The Parallel Universe Magazine


 

ISSUE 35

Intel® Rendering Framework Using Software Defined Visualization

The open source community initiative on software defined visualization (SDVis) continues to demonstrate that the CPU is better for large-scale rendering than GPU-based solutions, which suffer from memory limitations and high cost. Learn how SDVis is helping to maximize the benefits―and inherent performance―of modern Intel® Xeon® processors with software that takes advantage of high-thread count and data parallelism.

Read This Issue

36 Search Results
36 Search Results

Parallel Universe Magazine - Issue 12, November 2012

Contents:

  • Letter from the Editor: When Complex Is the Baseline, by James Reinders
     
  • Shedding Light on Cluster Performance with LAMMPS, by Walter Shands
    Highlights the features of Intel® Cluster Studio XE by using them to build and analyze LAMMPS, a complex cluster application and benchmark used in Spec MPI*.
     
  • Checklist for Programming Intel® Xeon Phi™ Coprocessors, by James Reinders
    Offers key tips for programming a high degree of parallelism, while using familiar programming methods and the latest Intel® tools supporting the Intel® Xeon Phi™ coprocessor.
     
  • Advanced Vectorization, by Georg Zitzlsberger
    Applying some of the vectorization techniques enabled by Intel® compilers and their Intel® Cilk™ Plus technologies to an example application.
     
  • Optimizing Correlation Analysis of Financial Market Data Streams Using Intel® Math Kernel Library, by Zhang Zhang, Andrey Nikolaev, and Victoriya Kardakova
    Demonstrates the performance advantages of Intel Math Kernel Library in the implementation of the online noise filtration algorithm on a correlation analysis of financial market data.

Parallel Universe Magazine - Issue 11, September 2012

Contents:

  • Letter from the Editor: Putting Intel® Parallel Studio XE 2013 to Work for the “New Normal", by James Reinders
     
  • Intel® Parallel Studio XE 2013: 10 Feature Highlights for Accelerated Performance, by James Reinders
    Get up to speed fast on the components and new feature sets in the Intel® Parallel Studio XE 2013 suite—and consider the potential for your applications.
     
  • Using Intel® Software Development Tools to Analyze HMME, by Walter Shands
    Explore techniques for developing applications like HMMER for the latest generation of multicore processors—from thread and memory error checking to performance and code optimization.
     
  • Pointer Checker: Easily Catch Out-of-Bounds Memory Access, by Kittur Ganesh
    Pointer Checker is designed to catch any out-of-bounds memory accesses before memory corruption occurs. Find out how to use Pointer Checker effectively, and to balance the trade-offs of security and runtime.
     
  • New Parallel Programming Features in Intel® (Visual) Fortran Composer XE, by Steve Lionel
    This overview of two new features, DO CONCURRENT and coarrays, brings insight into achieving excellent parallelism results with Fortran.
     
  • Using the Intel® Math Kernel Library and Intel® Compiler to Obtain Run-to-Run Numerical Reproducible Results, by Todd Rosenquist and Shane Story
    How do you balance demands for accelerated performance with reproducible results and runtime consistency? These techniques can help you generate reproducible results within applications under a manageable set of constraints.

Parallel Universe Magazine - Issue 10, June 2012

Contents:

  • Letter from the Editor: The Performance Opportunity: How to Achieve it—from Clusters to Devices, by James Reinders
     
  • Help Future-Proof Performance of Your Application with Vectorization in Six Steps, by Wendy Doerner and Shannon Cepeda
    Vectorization is a key form of hardware support for data parallelism, allowing you to process data in parallel within a single CPU core. It can provide a significant performance boost, and also be combined with threading and/or cluster parallelism.
     
  • Pockets of Parallel Computation, Fitting in Your Pocket​, by Robert Mueller, Noah Clemons, and Paul Fischer
    Employing performance library functions in applications running on small form factor devices can be a great way to streamline and unify the computational execution flow for data-intensive tasks. This article examines the Intel® Integrated Performance Primitives landscape for the Intel Atom® processor.
     
  • Tools that Boost .NET Apps’ Reliability and Performance, by Levent Akyil and Asaf Yaffe
    Read about the capabilities of the latest software tools for developers of .NET* code, native code, and “mixed” (.NET and native) applications during the development cycle.
     

Parallel Universe Magazine - Issue 9, February 2012

Contents:

  • Letter from the Editor: Parallel Performance from Feature Films to Advanced Clusters, by James Reinders
    Examine the impact of applying data parallelism to a geometry generator, and analyzing massively parallel applications for correctness and performance.
     
  • Parallelizing DreamWorks Animation* Fur Shader: How Intel® Tools Help Add Parallelism in Large Applications, by Sheng Fu
    Learn how Intel parallelization tools help DreamWorks Animation's fur shader take advantage of the performance and capabilities of multicore processors, while preserving legacy libraries needed in production.
     
  • New Analysis Tools in Intel® Cluster Studio XE, by David Mackay, Ph.D. and Krishna Ramkum
    Improve hybrid application analysis with new cluster tools, including Intel® VTune™ Amplifier XE. MPI programs can now be tuned more precisely and easily—regardless of the shared-memory programming model utilized in the hybrid—based on insight into the detailed activities on the nodes of a distributed program.

Parallel Universe Magazine - Issue 8, September 2011

Contents:

  • Letter from the Editor: Parallelism Programming: Who Signed Me Up for Writing a Book?, by James Reinders
    Reinders, chief evangelist and director of Intel® Software Development Products, shares how his opinions on Intel® Parallel Advisor have evolved, and explains why Flow Graph is his most favorite new feature of Intel® Threading Building Blocks.
     
  • HPC Study: Biophysicists and Mathematicians Embrace Parallelism with Intel® Parallel Advisor, by Zakhar A. Matveev
    Learn how a group of research scientists in Russia parallelized their applications in response to the growing data from biological experiences and increasing complexity of simulation requirements.
     
  • The Intel® Threading Building Blocks Flow Graph, by Michael J. Voss, Ph.D.
    User feedback inspired the Flow Graph feature in Intel® Threading Building Blocks, which allows programmers to express static and dynamic dependency graphs, as well as reactive or event-based graphs.
     
  • Intel® Parallel Studio XE SP1, by Michael D’Mello
    Intel® Parallel Studio XE combines Intel’s industry-leading C/C++ and Fortran compilers, high performance parallel libraries, error checking, code robustness, and performance profiling technologies into a single suite offering. The SP1 release now adds functionality to simplify the transition from multicore to many-core hardware platforms.
     

Parallel Universe Magazine - Issue 7, June 2011

Contents:

  • Letter from the Editor: Specifics: FLOP Count and Parallel Programming, by James Reinders
    Reinders, lead evangelist and director of Intel® Software Development Products, shares answers to three of the most common questions he receives, addressing FLOPS and Intel® VTune™ Amplifier XE, Intel® Cilk Plus, and Intel® Parallel Building Blocks (Intel® PBB) “parallel for.”
     
  • Intel® Cilk™ Plus: A C/C++ Language Extension for Parallel Programming, by Robert Geva
    Intel offers new products for parallel programming based on the new programming model called Intel® Parallel Building Blocks (Intel® PBB).
     
  • Three Flavors of ‘for’ Loops with Intel® Parallel Building Blocks (Intel® PBB), by Noah Clemons
    Each of the models in Intel Parallel Building Blocks offers a different kind of ‘for’ loop. Learn why it is important to understand the build environment, type of parallelism it represents, and level of parallel abstraction before choosing a model.
     
  • Easing the Performance Analysis of Serial and Parallel Applications, by Levent Akyil
    Intel® VTune™ Amplifier XE is a powerful performance analysis tool that helps software developers identify issues in their applications. Explore how its improved and intuitive user interface performs powerful performance analyses with just a few mouse clicks.
     
  • Case Study: Massachusetts General Hospital*, by Bevin Brett
    Follow the experiences of and lessons learned by developers at Massachusetts General Hospital and Intel as they identify, prioritize, and make changes to the C++ code to improve the serial algorithms and introduce parallelism to benefit virtual colonoscopies.
     

Parallel Universe Magazine - Issue 6, March 2011

Contents:

  • Letter from the Editor: PBB, XE, Cambrian Explosion, and the Art of Computer Programming, by James Reinders
    James Reinders, lead evangelist and director of Intel® Software Development Products, discusses the challenge of choice when determining which products and programming models make sense for your programming needs.
     
  • Parallelizing Intel® Integrated Performance Primitives Functions Using Intel® Cilk™ Plus and Intel® Threading Building Blocks, by Walter Shands
    The parallel models in Intel® Parallel Building Blocks easily integrate into existing applications, help preserve investments in existing code, and speed development of parallel applications.
     
  • Intel® Array Building Blocks Code Tips, by Zhang Zhang
    Assist the runtime system in generating high-performance code and develop a sound understanding of the Intel® Array Building Blocks API to help avoid errors.
     
  • Success Story Roundup
    Envivio, The Creative Assembly, and Altair share how they employed Intel® Software.
     

Parallel Universe Magazine - Issue 5, December 2010

Contents:

  • Letter from the Editor: High Performance Options Have Never Been Greater, by James Reinders
    James Reinders focuses on the latest Intel® Software developer tools designed to tap into the performance offered by today’s computers.

     

  • Simplifying High Performance with Intel® Parallel Studio XE and Intel® Cluster Studio Tool Suites, by Sanjay Goil and John McHugh
    With the introduction of Intel® Parallel Studio XE and Intel® Cluster Studio, Intel extends the reach of next-generation development tools to Windows* and Linux* C/C++ and Fortran developers.

     

  • Intel® Parallel Building Blocks: The Answer(s) to Cracking the Parallelism Puzzle, by David Sekowski
    Examine three models for parallelism—Intel® Threading Building Blocks (Intel® TBB), Intel® Cilk™ Plus, and Intel® Array Building Blocks (Intel® ArBB)—which together form a single comprehensive solution for task parallelism, data parallelism, and vectorization.

     

  • Intel® Array Building Blocks, by Michael McCool
    Intel ArBB is the answer to the following question: How can parallelism mechanisms in modern processor hardware, including vector SIMD instructions, be targeted in a portable, general way within existing programming languages?

     

  • Automatic Parallelism with the Intel® Math Kernel Library (Intel® MKL), by Greg Henry and Shane Story
    Explore the techniques Intel MKL uses to achieve the highest level of parallelism, as well as the hooks and knobs useful for getting the most from these threaded hotspots.

     

  • When Print Statements and Timer are Not Enough: Making the Parallelism Investment More Effective, by Don Gunning, Nick Meng, and Paul Besl
    See how real-world developers are applying Intel® Trace Analyzer and Collector to find issues that would be undetectable with print statements and a timer, correct those issues, and deliver scaling performance.

Parallel Universe Magazine - Issue 4, September 2010

Contents:

  • Letter from the Editor: Breaking Ground and Building Trust, by James Reinders
    James Reinders, lead evangelist and director of Intel® Software Development Products, addresses recent innovations in apps and tools, highlights key 2010 milestones, and explores what’s next in the new year and beyond.

     

  • Intel® Parallel Studio 2011: Getting Your App Ready for Multicore Just Got Easier, by Leila Chucri
    Engineer Leila Chucri introduces Intel® Parallel Studio 2011, examining new features with an eye to enabling the development environment for multicore.

     

  • Using Serial Modeling Tools to Tame the Parallel Beast, by John Pieper
    Addressing many of the key reasons why parallelism is considered difficult, Intel® Parallel Advisor offers a proven threading methodology, and enables parallel and serial modeling.

     

  • Intel® Cilk™ Plus, by Krishna Ramkumar
    Intel Cilk Plus adds fine-grained task parallelism support to C and C++, making it easy to add parallelism to both new and existing software, and efficiently exploit multiple processors.

     

  • Nine Tips to Parallel Programming Heaven, by Stephen Blair-Chappell
    In this interview, Dr. Yann Golanski shares with us his favorite tips on parallel programming. The tips are based on investigative work on parallel n-body simulation code carried out during his doctoral studies.

     

  • The World’s First Sudoku* “Thirty Niner”, by Stephen Blair-Chappell
    Lars Peters Endresen and Håvard Graff, two talented engineers from Oslo, share with us how they created what may be the world’s first Sudoku puzzle that has 39 clues.

Parallel Universe Magazine - Issue 3, June 2010

Contents:

  • Letter from the Editor: Parallelism Full Steam Ahead!, by James Reinders
    James Reinders, lead evangelist and director of Intel® Software Development Products, explains how recent industry and product developments have positioned parallelism to take off full throttle.

     

  • Enhancing Productivity and Achieving High Performance with Intel® Cluster Toolkit Compiler Edition, by Bill Magro
    Message-passing interface applications port seamlessly from dual-core desktops to multithousand server clusters, a key advantage of distributed memory parallelism.

     

  • Increase Productivity and Performance: Find out What IncrediBuild* and Intel® Parallel Composer Can Offer, by Jennifer Jiang and Uri Mishol
    Software companies use many software development methodologies, but none eliminate the need for building, testing, and tuning individual components or the whole application.

     

  • Optimizations for MSC.Software SimXpert* Using Intel® Threading Building Blocks, by Kathy Carver, Mark Lubin, and Bonnie Aona
    To address increasing customer model sizes and align with the multicore processor roadmaps for hardware vendors, MsC.software* engaged with Intel to thread simXpert*.

Parallel Universe Magazine - Issue 2, March 2010

Contents:

  • Letter from the Editor: Think Parallel: Good Programming Starts with the Developer, by James Reinders
    James Reinders, lead evangelist and director of Intel® Software Development Products, addresses recent innovations in apps and tools, highlights key 2010 milestones, and explores what’s next in the new year and beyond.

     

  • Where Are My Threads? Intel® VTune™ Performance Analyzer and Finding Threading and Parallelism Issues, by Levent Akyil
    Do you ever wonder how your parallel workload is distributed or scheduled across the available cores/processors? Explore how Intel VTune Performance Analyzer helps make such analysis easy.

     

  • Advisor Origins, by Paul Petersen
    As you change your application to make it ready to introduce parallelism, your test suite can be your biggest asset. Intel® Parallel Advisor is designed to be your assistant as you analyze your existing sequential implementations.

     

  • Understanding the Features of Intel® Parallel Inspector by Example, by Bradley J. Werth
    Intel® Parallel Inspector eases the correctness burden on programmers. Explore how it helps maintain memory and thread integrity.

     

  • Thread Your C# Code with Intel® Integrated Performance Primitives, by Naveen GV
    The most important consideration is how to manage the calls between the managed .NET* application and the unmanaged Intel® IPP Library.

     

  • Resources & Sites of Interest

     

Parallel Universe Magazine - Issue 1, April 2009

Contents:

  • Think Parallel or Perish, by James Reinders
    James Reinders, Lead Evangelist and a Director with Intel® Software Development Products, sees a future where every software developer needs to be thinking about parallelism first when programming. He first published “Think Parallel or Perish“ three years ago. Now he revisits his comments to offer an update on where we have gone and what still lies ahead.

     

  • Parallelization Methodology
    The four stages of parallel application development addressed by Intel® Parallel Studio.

     

  • Writing Parallel Code Safely, by Peter Varhol
    Writing multithreaded code to take full advantage of multiple processors and multicore processors is difficult. The new Intel® Parallel Studio should help us bridge that gap.

     

  • Are you Ready to Enter a Parallel Universe: Optimizing Applications for Multicore, by Levent Akyil
    A look at parallelization methods made possible by the new Intel® Parallel Studio—designed for Microsoft Visual Studio* C/C++ developers of Windows* applications.

     

  • 8 Rules for Parallel Programming for Multicore, by James Reinders
    There are some consistent rules that can help you solve the parallelism challenge and tap into the potential of multicore.

Pages

Get The Latest Issue

 
Intel’s quarterly magazine helps you take your software development into the future with the latest tools, tips, and training to expand your expertise.

Subscribe

The benchmark results reported above may need to be revised as additional testing is conducted. The results depend on the specific platform configurations and workloads utilized in the testing, and may not be applicable to any particular user’s components, computer system, or workloads. The results are not necessarily representative of other benchmarks and other benchmark results may show greater or lesser impact from mitigations.

Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more information, see Performance Benchmark Test Disclosure.