ScicomP 13 Tutorial: Optimizing Applications for Performance on IBM POWER architectures

From: Richard Gerber (ragerber_at_lbl.gov)
Date: 06/25/2007


ScicomP and IBM are pleased to announce a full-day tutorial that will open
the 13th Meeting of ScicomP, the IBM Systems Scientific User Group, in
Garching, Germany. The full conference runs July 16-20, 2007.



   OPTIMIZING APPLICATIONS FOR PERFORMANCE ON POWER ARCHITECTURES

                        ScicomP 13 Tutorial Day
                        Monday, July 16, 2007


Conference registration is open at the conference web site:
                        http://scicomp.rzg.mpg.de/

Early registration rates are in effect through June 29, 2007. A block of 
hotel
rooms in Garching is reserved through July 1, 2007. See the web site for 
details.

--------------------------------------------------------------------------------------

OPTIMIZING APPLICATIONS FOR PERFORMANCE ON POWER ARCHITECTURES

Roch Archambault,  IBM Software Group, Compiler Optimization Technology
Martin Feyereisen,  IBM Systems and Technology Group, Deep Computing 
Technology Group
I-Hsin Chung,  IBM Watson Research, Advanced Computer Technology


This tutorial will discuss and deliver techniques to derive optimal system
and application performance on IBM clusters.  Information will be provided
on five topics:

1)  Overview and intelligent use of IBM XL Compiler options

2)  Performance tools and libraries

3)  Techniques (including examples) for tuning applications for better 
cache utilization

4)  System tuning techniques including switches, memory, SMT, processor 
binding, etc.

5)  POWER6 specific performance issues


-- 
Richard Gerber, Ph.D.                      ragerber@lbl.gov  
NERSC                                      phone: 510-486-6820
Lawrence Berkeley National Lab             fax:   510-486-4316 
Berkeley, CA 94720

This archive was generated by hypermail 2.1.6 : 08/21/2008 PDT