Posts by Darrell
log in
1) Message boards : Number crunching : New Benchmark Thread - times wanted for any hardware, CPU or GPU, old or new! (Message 66672)
Posted 19 days ago by Darrell

Darrell
Thanks for your time :), is that from an average of 5 or more WUs?
Re DP FLOPS, weird, according to my table a 480 should do 323 DP GFLOPS, was it throttling?


Sorry, it is not a calculated average, but just an eyeball calculation from looking at the task results. An eyeball calculation of some of the new larger tasks is about 205 seconds.

The GPU is running fine, no throttling. Just a weird little message that shows up in each task result with the new GPU. It replaced an HD5850 back in March.

Task Results: http://milkyway.cs.rpi.edu/milkyway/results.php?userid=32442&offset=0&show_names=0&state=0&appid=
2) Message boards : Number crunching : N-Body Simulation (mt) WU (Message 66671)
Posted 19 days ago by Darrell
The Boinc Manager will do nothing. It is just a graphical interface between you and the Boinc client "Boinc.exe". The client handles all communication with the servers and the scheduling of tasks. Yes, it will pause enough running tasks and/or not start any new ones until enough cores are free when it decides it is time to run a multi-core task.
3) Message boards : Number crunching : New Benchmark Thread - times wanted for any hardware, CPU or GPU, old or new! (Message 66591)
Posted 6 Sep 2017 by Darrell
AMD Phenom II X6 1100T running Windows 7 with an MSI RX 480 Armor 8gb OC GPU. Running one task at a time on the GPU with an average of about 110 seconds per task.

Like this in the task results:

Estimated AMD GPU GFLOP/s: 468 SP GFLOP/s, 94 DP FLOP/s
Warning: Bizarrely low flops (93). Defaulting to 100
4) Message boards : Number crunching : Warnings in task result (Message 66435)
Posted 13 May 2017 by Darrell
I thought I had once seen a post about these, but a search does not find anything, so I am going to ask about them:

C:\Users\Darrell\AppData\Local\Temp\\OCL5992T3.cl:183:72: warning: unknown attribute 'max_constant_size' ignored
__constant real* _ap_consts __attribute__((max_constant_size(18 * sizeof(real)))),
^
C:\Users\Darrell\AppData\Local\Temp\\OCL5992T3.cl:185:62: warning: unknown attribute 'max_constant_size' ignored
__constant SC* sc __attribute__((max_constant_size(NSTREAM * sizeof(SC)))),
^
C:\Users\Darrell\AppData\Local\Temp\\OCL5992T3.cl:186:67: warning: unknown attribute 'max_constant_size' ignored
__constant real* sg_dx __attribute__((max_constant_size(256 * sizeof(real)))),
^
3 warnings generated.

Estimated AMD GPU GFLOP/s: 465 SP GFLOP/s, 93 DP FLOP/s
Warning: Bizarrely low flops (93). Defaulting to 100

Any ideas?
5) Message boards : News : Scheduled Server Maintenance Concluded (Message 66411)
Posted 8 May 2017 by Darrell
Hi Jake, this started this morning:

<search_application> milkyway_separation 1.46 Windows x86 double OpenCL </search_application>
Reading preferences ended prematurely
BOINC GPU type suggests using OpenCL vendor 'Advanced Micro Devices, Inc.'
Error loading Lua script 'astronomy_parameters.txt': [string "number_parameters: 4..."]:1: '<name>' expected near '4'
Switching to Parameter File 'astronomy_parameters.txt'
<number_WUs> 5 </number_WUs>
<number_params_per_WU> 21 </number_params_per_WU>
Number of parameters doesn't make sense

The tasks with the four you mentioned are all failing while those not from those runs are completing.

All four types of tasks do not like the number_params_per_WU set to 21, those tasks that have this parameter set to 20, run ok.
6) Message boards : Number crunching : Computation Errors on Cataylist 14.4 (Message 61830)
Posted 3 Jun 2014 by Darrell
Was tired after a busy day at work, and missed the sticky. Please follow the link.

http://milkyway.cs.rpi.edu/milkyway/forum_thread.php?id=3558
7) Questions and Answers : Windows : Computation Errors on Cataylist 14.4 (Message 61829)
Posted 2 Jun 2014 by Darrell
Was running an integrated HD3000 and a HD5850 on 13.1, this weekend I shutdown the HD3000 and upgraded the HD5850 to cataylist 14.4. Finally got some Milkyway tasks this afternoon and all of the Milkyway@home 1.2 task are failing. They are failing with an unknown error or memory access violation errors.

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=757905567

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=757905568

The separation modified fit task are completing ok.

Any ideas?

Edit: The errors are happening when tasks hits 100% completion.
8) Message boards : Application Code Discussion : MAC OS X Nvidia - MilkyWay Sepearation Modified Fit v1.30 (Message 61687)
Posted 3 May 2014 by Darrell
These are the exclusions I use to keep milkyway apps off my integrated HD3000:

<exclude_gpu>
<url>http://milkyway.cs.rpi.edu/milkyway/</url>
<device_num>1</device_num>
<type>ATI</type>
<app>milkyway_nbody</app>
</exclude_gpu>
<exclude_gpu>
<url>http://milkyway.cs.rpi.edu/milkyway/</url>
<device_num>1</device_num>
<type>ATI</type>
<app>milkyway_separation__modified_fit</app>
</exclude_gpu>
<exclude_gpu>
<url>http://milkyway.cs.rpi.edu/milkyway/</url>
<device_num>1</device_num>
<type>ATI</type>
<app>milkyway</app>
</exclude_gpu>

Based upon what you have posted, <type> should change to intel_gpu and <device_num> changed to 0

These exclusions go in the cc_config.xml file in the boinc data directory, please see http://boinc.berkeley.edu/wiki/Client_configuration for instructions on how to create it. You will need these exclusions until such time as the double precision requirement is added to boinc.
9) Message boards : Number crunching : warning: OpenCL extension is now part of core (Message 58195)
Posted 10 May 2013 by Darrell
go to the C:\AMD\support\"version name of driver installed"\Packages\Opencl directory and run the opencl.msi installer. It will ask you if you want to install or repair? Choose repair and let it run, then restart boinc. You can also download the "gpu_z" program and it will tell you if opencl is working before running boinc.




Main page · Your account · Message boards


Copyright © 2017 AstroInformatics Group