You are on page 1of 1

Abstract: Constellation Applications and Perspectives Abstract: VOLPEX -

Constellation is a platform for different aerospace related projects that There are three applications as sub-projects on the Constellation Parallel Execution in Volunteer environment
need intensive computational power. platform.
The platform supports the efforts of participating projects by providing Volpex[9-11] has the goal of enabling robust execution of communicating
Distributed Computing capability using BOINC[1]. o TrackJack is an ascend trajectory simulation and optimizer for space- parallel applications on volunteer PCs. The project developed the
Constellation will send work-units of attached projects to volunteering, launcher systems and space-crafts. TrackJack's origin is part of a diploma fundamental concept of autonomous redundant processes: a logical
idle PCs where the units are processed. The combined power of all thesis in Aerospace Engineering at the University of Applied Sciences process may have multiple distributed instances that are unaware of
volunteering users will help to solve important scientific tasks in fields Bremen. each other, process instances can be replicated, checkpointed or re-
from astronomy to aerospace-engineering beginning from student up to TrackJack app is processing test-workunits and will optimize the created independently, and individual process instances can fail without
university projects. maximum altitude of HyEnD hybrid-engine sounding rocket[4]. (Figure 2&3) application failure. The overall application progress is dictated by the
The bottom line is to benefit from the generosity of the volunteers and to state of the fastest active instance of each process. A single replication
benefit from the accumulation of different projects, like sharing o Extreme Machine's idea is not to create a huge, multimillion ton framework can potentially provide protection from process/node and
programming knowledge in distributed computing and influencing the exploration rover machine, rather an extremely optimized device, under network failures, varying processing speeds, and Byzantine failures
others' simulation by its own solutions. the realms of very classical mechanics, to perform specific tasks. caused by software and hardware errors and malicious hosts. Two
The platform is an open space for anyone, who is an air and space Extreme Machine simulates the rover dynamics. (Figure 4) prototype programming frameworks were successfully developed and
enthusiast and wants to donate idle computing time or even skill for a validated in this project:
sub-project on platform. Applications for sub-project are welcome! o On The Moon aims to simulate the process occurring at moon near the
surface. It is a large scale simulation aiming to create a total model of the o Volpex Dataspace API: An abstract „dataspace“ with asynchronous
moon system, and to compare it with data collected from the Google anonymous Put/Get communication operations from autonomous
Project Motivation Lunar X-PRIZE (GLXP)[5] mission. redundant processes.
In particular in aerospace sciences simulation and optimization are major o Volpex MPI: A highly failure resistant MPI implementation based on
tasks to minimize structure weight, to maximize thrust or to determine sender based logging.
system reliability.
These numerical tasks need a high level of resources and hardware- A Volpex prototype has been validated and evaluated with NAS and
support and Constellation platform offers distributed computing power other benchmarks, a Map-Reduce framework, and a Replica Exchange
to projects from professionals to students to solve their problems in an Molecular Dynamics code, and interfaces with BOINC.
adequate time without the need to maintain their own super-computer or
cluster system.
In this way it is possible to get access to the needed computing power by Figure 2 Figure 3 Figure 4
a wider range of researchers who wouldn't have been able to create those
Currently the BOINC infrastructure Constellation uses supports
resources because of financial, administration and operation or because
independent workunits. The above applications respect this limit by using
of bureaucracy reasons.
splitted tasks as workunits that doesn't rely on other workunits' result.
Constellation's goal is to expedite fundamental and applicable research
But there are aerospace tasks, like in computational fluid dynamics
and bonding researchers with citizen scientists and public.
(CFD), that are only feasible when the complete tasks is solved in
parallel to finish in a decent time. Therefore Constellation is working to
Project Implementation extend the system to combine the advantages of distributed computing
system with that of parallel clusters to create a virtual cluster where
As a DGLR (german aerospace society)[2] academic student team at the nodes are connected via the internet.
University of Stuttgart, Germany, we set up a distributed super-computer We work together with Volpex Group at University of Houston to bring Figure 7: VOLPEX
that offers computing power by idle single desktop computers of parallel execution to Constellation and to other BOINC-projects, and we
volunteers connected via the internet. This accumulated computing power
is provided to aerospace research purposes, that universities and private
examine MAGE[6] of University of Marburg as an additional candidate.
Results
research institutions and projects normally can't afford. With this approach Even though a lot of aerospace projects sounds like science-fiction we
we demonstrate the capability of synergetic co-operation of scientists and lay emphasis on applicable and fundamental work that will influence
scientific enthused ordinary persons. current research. So the participants will directly be involved and
In contrast to classic super-computers, that have high acquisition-, success in research can be feed back to the community to gratify them
maintenance- and operation-costs and aren't state of the art after just a few that leads to a good atmosphere and long-time participation.
years, our Constellation computer is a worldwide distributed, continuously Constellation as a platform will leave it to the sub-projects to openly
and dynamically evolving system with high heterogeneity in which anyone publish parts or the complete results.
can participate who runs a computer with Windows, Linux or Mac OS X
operating system. This high-performance is used to solve aerospace related
tasks, such as trajectory optimization (application: TrackJack). References
Constellation is in its early public productivity phase and even in the first
[1] BOINC – Berkeley Open Interface for Network Computing - http://boinc.berkeley.edu
month 500 volunteers with 1500 participating machines generated approx. [2] DGLR – Deutsche Gesellschaft für Luft- und Raumfahrt - http://stuttgart.dglr.de
Figure 5: CFD analysis with FLUENT
1.2 TFLOPS of computing power (1.2*10^12 FLoating point OPerations [3] RNA World – http://rnaworld.de/rnaworld | Rechenkraft.net e.V. - http.//.rechenkraft.net
per Second). It can be assumed that the amount of participating machines [4] HyEnD – Hybrid Engine Development - http://www.hybrid-engine-development.de
will increase up to 5000 with about 10 TFLOPS within one year (reference [5] Google Lunar X-Prize - http://www.glxp.org
We want to use parallel execution for CFD analysis.We want to use [6] MAGE – The Marburg Ad-hoc Grid Environment - http://mage.uni-marburg.de
data from RNA-World, another Rechenkraft.net e.V. project [3]). OpenFOAM[7] because it's used in the scientific and academic [7] OpenFOAM – Open Field Operation and Manipulation - http://www.openfoam.com
The Constellation computer represents a remarkable performance that is by community, it offers a wide range of solvers and the main reason is that [8] Ansys – CFX, Fluent - http://www.ansys.com
far superior to high-performance clusters and it increases daily. In this way [9] VOLPEX - Parallel Execution in Volunteer environment - http://volpex.cs.uh.edu/VCP
its GNU General Public License allows the use in a distributed [10] 'A Robust Communication Framework for Parallel Execution on Volunteer PC Grids', by
hundreds of trajectories can be simulated and optimized depending in the environment. In comparison Ansys' powerful CFX and FLUENT[8] Eshwar Rohit, Hien Nguyen, Nagarajan Kanna, Jaspal Subhlok, Edgar Gabriel, Qian Wang,
task's complexity per day. Participating users can follow their contribution programmes use a proprietary software licence that makes it difficult to Margaret S. Cheung, and David Anderson, The 11th IEEE/ACM International Symposium on
in a clearly arranged webinterface. Finished results will be send back use outside the given licence agreement. Cluster, Cloud, and Grid Computing , Newport Beach, CA, May 2011.
automatically and can be archived by the sub-projects scientists. [11] VolpexMPI: an MPI Library for Execution of Parallel Applications on Volatile Nodes, by
For Constellation a CFD application is intended to be used in T. LeBlanc, R. Anand, E. Gabriel, and J. Subhlok. In Proc. The 16th EuroPVM/MPI 2009
Operation and maintenance of this system requires expenditure of time aerodynamics and stability simulation, in engine combustion analysis for Conference, Espoo, Finland, 2009. Published as Springer-Verlag LNCS,5759.
during user support, who post a variety of questions on our online-forum, micro- and jet engines, in ramjet, scramjet and pulse detonation engine
so that besides the scientific aspect the project has a very interesting and rocket engines and motors and many more. We want to open up this Andreas Hornig(1,2), Lars Bausch, Sayandeep Khan,
educational component („science & society“).
important field of parallel execution for distributed computing. Maximilian Palm, Uwe Beckert, Sebastian de Cillia,
Matthias Fritzsche, S. Müller
1. Constellation, König-Karl-Str. 27, 70372 Stuttgart, Germany
2. corresponding author: constellation@aerospaceresearch.net
http://aerospaceresearch.net

"Space is big. Really big. You just won't


believe how vastly, hugely, mind- bogglingly
big it is. I mean, you may think it's a long
way down the road to the chemist's, but
that's just peanuts to space."
- The Hitchhiker's Guide to the Galaxy
Figure 1: Constellation website Figure 6: possible splitted mesh processing via internet-connected client-nodes
by Douglas Adams
Supported by:

You might also like