The world’s most cost effective scalable solution. Inexpensive to build, operate and maintain.
Perfect for Research
Develop new cluster architectures that scale at very low cost before committing to production designs.
Built with the amazing ARM based Raspberry Pi. Many software options and a vast developer community.
Ideal for Education
The world’s leading computing education platform can now be used to teach network, cluster and cloud computing. All open source.
The third best selling computer ever, this tiny device punches well above its weight with a 1.2 GHz Quad Core ARMv8 CPU.
Hardware, Ready For Action
Fully provisioned with memory, networking and flexible I/O including USB for additional storage, Raspberry Pi is ready for action “out of the box”. Even supports KVM or wireless access.
Software, Flexible Options
Capable of running a wide range of full stack software, Raspberry Pi’s focus on education, research and open source solutions has resulted in one of the world’s largest and most enthusiastic developer communities. Whatever your software design objectives, you will find it easier to achieve with Raspberry Pi.
The key building block of every Cluster Module.
Power & Mounting Solution
Cluster Packs simplify the mounting of thousands of nodes.
They route and regulate power to every node, locally.
No Wires, No Problems
Power the packs and you power the cluster.
Visit Us at SC17
Come and visit us at Super Computing 2017 in Denver next week.
You’ll find us at the Center for Advanced Research Computing Booth 535.
We’re exhibiting one of five modules to be used at the New Mexico Consortium Ultrascale Systems Research Center as part of a pilot program led by the Los Alamos National Laboratory and The University of New Mexico.
The aim of the consortium is to engage universities and industry nationally in support of exascale research and the goal of the research is to investigate the challenges of computing at extreme scales – millions rather than thousands of computers.
Such large systems pose questions that have not yet been answered.
The pilot is the first step in plans to construct a very large model cluster to facilitate research in extreme scale cluster design. The focus is on new network architectures, bootstrap, management and recovery algorithms and primary research in systems and distributed storage software.
Upon completion of the pilot, the plan is to extend this research cluster from its present 720 active nodes to 10,000 with an option to build out to 50,000 or more to explore questions arising at extreme scale.
This research project provided the initial motivation for the development of the compact 144 node Raspberry Pi BitScope Cluster Module. The largest we built before this was just 40 nodes! Los Alamos National Laboratory, the Raspberry Pi Foundation, BitScope Designs and SICORP are all interested in your feedback about this project, its goals and your thoughts about ultrascale cluster research, design and development.
We look forward to meeting you and sharing ideas, our plans and the roadmap for 2018
SOLVING THE SCALING PROBLEM
The Department of Energy’s Los Alamos National Laboratory is operating one of the largest supercomputers on the planet.
It does this through massively parallel nuclear simulations of ever greater geometric and physical fidelity which in turn requires solutions to a range of problems that only arise when developing computing systems capable of doing this at the required magnitude and scale.
Suffice to say, whether simulating nuclear stockpiles or evaluating climate models, doing this sort of thing is challenging and very expensive.
Trinity runs almost 20,000 nodes with 2PB of DRAM, 4PB of flash and 100PB of disk across the cluster. Newer systems like Crossroads currently in development are even larger.
Systems like these require 10 to 40MW power and 50kW to 250kW of cooling per rack and the machines themselves can cost up to $250M per cluster to build.
Shown here is installation work for the water cooling system for Trinity. Despite the efficient use of water from LANL’s Sanitary Effluent Reclamation Facility it still requires megawatts of power to keep it cool when in operation.
Exascale clusters planned for the future are even larger and potentially more power hungry. Notwithstanding efforts to improve operational efficiency, cutting edge solutions like this will always require substantial resources. The power and cooling requirement across a large facility like LANL is already enormous. It requires a considerable amount of dedicated infrastructure to support it all. Consequently, solutions that optimise the use of these large computing resources is critical.
Every design detail from network interconnection to storage architectures and processing pipelines needs to be considered.
A fundamental problem is that what we know works at one scale may not work well at larger scales and building a $250M machine to find out is not really an option.
Cluster simulations can help to some extent but in many cases real-world issues can intervene to mitigate their effectiveness.
What’s really needed is a low cost development platform on which to research the design options and prototypes new ideas without the expense of building a running a full scale HPC cluster to do this research.
CODE READY DESIGN
Without operational systems software, nothing will work and applications can’t get the science done but applications rely on stable systems software which needs to be developed for the cluster in the first place. A classic Catch-22.
Given the high cost of running the production HPC clusters, it’s not practical to use them to develop systems software and these machines are rarely available anyway because they’re usually running existing application software 24×7 already.
Earlier generation clusters may be available at a given facility for systems software development but they are also expensive and their architecture may not represent current and future challenges to the software stack. Gary identified that the key to solving these problems is to develop a way for R&D to design system software that scales well when working on solutions intended to run 100k+ nodes. “You simply don’t get the opportunity to use a large supercomputer for weeks to months at a time to try out things like scalable boot, launch, monitoring, io forwarding etc”.
THE MODEL SOLUTION
Gary said “We thought Raspberry Pi was potentially the answer but there were no good cluster packaging technologies.”
“SICORP helped us find a potential solution and we jointly worked with BitScope to develop the first unit and proceeded to get 5 units to try at towards 1000 node scale.”
“Subsequently other potential uses like simulation of thousands or tens of thousands of IOT devices and other similar applications have expressed interest.”