Northern California Computer 

Measurement Group

                              

Upcoming Meetings

May 4th

August 3rd

November 2nd

 

Prior Meetings

 & Agendas

 

Registration

 

Officers

Links & Other Info

 

CMG2009 Conference

CMG2008 Conference

CMG2007 Conference

CMG2006 Conference

CMG2005 Conference

 

 

CMG Home

CMG MeasureIt

NCCMG Bylaws

 

 

 

 

 

 

 

                 February 2, 2010

   Agenda 

(Sponsored by Compuware)

4733 Chabot Drive, Suite 100

Pleasanton, CA 94588

 

8:00 – 9:00      Registration and Continental Breakfast

 

9:00 – 10:00    Performance Improvements from the “Things I Wish They’d Told Me 8 years Ago” - Visualized

                        Speaker:  Tom Halinski, Compuware Corporation

 

Pearls of wisdom for application performance improvements using DB2 sound good and make a lot of sense.  But how do we know how well they work and to what extent?  This paper will take some of the performance tips from Bonnie Baker, a DB2 industry expert, and measure them.  It will explain the theory and show the actual before and after results of implementing tips like: synchronous vs. asynchronous I/O, index usage and stage 1 vs. stage 2 predicates.  After “seeing” the actual performance improvements, IT personnel will be much more confident that theory and reality can go hand in hand.

 

10:15 – 11:15  zWhole Wide World of Specialty Processors

Speaker:  Craig Mullins, NEON Corporation

 

What do you know about IBM’s specialty processors for z Series mainframe hardware? Chances are you’ve heard something about them, but do you know enough? How many are there, how many can you get, why would you want them, and what exactly do they all do?

 This presentation offers an informative, yet opinionated look at IBM specialty processors. As we investigate the particulars of zIIPs and zAAPs, ICFs and IFLs, we’ll also take a look at IBM’s strategy, give an opinion on the “intent” of that strategy, and how it is working. And we’ll take a look at how specialty processors can save you money, the caveats and concerns surrounding specialty processors, and what the ISVs are doing to take advantage of specialty processors.

This presentation should have something in it for anyone who works on a mainframe – whether you are a specialty processor novice or already know about these chips.

 

11:30 – 12:30  Best Practices in Batch Tuning – Empowering IT Staff to reduce CPU and Run-Time in the Enterprise

Speaker:  Doug Berg, Software Engineering of America

 

In this session, we’ll explore the key factors that often limit the focus on batch tuning, and we’ll discuss the technology framework and methods that effectively assist performance and capacity staff as well as empower other key staff members like applications and production support, in the identification and resolution of batch tuning opportunities.  We will discuss methods for identifying the major sources of batch inefficiencies that recover the greatest batch elapsed time, CPU and I/O savings quickly, and with minimum effort and impact to the IT organization. We will also discuss how complex batch issues related to DFSORT, DFSMS, DB2 and other inefficiencies, can be easily discovered and have solutions presented.

 

11:45 ‑ 1:00    NCCMG Business Meeting/ Lunch sponsored by Compuware/Compuware Product Presentation

 

1:30 – 2:30      Benchmarking the Efficiency of Array Processing for Various Types of Language Processors

Speaker:  Jozo Dujmovic, San Francisco State University

 

In this presentation, we discuss a benchmarking technique and performance indicators that can be used to evaluate and compare programming languages and language processors in the area of efficiency of array processing. The proposed subscript permutation technique is applied to matrix multiplication benchmarking and used to differentiate language processors and provide insight into performance levels attainable by scripting languages, virtual machine based languages, and languages that compile to the native machine language. Our experimental analysis covers 10 popular languages and 14 language processors. Included are C, C++,  C#, VB, Java, Javascript, Perl, Python, PHP, and Ruby. We also investigate general effects that the optimization of array processing has in software engineering and benchmarking.

 

2:45 – 3:45      ** 2009 Mullen Award Winner ** 

Load Testing is Easy.  Good Load Testing is Not.  Preparation is the Difference.

Speaker:  Chris Lynn, Safeway Corporation

 

This presentation discusses recommendations and considerations to plan and prepare for valuable performance and load testing.  It includes a guide to identifying and developing the:

1.       Testing Purposes

2.       Roles and Responsibilities

3.       Business Performance Requirements

4.       Scope of Testing

5.       Testing Environment Requirements

6.       Usage Patterns and Transaction Mix

7.       Proposed Test Scenarios

8.       Load Generation Requirements

9.       Proposed Monitoring, Tracking, and Reporting

10.   Once this planning is done the scripting and execution is “easy”.  Scripting not included.

 

Please pre-register by contacting Keith McAndrew at (916) 715-8352 by Friday January 29, 2010. Registration is $25 at the door.

 

Report from the November 2009 meeting:

   Speakers:  Emmanuel Sauvion, Dave Day, Scott Sumner and Brian Barnett

 

Call for speakers in 2009. If you are interested in speaking, call Cathy Nolan at (925) 675-5308 or (925) 890-8390.

 

If you have not attended a meeting within the last two years, you will be deleted from the mailing list.  To remain on the mailing list, either attend one meeting or email cathy.nolan@bankofamerica.com by November 1, 2010. 

  

Notices

bullet

Meetings are held on the first Tuesday of every February, May, August, and November.  

bullet

Next meeting is February 2nd

 

Questions or comments about this web site? Please email the webmaster.

Updated: 02/11/2010