SC09 kicks off next week in the US, and SGI has been dropping hints about a big product announcement coming up.

There’ll be the usual pimping of the latest lines from their product range:

Octane™ III, SGI’s personal supercomputer, ICE Cube™ modular data center, CloudRack™ scalable workgroup clusters, SGI® Altix® ICE departmental server, and SGI® InfiniteStorage hardware and software products.

I’m hoping the new shiny bit of kit is going to be a line of Xeon based Altix gear, but we shall see:

“Supercomputing 2009 is the preeminent conference for leading HPC companies to showcase their most innovative technologies,” said Mark J. Barrenechea, president and CEO of SGI. “SGI is proud to demonstrate influential HPC products that scale from the personal supercomputer to the largest scale-up platform, and to make a major product announcement.”

New toys aside, SGI’s CTO Dr. Eng Lim Goh is going to be giving a number of talks, which are always worth a listen. He’ll be presenting “Scalable Architecture for the Many-Core and Exascale Era” at the Exhibitor Speaker Forum on Tuesday, November 17, at 2:30 p.m. PST in room E143-144. He’ll also be talking about scaling up systems using the Nehalem EX in the Intel Theater within the Intel on Wednesday, November 18, at 4:00 p.m. PST.

Once again this year work has gotten in the way and I won’t be able to attend, but I highly recommend you keep on top of things with John’s coverage of SC09 over at insideHPC.

Those paying attention to Silicon Graphics history will recall Dr. Eng Lim Goh back in 2004 talking about Project Ultraviolet – a supercomputer that used different types of processor types in a single frame. Although the original white paper has vanished from the SGI site, archive.org has a mirror available here.

The idea of HEC Architecture (High Efficiency Computing) and Multi-Paradigm Computing is a good one, and we’ve already been seeing the fruits in that, specifically Altix gear with FPGAs, and the rise of the GPGPU. Is the current Project Ultraviolet the same beast as the one outlined 5+ years ago?

I mentioned back in February the possibility that, with Tukwila delays and Nehalem processors having a NUMA interface, the time was ripe for SGI to put Nehalem Xeons into the Altix.

Now that Rackable have taken over the shell of SGI and have finalised their product offerings, we can see an interesting mix of processing power. Rackable have both Opteron and Xeon in their gear, whereas the (old) SGI had Xeon and Itanium.

With the Nehalem Xeons having the QuickPath interconnect, and Opteron always having had the NUMA HyperTransport, is now the time for Itanium to be shown the door?

HPCWire and InsideHPC (who know their stuff and are well worth a read) seem to think so. Even the eternally inaccurate TPM at The Register is agreeing (top tip, Timothy – NUMAlink is not a ‘cluster’ interconnect).

Xeons and Opterons inside the shared memory Altix make a lot of sense – immediate cost savings, the chips already have NUMA interconnects so not too much engineering required, and an instant boost in apps and developers.

Existing Itanium customers aren’t going to be too happy, but I’d point people at John Mashey’s excellent essay on the design behind the NUMAflex architecture. These machines were designed to be flexible, to swap CPUs without having to swap the frames, I/O subsystems, and everything else, thus protecting the customer’s investment in the technology, and lowering the price (and pain) of upgrades.

SGI CEO Mark Barranechea has re-confirmed the company’s commitment to Itanium on his blog – but with so many existing customers running on Altix gear, it would have been a PR disaster not to.

I think it’s clear that the next Altix cc:NUMA system will be based around Nehalem Xeon processors. The odds are good that we’ll be seeing an Opteron version as well, and it’ll be interesting to see how that stacks up against offerings from Cray.

As for Itanium? I think we will be seeing a Tukwila based Altix next year sometime. After that, I doubt very much we’ll see future Itanium kit from SGI.

Concept cars have been around for a while. Every major motorshow, and vendors let their designers loose and parade around the results. Some of them are received so well they are actually made – I love the design that became the Lancia Stratos. Silicon Graphics seem to be going down this path with a fantastic piece of R&D madness at the Supercomputing 08 show.

Silicon Graphics have come up with the Molecule – 10,000 CPU cores in a single rack. Molecule uses the low power Intel Atom processor, which is more familiar from netbooks like the Asus EEE PC.

Much like Sun’s UltraSPARC T1 and T2 CPUs, such a high density of Atoms within a single system image would give massive horizontal scalability for multi-threaded applications – although Sun have yet to approach this sort of density.

SGI reckon Molecule has the following advantages:

• High concurrency with 20,000 threads of execution — 40 times more than a single rack x86 cluster system
• High throughput with 15TB/sec of memory bandwidth per rack — over 20 times faster than a single rack x86 cluster system
• Greater balance with up to three times the memory bandwidth/OPS compared to current x86 CPUs
• High performance with approximately 3.5 times the computational performance per rack
• Greener with low-watt consumer CPUs and low-power memory that deliver 7 times better memory bandwidth/watt
• Innovative Silicon Graphics Kelvin cooling technology, which enables denser packaging by stabilizing thermal operations in densely configured solutions

Molecule is still only a concept, but it’s cool for a number of reasons. First off it shows SGI are still capable of some pretty awesome R&D hackery. It could also point the way for the next generation of SGI’s single system image machines, like the Altix 4700s. You can check out the full press release at http://www.sgi.com/company_info/newsroom/press_releases/2008/november/project_kelvin.html

After the sad demise of Orion and their deskside super-cluster, maybe this will be the future of massively scalable computing? And with FPGAs becoming part of a large scale install, is this the fruit of Project Ultraviolet?