 |
|
"Plug and Play" Cluster Software Adds Support for LAM/MPI and mpich-gm while Enhancing Access behind Firewalls
"Pooch is the fastest and easiest way to enter parallel computing", said Dr. Dean Dauger, President of Dauger Research, Inc. "With this version we are making good on our commitment to making Pooch the most flexible parallel computing tool we can, supporting LAM/MPI and Myrinet hardware. Pooch now supports five MPI implementations." Pooch, winner the IEEE Cluster conference's latest "most innovative" award, combines powerful, numerically-intensive parallel-computing clusters with the famed ease-of-use of the Macintosh. Combining the best of cluster and grid computing, Pooch is the only solution that merges a modern graphical user interface with supercomputer-compatible parallel computing. It provides the user interface for the latest incarnation of AppleSeed, a UCLA Physics project begun in 1998. For six years, their software is being used world-wide to transform Macintoshes into easy-to-use, numerically-intensive parallel computers. Pooch has supported Message-Passing Interface (MPI) since day one. Adding LAM/MPI and mpich-gm with this release, it now supports five different MPI implementations to take advantage of parallel computing within boxes and across boxes simultaneously. The LAM/MPI implementation we modified is provided on our web site, while the mpich-gm implementation for Myrinet hardware required no modification. A suite of updated utilities designed for remote, command-line installation and access accompanies every Pooch shipped. Pooch is the easiest way to build and use a parallel computer. It debuted with features others have yet to accomplish and integrate. Pooch remains the only cluster or grid solution that installs on a node in seconds. Pooch's tolerance for variations in node configuration and execution environments is unparalleled. And Pooch continues combining computational resources over the Internet with a mouse click. Version 1.5.5 is the latest in a series of updates that utilize the latest technology. Pooch was the first to use Rendezvous to discover nodes for computation. Pooch takes advantage of AppleScript and multiprocessing in OS X, utilizes logged out OS X machines for parallel computing, and supports automated grid behavior and cluster access for other desktop applications. Pooch v1.5 is available for US$175 for the first compute node then US$125 for each node thereafter. Pooch Pro v1.5 is available for US$200 for the first compute node then US$150 for each node thereafter. See the web site for special academic pricing. Users may order Pooch and other available software using the forms on our web site or online through the Dauger Research Store. The Pooch web site recently debuted three new tutorials on writing parallel code. Users can download GUI and command-line installers containing a trial Pooch, sample parallel applications and source code, a Pooch Software Development Kit, and full documentation. With a discussion mailing list devoted to parallel computing and updated information about designing, compiling, and running code in parallel, the Pooch site makes it easier than ever to write, develop, and run your own parallel code today. Pooch requires networked Macintoshes and/or Xserve's running Mac OS 9 with CarbonLib 1.2 or later, Mac OS X 10.2 or later, and/or Mac OS X Server 10.2 or later with 4 MB of available RAM and 2 MB of disk space. We encourage you to revisit the Pooch web site. Dauger Research, Inc., was incorporated and founded by Dr. Dean E. Dauger. Dr. Dauger is the award-winning author of Atom in a Box and Fresnel Diffraction Explorer and co-authored the original, award-winning Kai's Power Tools software. After completing his Ph. D. in physics, he founded Dauger Research, Inc., to bridge the divides between the scientifically and technically complex and the mainstream by making high-performance computation and visualization easy to use and accessible to users. Other company and product names may be trademarks of the respective companies with which they are associated. |
||||