Slashdot Log In
IBM Optical Chip Zips Huge Files Using Little Power
Posted by
ScuttleMonkey
on Sat Mar 01, 2008 02:30 AM
from the zip-without-the-zap dept.
from the zip-without-the-zap dept.
An anonymous reader wrote to mention that IBM has unveiled a new prototype chip that can transmit data at up to 8 TB/sec, or about 5,000 high-def video streams. While this might not be entirely amazing, the fact that they did it using the same amount of juice required to light a 100-watt lightbulb, is. "The resulting total bi-directional data transfer rate is 300 Gb/s, nearly doubling the performance of a version IBM introduced last year. Compared to current commercial optical modules the transceiver provides 10-fold greater bandwidth in 1/10 the volume while consuming comparable power, IBM said."
Related Stories
[+]
Technology: Terabit-Per-Second Class Connections over FTTH 117 comments
Big Fat Dave writes "Thanks to research from Japan's Tohoku University, an article at Tech.co.uk wonders if someday the megabit and gigabit classes of net connections will join kilobits in the 'antique tech' bin. By doing some advanced mathematics and 'tweaking' existing network protocols, researchers may be able to enable standard fiber-optic cables to carry data at hundreds of terabits per second. 'At that speed, full movies could be downloaded almost instantaneously in their hundreds. At the heart of the development is a technique already used in some digital TV tuners and wireless data connections called quadrature amplitude modulation (QAM). One glance at the Wikipedia explanation shows that it's no easy science, but the basics of QAM in this scenario require a stable wavelength for data transmission. As the radio spectrum provides this, QAM-based methods work fine for some wireless protocols, however the nature of the optical spectrum means this has not been the case for fibre-optic cables ... until now.'"
[+]
Where's Our Terabit Ethernet? 218 comments
carusoj writes "Five years ago, we were talking about using Terabit Ethernet in 2008. Those plans have been pushed back a bit, but Ethernet inventor Bob Metcalfe this week is starting to throw around a new date for Terabit Ethernet: 2015. He's also suggesting that this be done in a non-standard way, at least at first, saying it's an opportunity to "break loose from the stranglehold of standards and move into some fun new technologies.""
Submission: IBM optical chip zips huge files using littlepower by Anonymous Coward
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
So that would make it use about... (Score:5, Funny)
Re: (Score:2, Interesting)
Re: (Score:2, Funny)
Re:So that would make it use about... (Score:5, Funny)
Start with a 100 Watt bulb
Divide by 7, which is the number of watts necessary to properly illuminate a square foot of floor space.
This gives roughly 14.28 square feet able to be illuminated.
Divide this into 2.1 million sq ft [nps.gov], the amount of square feet in the Library of Congress (USLOC).
This tells us that 147,000 watts are necessary to illuminate the US Library of Congress.
Divide by 1.09951163 × 10^13 bytes [google.com], the amount of storage per unit of USLOC. [jamesshuggins.com]
This tells us that 1.33 x 10^-8 bytes are illuminated per watt
Multiply by 7GB (7,516,192,768 bytes), which is the number of gigabytes of printed material that can be properly illuminated by a 1-watt bulb.
Answer: 100.4
So you were close.
Parent
Re:So that would make it use about... (Score:5, Funny)
Parent
Re: (Score:2)
Re:So that would make it use about... (Score:4, Funny)
Parent
Re:So that would make it use about... (Score:4, Funny)
You're a Mac user, aren't you.
Parent
Juice! (Score:5, Funny)
That's like... 100 Watts!
Unless you go compact florescent. Then its like 15watt.
Re:Juice! (Score:5, Funny)
"He was as tall as a six-foot-three-inch tree"
"The red brick wall was the color of a brick-red Crayola crayon."
"John and Mary had never met. They were like two hummingbirds who had also never met."
Parent
Re:Juice! (Score:5, Funny)
Parent
Re: (Score:2, Funny)
Re: (Score:2)
*waits for the comment "it's the same 100 watts..."*
Re: (Score:2)
How much power? (Score:5, Funny)
Re: (Score:2, Funny)
Re:How much power? (Score:5, Funny)
Ah, the never tiring slashdotter pick up line
Parent
Re: (Score:3, Funny)
"Want to see my rare collection of Star Trek memorabillia" would be a more typical pickup line.
Server use? (Score:1)
I know I'm interested!
What's with the summary? (Score:2, Insightful)
Re:What's with the summary? (Score:4, Informative)
My bet is on someone using the word "zip" somewhat like Ballmer used "squirt", i.e., to send quickly...
Parent
Re:What's with the summary? (Score:4, Funny)
Please, Mr. Ballmer, don't squirt me!...
YUCK!
The mental image of Sweaty MonkeyBoy and the work squirt should never be in the vicinity of each other. It is an abomination.
Parent
Re:What's with the summary? (Score:4, Interesting)
Parent
Re: (Score:1)
High-speed networking takes a non-trivial amount of power to drive the signals, be they electrical or optical. Especially for optical devices, the efficiency in getting that power onto the transmission medium is low. At high enough speeds, there are also a lot of high speed transistors switching in the control logic that use power for the same reasons as your CPU. So, they've improved the power consumption in these and other areas.
My quibble is with "IBM Optical Chip Zips Huge Files". Made me think IBM had some specialized compression photonic chips.
Re: (Score:2)
As for equipment, Optical switches use a couple Watts, optical routers aren't that bad, I can spec a system of about 2.5Tbps (Juniper T-se
Re: (Score:2)
The inefficiency, AIUI, is in the electrical -> optical energy conversion, not anything in the purely optical domain. If you need 100mW of optical power, it takes a lot more electrical power to get it. I don't know exact numbers off hand, or even how much power is typical (I'm not a networking guy, but I've looked at diode lasers for other purposes before).
I assumed there wasn't any discrete circuitry beyond perhaps the optical component and a temperature controller if there is one. It's the ASIC I
Re: (Score:2)
Re: (Score:2)
This story was one of the first things I looked at this morning, and I misread the title as "IBM optical chip zips huge flies" which sounded kind of weird in a cyborg sort of way.
And now parent post talks of zipping huge flies, which sounds kind of weird with a hint of goatse.
<!--
note to self:
Don't read slashdot before coffee
-->
Re: (Score:2)
A hundred watts, that's all good and well, but what does it have to do with zipping huge files? Or am I reading impaired?
No, you're reading fine. The problem is that ScuttleMonkey (or whomever wrote the headline) is a fucking illiterate moron. They used the verb "to zip" to mean "send", when it has no such meaning in regular speech. Now, it's usually acceptable to bend meanings for words and use their context as a clue, but in this case the verb "to zip" already has a common meaning in the computer world (i.e. to compress using the ZIP format developed by Phil Katz), so it's contextual meaning is overridden by its common mea
Scuttlemonkey (Score:2, Funny)
IBM Rocks! (Score:5, Insightful)
Even though a lowly peon like myself can barely aspire to ever own much real IBM hardware, I have to say they really make some great stuff. Since my P20 monitor finally died, all I have now is an IBM Z50 Workpad, which is a pretty sweet little thing.
I had a RS/6000 briefly, I experimented with running Debian on it. It was some impressive metal, but AIX ran circles around Debian and the graphics was unsupported in Linux. I sold it for more than I payed for it and kept the P20 monitor for free. I ran that monitor for about 5 years.
IBM hardware has always been esoteric, fantastically expensive, and of supreme quality; however, they are just a bit out of touch with regular lusers. For instance, why can't we buy a workstation with a CELL chip even now? We know it could run Linux, easily. Why are we forced to fool around with PS3 consoles when Big Blue could be making the next best thing since the IBM PC?
I'd seriously consider spending $5k for a spiffy IBM cell box running AIX or Linux as long as it could run a PCIe OpenGL card. Heck, I'd take it if it came with OS/2 even!
Re: (Score:2)
Re:IBM Rocks! (Score:5, Insightful)
Anyway, I agree with the OP, this is a killer chip for many many of the applications we use today, and IBM should talk Lenovo (or, oh please, SUN) into selling a Cell-based Linux (or, oh please, Solaris) workstation. That would be ridiculous for software development if it had a Java SDK to go with it.
Parent
Re: (Score:3, Insightful)
Software that's custom made for the cell chip barely exploits all the parallel compute power, so I doubt gcc would compile Linux to make use of it (if it can even compile to cell, which I'm not sure of).
IOW, you have no idea what you're talking about. :-) There are out-of-the-box distributions of Linux for Cell platforms (Yellow Dog, Fedora, Ubuntu even), and the gcc supplied in IBM's SDK is quite happy to compile for the PPE and SPE cores. Yes, I've played with all this on the PS/3. PCI and Blade hardware is available from Mercury and IBM, but it's pricey... you could drop one of Mercury's Cell PCI cards into a small IBM xSeries...
Anyway, I agree with the OP, this is a killer chip for many many of the applications we use today, and IBM should talk Lenovo (or, oh please, SUN) into selling a Cell-based Linux (or, oh please, Solaris) workstation. That would be ridiculous for software development if it had a Java SDK to go with it.
You're both half-wrong. Yes, you can get Linux running on a Cell just fine. No, software that was not written specifically with the Cell in mind (read: almost everything) uses the co-processors (SPU/SPE whatever) anywhere near capacity. And in fact, almost all of the software that is written for the Cell processor still doesn't use the co-processors anywhere near capacity. It is a very difficult platform to program for, and because of the inherent design of the Cell, it simply performs poorly compared
Re: (Score:2)
You're both half-wrong. Yes, you can get Linux running on a Cell just fine. No, software that was not written specifically with the Cell in mind (read: almost everything) uses the co-processors (SPU/SPE whatever) anywhere near capacity. And in fact, almost all of the software that is written for the Cell processor still doesn't use the co-processors anywhere near capacity. It is a very difficult platform to program for, and because of the inherent design of the Cell, it simply performs poorly compared to SMP for a large class of problems. And by difficult, I mean that you have to sit there trying to figure out how to fit your 17k of code and 512k of data into a unified 256k buffer (information theory comes in handy), because going outside the local buffer and using DMA is not only a huge pain in the ass to code up, it is also a huge performance hit. Programming for the Cell is a step backwards from the ideal computer science goal of abstracting the hardware from the code.
I work in the games industry, and I recently saw the performance timer graphs of a very popular racing game that was very recently released for the PS3, a second-generation PS3 title. It was using the co-processors at about 10% of their capacity, and that only came in regular-interval spikes. And this is a piece of software that the Cell was specifically designed to run.
Interesting to hear a perspective from the gaming industry. Disappointing results though, as someone who's played with the Cell in an academic environment.
Re: (Score:2)
Actually, you just haven't looked hard enough. :-) You can buy a QS21 "Cell Blade" for $9,995 [ibm.com]. Add $1949 for a BladeCenter S Chassis [ibm.com] and you're set.
You can also purchase these items used for a significant discount if you look in the right places [google.com].
ARRRR! (Score:2, Funny)
How to stops the retarted submissions? (Score:1, Insightful)
'Zips huge files' (Score:5, Insightful)
Re: (Score:2)
This is a TECH news site, where the readers can be assumed to have a certain minimal technical acumen. The editors MUST have a basic familiarity with the jargon and glossary of technical terms of the computer field. For example, in computerese "ZIP" doesn't specifically mean 'go fast' - it refers to a specific method of data compression or the idea of compressing data generally.
To not understand that suggests a level of editorial competence in this field below that of, oh, say Us magazine. Not
Am I the only one... (Score:2)
Maybe we would need a point of comparison.
Re: (Score:2)
This would be equivalent to 125mW per Gbit ethernet port.
IIRC, current implementations are a factor of 10-30 above that value.
This Story Raises The Burning Question (Score:5, Funny)
No one knows. Those who try keep getting electrocuted when their tinfoil hats make contact with the socket.
Re: (Score:3, Funny)
You'll learn that
1. Change light bulb
2. ???
3. Profit!
Also, they'll want to know if the light bulb runs Linux, and ask you to imagine a Beowulf cluster of them.
Re: (Score:2)
Ahhh.... true, it is so.
90's Flashback (Score:3, Interesting)
Re: (Score:2)
1. It's not lossless.
2. Someone patented it, tried to gloss over the first problem and priced it out of the market.
Not entirely amazing (Score:2)
Dad: "That's 100 watts to you and me, Billy"
Billy: "Wow!"
Bad Measurement.. (Score:2)
Well dang. (Score:2)