Blogs » Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs Fri, 25 May 2012 22:49:19 +0000 en hourly 1 http://wordpress.org/?v=3.1.3 Parallel Programming Talk #90 - Kathy Farrel, The New Parallel Programming Community Manager http://software.intel.com/en-us/blogs/2010/08/24/parallel-programming-talk-90-kathy-farrel-the-new-parallel-programming-community-manager/ http://software.intel.com/en-us/blogs/2010/08/24/parallel-programming-talk-90-kathy-farrel-the-new-parallel-programming-community-manager/#comments Tue, 24 Aug 2010 16:30:08 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/08/24/parallel-programming-talk-90-kathy-farrel-the-new-parallel-programming-community-manager/ Welcome to Parallel Programming Talk #90. Today is August 24th and we'll be talking with the Intel Software Network's New Parallel Programming Community Manager Kathy Farrel.

Download Link - MP3 Audio File (Small):


Download Link - High Quality MP4 Video File (Large):


First the News:


The Intel Threading Challenge
Phase 2 problem 1 is due Monday, August 30, 2010
(Apprentice: Bonev Sequences. Master: Taxi Paths.)
Problem 2 Starts on August 30th and ends September 20th.


Get ready to attend the CT Tutorial to be given by Intel’s Dr. Michael Klemm, at the Nineteenth International Conference on Parallel Architectures and Compilation Techniques (PACT) September 11-15, 2010 in Vienna, Austria. Registration for the conference is well underway and you can even register the week of the conference.


Superscalar Programming 101 (Matrix) Part 1 through 4 have been published.
For this 5-part article, ISN Black Belt Jim Dempsey takes a small, well-known algorithm, shows a common approach to parallelizing that algorithm, follows with a better one and lastly, produces a fully cache-sensitized approach. Readers of this article will learn a methodology for interpreting test run statistics and to improve their code using those interpretations.


Intel Developer Forum Returns to San Francisco, Sept. 13-15


SC10 - The Super Computing Conference is being held November 13-19, 2010 in New Orleans.

http://sc10.supercomputing.org/


If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail.... Send Email to parallelprogrammingtalk@intel.com


On Today's Show:


Please welcome Kathy Farrel as the new co-host of Parallel Programming Talk. Kathy is the New Parallel Programming Community Manager and will be taking the baton from Aaron to join Clay Breshears for future episodes. We've done some great things with our first 90 shows and we look forward to even better things in the parallel future.


History and Highlights of Parallel Programming Talk
Gone from 2,000 views a quarter to over 20,000! With over 500 visitors for each episode and the most popular receiving well over 5,000.


Started on July 29th 2008. The idea was kind of a cross between Car Talk and Love Lines. We want to provide some getting started information, share new innovations in parallel programing and talk with people who are developing tools/software that runs in parallel on multi-core systems. Our first guest was David Rich, Vice President of Marketing at Interactive Supercomputing.


In November 2008 Michael Wrinn and Aaron did their first LIVE on the road show with a broadcast from SC08 show floor in Austin, Texas on November 18th, 2008


The show exploded in popularity with a show Clay and Aaron did with Don Stewart about his book "Real World Haskell" with thousands of listens tuning in on January 13, 2009


First Listener Question Show, "Automatic Parallelization?" March 3, 2009


On June 10th, 2009 we made the move to video with the launch of Intel Software Network TV. Our first guest was Dr. David Patterson on the future of Parallel Programming!


We've had great conversations with guest from CERN, CILK, Cadence, Microsoft, Adobe, Simul Software, Virtos, Google, Travelocity, Professors, and many, many Intel Engineers.


Live from Intel Developer Forum, SC08, SC09 and Intel's Many Core Testing Lab!


We've been recognized by The American Marketing Association with the MAX award for Non-Traditional Single Media Advertising.


The show will go on and be even better with Kathy and Clay at the helm.


Kathy told us about herself and her new role at Intel. Kathy also talked about what is ahead for Parallel Programming Talk and the Parallel Programming Community.

  • Continue to provide the latest and greatest PP info – to give our Community Members an edge in their work
  • Threading challenge part two continuing
  • September Shows will spotlight the Atom Developer Program and we’ll have some guest interviews at IDF in San Francisco – both Clay and Kathy will both be there.
  • We’ll keep you posted on other show plans – will announce more guests closer to their appearances.

Coming up next on Parallel Programming Talk...


Every Other Tuesday at 8:00 AM Pacific - Watch Live on Intel Software Network TV


Thank you for listening, watching and all your great feedback. I'll miss talking to every week. It has been an amazing experience... And remember, let's be thread safe out there.

]]> http://software.intel.com/en-us/blogs/2010/08/24/parallel-programming-talk-90-kathy-farrel-the-new-parallel-programming-community-manager/feed/ 0 Parallel Programming Talk #89 - Prof. Alexandra Fedorova on Managing Contention for the Shared Resources on Multicore Processors http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-89-prof-alexandra-fedorova-on-managing-contention-for-the-shared-resources-on-multicore-processors/ http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-89-prof-alexandra-fedorova-on-managing-contention-for-the-shared-resources-on-multicore-processors/#comments Fri, 20 Aug 2010 18:19:52 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-89-prof-alexandra-fedorova-on-managing-contention-for-the-shared-resources-on-multicore-processors/ Welcome to Parallel Programming Talk #89. On the August 10th episode Clay and Aaron talked with Prof. Alexandra Fedorova about Managing Contention for the Shared Resources on Multicore Processors.

Download Link - MP3 Audio File (Small):

Download Link - High Quality MP4 Video File (Large):

First the News:

Threading Challenge Phase 2 Problem 1 began on Monday, August 9, and is due 2010 August 30, 2010 at 12:00 PM (Pacific Daylight Time).

Get ready to attend the CT Tutorial to be given by Intel’s Dr. Michael Klemm, at the Nineteenth International Conference on Parallel Architectures and Compilation Techniques (PACT) September 11-15, 2010 in Vienna Austria. Registration for the conference is well underway and you can even register the week of the conference.

Superscalar Programming 101 (Matrix). For this 5-part article, ISN Black Belt Jim Dempsey takes a small, well-known algorithm, shows a common approach to parallelizing that algorithm, follows with a better one and lastly, produces a fully cache-sensitized approach. Readers of this article will learn a methodology for interpreting test run statistics and to improve their code using those interpretations.

Intel Developer Forum Returns to San Francisco, Sept. 13-15

SC10 - The Super Computing Conference is being held November 13-19, 2010 in New Orleans.

If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail.... Send Email to parallelprogrammingtalk@intel.com

On Today's Show:

Dr. Alexandra Fedorova, Assistant Professor, School of Computing Science, Simon Fraser University

Dr. Fedorova leads the Systems Research Group at SFU, which is a part of the SyNAr (Systems, Networking and Architecture) lab that she co-founded. Her research focuses on system design for multicore processors and on parallel computing.

On the show Dr. Fedorova discussed her paper "Managing Contention for Shared Resources on Multicore Processors" that she co authored with Sergey Blagodurov, Sergey Zhuravlev; Simon Fraser University. The paper presents research showing that 
contention for caches, memory controllers, and interconnects can be alleviated by contention-aware scheduling algorithms.

From the paper, "Modern multicore systems are designed to allow clusters of cores to share various hardware structures, such as LLCs (last-level caches; for example, L2 or L3), memory controllers, and interconnects, as well as prefetching hardware. We refer to these resource-sharing clusters as memory domains, because the shared resources mostly have to do with the memory hierarchy. Figure 1 provides an illustration of a system with two memory domains and two cores per domain.

Threads running on cores in the same memory domain may compete for the shared resources, and this contention can significantly degrade their performance relative to what they could achieve running in a contention-free environment. Consider an example demonstrating how contention for shared resources can affect application performance. In this example, four applications—Soplex, Sphinx, Gamess, and Namd, from the SPEC (Standard Performance Evaluation Corporation) CPU 2006 benchmark suite6—run simultaneously on an Intel Quad-Core Xeon system similar to the one depicted in figure 1.

As a test, we ran this group of applications several times, on three different schedules, each time with two different pairings sharing a memory domain. The three pairing permutations afforded each application an opportunity to run with each of the other three applications within the same memory domain:

1. Soplex and Sphinx ran in a memory domain, while Gamess and Namd shared another memory domain.

2. Sphinx was paired with Gamess, while Soplex shared a domain with Namd.

3. Sphinx was paired with Namd, while Soplex ran in the same domain with Gamess.

Figure 2 contrasts the best performance of each application with its worst performance. The performance levels are indicated in terms of the percentage of degradation from solo execution time (when the application ran alone on the system), meaning that the lower the numbers, the better the performance."

Dr. Fedorova was awarded a Google research award to address the issues of power consumption and efficiency in data centers. Data centers are becoming an increasingly important part of the world-wide computing infrastructure. They offer a promise of scalability, reliability and manageability for the ever-more prevalent online services. The problem is that data centers consume inordinate amounts of power: over 7.2 billion dollars is spent every year on energy consumption in US data centers alone.

Dr. Fedorova and her students have been designing innovative solutions to improve energy efficiency of virtual machine technology (a key technology for data centers) and to enable the software to use modern multicore hardware more effectively. The research award from Google is a way of recognizing the importance of this work.

Coming up next on Parallel Programming Talk...

Introducing Kathy Farrel the new Parallel Programming Community Manager
Date/Time: 8/24/2010 at 8:00 AM Pacific - Watch Live on Intel Software Network TV

Set your alarm to watch Parallel Programming Talk every other Tuesday at 8:00AM PT.

]]> http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-89-prof-alexandra-fedorova-on-managing-contention-for-the-shared-resources-on-multicore-processors/feed/ 0 Parallel Programming Talk #88- Listener Question Show http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-88-listener-question-show/ http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-88-listener-question-show/#comments Fri, 20 Aug 2010 17:48:41 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-88-listener-question-show/ Today is August 3th and on show 88 Clay and I will be Answering Listener Questions with 1.21 Gigawatts of power running through our flux capacitor!

Download Link - MP3 Audio File (Small):

Download Link - High Quality MP4 Video File (Large):

First the News:


Congratulations to Our Threading Challenge Phase 1 Problem 2 winners!
Master Level: 2 - Skip List - 1st Place: Dmitriy Vyukov
Apprentice Level: 2 - Prime Array - 1st Place: doraemonok
Phase 2 Problem 1 began on Monday, August 9, and is due 2010 August 30, 2010 at 12:00 PM (Pacific Daylight Time)


Get ready to attend the CT Tutorial to be given by Intel’s Dr. Michael Klemm, at the Nineteenth International Conference on Parallel Architectures and Compilation Techniques (PACT) September 11-15, 2010 in Vienna Austria. Registration for the conference is well underway and you can even register the week of the conference.


Superscalar Programming 101 (Matrix)
For this 5-part article, ISN Black Belt Jim Dempsey takes a small, well-known algorithm, shows a common approach to parallelizing that algorithm, follows with a better one and lastly, produces a fully cache-sensitized approach. Readers of this article will learn a methodology for interpreting test run statistics and to improve their code using those interpretations.


The Intel Math Kernel Library 10.3 Beta has been Released
Intel® Advanced Vector Extensions (Intel AVX) optimization
Summary Statistics library - modern algorithms that enhance accuracy and performance of statistical computations.


Intel Developer Forum Returns to San Francisco, Sept. 13-15


If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail....
Send Email to parallelprogrammingtalk@intel.com


On Today's Show:


Clay will be discussing the recently completed Thread Challenge problem.


Connected Components in a Graph


Write a threaded program to compute the number of connected components and the maximum and minimum number of nodes from among the connected subgraphs within an input graph.


Prime Array Search


Write a threaded program that finds an example of a prime array that has the maximum number of primes hidden within it for a given array size.


Coming up next on Parallel Programming Talk...
Prof. Alexandra Fedorova - Managing Contention for the Shared Resources on Multicore Processors
Date/Time: 8/10/2010 at 8:00 AM Pacific - Watch Live on ISN TV


Set your alarm to watch Parallel Programming Talk Tuesday at 8:00AM PT on Intel Software Network TV.

]]> http://software.intel.com/en-us/blogs/2010/08/20/parallel-programming-talk-88-listener-question-show/feed/ 0 Parallel Programming Talk #87- Brock Taylor, HPC Cluster Solutions Architect http://software.intel.com/en-us/blogs/2010/08/13/parallel-programming-talk-87-brock-taylor-hpc-cluster-solutions-architect/ http://software.intel.com/en-us/blogs/2010/08/13/parallel-programming-talk-87-brock-taylor-hpc-cluster-solutions-architect/#comments Fri, 13 Aug 2010 22:55:46 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/08/13/parallel-programming-talk-87-brock-taylor-hpc-cluster-solutions-architect/ Welcome to Parallel Programming Talk #87. Today is July 27th and we'll be talking with HPC Cluster Solutions Architect Brock Taylor.

Download Link - High Quality MP4 Video File (Large):

Download Link - MP3 Audio File (Small):


First The News:

Our Threading Challenge Phase 2 problem 1 is due Monday, August 30, 2010
(Apprentice: Bonev Sequences. Master: Taxi Paths.)
Problem 2 Starts on August 30th and ends September 20th.


Get ready to attend the CT Tutorial to be given by Intel’s Dr. Michael Klemm, at the Nineteenth International Conference on Parallel Architectures and Compilation Techniques (PACT) September 11-15, 2010 in Vienna, Austria. Registration for the conference is well underway and you can even register the week of the conference.


Superscalar Programming 101 (Matrix) Part 1 through 3 have been published.
For this 5-part article, ISN Black Belt Jim Dempsey takes a small, well-known algorithm, shows a common approach to parallelizing that algorithm, follows with a better one and lastly, produces a fully cache-sensitized approach. Readers of this article will learn a methodology for interpreting test run statistics and to improve their code using those interpretations.


Intel Developer Forum Returns to San Francisco, Sept. 13-15


SC10 - The Super Computing Conference is being held November 13-19, 2010 in New Orleans.
If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail....
Send Email to parallelprogrammingtalk@intel.com


On The Show Today:


Intel HPC Cluster Solutions Architect Brock Taylor


Watch Parallel Programming Talk Every Tuesday at 8:00AM PT on Intel Software Network TV.

]]> http://software.intel.com/en-us/blogs/2010/08/13/parallel-programming-talk-87-brock-taylor-hpc-cluster-solutions-architect/feed/ 0 Parallel Programming Talk #86 -Don Tyson, SunGard Chief Technology Officer http://software.intel.com/en-us/blogs/2010/07/27/parallel-programming-talk-86-don-tyson-sungard-chief-technology-officer/ http://software.intel.com/en-us/blogs/2010/07/27/parallel-programming-talk-86-don-tyson-sungard-chief-technology-officer/#comments Tue, 27 Jul 2010 20:44:11 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/07/27/parallel-programming-talk-86-don-tyson-sungard-chief-technology-officer/
Welcome to Parallel Programming Talk #86. Today is July 20th and we'll be talking Massive Parallel Processing with SunGard Chief Technology Officer, Don Tyson.

Download Link - High Quality MP4 Video File (Large):
Download Link - MP3 Audio File (Small):

First the News:

UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.

Threading Challenge Phase 2 begins on Monday, August 9, 2010
Congratulations to our Threading Challenge Phase 1 winners!
Master Level:  1 - Hosoya Index - 1st Place:     Dmitriy Vyukov
Apprentice Level:  1 - Connected Components - 1st Place:    pbialas

The Intel(R) MKL 10.3 beta has been released and includes Intel(R) AVX optimizations, Summary Statistics functionality, C interface to LAPACK and Routine level mode control in VML. Please visit Intel MKL 10.3 beta program page () for more details on the new features, bug fixes, and registration/download of the Intel MKL 10.3 beta.

Open Source Convention July 19-23 - OSCON, Portland, OR
  • Explore the benefits and challenges of building scalable applications for the cloud
  • Use open source to target Android, iPhone and other mobile platforms
  • Understand how and when to use NoSQL databases
  • Learn best practice from experts in Python, Java, Ruby, Perl, PHP and JavaScript
  • Use open source effectively as part of your business strategy
  • Learn how to foster contribution and adoption of your open source projects

If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail....
Send Email to parallelprogrammingtalk@intel.com


On Today's Show:

SunGard Chief Technology Officer, Don Tyson.

SunGard is one of the world’s leading software and technology services companies.  SunGard has more than 20,000 employees and serves 25,000 customers in 70 countries.  SunGard provides software and processing solutions for financial services, higher education and the public sector.  SunGard also provides disaster recovery services, managed IT services, information availability consulting services and business continuity management software.  With annual revenue exceeding $5 billion, SunGard is ranked 380 on the Fortune 500 and is the largest privately held business software and IT services company.

Don discussed the impact that optimizing his application for massively parallel processing has had on his business with dramatic reductions in the time it takes to reconcile transactions. We also talked about Sungard's software development methodology, what he looks for in new technical hires, Sungard's transition from C+ to .Net. and what it takes for Sungard to stay ahead of the curve.

Watch Parallel Programming Talk every Tuesday at 8:00AM PT in Intel Software Network TV.

And remember, let's be thread safe out there.

]]> http://software.intel.com/en-us/blogs/2010/07/27/parallel-programming-talk-86-don-tyson-sungard-chief-technology-officer/feed/ 0 Parallel Programming Talk #85 - "What game developer can teach parallel programmers" with Intel engineer Brad Werth http://software.intel.com/en-us/blogs/2010/07/21/parallel-programming-talk-85-what-game-developer-can-teach-parallel-programmers-with-intel-engineer-brad-werth/ http://software.intel.com/en-us/blogs/2010/07/21/parallel-programming-talk-85-what-game-developer-can-teach-parallel-programmers-with-intel-engineer-brad-werth/#comments Wed, 21 Jul 2010 23:24:31 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/07/21/parallel-programming-talk-85-what-game-developer-can-teach-parallel-programmers-with-intel-engineer-brad-werth/ Welcome to Parallel Programming Talk #85. Today is July 13th and we'll be talking about "What game developer can teach parallel programmers" with Intel engineer Brad Werth.

Download Link - High Quality MP4 Video File (Large):

Download Link - MP3 Audio File (Small):

First the News:

UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.

Congratulations to our Threading Challenge Phase 1 winners!
Master Level:  1 - Hosoya Index - 1st Place:     Dmitriy Vyukov
Apprentice Level:  1 - Connected Components - 1st Place:    pbialas
Phase 2 begins on Monday, August 9, 2010

The Intel(R) MKL 10.3 beta has been released and includes Intel(R) AVX optimizations, Summary Statistics functionality, C interface to LAPACK and Routine level mode control in VML. Please visit Intel MKL 10.3 beta program page  for more details on the new features, bug fixes, and registration/download of the Intel MKL 10.3 beta.

Open Source Convention July 19-23 - OSCON, Portland, OR
The focus of this years convention is:
* Explore the benefits and challenges of building scalable applications for the cloud
* Use open source to target Android, iPhone and other mobile platforms
* Understand how and when to use NoSQL databases
* Learn best practice from experts in Python, Java, Ruby, Perl, PHP and JavaScript
* Use open source effectively as part of your business strategy
* Learn how to foster contribution and adoption of your open source projects

If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail....

On Today's Show:

Brad Werth, Sr. Software Engineering

Brad refer to Getting the Most From Your Middleware when he talk about how games are composed of pieces, potentially with independent threading approaches, and those pieces should be designed to unify.

Ticker Tape is designed this way and shows how the technique is used in games.


Watch Parallel Programming Talk every Tuesday at 8:00AM PT on Intel Software Network TV


And remember, let's be thread safe out there.

]]> http://software.intel.com/en-us/blogs/2010/07/21/parallel-programming-talk-85-what-game-developer-can-teach-parallel-programmers-with-intel-engineer-brad-werth/feed/ 0 Parallel Programming Talk #84 - Answering questions about "Windows events" on our Listener Question Show http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-84-answering-questions-about-windows-events-on-our-listener-question-show/ http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-84-answering-questions-about-windows-events-on-our-listener-question-show/#comments Mon, 19 Jul 2010 23:04:23 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-84-answering-questions-about-windows-events-on-our-listener-question-show/ Welcome to Show 84 of Parallel Programming Talk. Today is July 6th, the first Tuesday of the month. The mid west vuvuzela are blowing so that means "Listener Question Show". Today's question is about "Windows events".

Download Link - MP3 Audio File (Small):


Download Link - High Quality MP4 Video File (Large):


First The News:

UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.


Open Source Convention is July 19-23 in Portland, OR.
This year's OSCON will focus on:

  • Explore the benefits and challenges of building scalable applications for the cloud
  • Use open source to target Android, iPhone and other mobile platforms
  • Understand how and when to use NoSQL databases
  • Learn best practice from experts in Python, Java, Ruby, Perl, PHP and JavaScript
  • Use open source effectively as part of your business strategy
  • Learn how to foster contribution and adoption of your open source projects

On Today's Show:

Clay and Aaron selected the following question to discuss on today's show. Watch or listen to the show to hear the answer.


"I have just started reading the multi-threading chapters of "Windows System Programming", and am a bit perplexed. What are the differences between the different types of Windows events and how they are set and reset?  Why is PulseEvent considered to be dangerous?” --Clive Drake


Watch Parallel Programming Talk live every Tuesday at 8:00AM PT on Intel Software Network TV.


And remember, let's be thread safe out there.

]]> http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-84-answering-questions-about-windows-events-on-our-listener-question-show/feed/ 0 Parallel Programming Talk #83 - Single-chip Cloud Computer platform with Intel Engineer Rob Van Der Wijngaart http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-83-single-chip-cloud-computer-platform-with-intel-engineer-rob-van-der-wijngaart/ http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-83-single-chip-cloud-computer-platform-with-intel-engineer-rob-van-der-wijngaart/#comments Mon, 19 Jul 2010 22:50:26 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-83-single-chip-cloud-computer-platform-with-intel-engineer-rob-van-der-wijngaart/ Welcome to Show 83 of Parallel Programming Talk originally broadcast on June 29, 2010. On the show Clay and Aaron talked with Intel Engineer Rob Van Der Wijngaart about the Single-chip Cloud Computer platform and the Many-core Applications Research Community.

Download Link - MP3 Audio File (Small):

Rob van der Wijngaart is a senior software engineer in the Cluster Solutions and Technologies group. His main interest is parallel computing architecture and software. Before joining Intel almost 5 years ago, he worked at NASA Ames Research Center for a dozen years in parallel computing research, focusing on High Performance Computing applications and benchmarking.


If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail.... Send Email to parallelprogrammingtalk@intel.com


Clay and Aaron will be answering listener question on the next episode of Parallel Programming Talk .


Watch live episodes of Parallel Programming talk every Tuesday at 8:00AM PT on Intel Software Network TV.


And remember, let's be thread safe out there.

]]> http://software.intel.com/en-us/blogs/2010/07/19/parallel-programming-talk-83-single-chip-cloud-computer-platform-with-intel-engineer-rob-van-der-wijngaart/feed/ 0 Parallel Programming Talk #82 - Intel's Michael McCool talks Structured Parallel Programming with Deterministic Patterns http://software.intel.com/en-us/blogs/2010/07/02/parallel-programming-talk-82-intels-michael-mccool-talks-structured-parallel-programming-with-deterministic-patterns/ http://software.intel.com/en-us/blogs/2010/07/02/parallel-programming-talk-82-intels-michael-mccool-talks-structured-parallel-programming-with-deterministic-patterns/#comments Fri, 02 Jul 2010 21:44:21 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/07/02/parallel-programming-talk-82-intels-michael-mccool-talks-structured-parallel-programming-with-deterministic-patterns/ Welcome to Show 82 of Parallel Programming Talk. Today is June 22nd and were talking with Michael McCool about his recent papers Structured Parallel Programming with Deterministic Patterns.


Download Link - MP3 Audio File (Small):

Threading Challenge 2010!!!!
July 12 - Threading Challenge Phase 1 Problem 2 Closes. Choose the right level for you! Please see official rules for more information or visit the dedicated forum for this problem to get your questions answered.  Good Luck!


Participate in Intel® 20 Questions Contest and win free Intel® Parallel Studio license and gift card! Answer basic questions about Intel® Parallel Studio for a chance to win free license and gift card. Visit Intel® 20 Questions Contest home page to learn more. Intel Parallel Studio helps developers improve software performance, both for sequential and parallel algorithms. This contest will be an enjoyable exploration of the various features, capabilities and components of Intel Parallel Studio.


Concurrent Collections for Haskel
Announcing Intel Concurrent Collections for Haskell 0.1


Intel Unveils New Product Plans for High-Performance Computing Intel® Many Integrated Core Chips at the International Supercomputing Conference last week.


Intel® IPP 7.0 beta is available now, your feedback is critical to the success of our product. We are especially interested in your feedback on the key features listed below. We also encourage you to send us feedback about our beta programs, web site and support services.


If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail....Send Email to parallelprogrammingtalk@intel.com


On Today's Show:


Dr. Michael McCool works for the Software Services Group at Intel, specifically on software development platforms for high-productivity (yet efficient!) parallel computing. He has experience in computer graphics and medical imaging as well as parallel computing, and likes to approach the problem of designing systems by starting with the needs of the application and the application developer. Follow Michael on Twitter: @michaelmccool


Michael presented the technical paper Structured Parallel Programming with Deterministic Patterns at the HotPar ’10, 2nd USENIX Workshop on Hot Topics in Parallelism on 14-15 June 2010, in Berkeley, CA.

From the paper:
Many-core processors target improved computational performance by making available various forms of architectural parallelism, including but not limited to multiple cores and vector instructions. However, approaches to parallel programming based on targeting these low-level parallel mechanisms directly leads to overly complex, non-portable, and often unscalable and unreliable code.

A more structured approach to designing and implementing parallel algorithms is useful to reduce the complexity of developing software for such processors, and is particularly relevant for many-core processors with a large amount of parallelism and multiple parallelism mechanisms. In particular, efficient and reliable parallel programs can be designed around the composition of deterministic algorithmic skeletons, or patterns. While improving the productivity of experts, specific patterns and fused combinations of patterns can also guide relatively inexperienced users to developing efficient algorithm implementations that have good scalability.

The approach to parallelism described in this document includes both collective "data-parallel" patterns such as map and reduce as well as structured "task-parallel" patterns such as pipelining and superscalar task graphs. The structured pattern based approach, like data-parallel models, addresses issues of both data access and parallel task distribution in a common framework. Optimization of data access is important for both many-core processors with shared memory systems and accelerators with their own memories not directly attached to the host processor.

A catalog of useful structured serial and parallel patterns will be presented. Serial patterns are presented because structured parallel programming can be considered an extension of structured control flow in serial programming. We will emphasize deterministic patterns in order to support the development of systems that automatically avoid unsafe race conditions and deadlock.


Coming Up Next on Parallel Programming Talk


What Parallel Programmers Can Learn from Game Developers - Brad Werth
Date/Time: 7/13/2010 at 8:00 AM Pacific - Watch Live on ISN TV


Watch Parallel Programming Talk every Tuesday at 8:00AM PT live on Intel Software Network TV.


And remember, let's be thread safe out there.

]]> http://software.intel.com/en-us/blogs/2010/07/02/parallel-programming-talk-82-intels-michael-mccool-talks-structured-parallel-programming-with-deterministic-patterns/feed/ 0 Parallel Programming Talk #81 - Robert Chesebrough's Experiences Parallelizing a Game using OpenMP http://software.intel.com/en-us/blogs/2010/06/30/parallel-programming-talk-81-robert-chesebroughs-experiences-parallelizing-a-game-using-openmp/ http://software.intel.com/en-us/blogs/2010/06/30/parallel-programming-talk-81-robert-chesebroughs-experiences-parallelizing-a-game-using-openmp/#comments Wed, 30 Jun 2010 21:44:35 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/06/30/parallel-programming-talk-81-robert-chesebroughs-experiences-parallelizing-a-game-using-openmp/ Welcome to Show 81 of Parallel Programming Talk. Today is June 15th and were talking with Robert Chesebrough about his experiences Parallelizing a Game using OpenMP

First The News:
Threading Challenge 2010!!!!
July 12 - Threading Challenge Phase 1 Problem 2 Closes
Choose the right level for you! Please see official rules for more information or visit the dedicated forum for this problem to get your questions answered.  Good Luck!

Participate in Intel® 20 Questions Contest and win free Intel® Parallel Studio license and gift card! Answer basic questions about Intel® Parallel Studio for a chance to win free license and gift card. Visit Intel® 20 Questions Contest home page to learn more. Intel Parallel Studio helps developers improve software performance, both for sequential and parallel algorithms. This contest will be an enjoyable exploration of the various features, capabilities and components of Intel Parallel Studio.

Concurrent Collections for Haskel
Announcing Intel Concurrent Collections for Haskell 0.1

Intel Unveils New Product Plans for High-Performance Computing Intel® Many Integrated Core Chips at the International Supercomputing Conference last week.
  • The first product codenamed "Knights Corner" will target Intel's 22nm process and use Moore's Law to scale to more than 50 Intel cores.
  • Intel® Xeon® processors and Intel® Many Integrated Core architecture-based products to share common tools, software algorithms and programming techniques.
  • Products build upon Intel's history of many-core related research including Intel's "Larrabee" program and Single-chip Cloud Computer.
  • The share of the TOP500 list that features Intel processors grows to 408 systems, nearly 82 percent.

Intel® IPP 7.0 beta is available now, your feedback is critical to the success of our product. We are especially interested in your feedback on the key features listed below. We also encourage you to send us feedback about our beta programs, web site and support services.
New key features:
  • New performance optimziations for the Intel® Advanced Vector Extensions (Intel AVX) for faster floating point operations in signal processing and image processing domains for the upcoming Sandy Bridge processors.
  • Intel® AES-NI optimization
  • Improved performance and new capabilities for high-level Data Compression Libraries (zlib, bzip2, gzip and lzo)
  • Improved JPEG codec multicore performance scaling, now up to 6x speedup on 8-core systems.
  • New JPEG-XR CODEC, (aka HD Photo) a new image compression standard which provides

UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.

If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail....
Send Email to parallelprogrammingtalk@intel.com

On Today's Show:
Robert Chesebrough is a Senior Course Architect in the Intel Innovative Software Education team, and is responsible for bringing new course content to the ISE portfolio. He has been a contributing manager and/or course ware developer and instructor for Intel Software College for over 8 years. He spearheaded Intel's effort in the High School Parallelism boot cap at Brooklyn Technical High School in July 2009 and continues to spearhead efforts with mid school & high school education with the New Mexico Supercomputing Challenge.

Robert Chesebrough has blogged extensively about his experiences Parallelizing a Game using OpenMP.

Watch Parallel Programming Talk every Tuesday at 8:00AM PT.
And remember, let's be thread safe out there.
]]> http://software.intel.com/en-us/blogs/2010/06/30/parallel-programming-talk-81-robert-chesebroughs-experiences-parallelizing-a-game-using-openmp/feed/ 0 Parallel Programming Talk #80 - Professor Uzi Vishkin discusses Using Simple Abstraction to Guide the Reinvention of Computing for Parallelism http://software.intel.com/en-us/blogs/2010/06/22/parallel-programming-talk-80-professor-uzi-vishkin-discusses-using-simple-abstraction-to-guide-the-reinvention-of-computing-for-parallelism/ http://software.intel.com/en-us/blogs/2010/06/22/parallel-programming-talk-80-professor-uzi-vishkin-discusses-using-simple-abstraction-to-guide-the-reinvention-of-computing-for-parallelism/#comments Tue, 22 Jun 2010 21:48:10 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/06/22/parallel-programming-talk-80-professor-uzi-vishkin-discusses-using-simple-abstraction-to-guide-the-reinvention-of-computing-for-parallelism/ Welcome to Show 80 of Parallel Programming Talk. Today is June 8th and were talking with
Professor Uzi Vishkin from the University of Maryland to discuss Using Simple Abstraction to Guide the Reinvention of Computing for Parallelism.

First the News:

The Intel Threading Challenge 2010 is in full swing. Challenge #2 has been posted and includes both an Apprentice Level and Master Level problem. Coder have until July 12th to submit their entry. The forums are very active with questions about the contest. Visit the site today and enter to win cash, an iPod Touch or a new Laptop!

Announcing Intel Concurrent Collections for Haskell 0.1. Read the blog by Ryan Newton (Intel). Listen/watch Ryan talk with with Paul Steinberg on the Teach Parallel show.

  • The first product codenamed "Knights Corner" will target Intel's 22nm process and use Moore's Law to scale to more than 50 Intel cores.
  • Intel® Xeon® processors and Intel® Many Integrated Core architecture-based products to share common tools, software algorithms and programming techniques.
  • Products build upon Intel's history of many-core related research including Intel's "Larrabee" program and Single-chip Cloud Computer.
  • The share of the TOP500 list that features Intel processors grows to 408 systems, nearly 82 percent.

UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.

If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail.... Send Email to parallelprogrammingtalk@intel.com

On Today's Show:

Uzi Vishkin, Professor of ECE University of Maryland Institute for Advanced Computer Studies
Professor Uzi Vishkin started his work on parallel computing in 1979 as a PhD student at the Tech- nion, Israel. His initial focus was on parallel algo- rithms and parallel algorithmic thinking. He co- authored several articles that helped build a theory of parallel algorithms – also known as PRAM algo- rithms. This work led to his invention of the PRAM- On-Chip desktop supercomputer framework that scales beyond 1000 processors on a chip. He ws inducted as an ACM Fellow for playing “a lead- ing role in forming and shaping what thinking in parallel has come to mean in the fundamental theory of Computer Science.” Vishkin is currently a professor of electrical and computer engineering at the University of Maryland Institute for Advanced Computer Studies (UMIACS). He has also worked for IBM T.J. Watson, New York University, and was the chair of computer science at Tel Aviv University.

Abstract
The sudden shift from single-processor computer systems to many-processor parallel ones requires reinventing much of Computer Science (CS): how to actually build and program the new parallel sys- tems. CS urgently requires convergence to a robust parallel general-purpose platform that provides good performance and is easy enough to program by at least all CS majors. Unfortunately, lesser ease-of- programming objectives have eluded de- cades of parallel computing research. The idea of starting with an established easy parallel program- ming model and build an architecture for it has been treated as radical by vendors. This talk advo- cates a more radical idea. Start with a minimalist stepping-stone: a simple abstraction that encapsu- lates the desired interface between programmers and system builders.

Coming up next week on Parallel Programming Talk.

Robert Chesebrough's Experiences Parallelizing a Game using OpenMP
Date/Time: 6/15/2010 at 8:00 AM Pacific - Watch Live on ISN TV

Michael McCool - Structured Parallel Programming with Deterministic Patterns
Date/Time: 6/22/2010 at 8:00 AM Pacific - Watch Live on ISN TV

Rob Van Der Wijngaart - Single-chip Cloud Computer
Date/Time: 6/29/2010 at 8:00 AM Pacific - Watch Live on ISN TV

Listener Question Show
Date/Time: 7/6/2010 at 8:00 AM Pacific - Watch Live on ISN TV

What Parallel Programmers Can Learn from Game Developers - Brad Werth
Date/Time: 7/13/2010 at 8:00 AM Pacific - Watch Live on ISN TV

Prof. Alexandra Fedorova - Managing Contention for the Shared Resources on Multicore Processors
Date/Time: 8/10/2010 at 8:00 AM Pacific - Watch Live on ISN TV

Watch Parallel Programming Talk every Tuesday at 8:00AM PT.
And remember, let's be thread safe out there.

]]> http://software.intel.com/en-us/blogs/2010/06/22/parallel-programming-talk-80-professor-uzi-vishkin-discusses-using-simple-abstraction-to-guide-the-reinvention-of-computing-for-parallelism/feed/ 0 Asaf Shelly - The Newest Black Belt in the Parallel Programming Community http://software.intel.com/en-us/blogs/2010/06/21/asaf-shelly-the-newest-black-belt-in-the-parallel-programming-community/ http://software.intel.com/en-us/blogs/2010/06/21/asaf-shelly-the-newest-black-belt-in-the-parallel-programming-community/#comments Mon, 21 Jun 2010 22:51:38 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/06/21/asaf-shelly-the-newest-black-belt-in-the-parallel-programming-community/ I'd like to personally welcome Asaf Shelly to our small and elite group of Intel Software Network Black Belt Developers.

I've know Asaf Shelly for a quite a while. We met a few years ago when he was visiting Washington State for an MVP event at Microsoft. I can't recall the exact context of our connection but since we both are active in the parallel programming community we were bound to met.

Asaf has been an active and popular guest blogger on the Intel Software network since he introduced himself to our community in August of 2008. With 21 post and many many more replies to post comments he has proven himself to be an active and highly technical Parallel Programming Community Member.

Asaf, Thank you for your past contributions. I look forward to reading more of your thought around parallel programming and look forward to sharing a meal again with you in the near future.

]]> http://software.intel.com/en-us/blogs/2010/06/21/asaf-shelly-the-newest-black-belt-in-the-parallel-programming-community/feed/ 0 Parallel Programming Talk #79 - Listener Question "OpenMP and explicit threads?" http://software.intel.com/en-us/blogs/2010/06/04/parallel-programming-talk-79-listener-question-openmp-and-explicit-threads/ http://software.intel.com/en-us/blogs/2010/06/04/parallel-programming-talk-79-listener-question-openmp-and-explicit-threads/#comments Sat, 05 Jun 2010 00:00:24 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/06/04/parallel-programming-talk-79-listener-question-openmp-and-explicit-threads/ Welcome to Show 79 of Parallel Programming Talk. The show was originally broadcast on June 1st, the first Tuesday of the month so it's a Listener Question show.

First The News:

Threading Challenge 2010!!!!
ARE YOU READY TO TEST YOUR SKILLS IN THIS YEAR'S THREADING CHALLENGE?
Over the last two years the Intel® Threading Challenge has attracted developers of varying experience, from all over the globe.  That continued participation from the community has driven us to offer a new iteration, with new problems, and a chance to win prizes again this year.  We know you love a good puzzle; so this year our resident experts have agreed to pull together new and interesting problems for you!
Phase 1 Launched (both levels) on Monday May 31, 2010 an 12:00 PM (PDT) and this year's contest will have some similarities to last year but will also have new elements that you should be aware of so get more on those changes below and start threading your way to prizes today!
Choose the right level for you!

Announcing Intel Concurrent Collections for Haskell 0.1
Whether you're a functional programmer or not you've probably noticed an increasing number of FP-related concepts circulating in this Age of Parallelism: immutability, implicit parallelism, data flow, and so on. These ideas seem to be getting around and in fact are alive and well here at Intel. They play a major (though possibly non-obvious) role within Intel Concurrent Collections and we've decided to bring them out to the surface with a Haskell edition of that library.

Threading Building Blocks 3.0
What’s New in Intel TBB 3.0:
** Extended compatibility and interoperability support for Microsoft Visual Studio 2010 Parallel Patterns Library* (PPL) and Concurrency Runtime* (ConcRT)
** Added Microsoft Windows* 7, and Apple Mac OS* Snow Leopard support
** Enhanced Task Scheduler provides starvation-proof scheduling tasks for queue-like work; Master Thread Isolation improves task scheduling predictability and responsiveness
** Enhanced Memory Allocator includes performance optimization for large-block allocations
** Expanded lambdas support provides C++ 0x condition variable; parallel_pipeline a strongly typed lambda friendly interface for building and running pipelines; new container concurrent_unordered_map support

International Supercomputing Conference
ISC'10 kicked off on Sunday May 30 in Hamburg. It runs to June 3rd.
About 2,000 attendees and more than 140 exhibitors from over 45 countries are expected to attend turning ISC’10 into a powerful and memorable event.

UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.

If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail.... Send Email to parallelprogrammingtalk@intel.com

On Today's Show:

Listener Question Show:
Clay and I reviewed our email and the parallel programming forum and selected a question regarding OpenMP and explicit threads.
Anupam Dev asks " How to explicitly make a thread? I want to make a thread explicitly. Is there any OpenMP construct or way to do this. Suppose at every loop iteration i want to make another team of threads after checking a condition in the loop body. can i do this....or it is illegal!!! how???"

You can listen to the show and check out the discussion forum to see how Clay and other developer answered the question.

Clay asked me to add that during the show he was not feeling well and went on mute to cough. Hope your feeling better buddy!

Our Next Parallel Programming Talk will be June 8th.

We'll we talking with Uzi Vishkin from the University of Maryland to discuss Using Simple Abstraction to Guide the Reinvention of Computing for Parallelism.

Watch Parallel Programming Talk every Tuesday at 8:00AM PT.

And remember, let's be thread safe out there.
]]> http://software.intel.com/en-us/blogs/2010/06/04/parallel-programming-talk-79-listener-question-openmp-and-explicit-threads/feed/ 0 Parallel Programming Talk #78 - Dr. Professor Wen-mei Hwu - Co Director of UPCRC and distinguish professor at University of Illinois at Urbana-Champaign http://software.intel.com/en-us/blogs/2010/06/01/parallel-programming-talk-78-dr-professor-wen-mei-hwu-co-director-of-upcrc-and-distinguish-professor-at-university-of-illinois-at-urbana-champaign/ http://software.intel.com/en-us/blogs/2010/06/01/parallel-programming-talk-78-dr-professor-wen-mei-hwu-co-director-of-upcrc-and-distinguish-professor-at-university-of-illinois-at-urbana-champaign/#comments Tue, 01 Jun 2010 17:48:46 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/06/01/parallel-programming-talk-78-dr-professor-wen-mei-hwu-co-director-of-upcrc-and-distinguish-professor-at-university-of-illinois-at-urbana-champaign/ Welcome to Show 78 of Parallel Programming Talk originally broadcast on May 25th. Clay and Aaron spoke with Dr. Wen-mei Hwu - Co Director of UPCRC and distinguish professor at University of Illinois at Urbana-Champaign.

Download and listen to an  MP3 of the show.
Download and watch a video of the show.

First the News:
The Intel Tools group just wrapped up a series of three parallel programming webinars. You can watch an on demand broadcast of these webinars.
  • May 12 — James Reinders and Herb Sutter, Microsoft software architect, prominent C++ thinker, and best-selling author
    Title: "Five Years Since Free Lunches: Making Use of Multicore Parallelism"
  • May 19 — James Reinders and Steve Teixeira, Product Unit Manager of Parallel Computing Platform Developer Division, Microsoft* Corporation
    Title: "Intel Parallel Studio and Microsoft Visual Studio*: Using Abstractions to Prepare for Multicore"
  • May 26 — James Reinders and David Mackay, Manager of Technical Consulting and Support for the Performance, Analysis, and Threading group, Intel Corporation
    Title: "Intel Parallel Studio: Creating Fast, Reliable Parallel Programs"

ISC'10 will take place from May 30 – June 3, 2010 again in Hamburg.
About 2,000 attendees and more than 140 exhibitors from over 45 countries are expected to attend turning ISC’10 into a powerful and memorable event.

UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.

If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail.... Send Email to parallelprogrammingtalk@intel.com

On Today's Show:
Dr. Wen-mei Hwu - distinguish professor and Co-Director of  Universal Parallel Computing Research Center at the University of Illinois at Urbana-Champaign.

We discussed the University's up coming Parallel Programming Summer School, the Blue Waters project (still very hush, hush), and his new book co authors with David Kirk Programming Massively Parallel Processors: A Hands-on Approach. Watch or listen to the show for the full discussion.

Our Next Parallel Programming Talk will be June 1st.
We'll be taking listener questions.

Watch Parallel Programming Talk every Tuesday at 8:00AM PT.
And remember, let's be thread safe out there.
]]> http://software.intel.com/en-us/blogs/2010/06/01/parallel-programming-talk-78-dr-professor-wen-mei-hwu-co-director-of-upcrc-and-distinguish-professor-at-university-of-illinois-at-urbana-champaign/feed/ 0 Parallel Programming Talk #74 - Auto Tuning Parallel Applications - Dr. Walter Tichy http://software.intel.com/en-us/blogs/2010/05/05/parallel-programming-talk-74-auto-tuning-parallel-applications-dr-walter-tichy/ http://software.intel.com/en-us/blogs/2010/05/05/parallel-programming-talk-74-auto-tuning-parallel-applications-dr-walter-tichy/#comments Wed, 05 May 2010 19:08:46 +0000 Aaron Tersteeg (Intel) http://software.intel.com/en-us/blogs/2010/05/05/parallel-programming-talk-74-auto-tuning-parallel-applications-dr-walter-tichy/ Welcome to Show 74 of Parallel Programming Talk originally broadcast on April 20th, 2010. On the show Clay and Aaron talked with Dr. Walter Tichy about Auto Tuning Parallel Applications.

Download Link - MP4 Video File (Large):

Download Link - MP3 Audio File (Small):

First The News:

Threading Building Blocks 3.0 came out today!
Intel(R) Threading Building Blocks 3.0 (Intel(R) TBB) is now available for download. This latest release of Intel TBB 3.0 offers extended compatibility support for Microsoft* Visual Studio* 2010 Parallel Patterns Library (PPL) and Concurrency Runtime (ConcRT); new task scheduler features; enhanced performance; and expanded functions.

UPCRC Illinois Research Seminar
The Future of Many-core Processors: A Tale of Two Processors
by Tim Mattson, Intel
Thursday, May 6, 2010 at 4:00 PM (Central Time)
2405 Siebel Center for Computer Science
Live Stream: http://media.cs.uiuc.edu/live/upcrc0910/upcrc10-0506l1.asx
Live Chat: http://www.upcrc.illinois.edu/chat/
Will be activated at day/time of seminar.
Abstract: Ours is a many-core future. That much is clear. What is unclear is how those cores will be connected, what memory architecture will these processors use, and how will we program these systems. It is the answers to those questions that will define the shape of our many-core future. In this talk, we will explore these questions through the lens of the two most recent research processors from Intel; the 80-core terascale processor (2007) and the recently announced 48 core SCC processor. You may have heard other talks on the SCC processor, but this talk stands apart by its focus on how we actually program these chips. We will close with some thoughts on the implications of our work on how programming models must adapt to prepare for a future dominated by many-core processors.

Three Webinars About Multicore Parallelism - May 12, 19 & 26th.
James Reinders will be talking with fellow industry leaders and innovators Herb Sutter, Steve Teixeira & David Mackay. Learn the very latest about how to bring threading to robust Windows* applications and pull more from multicore platforms.


UPCRC Illinois Summer School to be held July 19-23, 2010 at the University of Illinois at Urbana-Champaign. Prerequisites for the summer school include solid programming experience (C, C++, C# or Java languages) and a demonstrated interest in applying multicore programming to academic or professional pursuits.


If you have questions you'd like to see up discuss, ideas for show topics or just want to send fan mail....
Send Email to parallelprogrammingtalk@intel.com


On the show today:


Walter Tichy earned his PhD at Carnegie-Mellon University with one of the first dissertations on software architecture (called programming-in-the large then). For his 1979 paper on this subject he later received the most-influential paper award at the 14th International Conference on Software Engineering in 1992 (this award is presented ten instances of the conference after publication, when the impact of an article can be assessed.)


In 1981, after joining Purdue University, he developed the Revision Control System (RCS), a version management system that is the basis of CVS and has been, and still is, in world-wide use almost thirty years later. After a year at an AI-startup in Pittsburgh, he returned to his native Germany in 1986, where he was appointed chair of programming systems at the University Karlsruhe. He is also a director of FZI, a technology transfer institute.


Prof. Tichy's interests are software engineering and  parallel computing. He has pioneered a number of new software tools, such as smart recompilation (1985),  graph editors with automatic layout (1990), analysis of software project repositories (1994), and language-aware software differencing and merging (2002). In the 1990s, he and his students developed Parastation, a communication and management software for computer clusters. The commercial version of Parastation runs JUROPA,  a computer that was ranked 10th on the Top 500 list as of June 2009, and 14th as of Nov. 2009.


Perhaps his most important contribution was to help convince researchers in software engineering to test claims about their tools and techniques with empirical methods. In 1995, he published an influential paper, "Experimental Evaluation in Computer Science:  A Quantitative Study" (J. of Systems and Software), in which the state of empirical work in computing was analyzed. This paper and others helped reach a state today, where high-quality conferences and journals expect rigorous evaluation of all programming tools and techniques for publication. He has also conducted controlled experiments testing the influence of type-checking, inheritance depth, design patterns, testing methods, and agile methods on programmer productivity.


With the emergence of multi/manycore chips, parallel programming is now becoming  mainstream quickly. Once again, Prof. Tichy is on the forefront of this development. He is researching tools and techniques to simplify the engineering of general-purpose, parallel software. In particular, his work on parallel programming languages (XJava), auto-tuning (Atune), and automatic race detection (Helgind+) is beginning to be noted internationally.


Watch Parallel Programming Talk every wednesday at 8:00AM PT.

]]> http://software.intel.com/en-us/blogs/2010/05/05/parallel-programming-talk-74-auto-tuning-parallel-applications-dr-walter-tichy/feed/ 0