Optimize your GPU. Find the value the easy way.

Starting automatic test: (x41z 64 bit cuda 42)
28 August 2012 - 10:25:26 Start, devices: 2, device count: 1 (1.00)
28 August 2012 - 10:25:26 Set: x41z 64 bit cuda 42 , Exe: lunatics_x41z_win32_cuda42.exe , Parameters: --device %device
ERROR: Missing file: work_unit.sah.
Aborted

Fred,
What am I doing wrong? 2 GTX570. I copied work_unit.sah from x41g file.
Thanks
____________
Now a proud GPU Users Group 10.1 percenter. Yes Tron, all your base are belong to us! Volunteer idiot.

**********CAUTION! competitive jerk**********

Right. Slot folders 0,1,2,and 3 do contain work_unit.sah.

To run stand alone it needs work_unit.sah.

Hmmm.... I have the x41z folder setup exactly like the x41g folder, with the files for _z of course. The work_unit.sah was copied exactly from the g to the z folder but the program cannot find it. I'm assuming the work_unit.sah is generic and can be used with either the g or z? Like I said the g settings work fine. I'm stumped!

EDIT: Checked again, work_unit.sah is NOT getting into slot 0. Does the program put the work_unit.sah in the slot or is that manual placement?
____________
Now a proud GPU Users Group 10.1 percenter. Yes Tron, all your base are belong to us! Volunteer idiot.

**********CAUTION! competitive jerk**********

Dual GTX 660Ti reference cards

Starting automatic test: (x41z)
28 August 2012 - 16:11:31 Start, devices: 2, device count: 1 (1.00)
28 August 2012 - 16:14:14 Runtime: Device: 1, count: 0, 162 seconds
28 August 2012 - 16:14:14 Device: 1, Count: 0, finished.
28 August 2012 - 16:14:17 Runtime: Device: 0, count: 0, 165 seconds
28 August 2012 - 16:14:17 Device: 0, Count: 0, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 1, average time / count: 165, average time on device: 165 Seconds (2

Minutes, 45 Seconds)
Device: 1, device count: 1, average time / count: 162, average time on device: 162 Seconds (2

Minutes, 42 Seconds)
Next ---------------------------------------------------------------------
28 August 2012 - 16:14:18 Start, devices: 2, device count: 2 (0.50)
28 August 2012 - 16:18:29 Runtime: Device: 1, count: 0, 250 seconds
28 August 2012 - 16:18:29 Device: 1, Count: 0, finished.
28 August 2012 - 16:18:29 Runtime: Device: 1, count: 1, 250 seconds
28 August 2012 - 16:18:29 Device: 1, Count: 1, finished.
28 August 2012 - 16:18:30 Runtime: Device: 0, count: 0, 251 seconds
28 August 2012 - 16:18:30 Device: 0, Count: 0, finished.
28 August 2012 - 16:18:30 Runtime: Device: 0, count: 1, 251 seconds
28 August 2012 - 16:18:30 Device: 0, Count: 1, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 2, average time / count: 251, average time on device: 125 Seconds (2

Minutes, 5 Seconds)
Device: 1, device count: 2, average time / count: 250, average time on device: 125 Seconds (2

Minutes, 5 Seconds)
Next ---------------------------------------------------------------------
28 August 2012 - 16:18:32 Start, devices: 2, device count: 3 (0.33)
28 August 2012 - 16:24:37 Runtime: Device: 1, count: 2, 364 seconds
28 August 2012 - 16:24:37 Device: 1, Count: 2, finished.
28 August 2012 - 16:24:37 Runtime: Device: 1, count: 1, 364 seconds
28 August 2012 - 16:24:37 Device: 1, Count: 1, finished.
28 August 2012 - 16:24:38 Runtime: Device: 1, count: 0, 365 seconds
28 August 2012 - 16:24:38 Device: 1, Count: 0, finished.
28 August 2012 - 16:24:40 Runtime: Device: 0, count: 0, 367 seconds
28 August 2012 - 16:24:40 Device: 0, Count: 0, finished.
28 August 2012 - 16:24:41 Runtime: Device: 0, count: 1, 368 seconds
28 August 2012 - 16:24:41 Device: 0, Count: 1, finished.
28 August 2012 - 16:24:42 Runtime: Device: 0, count: 2, 369 seconds
28 August 2012 - 16:24:42 Device: 0, Count: 2, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 3, average time / count: 368, average time on device: 122 Seconds (2

Minutes, 2 Seconds)
Device: 1, device count: 3, average time / count: 364, average time on device: 121 Seconds (2

Minutes, 1 Seconds)
Next ---------------------------------------------------------------------
28 August 2012 - 16:24:44 Start, devices: 2, device count: 4 (0.25)
28 August 2012 - 16:32:46 Runtime: Device: 0, count: 0, 480 seconds
28 August 2012 - 16:32:46 Device: 0, Count: 0, finished.
28 August 2012 - 16:32:48 Runtime: Device: 1, count: 0, 482 seconds
28 August 2012 - 16:32:48 Device: 1, Count: 0, finished.
28 August 2012 - 16:32:48 Runtime: Device: 1, count: 1, 482 seconds
28 August 2012 - 16:32:48 Device: 1, Count: 1, finished.
28 August 2012 - 16:32:48 Runtime: Device: 1, count: 2, 482 seconds
28 August 2012 - 16:32:48 Device: 1, Count: 2, finished.
28 August 2012 - 16:32:48 Runtime: Device: 1, count: 3, 482 seconds
28 August 2012 - 16:32:48 Device: 1, Count: 3, finished.
28 August 2012 - 16:32:48 Runtime: Device: 0, count: 2, 482 seconds
28 August 2012 - 16:32:48 Device: 0, Count: 2, finished.
28 August 2012 - 16:32:48 Runtime: Device: 0, count: 1, 482 seconds
28 August 2012 - 16:32:48 Device: 0, Count: 1, finished.
28 August 2012 - 16:32:48 Runtime: Device: 0, count: 3, 482 seconds
28 August 2012 - 16:32:48 Device: 0, Count: 3, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 4, average time / count: 481, average time on device: 120 Seconds (2

Minutes, 0 Seconds)
Device: 1, device count: 4, average time / count: 482, average time on device: 120 Seconds (2

Minutes, 0 Seconds)
The best average time found: 121 Seconds (2 Minutes, 1 Seconds), with count: 0.33 (3)

x41z EVGA GTX670 reference card

Starting automatic test: (x41z)
28 August 2012 - 16:30:59 Start, devices: 1, device count: 1 (1.00)
28 August 2012 - 16:33:14 Runtime: Device: 0, count: 0, 134 seconds
28 August 2012 - 16:33:14 Device: 0, Count: 0, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 1, average time / count: 134, average time on device: 134 Seconds (2 Minutes, 14 Seconds)
Next ---------------------------------------------------------------------
28 August 2012 - 16:33:16 Start, devices: 1, device count: 2 (0.50)
28 August 2012 - 16:36:45 Runtime: Device: 0, count: 0, 208 seconds
28 August 2012 - 16:36:45 Device: 0, Count: 0, finished.
28 August 2012 - 16:36:50 Runtime: Device: 0, count: 1, 213 seconds
28 August 2012 - 16:36:50 Device: 0, Count: 1, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 2, average time / count: 210, average time on device: 105 Seconds (1 Minutes, 45 Seconds)
Next ---------------------------------------------------------------------
28 August 2012 - 16:36:51 Start, devices: 1, device count: 3 (0.33)
28 August 2012 - 16:41:58 Runtime: Device: 0, count: 0, 306 seconds
28 August 2012 - 16:41:58 Device: 0, Count: 0, finished.
28 August 2012 - 16:42:02 Runtime: Device: 0, count: 2, 310 seconds
28 August 2012 - 16:42:02 Device: 0, Count: 2, finished.
28 August 2012 - 16:42:04 Runtime: Device: 0, count: 1, 312 seconds
28 August 2012 - 16:42:04 Device: 0, Count: 1, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 3, average time / count: 309, average time on device: 103 Seconds (1 Minutes, 43 Seconds)
The best average time found: 105 Seconds (1 Minutes, 45 Seconds), with count: 0.50 (2)

x41z Dual GTX 560Ti reference cards

Starting automatic test: (x41z)
28 August 2012 - 16:42:12 Start, devices: 2, device count: 1 (1.00)
28 August 2012 - 16:44:30 Runtime: Device: 1, count: 0, 137 seconds
28 August 2012 - 16:44:30 Device: 1, Count: 0, finished.
28 August 2012 - 16:44:31 Runtime: Device: 0, count: 0, 138 seconds
28 August 2012 - 16:44:31 Device: 0, Count: 0, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 1, average time / count: 138, average time on device: 138 Seconds (2 Minutes, 18 Seconds)
Device: 1, device count: 1, average time / count: 137, average time on device: 137 Seconds (2 Minutes, 17 Seconds)
Next ---------------------------------------------------------------------
28 August 2012 - 16:44:31 Start, devices: 2, device count: 2 (0.50)
28 August 2012 - 16:48:27 Runtime: Device: 0, count: 1, 235 seconds
28 August 2012 - 16:48:27 Device: 0, Count: 1, finished.
28 August 2012 - 16:48:28 Runtime: Device: 1, count: 1, 236 seconds
28 August 2012 - 16:48:28 Device: 1, Count: 1, finished.
28 August 2012 - 16:48:28 Runtime: Device: 1, count: 0, 236 seconds
28 August 2012 - 16:48:28 Device: 1, Count: 0, finished.
28 August 2012 - 16:48:29 Runtime: Device: 0, count: 0, 236 seconds
28 August 2012 - 16:48:29 Device: 0, Count: 0, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 2, average time / count: 235, average time on device: 117 Seconds (1 Minutes, 57 Seconds)
Device: 1, device count: 2, average time / count: 236, average time on device: 118 Seconds (1 Minutes, 58 Seconds)
Next ---------------------------------------------------------------------
28 August 2012 - 16:48:31 Start, devices: 2, device count: 3 (0.33)
28 August 2012 - 16:54:20 Runtime: Device: 0, count: 0, 348 seconds
28 August 2012 - 16:54:20 Device: 0, Count: 0, finished.
28 August 2012 - 16:54:22 Runtime: Device: 0, count: 2, 350 seconds
28 August 2012 - 16:54:22 Device: 0, Count: 2, finished.
28 August 2012 - 16:54:23 Runtime: Device: 0, count: 1, 351 seconds
28 August 2012 - 16:54:23 Runtime: Device: 1, count: 0, 351 seconds
28 August 2012 - 16:54:23 Device: 0, Count: 1, finished.
28 August 2012 - 16:54:23 Device: 1, Count: 0, finished.
28 August 2012 - 16:54:24 Runtime: Device: 1, count: 2, 352 seconds
28 August 2012 - 16:54:24 Runtime: Device: 1, count: 1, 352 seconds
28 August 2012 - 16:54:24 Device: 1, Count: 1, finished.
28 August 2012 - 16:54:24 Device: 1, Count: 2, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 3, average time / count: 349, average time on device: 116 Seconds (1 Minutes, 56 Seconds)
Device: 1, device count: 3, average time / count: 351, average time on device: 117 Seconds (1 Minutes, 57 Seconds)
The best average time found: 117 Seconds (1 Minutes, 57 Seconds), with count: 0.50 (2)

Starting test: (lunatics_x41g_win32_cuda32_perf.exe)

(Dual GTX 460's (O/c'd)

Device: 0, device count: 1, average time / count: 170, average time on device: 170 Seconds (2 Minutes, 50 Seconds)
Device: 1, device count: 1, average time / count: 173, average time on device: 173 Seconds (2 Minutes, 53 Seconds)

Device: 0, device count: 2, average time / count: 319, average time on device: 159 Seconds (2 Minutes, 39 Seconds)
Device: 1, device count: 2, average time / count: 330, average time on device: 165 Seconds (2 Minutes, 45 Seconds)

Device: 0, device count: 3, average time / count: 485, average time on device: 161 Seconds (2 Minutes, 41 Seconds)
Device: 1, device count: 3, average time / count: 489, average time on device: 163 Seconds (2 Minutes, 43 Seconds)

Device: 0, device count: 4, average time / count: 638, average time on device: 159 Seconds (2 Minutes, 39 Seconds)
Device: 1, device count: 4, average time / count: 643, average time on device: 160 Seconds (2 Minutes, 40 Seconds)

The best average time found: 160 Seconds (2 Minutes, 40 Seconds), with count: 0.25 (4)


Thanks for another terrific app, Fred!!


Lt

hi friends

i know my gpu is not the best...but for me good enough ;)

here are results from my Nvidia GT630

Starting automatic test: (x41g)
29 August 2012 - 09:33:44 Start, devices: 1, device count: 1 (1.00)
29 August 2012 - 09:41:18 Runtime: Device: 0, count: 0, 453 seconds
29 August 2012 - 09:41:18 Device: 0, Count: 0, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 1, average time / count: 453, average time on device: 453 Seconds (7 Minutes, 33 Seconds)
Next ---------------------------------------------------------------------
29 August 2012 - 09:41:19 Start, devices: 1, device count: 2 (0.50)
29 August 2012 - 09:54:59 Runtime: Device: 0, count: 0, 819 seconds
29 August 2012 - 09:54:59 Device: 0, Count: 0, finished.
29 August 2012 - 09:55:03 Runtime: Device: 0, count: 1, 823 seconds
29 August 2012 - 09:55:03 Device: 0, Count: 1, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 2, average time / count: 821, average time on device: 410 Seconds (6 Minutes, 50 Seconds)
Next ---------------------------------------------------------------------
29 August 2012 - 09:55:04 Start, devices: 1, device count: 3 (0.33)
29 August 2012 - 10:15:19 Runtime: Device: 0, count: 2, 1214 seconds
29 August 2012 - 10:15:19 Device: 0, Count: 2, finished.
29 August 2012 - 10:15:25 Runtime: Device: 0, count: 1, 1220 seconds
29 August 2012 - 10:15:25 Device: 0, Count: 1, finished.
29 August 2012 - 10:15:28 Runtime: Device: 0, count: 0, 1223 seconds
29 August 2012 - 10:15:28 Device: 0, Count: 0, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 3, average time / count: 1219, average time on device: 406 Seconds (6 Minutes, 46 Seconds)
Next ---------------------------------------------------------------------
29 August 2012 - 10:15:29 Start, devices: 1, device count: 4 (0.25)
29 August 2012 - 10:42:33 Runtime: Device: 0, count: 2, 1622 seconds
29 August 2012 - 10:42:33 Device: 0, Count: 2, finished.
29 August 2012 - 10:42:35 Runtime: Device: 0, count: 1, 1624 seconds
29 August 2012 - 10:42:35 Device: 0, Count: 1, finished.
29 August 2012 - 10:42:35 Runtime: Device: 0, count: 3, 1624 seconds
29 August 2012 - 10:42:35 Device: 0, Count: 3, finished.
29 August 2012 - 10:42:39 Runtime: Device: 0, count: 0, 1628 seconds
29 August 2012 - 10:42:39 Device: 0, Count: 0, finished.
Ready ---------------------------------------------------------------------
Results:
Device: 0, device count: 4, average time / count: 1624, average time on device: 406 Seconds (6 Minutes, 46 Seconds)
The best average time found: 406 Seconds (6 Minutes, 46 Seconds), with count: 0.33 (3)

looks like there is no difference between 3 or 4 counts.
hope it help you ;)

greetings
ralf
____________
Boinc runs here on:
Intel i7-3770K (Limited to 6 Cores)
Nvidia GT-630 (Fermi)

Thanks Fred.

<config>
<data>
<name>x41g</name>
<folder>x41g</folder>
<exe>Lunatics_x41g_win32_cuda32_perf.exe</exe>
<parameter>%20--device%20%device</parameter>
</data>

<!-- Some more settings: You can add additional data folders as shown below -->
<!-- Additional gui options are also available for experts -->


<data>
<name>x41z%20cuda%2032</name>
<folder>x41z</folder>
<exe>Lunatics_x41z_win32_cuda32_perf.exe</exe>
<parameter>%20--device%20%device</parameter>
</data>
<data>
<name>x41z%20cuda%2042</name>
<folder>x41z_cuda42</folder>
<exe>Lunatics_x41z_win32_cuda42.exe</exe>
<parameter>%20--device%20%device</parameter>
</data>
<data>
<name>x41z%2064%20bit%20cuda%2042</name>
<folder>x41z_64_cuda42</folder>
<exe>Lunatics_x41z_win32_cuda42.exe</exe>
<parameter>%20--device%20%device</parameter>
</data>

<gui>
<showParameters>1</showParameters>
<showReadXmlButton>1</showReadXmlButton>
<maxAutoCount>3</maxAutoCount>
<showExpert>1</showexpert>
</gui>
-->
</config>


<!--

Make sure you open this file in a simple text editor, like notepad.exe only.
This file has to be stored in ascii format.

%20 = space

<data> Is the selection data that shows up in the combi box. (more than 1 item)

<parameter> %device = device number %device replaced by 0, 1, 2, 3, 4
<showParameters> 1 = show field where you can put in additional parameters. This value is added to <parameter> in <data>. Make sure to add an additional space.
e.g. <parameter>%20--device%20%device and parameter field --test send to the application -> --device 0 --test
<showexpert> shows additional information in the screen log.
<maxAutoCount> 2 = 0.5, 3 = 0.33, 4 = 0.25 So fill in 1 or 2 or 3 or 4

-->

I basically just took out the comment to get the rest to run.

BTW, is this test system specific or does it give a general return for any/all cards?
____________
Now a proud GPU Users Group 10.1 percenter. Yes Tron, all your base are belong to us! Volunteer idiot.

**********CAUTION! competitive jerk**********

I have some questions:
Can I use another WU for testing the performance?
Im thinking that if the system is slow feeding the GPU (or there is any other bottleneck other than the raw performance of the GPU), then the optimal number of concurrent WUs may be different if the WU takes more (or less) time to be crunched...
I guess that it should be enough just to replace the "work_unit.sah" with another WU (renamed as "work_unit.sah", I guess) or does the test a validation on the result and it will fail if I change the WU?
____________