Paul E. McKenney has been coding for almost four decades, more than half of that on parallel hardware, where his work has earned him a reputation among some as a flaming heretic. Over the past decade, Paul has been an IBM Distinguished Engineer at the IBM Linux Technology Center, and more recently has taken on the role of CTO Linux. Paul maintains the RCU implementation within the Linux kernel, where the variety of workloads present highly entertaining performance, scalability, real-time response, and energy-efficiency challenges. Prior to that, he worked on the DYNIX/ptx kernel at Sequent, and prior to that on packet-radio and Internet protocols (but long before it was polite to mention Internet at cocktail parties), system administration, business applications, and real-time systems. His hobbies include what passes for running at his age along with the usual house-wife-and-kids habit.

Advertisements

Lenz Gschwendtner is a true geek. He runs the Functional Programming User Group in Wellington, New Zealand. Lenz has a strong interest in concurrent programming and is always on the look for the optimal tool for the job. Currently is Team Leader at Open Parallel Ltd and CTO of idegeeo Group Ltd. Previously, he was CTO of United-Domains in Germany and Technical Director Domain Business at Lycos Europe. Lenz likes Perl, Erlang and life in New Zealand.

 

Dr Wayne Kelly started research in the field of parallel computing in 1990, completing his doctoral studies at the University of Maryland, USA in 1996. He has worked actively as a researcher in the area ever since and is now a Senior Lecturer at the Queensland University of Technology. As well as researching in this area, he has also recently introduced a course on “Parallel Programming and Multicore Processors” into the QUT under graduate curriculum. He also teaches advanced web development and enterprise software architecture. Dr Kelly previously founded and led a large team of developers in the Ruby.NET open source project and was an invited speaker at the RubyFools conferences held in Oslo and Copenhagen. Recent publications

John Williams is Founder and CEO of PetaLogix, and Research Fellow at The University of Queensland. Since completing the Linux kernel port for MicroBlaze back in 2003, John has been recognised as a world leader in the FPGA/Embedded Linux technology platform, working with a wide range of commercial and public sector organisations, including providing research support to NASA for the Reconfigurable Scalable Computing Project. Starting as a consulting service through The University of Queensland where he retains teaching and research positions, John oversaw the successful spinout of PetaLogix into a privately held company in 2007. John holds Honors degrees in Electronic Engineering and Information Technology, and was awarded a PhD in 2001 for his work in 3D computer vision and image processing.

Solutions Architect, Enspiral Ltd. Wellington, New Zealand.

Tim Uckun is a Project Manager, Programmer and IT Entrepreneur who has established entire IT departments and strategies in different organizations in the last 20 years between the US and New Zealand. He has been IT Manager / Chief Architect of the Commercial Division at USIS (United States Investigation Services); CTO and Vice President responsible for all IT infrastructure at Due Diligence Inc.; Network Engineer at Community Medical Center in Missoula, Montana; Data Integration Consultant at MCI/WorldCom and IT Manager at Pantzel (NZ-UK). Currently is Project Manager/Solutions Architect at Enspiral Ltd, NZ. Other roles included Information Architect, SDLC Manager and Infrastructure Manager. Tim lived and worked in the US, NZ, Japan and Turkey, and is fluent in English and Turkish.

II Multicore and Parallel Computing miniconference, part of LCA2011

Tuesday 25 of January 2011. Brisbane, Australia.

 

SCHEDULE

10:30 – 11:00 Verifying Parallel Software: Can Theory Meet Practice?

Paul McKenney – CTO Linux, IBM.

Abstract – OutlineBio

11:05 – 11:10 Lightning Talk –

How to speed up WordPress using Intel’s Threading Building Blocks (TBB) and Facebook’s HipHop

11:10 – 12:10 In Search of Transmission Capacity – a Multicore Dilemma

Vinton Cerf – VicePresident and Chief Internet Evangelist, Google

Abstract – Outline – Bio

12:15 – 13:30  Lunch

13:30 – 14:20 Is Parallel Programming Hard, And If So, Why?

Paul McKenney – CTO Linux, IBM.

Abstract – OutlineBio

14:25 – 14:30 Lightning Talk – How to build large scale applications using PHP

14:30 – 15:15 Parallel Programming – an Overview of Non Mainstream Languages

Lenz Gschwendtner – Team Leader, Open Parallel

Abstract – Outline – Bio

15:15 – 15:45  Interval

15:45 – 16:10 Multicore vs FPGAs

John Williams – CEO, PetaLogix and Lecturer, University of Queensland

Abstract – Outline – Bio

16:10 – 16:35 Painless Parallelization with Gearman

Tim Uckun – Solutions Architect, Enspiral

Abstract – Outline – Bio

16:35 – 17:00 Discovering Inherent Parallelism in Sequential Programs

Wayne Kelly – Senior Lecturer, Queensland University of Technology

Abstract – OutlineBio

17:00 – 17:20 Panel – Which Industries / Applications Need Parallelization TODAY? –

Moderator –Nicolás Erdödy

17:20 – 17:30 Birds of a Feather

17:30 Miniconference (formally) Ends.

Tradition says that it continues at the nearest pub.

Look forward to see you in Brisbane in January!

Dr. Vinton G. Cerf, Google’s Vice President and Chief Internet Evangelist is another keynote of the II Multicore and Parallel Computing miniconference that will be held on Tuesday 25 of January 2011 in Brisbane, Australia, part of LCA2011.

Known as the “Father of the Internet”, Vint won the ACM Turing award in 2004 with Robert Kahn.

Vint will be presenting from 10:30 till 11:30 am. Details of his talk will be posted soon.

You can still join the speakers of this miniconf: CFP ENDS November 8, 2010.

This is the title of Paul McKenney’s main presentation at the II Open Source, Multicore and Parallel Computing miniconf (part of LCA2011) that will be a full day on Tuesday 25th, January 2011, in Brisbane, Australia. CFP ends November 8, 2010

Abstract:

In less than a decade, multicore hardware has made the transition from exotic to ubiquitous.  To those of you who fear and loathe parallel programming, I offer my condolences, but the settled fact of the matter is that parallel programming has irrevocably joined mainstream programming practice.  However, I can also offer some good news along with the bad.  The good news is that parallel programming is not all that much more difficult than sequential programming.  Of course, some additional bad news is that most people cannot deal even with sequential programming. This talk will discuss ways that we can not just cope, but actually thrive in this new multicore environment.

Outline:

Review of MIPS/clock-frequency trends.
Parallel is here to stay: parallel hand-held battery anecdote.
Pastiche of “parallel is inhumanly hard” quotes.
But the universe is concurrent!!!  And people are too!!! (cartoon)  Additional examples.
But just because concurrency is natural does not mean that concurrent programming is natural.  Especially given that -programming- does not seem to be natural!  Three obstacles: (1) theory of mind (2) common sense (3) fragmentary plans. (Auto-rental example — free upgrade due to being Linux kernel hacker.)

Most people are not going to undertake parallel programming, mostly because most people are not going to program period!!!
Other topics from the blog series will be chosen randomly and capriciously, as there will be time for only a few:

  • The Great Multicore Software Crisis is upon us, but we can learn from the 1970s/1980s Great Software Crisis.
  • Embarrassing parallelism isn’t.
  • Parallel programmers can be trained.  Without experience and/or proper training, high IQ is a negative.
  • Darwinian selection favored fear and loathing of parallelism, but the fitness in the past does not necessarily imply fitness in the future.
  • Code is like water.  It is easy to do something with a cupful of water, but not so easy to do the same thing with the Pacific Ocean.
  • Past serial-only design and coding decisions cannot be wished away.
  • Parallelism introduces global constraints that are not as prevalent in sequential software.  A global view of parallel source code is critically important.
  • You get what you measure.  So be careful what you measure.
  • Amdahl’s Law is a great tool for evaluating scalability. Too bad that performance is what really matters.
  • Tools.  Parallel tools.  We need them.
  • Validating parallel programs requires special care.
  • Don’t ask the janitor to remodel your building. This caution also applies to software, despite the fact that your speaker is an exception to this rule.

But there is hope: like the Great Software Crisis of the 1970s and 1980s, the Great Multicore Software Crisis will spawn the good, the fad, and the ugly.  The new ubiquitous multicore hardware will be available to countless millions of developers and users, which will fuel a huge burst of creativity that will shock and amaze all of us, especially those who still fear and loathe parallel software.  As in the past this creativity will tend to favor open-source projects: if two heads are better than one, just try ten thousand heads!

Target audience:

Parallel developers, sequential developers, academics, users, and most especially innocent bystanders caught in the crossfire.

Objective of presentation:

To advocate for the position that although parallel programming might be unfamiliar to many, it is inevitable and not as difficult as the doom-cryers would have you believe.  If done properly, work-a-day parallel programming requires perhaps 5% more training than does sequential programming.

Project homepage / blog:
http://www.rdrop.com/user/paulmck
http://kernel.org/pub/linux/kernel/people/paulmck/perfbook/perfbook.html
http://paulmck.livejournal.com/tag/is%20parallel%20programming%20hard

Speaker bio:

Paul E. McKenney has been coding for almost four decades, more than half of that on parallel hardware.  Over the past decade, Paul has been an IBM Distinguished Engineer at the Linux Technology Center, and more recently has taken on the role of CTO Linux.

Paul maintains the RCU implementation within the Linux kernel, where the variety of workloads present highly entertaining performance, scalability, real-time response, and energy-efficiency challenges.  Prior to that, he worked on the DYNIX/ptx kernel at Sequent, and prior to that on packet-radio and Internet protocols (but long before it was polite to mention Internet at cocktail parties), system administration, business applications, and real-time systems.  His hobbies include what passes for running at his age along with the usual house-wife-and-kids habit.

The deadline for the CFP of the II Open Source, Multicore and Parallel Computing miniconf has been extended until Monday 8 of November 2010.

The II Open Source, Multicore and Parallel Computing miniconference presents its initial keynotes:

Paul McKenney (CTO of Linux at IBM) will present “Is Parallel Programming Hard, And If So, Why?” and also give an overview of remaining challenges facing transactional memory

James Reinders (Director of Software Products from Intel) will talk about the recent open source developments of TBB 3.0 (Threading Building Blocks) and about Intel Array Building Blocks: a flexible Parallel Programming Model for Multicore and Many-Core Architectures

Join Paul and James and other world class presenters in Brisbane at LCA2011: there is still time to submit proposals for the miniconf!!.

We strongly encourage developers and students to present their work and discuss publicly their interests, either in a lightning talk or during the panels and BOF that characterise the miniconf. This is a unique opportunity to exchange ideas within the growing community of Multicore and Parallel Computing!