1 877 422 8729

This week has seen a couple very interesting stories in high performance computing. We shared both of them over our Facebook and Twitter channels.

The first was cast as quite possibly the cheapest supercomputer you could build… and it used Raspberry Pis and legos!

Ever dreamt of owning a supercomputer but didn’t have millions of dollars to spare? Thanks to some inventive thinking by one professor, you can now make a supercomputer all your own. All you’ll need is a collection of credit card-sized computers, some Legos, and about $4,000.

This summer Simon Cox, Professor of Computational Methods at the University of Southampton, wanted to get his 6-year-old son, James, interested in computing. At about the same time the makers of Raspberry Pi – the small Linux-based computer – suggested the Pis might be linked to form a single cluster. Even better. Why teach your son computing on a computer when you can teach him on a supercomputer?

To build it, they linked 64 Pis using software called Message Passing Interface (MPI), which provides a standard language and enables communication between the cluster nodes. Cox boosted meager storage of the Pis by fitting each of them with a 16GB SD card, bringing total storage capacity to about 1 TB, and equipped it with the free plug-in, ‘Python Tools for Visual Studio.’ for code developing. They named their supercomputer “Iridis-Pi,” after the University’s own supercomputer Iridis. Iridis-Pi’s power configuration is far from optimal, however, as each Raspberry Pi requires its own power supply.

The Raspberry Pi is already seriously popular among programming enthusiasts. It’s not very powerful, but then, it’s not supposed to be. Raspberry Pi founder Eben Upton built it to be a low cost learning tool, meant for hobbyists who wanted to tinker with and learn about Linux. At just $35 a piece, the Model B still has plenty of tools: a 700MHz ARM-11 processor, 256MB of RAM, HDMI output, 2 USB ports and an Ethernet port. It’s not supposed to replace your desktop, but supplement it, and it can do many things that a PC does. You can run spreadsheets, word-processing programs, create graphics, even play games.

Read the full article – Build Your Own Supercomputer with Raspberry Pis and Legos – For Reals!

Of course this may not be cheapest way to break into HPC space thanks to innovation in ICC’s NovaServ line and Intel’s Xeon E5 processor series, as last week’s article HPC on a Budget showed.

But now all kidding aside, HPC attempts to do something that has never been tried – building a new universe!

How do you follow a galaxy through nearly all of time? You build a new universe.

The real challenge for cosmology is figuring out exactly what happened to those first nascent galaxies. Our telescopes don’t let us watch them in time-lapse; we can’t fast forward our images of the young universe. Instead, cosmologists must craft mathematical narratives that explain why some of those galaxies flew apart from one another, while others merged and fell into the enormous clusters and filaments that we see around us today. Even when cosmologists manage to cobble together a plausible such story, they find it difficult to check their work. If you can’t see a galaxy at every stage of its evolution, how do you make sure your story about it matches up with reality? How do you follow a galaxy through nearly all of time? Thanks to the astonishing computational power of supercomputers, a solution to this problem is beginning to emerge: You build a new universe.

In October, the world’s third fastest supercomputer, Mira, is scheduled to run the largest, most complex universe simulation ever attempted. The simulation will cram more than 12 billion years worth of cosmic evolution into just two weeks, tracking trillions of particles as they slowly coalesce into the web-like structure that defines our universe on a large scale. Cosmic simulations have been around for decades, but the technology needed to run a trillion-particle simulation only recently became available. Thanks to Moore’s Law, that technology is getting better every year. If Moore’s Law holds, the supercomputers of the late 2010s will be a thousand times more powerful than Mira and her peers. That means computational cosmologists will be able to run more simulations at faster speeds and higher resolutions. The virtual universes they create will become the testing ground for our most sophisticated ideas about the cosmos.

This could perhaps be the most ambitious project undertaken in supercomputing. We’ve never seen anyone try to build a new universe before, so we’ll be looking forward to how it goes!

Read the full article – Meet Mira, the Supercomputer That Makes Universes