Unholy Matrimony? Microsoft and Cray 358
fetusbear writes with a ZDNet story that says "'Microsoft and Cray are set to unveil on September 16 the Cray CX1, a compact supercomputer running Windows HPC Server 2008. The pair is expected to tout the new offering as "the most affordable supercomputer Cray has ever offered," with pricing starting at $25,000.' Although this would be the lowest cost hardware ever offered by Cray, it would also be the most expensive desktop ever offered by Microsoft."
Re:No so, it can run vista smoothly, if... (Score:5, Interesting)
I beg to differ, I was running it just fine with only 512mb or ram on a 2.39ghz celeron processor. Once I turned off all the eye candy there were no performance issues.
It's probably the only case I can think of where the minimum requirements were at all realistic.
Doubtful... (Score:4, Interesting)
If they're running their shopping cart on it. I just tried to configure one and got the following error. I mean, honestly, what has happened to Cray if they're releasing applications that don't handle simple CRUD exceptions? This would earn an F in high school level computer science and released into production should be enough to tank their stock:
Server Error in '/configurator' Application.
An item with the same key has already been added.
Description: An unhandled exception occurred during the execution of the current web request. Please review the stack trace for more information about the error and where it originated in the code.
Stack Trace:
[ArgumentException: An item with the same key has already been added.] ...
Version Information: Microsoft .NET Framework Version:2.0.50727.42; ASP.NET Version:2.0.50727.42
Re:What's the frame rate and resolution? (Score:4, Interesting)
Like the linux kernel developers are any better...every OS maker is greedy about increased CPU power. I first ran Linux in 1995 and it isn't that much faster now.
Cray is dead. (Score:3, Interesting)
Cray is just barely more relevant to modern HPC than Silicon Graphics. Whether they're making a PC that runs Linux or a PC that runs Windows, it's still a PC. Yes, a massively parallel one, but it's a PC. The XMT series is the only really innovative thing that distinguishes Cray from the next guy down the street.
Computing has come to the point where commodity hardware can be almost endlessly strung together with commodity equipment to achieve the computing level necessary for most purposes. Furthermore, in the rare cases where it's necessary to go beyond this level, the cost of building a custom machine that outperforms commodity equipment is roughly one to two orders of magnitude more. Bottom line, it's just not cost effective for almost anyone to buy the cool high-end non-commodity gear anymore.
Which means that Cray will be reduced to a company that makes interconnects, like SGI is. Neat engineering, but the interconnects are now becoming commodity gear as well, which means that these companies won't be able to make enough profit to keep engineering as the focus of the company. They'll be forced into being a support/service company of their commodity hardware sold at a meagre 5% profit margin.
The one escape is gone as well--pushing Linux and Windows and the primary (or only) OSes means that they won't have anything special to offer. If, for instance, SGI had aggressively driven Irix, things might have been different for them.
The last front for development in current computing is in the labs of Intel and AMD, working on commodity gear. The days of boutique computing are dying.
Re:Too dinosaurs working together. (Score:5, Interesting)
I disagree, but then again, I work in the HPC industry.
1. Standard computers have already taken over all of those jobs that used to require a supercomputer. There's no more market to loose. HPC is a 6-7 billion dollar market. The TAM is growing slower than the rest of the IT industry, but it's still a large niche market.
2. Clusters got really popular for a few years, but have really fallen out of favor at the high end of the HPC market. That said, the difference between a high-end super, and a cluster, is rather small. Thankfully the price difference is shrinking too. Moreover, this product IS a cluster. It looks like an attempt, by Cray, to get into the low end of the HPC market. Cray, like everyone else, would like to be the company taking market share away from itself, rather than let someone else take it.
3. IBM has a compelling strategy of reusing their high-end POWER-X processor super-servers, and selling them as supercomputers. The problem with this, is that they are obscenely expensive as supercomputers. A high-end database server has a whole pile of functionality that is completely unnecessary for HPC jobs, both in hardware, and in software. Big iron servers are also WAY more expensive, per-processor, than a super. As such, IBM is also making supers out of commodity clusers, commodity clusters with CELL coprocessors, and BlueGene, which is much closer to CrayXT than it is to an IBM mainframe or superserver. I would argue that IBM's diversity may work against it, in the HPC market, as it tries to fit a round peg into a square hole.
I'm not sure Cray will be very successful with this CX1 product, or generally, selling to the low-end HPC market. That, however, is not reason to believe that there is no need for venders specialized in HPC systems. Cray has made quite a comeback, in the last few years. The reason one thinks of Cray as a dinosaur, is that the HPC market is so much smaller now, relative to the entire IT industry, compared to the 1980s. Nonetheless, it's still an important niche.
Re:Poor Seymour (Score:3, Interesting)
Cray is pretty much the Monster Cable of the supercomputing world these days, right? A company that offers little to no tangible benefit over its competitors, but gets by on brand recognition alone?
I know that Cray was at the top of the world twenty years ago, because that's what we were taught in 7th grade Computers class, where we learned how to program in BASIC on a room full of TRS-80s; that the four types of computer are microcomputer, minicomputer, mainframe, and supercomputer; and that other popular computer languages included Pascal, FORTRAN, and COBOL. Every one of those facts is outdated today; is not Cray's reputation, as well?
Re:This thing... (Score:5, Interesting)
Because by saying it runs Windows, they are implicitly defining the development tools and APIs that it supports.
So an organization that has Windows devs but needs more horsepower is likely to turn to this before looking at a Beowolf cluster.
Now, writing massively parallel code is admittedly a different skill set than writing ordinary desktop or web development, but starting with the same tools and environments gives them at least a head start.
Re:!supercomputer (Score:5, Interesting)
A supercomputer turns all tasks into IO bound problems.
A mainframe turns all tasks into a CPU bound problem.
A microcomputer just runs awhile and crashes.
Re:What's the frame rate and resolution? (Score:5, Interesting)
Good point: mutt, for example, is still the fastest emailreader ive ever seen.
And yeah. Its much faster now than in 98.
Re:What's the frame rate and resolution? (Score:5, Interesting)
I think the new kernels are faster.
My Pentium 600 running slackware with a 2.4.10 kernel is a lot slower than my Pentium 600 running debian 4.0r2 with a 2.6.x kernel.
Re:What's the frame rate and resolution? (Score:4, Interesting)
There was a Microsoft podcast, where some Microsoft programmers were being asked about the future of the API they developed and one thought was that every DCOM/COM/kernel object would have its own lock, as the attitude was "Hey, you will have 80 cores on every machine, you will be able to afford it!".
Re:This thing... (Score:3, Interesting)
From my experience programming properly threaded daemons on Linux and Windows, a head start in development on Windows can't even begin to make up for the extremely broken APIs available there. Even condition variables have to be hacked together, since Windows doesn't support the POSIX threading standards.
Re:What's the frame rate and resolution? (Score:3, Interesting)
The Register [theregister.co.uk] says
If you want to cut off the air that Linux breathes, as Microsoft certainly does, one of the choke points where you try to get your Windows tentacles wrapped around is supercomputing, or what people for some reason now call high performance computing. But to take on Linux in HPC requires a slightly different tack than what worked for Windows in the data center, and it requires something a little more subtle than the cheap software and portability across architectures that made Linux the darling of academic, government, and corporate supercomputing centers in a mere decade, supplanting Unix.
Microsoft's strategy - one that no supercomputer maker and no X64 chip maker can ignore - is to attack from the bottom, to find those myriad new HPC users who never learned Unix, never learned Linux, and have no desire to. This strategy is what moved Windows from the desktop to the data center in the 1990s, and it worked so brilliantly that Windows machines account for more than two-thirds of server revenues each quarter and the lion's share of shipments. People use the software they are comfortable with, and Linux was an easy transition for Unix shops, just as moving from a Windows desktop to Windows servers is relatively simple.
So Cray is trying to democratize the supercomputer-- just as DEC democratized the mainframe.