We are very pleased to announce that our application to the Google Summer of Code 2014 was successful and that we were selected as a mentor organization!
We are looking forward to an exciting summer with awesome contributions from students from all around the world. Be sure to check our ideas page and talk about possible proposals today!
For more information about the Google Summer of Code program visit the website here.
From the release announcement:
The first stable release of the 3.x series of MetaScale’s open-source software is available: NT² 3.0. Many Issues have been closed since last beta. The main focus of this release cycle was to fix performances issues and to stabilize some parts of the API.
This release adds support for HPX, STE||AR’s flagship library. This is excellent news for us, as it demonstrates growing interest in the community to rely on a solid runtime system for all parallelization needs.
“Provide students the opportunity to do work related to their academic pursuits (think “flip bits, not burgers”)” — What are the goals of GSoC?
Google Summer of Code 2014 is a unique program with the goal to fund Open Source Projects and give Students a possibility to gain real world programming experience with a small bonus of $5000!
The STE||AR group decided to apply again as a mentoring organization this year (after being denied last year ). All interested students are welcome to submit proposals. For a list of ideas you can visit our GSoC 2014 Project Ideas wiki page. Find your match and discuss your ideas with us now!
Next week, the STE||AR team will be at SuperComputing 2013! This year, we will be presenting three HPX demos at the LSU booth (booth 1901) in collaboration with Dell.
- The Octopus Torus demo is an interactive hydrodynamics simulation of a differentially rotating torus, using Octopus, an HPX AMR framework for Eulerian fluid simulations. Observers can change the numerical methods and underlying physics of the simulation and watch the effects in real time!
- The vanDouken demo, presented in collaboration with Friedrich-Alexander University (FAU) in Nuremberg, is an artistic interpretation of a full-fledged Particle in Cell simulation with in-situ visualization and live steering. This demo is built on top of the HPX backend to the LibGeoDecomp library. It presents numerical representations of artwork, such as van Gogh’s Starry Night, which can be manipulated by users.
- Our final demo presents a visualization of a new garbage collection scheme for parallel and distributed systems, which does not require “stopping the world” to reclaim memory. This tablet-based demo allows users to “prototype” various reference counting scenarios, and then visualize how they would be garbage collected.
Thomas Heller will be giving at talk about HPX and LibGeoDecomp at the ScalA 2013 workshop at SC. His talk will be at 11:15 AM on November 18th, in room 507 of the Colorado Convention Center.
The newest version of HPX (V0.9.7) is now available for download! Over the past few months the STE||AR Group at Louisiana State University, has been hard at work making HPX more portable than ever before! With the port of HPX to the BlueGene/Q machine, we now can run on almost all of the world’s top 500 machines. We have improved our support for the Intel Xeon Phi ® which will allow HPX users to more fully exploit this exciting accelerator. HPX V0.9.7 will give users the ability to write straight forward code which will automatically utilize the hardware available in their machines and simultaneously be able to run on different architectures around the world.
HPX is making its Museum Debut! A variation of the HPX + LibGeoDecomp demo, vanDouken (Highly Parallel Interactive Image Flow), is being installed in an interactive museum exhibit designed to inspire 5th through 8th graders to become interested in the natural sciences and engineering. This demo (which we originally wrote about here) allows users to insert “forces” on a particle in cell code by swiping a finger across a tablet which interfaces with the simulation. This particular demonstration has been enhanced so that visitors will be able to not only interact with the image but will be able to change the settings of the force fields using a graphical programing environment. The setup is being displayed at the Nuremberg Museum for Industrial Culture. A video of the demonstration with the GUI can be seen here. For more videos and information visit the vanDouken site at http://vandouken.github.io/
Pictured: The Demo installation
Since our 0.9.6 release the STE||AR Group has been busy moving to a new facility! Our new offices will provide us plenty of space to grow and develop our group. In addition to gaining two new offices we also will have access to more rack space, more meeting areas, and a large collaborative space right outside of our offices. As we unpack our boxes we cannot wait to start this new chapter of the STE||AR Group!
The STE||AR Group is proud to announce the sixth formal release of HPX (V0.9.6). We would like to thank everyone for their time and dedication which continues to push HPX to the edge of parallel computation.
HPX (High Performance ParalleX) provides a unified programming model for parallel and distributed applications of any scale. It is the first freely available, open source, feature-complete, modular, and performance oriented implementation of the ParalleX execution model. HPX is a general purpose C++ runtime system for applications targeted at conventional, widely available architectures.
Contour lines are essential in the mapping and comprehension of hurricane data. However, larger sets of data require more time to be processed. This issue is compounded by the increasing granularity of information output by modern models and can be a significant expenditure of computational resources and time when executed serially. To address this issue, I use the HPX library to generate contour lines on multiple processors simultaneously.
This year the STE||AR Group attended the annual C++Now conference in Aspen, Colorado. Three members of the group gave talks at the conference, which is dedicated to the discussion, development and spread of C++ and Boost Libraries. Hartmut Kaiser and Vinay Amatya presented “HPX: A C++ Standards Compliant Runtime System for Asynchronous Parallel and Distributed Computing”, while “Boost.Asio and Boost.Serialization: Design Patterns for Object Transmission” was presented by Bryce Adelstein-Lelbach. In addition, we were able to send two students, Michael LeSane and Alexander Duchene, through the C++Now’s Student Volunteer Program. This program waived the conference fee for select students that volunteered to help run the conference. In addition, the LSU Center for Computation & Technology agreed to cover the room and board of these students. “Volunteering at the 2013 C++ Now convention was a fantastic experience,” reported Alexander Duchene, “although the talks can be seen online, nothing can compare to being surrounded by over a hundred C++ enthusiasts.”