LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (May 2004, week 3)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Mon, 17 May 2004 16:09:04 -0400
Reply-To:     "Fehd, Ronald J. (PHPPO)" <rjf2@CDC.GOV>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "Fehd, Ronald J. (PHPPO)" <rjf2@CDC.GOV>
Subject:      Re: Best of SUGI29 - Tips & Tricks
Content-Type: text/plain; charset="us-ascii"

> From: Choate, Paul@DDS [mailto:pchoate@DDS.CA.GOV] > > Would any SUGI29 attendees care to share with SAS-L their > favorite golden nugget of SAS from the conference?

Paul Kent presented a SEUGI paper written by someone in one of Europe's largest Insurance companies that showed some test runs of BigIron (z/OS: formerly OS/390) using several CPUs comparing test suites run under v8.2, v9 and v9 w/3 CPUs

see v9.1 OnLineDoc: What's New in the SAS 9 and 9.1 Macro Language Facility

new automatic macro variable -- more correctly named: macro constant -- SYSnCPU contains the current number of CPUs that SAS can use during the current session.

the number of CPUs can be set in config, invocation, or (any) options statement ... PROC OPTIONS GROUP= PERFORMANCE

options CPUcount = <1:1024 or actual>

see also: Threads UtilLoc

the paper presented code which divided the tasks for each CPU one such subset division was by use of mod operator and another by expert use of an identifier: CPU-1 gets all less than '33' CPU-2 gets all equal to '33' CPU-3 gets all greater than '33'

interesting main point: elapsed time may decrease but CPU time may increase

a side effect was that the EXCP count increased in each of the trials with the decreases in elapsed time and CPU time for use of more CPUs

some sites charge back mainframe costs based on both CPU time used and EXCP count, so tripling the EXCP count needs to be factored in, and could probably be reduced with other tuning.

Paul's down-home example, -- North Carolina being, as the name implies, just north of South Carolina, the home of NASCAR: Nat'l Assoc of Stock Car Auto Racers http://www.nascar.com/ -- was that if you want a car with eight cylinders you have to pay in one way or another for use of that much horsepower, in increased gas consumption, maintenance, etc.

Ron Fehd the macro maven CDC Atlanta GA USA RJF2@cdc.gov

see SUGI29 Proceedings http://www2.sas.com/proceedings/sugi29/toc.html

note: Lex Jansen has SUGI 29 proceedings available http://www.lexjansen.com/sugi/

http://support.sas.com/usergroups/sugi/intro.html SUGI 30 April 10-13, 2005 Pennsylvania Convention Center Gregory S. Nelson, Conference Chair


Back to: Top of message | Previous page | Main SAS-L page