Intel have announced their “Nehalem” processors will be coming to market in Q1 2009, with 2, 4 or 8 cores. Nothing to spectacular there (see Sun’s OpenSPARC CPU to see how to really scale with cores) but moving away from arguments about how multi-cores are better, Nehalem uses Intel’s QuickPath Interconnect (QPI) and that’s of great interest to Silicon Graphics customers.

QPI will be used by both Nehalem Xeon processors and the upcoming Tukwila Itaniums. This means that SGI’s biggest class of box - the Altix 4700 - could in theory be perfectly happy with either newer Itaniums, or make the move to cheaper Nehalem Xeons.

The next generation of Altix ICE blades will definitely be sporting the new Xeon processors (along with double data rate (DDR) Infiniband), but it’s the scalability of the bigger Altix NUMA boxes that are of interest to many customers. Given the architecture can scale to 128TB of shared memory, and with installations running up to 4096+ cores, being able to shove 8-way CPUs per socket would be a massive shot in the arm to the system - along with the increases in memory density and cooler running that will come with the new processors.

Being able to shove the cheaper Xeons into the high end offerings also means Silicon Graphics can lower production costs and increase margin, which given the recent quarterly earnings reports can only be a good thing.

Transitive are the guys who came up with the immensely clever emulation software that allows MIPS code to run on x86 and Itanium platforms. Apple also licensed a version called Rosetta, which enables PowerPC code to run on their newer x86 machines. Intel and Sun are users as well, allowing legacy SPARC code to run on Solaris on x86.

IBM have been using Transitive software for a while, allowing legacy x86 code to run on their Power machines. So the news that IBM has bought transitive could herald some problems ahead, especially with IBM saying “IBM is evaluating Transitive’s other products as part of its overall Systems product strategy.”

Hmm. You could argue that, come on, MIPS for SGI and PowerPC for Apple died years ago, upgrade already. Maybe that’s true for Apple, but a lot of Silicon Graphics gear is bought for the long haul, and isn’t part of the usual 2-3 year cycle of upgrades that desktops and workgroup servers get. A lot of MIPS based kit is still in support and still being heavily used - although the market can’t grow any more, that installed base isn’t shrinking too rapidly either.

It’s unclear at this stage what effect IBM dropping non-Power support for Transitive would have. Presumably new customers with MIPS gear would be left in the cold (although they’ve left it a bit late to think about a migration) but with no new versions of IRIX coming out it’s doubtful the announcement would have any effect on existing users.

Apple appear to have licensed Transitive code as Rosetta and bundled it into OS X. With Snow Leopard (10.6) rumoured to totally drop PowerPC support, no longer having an emulation layer in the OS could be a non-issue.

Supercomputing 08 is on all this week, so there should be shed loads of interesting news coming out. It’s one of the high points of the geek year, even if you’re not a Silicon Graphics fan, and each year I’m gutted I can’t attend.

The latest news is from HPCwire, who have published their Reader’s Choice Awards. Silicon Graphics have been voted for three of them by HPCwire readers:

• Best HPC Server Product or Technology was awarded to the SGI Altix ICE 8200 blade server
• Best HPC Visualization Product or Technology went to Silicon Graphics RemoteVUE
• one of the Top 5 Vendors to Watch in 2009 is SGI

The entire VUE software suite is going to be really interesting - it’s another great breakthrough for SGI and it has some real potential. The Altix ICE gear has been slowly gaining traction and although clusters don’t strike me as impressive as large (traditional even?) supercomputers, they’re still damn complex and very interesting technology.

Way down in Middle Earth, Weta Digital picked up a Reader’s Choice award for Best Use of HPC in the Entertainment Industry.

As a life long Ferrari fan (and driver!) I’m pleased to see the HPCwire Editor’s Choice award for Best Use of HPC in the Automotive Industry has gone to the Ferrari F1 team.

You can read through the full list of awards at http://www.hpcwire.com/specialfeatures/sc08/offthewire/HPCwire_Announces_Annual_Readers_Choice_Awards_at_SC08.html

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?

Supercomputing 2008 kicks off this week, and that means a new update to the Top 500 list.

IBM have given RoadRunner a shot in the arm, boosting sustained Linpack performance to 1.105 petaflops, up from it’s previous best of 1.026.

Cray have done a good job with Jaguar, moving from XT4 frames with a sustained 205 teraflops, to XT5 frames, boosting sustained performance to 1.059 petaflops.

Silicon Graphics come in at third place, with the Pleiades Altix ICE cluster, which they put together for NASA’s Ames Research Center. At 51200 cores and 51TB of memory it’s a bit of a beast, although as a cluster it’s a bit less interesting than a Single System Image (SSI) machine.

SGI’s Pleiades manages to sustain 487 teraflops, pushing BlueGene/L into fourth place. The previous supercomputer Silicon Graphics built for NASA Ames, Columbia, languishes down in 39th place, which should give some idea of the immense scale of performance improvements taking place.

You can grab the full system stats for Pleiades from http://www.top500.org/system/9832

Silicon Graphics have just announced that more global shared memory is available with fewer CPUs on their Altix 4700 systems. Increased DIMM density now means you can get an Altix 4700 with 2TB of memory, with only 8 processors.

If you’ve got applications that require large amounts of memory but not much in the way of compute-intensive processes, this is very good news indeed.

Global shared memory is memory which is accessible from all processors/cores. So in an SGI Altix with 1024 processors and 4TB of RAM, any one of the 1024 CPUs can access any part of that 4TB of memory. This is due to the design of Silicon Graphics’ large scale systems, which are Single System Image (SSI) machines - all resources are shared.

Clusters work in a different way, where each node has ‘local’ CPU and memory, and this can’t be accessed from another node.

Both SSI and clusters can scale, but in different ways and with different workloads. Shared memory jobs, where you’re doing lots of memory I/O and you can peg your dataset in physical RAM, don’t scale well with clusters, whereas rendering (where discrete jobs can be chopped up and executed in batches) are just right for clusters but not SSI machines.

With lots of memory density enhancements coming down the line, I’m wondering when Silicon Graphics will break through the 4TB system memory barrier?

McObject are one of those database vendors who you don’t normally hear of, but who are really pushing the boundaries of what can be done with your data.

Their product, extremeDB-64, is written to take advantage of large memory systems by pegging the entire dataset in physical RAM. The advantages are pretty obvious - as are the downsides as well. The McObject guys have really thought about the problems, though, and extremeDB-64 is an impressive database solution.

What’s more impressive is McObject’s recent benchmark and scalability testing, where they test a 1.17 Terabyte, 15.54 billion row in-memory database on a 160-core SGI Altix 4700 server. They measured transaction throughput of up to 87.78 million query transactions per second, which is the sort of uber data-warehousing capability I know a number of businesses would love to get their hands on.

The benchmark white paper is available as a free download - head on over to this page to enter your details.

Kathy Lanterman has been CFO at Silicon Graphics since 2006, having been with the company over 10 years. She’s due to step down on November 10th, and will stay for a few weeks to help the transition to the new CFO. Kathy had been a VP and corporate controller since early 2002.

Replacing her is Greg Wood, who’s a bit of a wild card. He doesn’t appear to have much of a background with ‘hard’ technology companies, with a portfolio that includes marketing, DRM and interactive TV companies. He’s held executive financial positions for over 25 years, so clearly has lots of experience - but will this be a case of more new blood that doesn’t understand SGI’s niche, or new talent that can help the company grow into new markets?

One of the first moves when a company comes out of Chapter 11 restructuring, or acquires new investors on the board, is a shuffle of senior positions while the new board members flex their muscle. It would be easy to say that this is why Kathy is leaving, but she’s had a pretty tumultuous ride during tough times at Silicon Graphics, so I can’t blame her at all for wanting some time off.

Silicon Graphics have just announced their Q1 2009 financial results. Revenue and operating expenses are both down compared to Q4 2008, but are both up compared to Q1 2008.

Pro-forma results though show a loss of $7 million for Q1 2009, compared to a loss o $3 million for Q4 2008 and $3.8 million for Q1 2008.

With Sun’s recent financial results as well, it’s clear that this quarter is a less than stellar one for R&D heavy tech firms. The real test will be to see how both Sun and SGI perform in the next quarter, as the knock on effects of the credit crisis really start to bite.

With the launch of VUE and good sales of the Oracle datawarehouse solution based on Altix 450s, I think Silicon Graphics could make some good sales in the next quarter. An upcoming restructuring of the Global Developer Program and the continued push to get ISVs and IHVs on board is really going to help here - and, to be honest, it’s something they should have been doing years ago.

The lack of focus on large scale database systems for business basically meant Silicon Graphics handed the datacentre on a plate to Sun, who stepped in with the E10k and the awesome F15k.

You can also find an entire transcript of the conference call online at http://seekingalpha.com/article/104042-silicon-graphics-q1-2009-earnings-call-transcript

After Y2K was a comic started by Nitrozac and Snaggy way way back … before Y2K in fact. Sadly it’s no longer being updated, but the archives are still available on the Joy Of Tech website.

The pinnacle of the entire AY2K comic (for me at least, anyway) was when the survivors of the Y2K disaster tried to rebuilt computing using the humble abacus - leading to Abacus World Expo!

And the comic that made me laugh out loud was this one:

You can view the full page here - I can recommend reading from the beginning, it’s good stuff.