtime: 1.4.427
Found 1 CAL device

Device 0: ATI Radeon HD5800 series (Cypress) 1024 MB local RAM (remote 831 MB cached + 831 MB uncached)
GPU core clock: 850 MHz, memory clock: 300 MHz
1600 shader units organized in 20 SIMDs with 16 VLIW units (5-issue), wavefront size 64 threads
supporting double precision

Starting WU on GPU 0

main integral, 320 iterations
predicted runtime per iteration is 61 ms (33.3333 ms are allowed), dividing each iteration in 2 parts
borders of the domains at 0 800 1600
Calculated about 8.22242e+012 floatingpoint ops on GPU, 1.23583e+008 on FPU. Approximate GPU time 20.6122 seconds.

probability calculation (stars)
Calculated about 3.34818e+009 floatingpoint ops on FPU.

WU completed.
CPU time: 2.51162 seconds,  GPU time: 20.6122 seconds,  wall clock time: 21.768 seconds,  CPU frequency: 2.87016 GHz

</stderr_txt>
]]>

<app_info>
 <app>
 <name>milkyway</name>
 </app>
 <file_info>
  <name>astronomy_0.20b_ATI_x64_ati.exe</name>
  <executable/>
 </file_info>
 <file_info>
  <name>brook64.dll</name>
  <executable/>
 </file_info>

 <app_version>
  <app_name>milkyway</app_name>
  <version_num>20</version_num>
    <flops>1.0e11</flops>
    <avg_ncpus>0.05</avg_ncpus>
    <max_ncpus>1</max_ncpus>
    <coproc>
      <type>ATI</type>
      <count>1</count>
    </coproc>
    <cmdline></cmdline>
  <file_ref>
   <file_name>astronomy_0.20b_ATI_x64_ati.exe</file_name>
   <main_program/>
  </file_ref>
  <file_ref>
   <file_name>brook64.dll</file_name>
  </file_ref>
 </app_version>

</app_info>

Hmmmm...
Very interesting results.... http://milkyway.cs.rpi.edu/milkyway/results.php?hostid=107881&offset=0&show_names=0&state=3

You are right. "Very interesting" times for two RV 670...

He is running a script that alters the WUs after downloading. He reduces the number of iterations calculated in the WUs resulting in a massive speedup. And I can prove it. I will notify Travis/Anthony of this cheater. In my opinion this guy should be banned.

GPUGRID uses single precision math which is 8 times faster than the double precision math that Milkyway@Home requires. For reference, the single precision version of the Milkyway@Home CUDA app can do a WU in 15 seconds, while the double precision version takes upwards around 85 seconds. Granted the WU were smaller than the ones on BOINC, but it clearly shows the performance between single and double precision.

Thanks a lot, I'm implementing it now so the new version should be up within the hour.

Edit: The newest version is now on BOINC, the completion times should be more stable around 5-6 minutes, thanks to Cluster Physik.