Slashdot Mirror
IBM Touts Supercomputers for Enterprise
Stony Stevenson writes "IBM has announced an initiative to offer smaller versions of its high-performance computers to enterprise customers. The first new machine is a QS22 BladeCenter server powered by a Cell processor. Developed to power gaming systems, the Cell chip has also garnered interest from the supercomputing community owing to its ability to handle large amounts of floating point calculations. IBM hopes that the chips, which currently power climate modeling and other traditional supercomputing tasks, will also appeal to customers ranging from financial analysis firms to animation studios."
But is it Vista capable?
Do it yourself, because no one else will do it yourself. [beta blockade 10-17 Feb]
Personally, I'm sick of managing farms of physical servers, and with the introduction of VMWare, I'm now managing 3x the number of machines (albeit virtual machines). Have an FTP server? Run that in it's own image. Also have a syslog server? Yet another virtual machine. I really hope this sells well. Maybe I can now play PS3 games in the datacenter.
Developed to power gaming systems, the Cell chip...
That's just what we need to introduce to enterprise computing, the flame wars and invectives of the console world.
Admin #1 cell totally rockzorz!!!11!!!1 u n00bs using virtualization are in the past
Admin #2 IBM SUCKS!!! YOU KNOW IT!!! YOUR WHOLE BUSINESS IS TOTALLY GAY FOR THEM!!!!
I got a catholic block.
SCOTTY: Computer. Computer! Hello computer!
SAM PALMISANO: Uh, just use the keyboard.
SCOTTY: Keyboard... how quaint.
If specialized hardware returns to vogue, then there problems will crop up with the new specialized hardware. Dude face it, if you are a sysadmin, God will provide you with your share of things to complain about. It is the natural working order of things.
I got a catholic block.
> Personally, I'm sick of managing farms of
> physical servers, and with the introduction of
> VMWare, I'm now managing 3x the number of
> machines (albeit virtual machines).
All those Virtual machines to do the same thing with 4 times the resources as one well configured Linux box. Tsk Tsk.
Oh, but don't you LOOK busy.....
Sig Battery depleted. Reverting to safe mode.
That means that a PS3 running Linux, even with its ridiculously low 512MB RAM, can be used as a $500 development platform for these CellBE BladeServers.
And, in turn, some QS22 SW might be usable on the PS3, if it can be ported to use the tiny RAM. Or if someone hooks an i-RAM bank to the SATA port as swap/ramdisk, using perhaps iSCSI over its Gb-e for storage.
--
make install -not war
N-C-C one seven oh one. no bloody A, B, C, or D.
upon the advice of my lawyer, i have no sig at this time
Completely wrong. This is industrial supercomputing, not random web applications. The applications IBM is targetting Cell at are things like seismic analysis for oil companies, and this requires highly tuned implementations and specialised algorithms. This is expensive. It takes a lot of developer hours, and those developers are top-rung, very highly paid, because this stuff is very hard. And it costs a lot in hardware. Unfortunately for IBM, while Cell is fast, it's not fast enough to justify the cost for most companies. And it has a lot of competition from NVIDIA's Tesla platform, AMD/ATI's FireStream, and plain old clusters.
First off, I should admit that the Cell is quite a good processor, however it has shortcomings. Many shortcomings.
I'll begin first by listing the positives:
It has very good single precision floating point performance
Very high bandwidth on chip (25 GB/s)
With the e[nhanced]D[ouble]P[recision] addition to it IBM is adding for Los Alamos' Road Runner, it should be even better.
IBM Developerworks is a useful resource for programmers
It's a processor that gives the academic community a chance to publish more papers
The negatives:
Far too expensive
Floating point performance, single or otherwise, is useless for most enterprise work (no point running a database on a Cell)
The things that makes the Cell fast and unique are the SPEs (SIMD processors) are useless for servers*(I'll elaborate below)
Developing software to make use of the SPEs is time consuming and difficult. Orders of magnitude more so if your algorithm isn't suited for being split across SPEs
Computer Science or Engineering students who are doing research in this field have to read redundant papers that reword the IBM Cell manual (plagarism?) for 70% of it and what they actually did with the Cell for about 10%. 20% is of course left for citations.
You can't actually play games on a Cell. The PS3 games use them for physics engines, sound or such; the video is done on a video card.
Worst of all, YOU HAVE TO GET DATA FROM MAIN MEMORY TO SPU'S CACHE YOURSELF! (also known as Local Store, 256KB)
Now to talk about the SPEs... They are what makes the Cell tick. If the Cell didn't have them, it would just be an old Mac processor. (IBM Power 4 was it? I've trying to avoid research papers on the Cell) The graduate students (a year away from a PhD) that I was observing who were doing developing a scientific application on the Cell.. when we summed their year in development, they essentially told me it was a pain in the ass. Why? Because you have to get data from main memory to local store. Imagine if you had to get data from memory to your x86 processors L2 or L1 cache. (No, you don't actually want that. Trust me, you don't.) Scientists don't want to develop applications on this platform. Researchers like it because they can publish papers talking about it. This is why Los Alamos' Road Runner might be a flop. Bye bye to $100m of US tax payer money.
Back to the discussion with the grad students... I then came up with the idea that the Cell would be perfectly suited to an Asterix server. Why? Because sometimes Asterix needs to convert from one format to another when audio codecs differ. This is a perfect SIMD application, except we have a problem. While the Cell does have great on chip bandwidth, it has very poor Power5 processor (PPU) to SPU latency*. There is a research paper out there that puts PPU initiated memory transfers to SPU latency at about 4 microseconds. Compare this to SPU initiated transfer to SPU latency of about a tenth of a microsecond. Huge difference. You can't really avoid this unless you want to develop something horrendous that avoid the PPU but that's unlikely. The PPU would run the actual server and then it would need to notify the SPU of data, either by sending message (slow) and the SPU getting the data itself (2*slow=2slow) or sending the data and a message (slower).
It will be about 5 years until good software development tools are written for this architecture that will address most of the issues. This is assuming that IBM doesn't ditch it, which seemed likely before this announcement.
Oh, by the way, the QS22 doesn't support a hard drive which means you need fast NFS. The cost of ownership is more than just the cost of single blade.
You make it sound like it's a bad thing...