Getting most out of your CUDA 50 app

Questions and Answers : GPU applications : Getting most out of your CUDA 50 app
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Tom Miller
Volunteer tester
Avatar

Send message
Joined: 28 Nov 02
Posts: 768
Credit: 18,727,685
RAC: 20,735
United States
Message 1881407 - Posted: 31 Jul 2017, 21:47:24 UTC

Hi,
Although I am getting a lot of SOG's for my new box's (its been online a week or so) Gtx 1060 3GB I just noticed that the Seti scheduler had dropped a 20 odd Cuda50's on me. So I went and copy/pasted the cfg.sample and put in the "improved" parameters.

;;; This configuration file is for optional control of Cuda Multibeam x41zi
;;; Currently, the available options are for
;;; application process priority control (without external tools), and
;;; per gpu priority control (useful for multiple Cuda GPU systems)
[mbcuda]
;;;;; Global applications settings, to apply to all Cuda devices
;;; You can uncomment the processpriority line below, by removing the ';', to engage machine global priority control of 

x41zi
;;; possible options are 'belownormal' (which is the default), 'normal', 'abovenormal', or 'high'
;;; For dedicated crunching machines, 'abovenormal' is recommended
;;; raising global application priorities above the default
;;;   may have system dependant usability effects, and can have positive or negative effects on overall throughput 
;processpriority = abovenormal
;;; Pulsefinding: Advanced options for long pulsefinds (affect display usability & long kernel runs)
;;; defaults are conservative.
;;; WARNING: Excessive values may induce display lag, driver timeout & recovery, or errors. 
;;; pulsefinding blocks per multiprocessor (1-16), default is 1 for Pre-Fermi, 4 for Fermi or newer GPUs
;pfblockspersm = 8
;;; pulsefinding maximum periods per kernel launch  (1-1000), default is 100, as per 6.09
;pfperiodsperlaunch = 200

;[bus1slot0]
;;; Optional GPU specifc control (requires Cuda 3.2 or newer app), example
processpriority = abovenormal
pfblockspersm = 8
pfperiodsperlaunch = 200


So my question is. For the "newer" generation of GPU's like my Gtx 1060 3GB has anyone found a "faster" while still being reliable, set of parameters?

Thank you,
Tom
"You are entitled to your own opinion but not to your own facts." Senator and Professor Patrick Moynihan
---
https://GalensonConsulting.WordPress.com
ID: 1881407 · Report as offensive
rob smithProject Donor
Volunteer tester

Send message
Joined: 7 Mar 03
Posts: 15198
Credit: 251,688,420
RAC: 325,770
United Kingdom
Message 1881515 - Posted: 1 Aug 2017, 8:46:24 UTC

Let them run through with the default settings, BOINC will decide they are too slow to worry about and not send you any more.

btw. - There is NO difference between a "SoG" task and a "CUDA50" task. What is different is the application the task is target at.
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1881515 · Report as offensive

Questions and Answers : GPU applications : Getting most out of your CUDA 50 app


 
©2017 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.