Comments (5) Visits (19871)
Tonight PBS plans to air Season 38, Episode 6 of NOVA, titled [Smartest Machine On Earth]. Here is an excerpt from the station listing:
"What's so special about human intelligence and will scientists ever build a computer that rivals the flexibility and power of a human brain? In "Artificial Intelligence," NOVA takes viewers inside an IBM lab where a crack team has been working for nearly three years to perfect a machine that can answer any question. The scientists hope their machine will be able to beat expert contestants in one of the USA's most challenging TV quiz shows -- Jeopardy, which has entertained viewers for over four decades. "Artificial Intelligence" presents the exclusive inside story of how the IBM team developed the world's smartest computer from scratch. Now they're racing to finish it for a special Jeopardy airdate in February 2011. They've built an exact replica of the studio at its research lab near New York and invited past champions to compete against the machine, a big black box code -- named Watson after IBM's founder, Thomas J. Watson. But will Watson be able to beat out its human competition?"
Craig Rhinehart offers [10 Things You Need to Know About the Technology Behind Watson].
An artist has come up with this clever [unofficial poster].
Like most supercomputers, Watson runs the Linux operating system. The system runs 2,880 cores (90 IBM Power 750 servers, four sockets each, eight cores per socket) to achieve 80 [TeraFlops]. TeraFlops is the unit of measure for supercomputers, representing a trillion floating point operations. By comparison, Hans Morvec, principal research scientist at the Robotics Institute of Carnegie Mellon University (CMU) estimates that the [human brain is about 100 TeraFlops]. So, in the three seconds that Watson gets to calculate its response, it would have processed 240 trillion operations.
Several readers of my blog have asked for details on the storage aspects of Watson. Basically, it is a modified version of IBM Scale-Out NAS [SONAS] that IBM offers commercially, but running Linux on POWER instead of Linux-x86. System p expansion drawers of SAS 15K RPM 450GB drives, 12 drives each, are dual-connected to two storage nodes, for a total of 21.6TB of raw disk capacity. The storage nodes use IBM's General Parallel File System (GPFS) to provide clustered NFS access to the rest of the system. Each Power 750 has minimal internal storage mostly to hold the Linux operating system and programs.
When Watson is booted up, the 15TB of total RAM are loaded up, and thereafter the DeepQA processing is all done from memory. According to IBM Research, "The actual size of the data (analyzed and indexed text, knowledge bases, etc.) used for candidate answer generation and evidence evaluation is under 1TB." For performance reasons, various subsets of the data are replicated in RAM on different functional groups of cluster nodes. The entire system is self-contained, Watson is NOT going to the internet searching for answers.
On ZDnet, Steven J. Vaughan-Nichols welcomes our new [Linux Penguin Jeopardy overlords]. I have to say I share his enthusiasm!
Continuing this week's discussion on IBM announcements, today I'll cover our integrated systems.
The problem with spreading out these announcements across several days' worth of blog posts is that others beat you to the punch. Fellow blogger Richard Swain (IBM) has his post [Move that File], and TechTarget's Dave Raffo has an article titled [ "IBM SONAS gains policy-driven tiering, gateway to IBM XIV Storage System"].
By combining multiple components into a single "integrated system", IBM can offer a blended disk-and-tape storage solutions. This provides the best of both worlds, high speed access using disk, while providing lower costs and more energy efficiency with tape. According to a study by the Clipper Group, tape can be 23 times less expensive than disk over a 5 year total cost of ownership (TCO).
The two we introduced recently were the [IBM Information Archive] and the Scale-Out Network Attached Storage (SONAS). This week, IBM announced some enhancements as SONAS v1.1.1 release. SONAS is the productized version of IBM's Scale-Out File Services (SoFS), which I discussed in my posts [Area Rugs versus Wall-to-Wall Carpeting] and [More details about IBM's Clustered Scalable NAS].
For those who are wondering how this positions against IBM's other NAS solution, the IBM System Storage N series, the rule of thumb is simple. If your capacity needs can be satisfied with a single N series box per location, use that. If not, consider SONAS instead. For those with non-IBM NAS filers that realize now that SONAS is a better approach, IBM offers migration services.
Both the Information Archive and the SONAS can be accessed from z/OS or Linux on System z mainframe, from "IBM i", AIX and Linux on POWER systems, all x86-based operating systems that run on System x servers, as well as any non-IBM server that has a supported NAS client.
Greg and 3PAR's Marc Farley did an "ambush" interview with the folks at the IBM booth at SNW, including Paula Koziol about Twitter, and [Rich Swain] about IBM's latest SONAS product. Here is their post [Storage Monkey business with IBM]:
You can learn more about SONAS from my post [More Details about IBM Clustered NAS]. SONAS is based on software that has been available since 1996, on commodity off-the-shelf server and storage systems, but building a complete system was left as an exercise to the end-user, which many of the top 500 Supercomputers have done.
Back in November 2007, IBM announced Scale-Out File Services (SoFS) which was a set of IBM Global Technical Services to build a customized solution from the software and a set of servers, disk and tape storage. Customized configurations were done for a variety of workloads from Digital Media to Scientific Research High Performance Computing (HPC). Last year, SoFS was renamed to IBM Smart Business Storage Cloud (SBSC).
This year, IBM was able to package all of the software and hardware into an easy to order machine-type model that has everything cabled and ready to use. This is what SONAS is today.
From Timothy Morgan of [The Register]:
"With Cisco Systems, EMC, and VMware teaming up to sell integrated IT stacks, Oracle buying Sun Microsystems to create its own integrated stacks, and IBM having sold integrated legacy system stacks and rolling in profits from them for decades, it was only a matter of time before other big IT players paired off."
Once again we are reminded that IBM, as an IT "supermarket", is able to deliver integrated soft
For full details on these new ordering options, see the IBM [Press Release].
technorati tags: System x, BladeCenter, IntelliStation, Cisco, EMC, VMware, VCE, Oracle, Sun, HP, Microsoft, FastBack, FlashCopy, GPFS, Windows, Linux, SAP, SVC, VSS, DS8000, DS5000, DS4000, DS3000, SQL, Lotus, Domino