• News Archive
• Article & White Paper Archive
• TBB on Sun Solaris*
• Coding with Intel® TBB Sweepstakes Results

PC Games Hardware: Ric Broadhurst of Creative Assembly talks about using TBB in Napoleon: Total War - Better performance coming with the Empire add-on?

Intel® Software Network: In Optimizing Without Breaking a Sweat authors John O'Neill, Alex Wells, and Matt Walsh show how to use TBB 2.2's automatic memory allocator replacement to get great performance improvements in DreamWorks Animation's rendering, animation, and special effects applications.

Dr. Dobb's Journal: Learn about how Intel TBB's work-stealing task scheduler improves CPU utilization and frame update rate here.

Intel® Threading Building Blocks 2.2 Commercial Version Available Now:  The commercial version is available to evaluate and the new commercially aligned release is available for download now.  Learn more about the great additions to TBB in 2.2 in Terry Wilmarth's and James Reinders' blogs on the Intel Software Network.

• Read Intel's Announcement
• Read Terry Wilmarth's blog What's New in Intel® TBB 2.2?
• Read James Reinders' blogs about 2.2:
  
  • Version 2.2, Intel Threading Building Blocks, worth a look
  • parallel_for is easier with lambdas, Intel Threading Building Blocks
  • "Hello Lambdas" C++ 0x, a quick guide to Lambdas in C++

Epic Games Unreal Engine and Intel® TBB 2.2:  August 4, 2009: Epic Games, Inc. today announced that Intel® Threading Building Blocks (Intel® TBB) 2.2 has been incorporated into Unreal Engine 3.  As part of this collaboration, Intel has joined Epic’s premier Integrated Partners Program (IPP). 

• Read Epic Games' Press Release
• Read Intel Software Network's Article

Gamasutra Sponsored Feature: Intel's Quentin Froemke discusses the use of TBB in games in Gamasutra's recent Sponsored Feature: Multi-Threaded Fluid Simulation for Games.  

User Success Page Available: Check out who is having success using TBB here.  If you have something you would like to say about TBB let us know by emailing us at tbb-users@lists.sourceforge.net. 

TBB Wins another Jolt Award: TBB was selected as a Jolt Productivity award winner for 2008 in the Libraries, Frameworks and Components category.  This is the second time TBB has won the award.  See the other winners here.

Gamasutra Sponsored Feature: Intel's Brad Werth discusses the use of TBB in games in Gamasutra's recent Sponsored Feature: Optimizing Game Architectures with Intel Threading Building Blocks. 

Intel® Threading Building Blocks 2.1 Commercial Version Available Now:  The commercial version is available to evaluate and the new commercially aligned release is available for download now.  Learn more about the great additions to TBB in 2.1 on the What's New page.

• Read Intel’s Announcement
• Read about TBB 2.1 at Dr. Dobb's Journal, The Register, InternetNews, InfoWorld, HPCwire, eWEEK, Redmond Developer News, and Linux Devices

TBB Wins an InfoWorld BOSSIE: Chosen by InfoWorld Test Center editors, analysts, and reviewers, InfoWorld’s annual Best of Open Source Software awards (or Bossies, for short) celebrate the best products that open source has to offer: the best free software on the planet for businesses, their IT staffs, and their employees’ workstations.

Deep Shadows Ports TBB to XBOX 360*:  The Boiling Point developer announced last week that they used TBB 2.0 to make their Vital Engine threaded for cross-platform development on PC and XBOX 360.  The original contribution is available in the new Contribution Archive.  Read more at Develop Mag.

Contribution Archive Posted:  Thanks to welcome feedback from several community members we have created a Contribution Archive under the Downloads section to post community contributions to TBB.  Users can now access contributions as they are received and before they are integrated in the mainline build of TBB.

DevX Videos: Learn more about multi-core processors and threading for performance and scalabilty at the DevX Go Parallel Videos page.

PACT 2007 Keynote: Texas A&M University professor Bjarne Stroustrup recently spoke at this year's PACT conference in a keynote presentation called Write clean (parallel) code! He discusses two ways for mainstream developers to write clean parallel code using either TBB or STAPL.

PACT 2007 Tutorial: Intel's Jim Cownie presented at this year's Parallel Architectures and Compilation Techniques (PACT) conference in Brasov, Romania. His tutorial on Building High Performance Threaded Applications using Libraries is now available online.

Upcoming Features: The TBB Release Features list has been posted! This is the list of the upcoming features the TBB team is planning for the next major release of TBB. We look forward to your comments and suggestions. Look for more information on these features in the blogs and mailing list.

Threading Building Blocks Mailing Lists: Two TBB mailing lists are now available for TBB users and developers. To join a TBB mailing list go to http://sourceforge.net/projects/tbb and click on the "Mailing Lists" tab.

#TBB IRC Channel on Freenode: Threading Building Blocks real-time chat is available on IRC. Go to channel #tbb on the Freenode IRC network, and join the TBB online discussion.

Linux Distributions & TBB: New partner announcements with Linux distributors including Novell, Red Hat, and other Linux distributions are bringing TBB into their upcoming releases.

The TBB Book: O’Reilly publishes new book on Intel Threading Building Blocks. Read Chapter 1 ("Why Threading Building Blocks?") now available as a free PDF download.

Intel's Official Press Release on Open Sourcing TBB: Intel creates open source project for its popular multi-core development software.

Article & White Paper Archive

DevX Article Series: Nicolae Popovici and Thomas Willhalm discuss how Putting Intel® Threading Building Blocks to Work can help you take advantage of the TBB task-based programming model in your code.

DevX Article Series: In the first part of a two part series Dave Vanden Bout talks about parallel_for, parallel_scan, and parallel_sort and provides templates to help you get started using those algorithms quickly in Five Easy Pieces: TBB's parallel_* Constructs, Part 1.

DevX Featured Algorithm Series: Alexandra Weber Morales talks with Adrien Guillon, an undergraduate student in the computer science and mathematics specialist program at the University of Toronto, about his YetiSim application.  YetiSim uses TBB's parallel_reduce to "divide-and-conquer" as discussed in Intel Threading Building Blocks: parallel_reduce.

DevX Featured Algorithm Series: Alexandra Weber Morales talks with Richard Bowler, CTO of Aeshen LLC, about his PackRat application, which uses multithreading via a TBB pipeline to speed up file compression in Threading Building Blocks: The Pipeline Class.

DevX Article Series: In The Challenges of Developing Multithreaded Processing Pipelines Ryan Bloom talks about how developing applications for multi-core processors will require developers to introduce threading into their software to allow more instructions to be executed simultaneously. He then describes how to go about doing this and how it depends upon your objectives, knowledge and how soon you need to deploy your application.

DevX Featured Algorithm Series: Alexandra Weber Morales talks with the Coding with TBB Contest winner Vincent Tan about his use of parallel_for in par2cmdline 0.4 in Intel Threading Building Blocks: parallel_for().

Intel Technology Journal: Learn about TBB's work-stealing task scheduler and scalable memory allocator in The Foundations for Scalable Multi-Core Software in Intel® Threading Building Blocks by Alexey Kukanov and Michael Voss.

DevX Interview Series: In Threaded Building Blocks: The Insider's Perspective Federico Biancuzzi and James Reinders discussed the advantages of TBB, which platforms are supported, possible porting efforts (SPARC, Playstation 3), the interaction between schedulers and TBB, and "future proofing" development.

Intel® Threading Building Blocks, OpenMP, or native threads?

Which API do you choose to introduce threading to your software application, if you have a choice? Is there one answer that always works? In this paper, we review different considerations that a developer needs to make when it is time to decide. The key areas to focus on are your development environment and the complexity of your parallel model. Let us compare capabilities and address considerations around coexistence of these APIs in your software.

Enable safe, scalable parallelism with Intel® Threading Building Blocks concurrent containers

If you're among the many developers who are tackling the multicore future by writing multithreaded applications today, you'll soon learn that the container classes provided by the C++ STL are not thread friendly. Intel provides a C++ template library with thread-safe concurrent containers. Get a walk-through of what you can expect.

Demystify scalable parallelism with Intel® Threading Building Blocks generic parallel algorithms

Multithreaded applications are notoriously difficult to write, test, and debug, but for many client-server developers, this task will soon become necessary for some high-performance applications. If it's in your future, start here to get an introduction to the algorithms behind the scenes in Intel's C++ template library for multithreading and start demystifing the multicore future.

Why Too Many Threads Hurts Performance, and What to do About It

Threading is the current method of choice for extracting performance from multi-core chips. It might seem that if a little threading is good, then a lot must be better. In fact, having too many threads can bog down a program. This article discusses why and how task-based programming avoids the problem. The Intel® Threading Building Blocks (Intel® TBB) task scheduler serves as an example.

Scalable parallelism with Intel® Threading Building Blocks

This paper discusses the approach to parallelize the Data Encryption Standard (DES) algorithm with Intel® Threading Building Blocks and how it can scale for future processors.

A Template based programming model for multi-core

Mit den Threading Buildings Blocks 1.0 bietet Intel für Parallelprogrammierung ein C++-Template-basiertes kommerzielles Framework an. Zwei Intel-Entwickler führen in das komplexe Konzept ein, das sich für alle Multicore- und SMP-Systeme eignet, und stellen wichtige Features vor.

Product Review: Intel Threading Building Blocks