2009/06/23
TheRegister: Top 500 supers - world yawns at petaflops
by Timothy Prickett Morgan
The annual International Supercomputing Conference kicked off this morning in Hamburg, Germany, with the announcement of the 33rd edition of the Top 500 supercomputer rankings. While petaflops-scale machines are far from normal, they soon will be.
Not surprisingly, HPC vendors and academics are gearing up to try to push performance up by three orders of magnitude to break through the exaflops barrier - something that will take radically different server and network fabric designs and plenty of time to accomplish. But in the meantime, everyone is trying to show they can break the petaflops barrier, and soon, they will be breaking the 10 petaflops barrier.
With the June 2009 ranking, the home team in Germany - which has two monster machines in the top ten this time around - will be celebrating. Well, as much as supercomputer nerds celebrate. (We know you are really using the new Jugene and Juropa supers to play video games, at least when the administrators aren't looking. Let's hope the game is not global thermonuclear war).
The Forschungszentrum Juelich (FZJ) has been on a buying binge this year, upgrading its two supercomputers so it can lay the claim of being the floppiest supercomputer center in Europe. The Jugene BlueGene/P system that FZJ bought from IBM packs together 294,912 PowerPC 450 cores running at 3.4 GHz, using a proprietary BlueGene interconnect to deliver 825.5 teraflops of oomph for various research projects, giving it the number three position on the Top 500 list. It runs SUSE Linux - as if you expecte anything else.
Down the hall at FZJ is a hybrid machine made by Bull and Sun Microsystems, called Juropa, which is comprised of a mix of Bull NovaScale R422-E2 rack servers and Sun's X6275 blade servers, all linked together using the new quad data rate InfiniBand switches from Mellanox. It's ranked at number ten on the list. (Those Mellanox switches were the final nail in interconnect maker Quadrics' coffin, since the Juropa prototype used its products and the final machine did not).
The Juropa nodes all use Intel's quad-core Xeon 5500 processors (formerly known as "Nehalem EP" or "Gainestown" if you track code names) and run SUSE Linux. The combined bits of the Juropa machine have 26,304 cores in total and were rated at 274,800 on the Linpack Fortran test, which means 89.1 percent of the peak theoretical performance of the processors was delivered when the Fortran test was run. The Jugene machine has an efficiency of about 82.3 percent on the Linpack test.
The Top 500 supercomputer list comes out twice a year, giving food for thought to the two major HPC events of the year, Supercomputing in North America and ISC in Europe. The list is maintained by Erich Strohmaier and Horst Simon, computer scientists at Lawrence Berkeley National Laboratory, Jack Dongarra of the University of Tennessee, and Hans Meuer of the University of Manheim. The ranking is based on the installed machine running the Linpack Fortran benchmark test created by Dongarra and colleagues Jim Bunch, Cleve Moler, and Pete Stewart back in the 1970s to gauge the relative performance of computers of all stripes and sizes on numerical calculations.
The two machines at the top of the June 2009 ranking are exactly the same as they were on the November 2008 list. Number one is IBM's hybrid Opteron-Cell "Roadrunner" machine, which the U.S. Department of Energy has installed at Los Alamos National Laboratory. The machine is currently using dual-core 1.8 GHz Opteron chips and 3.2 GHz PowerXCell 8i co-processors, delivering 1.1 petaflops of number-crunching power (the same performance it had last November). Roadrunner has 129,600 processor cores in total and runs at about 75.9 per cent of peak theoretical throughput. (Moving up to faster 40 Gb/sec InfiniBand switches would probably boost performance on Roadrunner without adding cores to the box).
Number two on the Top 500 is the "Jaguar" Cray XT5 cluster installed at the DOE's Oak Ridge National Laboratory, which is made from 37,538 of Advanced Micro Devices' quad-core "Shanghai" processors running at 2.3 GHz and delivering 1.06 petaflops of oomph. It too had the same ranking late last year. (That's because the heavy workload that Jaguar has been under has not allowed it to be retested, according to Strohmaier).
The "Pleiades" Altix ICE 8200 cluster made by Silicon Graphics (the old one, not the new one that is really Rackable Systems with the old SGI product line added in) for NASA's Ames Research Center is ranked at number four on the list, with 487 teraflops, the same as six months ago but Jugene bumped it down. The number five box on the ranking - IBM's BlueGene/L massively parallel box installed at Lawrence Livermore National Laboratory and the number one machine on the November 2007 list when it debuted - was still rated at 478.2 teraflops.
There are two more BlueGene/P systems in the top ten, which are kickers to this BlueGene/L and siblings to the larger Jugene machine at FZJ.
Number six on the Top 500 list this time around is a sibling machine nicknamed "Kraken" that is also an XT5 machine from Cray that is installed at the University of Tennessee. It has 66,000 cores, is rated at 463.3 teraflops, and is the most powerful supercomputer installed at a university anywhere in the world.
Number seven on the list is a BlueGene/P box installed at Argonne National Laboratory, which was upgraded a smidgen to 458.6 teraflops but which still fell two spots in the ranking. Number eight on the list is the the parallel machine built by Sun Microsystems using its X6420 blade servers with quad-core Shanghai Opterons running at 2.3 GHz and linked by Sun's "Magnum" InfiniBand DDR switches. The Ranger cluster has a total of 62,976 cores and it's rated at 433.2 teraflops.
Rounding out the top ten is "Ranger," at number nine on the list, is a machine named "Dawn," a companion BlueGene/P box that sits next to that BlueGene/L box at Lawrence Livermore National Laboratory. It's rated at 415.7 teraflops.
Other new and notable machines on the list include a 185.2 teraflops BlueGene/P super sold by IBM to the King Abdullah University of Science and Technology in Saudi Arabia, ranked number 14 on the list, and a 180.6 teraflops cluster called "Magic Cube" at the Shanghai Supercomputer Center, the largest machine on the list equipped with Microsoft's Windows HPC Server 2008 operating system. This system was built by Chinese server maker Dawning and was on the list as of last November.
InfoWorld: Sun tools upgrade geared for multicore apps
by Paul Krill
Recognizing that developers these days must program for multicore processors, Sun Microsystems on Tuesday is releasing an upgrade to its native development tools package geared to this new responsibility.
Sun, though, would not comment on what Oracle's impending acquisition plans might mean for the product, called Sun Studio 12 Update 1, thus leaving its fate up in the air similar to other Sun technologies.
Built for programmers developing applications in C, C++, and Fortran, Sun Studio 12 Update 1 is "focused on really unleashing application performance on multicore processors as well as simplifying parallel development on those processors," said Dan Roberts, director of product management for the data center software group at Sun.
But Roberts, asked what the impending purchase of Sun might mean for the tool, instead deferred to Sun statements on the merger. Sun on that page said Solaris has been the leading OS for the Oracle database. But no specific statement pertaining to Sun Studio could be found. An Oracle representative, when asked about the fate of the product, merely responded that the transaction had not closed yet.
Sun Studio is commonly used for building transactional applications as well as telecommunications, government, and military applications. It also is being used in retail and manufacturing application realms. The package consists of tools such as parallelizing compilers, debuggers, and libraries.
Developers, Roberts said, must deal with parallelizing code. Conditions that can crop up if an application does not accommodate parallel development include race conditions, with two commands waiting for the other complete. Thread locking also is an issue. Included in Sun Studio 12 Update 1 are improved tools for dealing with such maladies as race detection, thread lock assistance, and application profiling.
Graphical capabilities have been added and more issues can be detected than before. A visual profiling tool based on Dynamic Tracing technology in Solaris is featured.
The tools package, which is offered free of charge with optional support plans available, can be used to build applications for OpenSolaris, Solaris, and different forms of Linux on Intel, AMD, and Sun Sparc chips.
Also featured is improved performance and optimizations for delivering optimized code for Solaris. The update also supports libraries and tools from the OpenMP 3.0 API specification, featuring capabilities for scheduling and synchronization to control code execution.
A stand-alone GUI debugger is included, called dbxTool.
CNet: The new generation of cloud-development platforms
by James Urquhart
Software development "in the cloud" has been one of the really interesting developments to come out of the cloud computing market so far. While many early players, such as Zimky and Coghead died on the vine, there is a pretty robust Platform as a Service (or "PaaS") market out there today, with Google App Engine taking the most visible lead, and a pretty solid stable of Ruby on Rails-based hosting providers telling a compelling story of their own.
Such success is driving some new players to seek the spotlight, however. I wanted to highlight two that I found most interesting. They are very different from one another, but those differences highlight the breadth of opportunity that remains in the PaaS market.
(Credit: CNET News)Take AppScale, for instance. From RACELab, the same computer science lab at the University of California, Santa Barbara that brought you EUCALYPTUS, comes a completely open-source implementation of Google AppEngine cloud interface. Much more than another client-side implementation of the development tools alone, AppScale is a complete platform that allows you to run your App Engine applications on a virtualized cluster in your own data center equipment, or-get this-on Amazon EC2.
AppScale is likely most useful for those who want to save a buck or two by using existing software development and testing labs to build, test, and stress App Engine applications before paying for the Google service, and for those wishing to get an idea of how the underlying platform might make decisions relative to their application's performance. The platform also promises to provide a "way out" of App Engine should the economics, performance, or existence of that platform come into question.
App Engine, though, is a framework generally limited to building high scale Web applications. What if you are trying to build out your complete enterprise architecture in a cloud centric fashion? In that case, you might want to take a look at TIBCO Silver. A complete development, integration, and operations platform for service-oriented enterprise architectures, Silver takes a very unusual tack towards providing development to the clouds.
First, it's a three-element architecture:
1. An Eclipse-based software development tools that you load onto your desktop (much like the App Engine developer tools) and use to write code, integrate systems, utilize governance, and so-on.
2. TIBCO's "secret sauce": the management systems and middleware that work together to coordinate composition and governance, integration and orchestration, and automated performance management for your application.
3. A third-party cloud provider (today limited to Amazon EC2), on which to deploy and run your application. What is really cool here is that you create the instances you want to use, but Silver will install the software agents and configurations that need to be in place for it to deploy and manage your application-automatically.Did you get that last bit? Silver is a cloud development environment that automatically manages your applications in a cloud data center-just not TIBCO's data center. I still haven't decided if that qualifies as PaaS or not. Given that the automation systems do run in TIBCO's data centers, I'm tempted to say it is-what do you think?
If you choose the TIBCO route, you are certainly committing to their platform in some ways. However, everything is done entirely on open standards, so in theory (with significant work, I'm sure), you could port your systems (or components of a system) to another standards-based environment, should you so choose.
Both of these new options give me new hope for software development in the cloud, though each for a different reason. AppScale represents the power that open source has in creating options for what might otherwise be a "lock-in" risk. Silver, on the other hand, represents the first stab at a complete enterprise software architecture in the cloud that I've seen to date. I'd be interested in your reaction to either or both of these tools. Are either compelling to your situation?
