Slashdot Mirror
Frozen Chip from IBM hits 500 GHz
sideshow2004 writes "EETimes is reporting this morning that IBM and Georiga Tech have demonstrated a 500 GHz Silicon-germanium (SiGe) chip, operating at 4.5 Kelvins. The 'frozen chip' was fabricated by IBM on 200mm wafers, and, at room temperature, the circuits operated at approximately 350 GHz."
Still hope for the G5 Powerbook then!
does it run linux?
I think that speaks for itself.
Pain lasts, kid. Its how you know you're alive. Sometimes I think this growing up thing is just pain management-TheMaxx
How long before I can get a kit like that for my P4?
and that is to IMAGINE A BEOWULF CLUSTER!
Oh, you thought I had something insightful to say? Nope ^_^
By comparison, 500 GHz is more than 250 times faster than today's cell phones, which typically operate at approximately 2 GHz, according to the organizations.
Wow, I didn't realize that cell phones typically run at 2GHz+
You create your own reality - Leave mine to me.
a compile farm of these :D
http://chimpbox.us
Suit has been filed against a well known business and a school for violations of Moore's law.
This space for rent.
It's interesting, but wouldn't it be better to just use two of these chips at room temperature, rather than spend time/money/space on cooling the chip to 4.5 Kelvins?
Imagine a beowulf cluster of these!!!11
the real step is pondering WHETHER IT CAN RUN LINUX!
Obviously in soviet russia linux ponders you... or... something...
Is this enough for Vista?
TFA wasn't clear... I assume this wasn't running a larger fully synchronized CPU with memory and multi-level cache at 500GHz, but is instead running a smaller number of transistors at that speed?
Or have they just been fabricated to demonstrate that they can attain high GHz rates?
Everybody knows you can't trust ghz ratings. I mean, a 3.2 ghz athlon is clearly a bit faster than the 3.2 ghz pentium. Right? Oh, wait, you said .5 TERAHERTZ?!?! Oh, yeah, then I'll take one of those please. And that big ass freezer, thanks.
I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
AMD today announced the launch of the Athlon XP 500000+. The chip has a "stock speed of around 3.0 GHz, but is named for it's IBM equivalent".
Arggg read the article they said they wanted to test the theoretical limits of these chips. They know speed increases with temperature. They wanted to know how much.
Ooo man the floppy drive is broken. No wait. The computer is just upside down.
Is capable of running Windows Vista
Slashdot Burying Stories About Slashdot Media Owned
... preparing for Vista already I see
1. Will it run Linux?
2. Will it run MAME at full speed?
3. Will Word load up any faster?
Have I forgotten any?
Summation 2
all i need now is to get one of these working at room temperature for less than the cost of my current house and then convince microsoft it might be a good idea to do a vista driver for it and then maybe, just maybe vista will boot in under four minutes. happy day!
Was it blazingly fast? Is this destined to be the new hot item this Christmas? Will IBM come under fire from companies like AMD and Intel?
Hrm... a batch of transistors that'll relay at clock speeds of 350Ghz. Then they tossed on their P4 cooler and watched it superconduct. Why am I not surprised at 500Ghz? At 4.5K, it's clearly superconducting. And the phone comparison... I like EE Times, but that writer needs to be shot. The editor deserves a slap on the wrists for letting it in (unless they're referring to some strange property of phones). "For the first time, Georgia Tech and IBM have demonstrated that speeds of half a trillion cycles per second can be achieved in a commercial silicon-based technology, using large wafers and silicon-compatible low-cost manufacturing techniques,[and absurd cooling that allows us to leverage the properties of superconductivity]" (fixed). IBM: Design it Today, Figure out what the hell we're going to do with it 7 years from Tomorrow. (And yes, I'd get a microprocessor designed with these ubersistors).
"I've spent my whole life figuring out crazy ways to do things. It'll work." -- Montgomery Scott, "Relics"
Do not place one of those "thin, mint wafers" on Mr. Creosote's tongue.
You are welcome.
Get thee glass eyes, and, like a scurvy politician, seem to see things thou dost not.--King Lear
350 * 1024 * 1024 * 1024 (375 809 638 400) cycles per second divided by the distance light travels in a second (299 792 458 000 mm / s) is 1.2 mm. Just thought I'd throw that in.
Religion is what happens when nature strikes and groupthink goes wrong.
Brings a whole new meaning to the engineers traditional sigh of relief
**Life is too short to be serious**
Stroller.
Does it still take thirty seconds to fire up Acrobat Reader?
Do you need a pair of them for Oracle 9i?
Is it on the minimum spec for Vista Ultimate?
I'll get me coat.
The problem with socialism is that they always run out of other people's money. - Margaret Thatcher
Since these temperatures only occurs naturally in space, why not build a super, big cluster of these things, hook them up to a satallite and launch it into orbit.
So we have a chip that operates at the same frequency as the radiation that it emits as heat. My brain hurts!
I want a dual core version! That way I'll be able to play Duke Nuke Em Forever on Windows Vista.
In the not too distant future, next Sunday A.D.
You do know that jokes are meant to be funny, and don't have to be factually accurate, right?
dragonhawk@iname.microsoft.com
I do not like Microsoft. Remove them from my email address.
From TFA - my emphasis
IBM (Armonk, N.Y.) and Georgia Tech (Atlanta) claimed that they have demonstrated the first silicon-based chip capable of operating at frequencies above 500 GHz by cryogenically "freezing" the circuit to minus 451 degrees Fahrenheit (4.5 Kelvins).
Is anyone in the scientific world still seriously using Fahrenheit? What happened to si. Ok, for old farts like me it's nice to have the weather in Fahrenheit because I know that 60 is a nice spring day, 70 is hot and 80, phew, what a scorcher, but if I'm doing science I would no more use Fahrenheit than I would measure distance in poles.
init 11 - for when you need that edge.
If this is ever planning to come home, all you case modders had better start working on a cooling system that'll take it down that far.
In other words, at these temps, it's not very practical for the end user.
First: Nice. I bet Pixar and Walmart will want a couple of these babies. Second: 2GHz chips in cell phones? No way, it's more like 450-500MHz scalable chips in those brick sized cell phone PDAs, and like 200-300 scaleable chips in regular cell phones. A processor operating at 2GHz in a cell phone would likely not only melt, or atleast damage the thing from the heat produced, but also make short work of the batteries. In fact, I'm quite sure, that if you removed the active cooling from a 2ghz processor, and instead of putting a really big copper heatsink on it, placed a lithium battery on it, it would either explode, or burn like magnesium. At the very, VERY least, the chip would go the way of the dodos, and the battery would degrade and lose it's ability to hold current. Am I talking out of my ass?
Will it be fast enough to handle Vista?
LK
"Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
"The achievement is a major step in the evolution of computer semiconductor technology that could eventually lead to faster networks and more powerful electronics at lower prices, said Bernard Meyerson, vice president and chief technologist in I.B.M.'s systems and technology group. He said developments like this one typically found their way into commercial products in 12 to 24 months."
I think I'll put off buying a new computer for a couple of years or so...
NEWS ITEM: Computer industry collapses due to consumers putting off purchases in anticipation of 500 GHz computers coming real soon now.
E Proelio Veritas.
... Not to RUN Duke Nukem Forever, of course, just to run the development environment at a decent speed, so that we may have a chance to actually play the finished game (or at least a decent beta, or even a playable pre-alpha, for christ's sake) before we die.
-- javaDragon is an instance of JavaDragon.
That's a pretty odd microwave then, since most of them operate at 2.45 GHz, which is chosen because of the way it causes liquid water molecules to vibrate. See this article, particularly the graphs showing dielectric temperature as a function of frequency. It's pretty clear that a 10GHz microwave oven would be a lot less efficient at heating water than a conventional 2.45 GHz one, although I suppose you could choose a multiple of 2.45GHz and probably still have a functional product.
Overall, unless your goal was to build a miniature microwave (a 21st century E-Z Bake Oven?), I don't know why you'd want to use 10GHz instead of 2.4Ghz ones. The tolerances of parts in the magnetron and waveguide would have to be much tighter, I think, and this would almost certainly cause it to be more expensive.
"Ladies and gentlemen, my killbot features Lotus Notes and a machine gun. It is the finest available."
Sadly, even my own school's press release says the chip operates at 250x cellphone speed. But the press release has much more techincal info then the EE Times article http://gtresearchnews.gatech.edu/newsrelease/half- terahertz.htm/
That would be why it was crap, then.
I wonder if it can be overclocked? And if so, by how much?
E Proelio Veritas.
Radiation is a big issue for computers in space. Shielding equipment is heavy (=expensive to get up there), and the smaller (and faster) CPU's ICs become, the more susceptible to radiation they become.
There's a reason why NASA is trying their best to get their fingers on ancient CPUs.
We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
The temperature at which a SiGe chip freezes.
Yeah, incompetence is my guess here also. Most cell phones are running around a 500Mhz chip operating at a 2-2.4 Ghz transmit frequency.
Now saying that the chip is running 1000X faster than the chip in your cellphone would have been a good comparison, or some quote about the average PC chip being 2Ghz & this being 250X faster would have been good comparisons, but comparing the chip to the transmit frequency of the cell phone was stupid.
I wonder if we'll have to wait for Sony to put these in the PS3
Didn't you ever think that if you had a digital signal entering your cell phone at 2.4 Ghz, you'd need a transistor in there that could switch at least that fast? You realize that there are other types of chips than microprocessors, right?
Could this chip going "break" the crypto community for a while? WWBSD?
"I hate to advocate drugs, alcohol, violence or insanity but they've always worked for me" - HST
Nope. It's just slashdot posters taking the story out of context. Go actually read the article and notice that it doesn't say anything about PC chips or microprocessors.
Do you think that 2.4Ghz digital transmission is generated by magic?
The problem isn't that the writer is incompetent, it's that he assumed his readers weren't.
OMGFramerates!! FRAME RATES!!!!!11!1!12@3#
*ahem*
Sorry about that, Pavlovian reaction...
The colder, the faster we can make computers run..right?
So why don't we have supercomputers located on the Artics yet? It won't be a huge problem to get data-transport there. And the natural cooling will be very cheap and energy efficient.
My blog: http://www.redcode.nl
According to Microsoft (TM,C,BS), this will finally meet the minimum requirements for Windows VISTA when it ships in 2006, er. 2007, er. 2008.
EE as in Electrical Engineering!
Their readership would be mostly EE's and other technical types, I would think. Which makes the comparison between a cellphone's RF output and a processor clock even more ridiculous.
Remember "News for Nerds, Stuff that Matters"? Help make it a reality again! http://soylentnews.org
Wait a minute! These things can run at 350GHz (o_o) at ROOM TEMPERATURE! The fancy cooling is all nice and good, and 500GHz... well congratulations!
But heck, I'll take one even without the cooling.
Arggg read the article they said they wanted to test the theoretical limits of these chips. They know speed increases with temperature. They wanted to know how much.
The word "increases" does not mean what you think it does.
Coding with assembly is like playing with Legos. Coding an application in assembly is like building a car with Legos.
Because these dials go to 4.5 Kelvin.
Does it run linux? Immagine a beowulf cluster of these!!! 500GHz? How much is that in bogoMIPS?
nice
The chip is codenamed Detritus, right?
First, mobile phones do have extremely high frequency chips in them. They have to in order to recieve and process the high frequency signals they deal with. Those high frequency chips are a fairly large part of their power draw, too - yet their draw is *tiny* compared to even the simplest CPU of that clock. Remember that clock speed means very little without a consideration of the number of transistors on the chip, energy leakage rates, and lots more I know nothing about.
/., this chip is a very fast very simple unit - not a large microprocessor. I'd guess they're looking into ultra-high-speed signal processing (hence the mobile phone analogy) rather than computer CPUs here.
You're making the erroneous equation that "chip" == CPU, which is far from the case. A phone's CPU may be clocked much lower. Even if it's integrated with the RF chip (I'm not sure this is ever done, is it?), the RF processing parts will be clock-multiplied or the CPU parts will be clock-divided to ensure sensible running frequencies.
I think you'll also find that, contrary to the assumptions made by most posters here on
I can't imagine what it would take to design a microprocessor using this technique. At 500GHz, a quarter-wave antenna is only 150 nanometers. If you imagine a square wave at 500GHZ, the next 3 Fourier terms imply quarter wave antennas of lengths of 50, 30, and 22 nanometers. Designing a cpu where you have to allow for transmission effects on the nanometer scale will be extremely challenging, I'd imagine.
Weaselmancer
rediculous.
No, what you need is a signal generator that produces a 2.401 GHz signal and a mixer to produce a beat frequency. Then, you process that much slower signal. You don't work with a 2.4 GHz signal.
And over there we have the labyrinth guards. One always lies, one always tells the truth, and one stabs people who ask t
Who the hell marked this as interesting?!?! Hertz is an SI unit of frequency, and as such prefixes follow a base ten scheme (i.e. Megaherz = 10^6 Hz, Gigahertz = 10^9 Hz) not a base two scheme (Megabyte = 2^20 bytes, Gigabyte 2^30 bytes)
350 Ghz at room temperature (warmer)
Clearly lower speed at higher temperature. What's up with the mods today?
the more they over-think the plumbing the easier it is to stop up the pipe
I am wondering what kind of rf noise this would make on the 300+ghz ham radio bands
It takes two to make a...
It takes two to make a...
It takes two to make a THz, YEA!
It takes two to make it out of sight!
:T:R:A:N:S:
Will you able to overclock the retail version?
I know a lot of people here are irked about the cellphone comparison, but did you stop to consider that this may not be a digital chip? Transistors can also build analog amplifiers, mixers, frequency multipliers, and other lovely gizmos. Comparing the frequency of this chip to the RF frequency of a cellphone may be entirely appropriate.
I have suffered from being misunderstood, but I would have suffered a hell of a lot more if I had been understood.
Kind of makes me regret eating some last night
If we can put a man on the moon, why can't we shoot people for Apollo-related non-sequiturs?
Now only if they had thought of it earlier, they could have stopped all that Pentium melting stuff.....
Maybe?
"You will do foolish things, but do them with enthusiasm." - S. G. Colette
Now imagine a beowulf cluster of these!
And in other news, apples and oranges usually taste different.
The only question about computer speed that is important is, "Is it fast enough?" Of course, "fast enough" may change over time, and anytime you come up with a faster processor, some company like Microsoft will succeed in loading it down with bloatware. But I've got a customer who runs his company on software that I wrote for him 15 years ago, and the only reason he ever upgrades his hardware is because something breaks that is no longer available. Otherwise, the 8MHz 286 system would have been perfectly adequate.
Concealed Handgun License Courses in Plano, Texas
Hey idiot, you realize it's an analog modulated RF signal that gets picked up by the receiver? There's no switching involved in receiving. None. You might make a case about the diode mixer being a switching device but it uses the analog RF input from a linear amplifier.
So uh... is it a general purpose machine, or has it got an instruction set like brainfuck? No point in running at 500ghz if it's going to take 10,000 clock cycles to perform addition...
I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
First, mobile phones do have extremely high frequency chips in them. They have to in order to recieve and process the high frequency signals they deal with.
Rubbish. You don't need digital circuitry to handle the 2.4GHz signal. You use standard analogue RF circuitry and only get digital once you've demodulated it.
Ydco co
Simple calculation: speed of light is 3*10^8 m/s, frequency is 5*10^11, so in one clock you can travel 3/5 millimeter at the speed of light. But electrical signals in copper and semiconductors travel at approx. two third of the speed of light, so in one clock an electrical pulse can travel roughly 0.4 mm. Your processor has to be way smaller than this, because all routes signals can take from anywhere to anywhere must be shorter than this distance. And let's forget entirely about phase-problems, synchronization, ... These things are now already causing difficulties in chip-design, at current speeds where signals can travel several centimeters.
I honestly do not expect that processor speeds will increase very much anymore. The past however has time after time proven everybody wrong that made that statement.
int main(void) {while(1) fork(); return 0;}
IBM has actually done this kind of work for a while, but unfortunately I don't think we are talking about CPU chips. The articles about this that I have read before have been about RF chips, hence the reference to cell phones. The author of the article apparently doesn't get it or neglected to mention this. Still an achievement but I doubt you'll be seeing this technology used in CPU's any time soon. It may mean more spectrum for the FCC to dole out in 7 years however.
Sure, we engineers can use Fahrenheit if it's appropriate. And it would be a reasonable unit if we were talking about temperatures in the range of 0 F to 450 F. Those are temperatures that the average person can experience firsthand in their home (freezer to oven).
But these chips were chilled down near absolute zero. That's a physically special temperature, but you'd never guess that from the Fahrenheit scale. What's the difference between -450 F and -460 F? The difference is not 10 degrees. The difference is that one is physically possible and the other is not. Minus 460 F would be below absolute zero.
So if you're talking about temperatures near absolute zero, the sensible units are K or R. This is especially true if you're talking about chilling to within fractions of a degree of absolute zero. A value of 0.01 K is meaningful. Stating a value of -459.57 F would make me question your understanding of significant figures.
AlpineR
You know, someone somewhere is dying to get their hands on that cooling rig so they can overclock the hell out of their Celeron..
you're right, of course, in this instance it is a "real" giga, meaning a billion cycles per second.
The terahertz band is the holy grail of telecommunications because at such high frequencies, we can begin to test communications based on gravitational waves instead of electromagnetic waves. This represents significant progress toward that end. Gravitational waves potentially are not limited to the speed of light, which might pave the way to real-time satellite communications with no lag or communications with operations on other planets with significantly shorter wait times.
"a 500 GHz Silicon-germanium (SiGe) chip, operating at 4.5 Kelvins."
Imagine how fast it would run if they got it down to 0 Kelvins!
I just wanted to point that out, I think some posters are thinking about it incorrectly: "The 500 GHz mark was the goal when Feng and UI colleagues received a $2.1 million, five-year grant for the project from the Defense Advanced Research Projects Agency in October. In contrast, the transistors inside the central chip of a powerful personal computer run at around 50 or 100 GHz, Feng said. The fastest that such a chip runs as a package is currently around 3 GHz." http://www.news-gazette.com/news/local/2003/01/24/ fastest_transistor_made_at_ui/
In addition, University of Illinois broke 600 Ghz last year.
http://www.physorg.com/news3662.html
"The speeds quoted in this article are maximum rated *switching* speeds of a single transistor. Synchronous logic designs of the type found in microprocessors involve synchronous cells (known as flip-flops) and asynchronous gates providing boolean functions on the signals passing between flip-flops. The maximum rated frequency of any design is limited by the slowest path between flip-flops and this is what the clock signal will be set at.
As the paths between the clocked flip-flops are typically anywhere between 2 and 10 logic cells deep and with each one comprising 10's of transistors (usually in complementary configuration to aid switching speed), the overall figure for an ASIC design such as a uProcessor would be at least 2-4 times slower than the maximum transistor switching speed (it's not quite cumulative, because as one transistor starts switching, the voltage at the at the `gate' of the next one has already started changing causing it to start conducting, and so on). I also have a suspicion that there would be other real-world constraints such as cross-talk (noise between transistors) and thermal problems. I'd hazard a guess that a production-quality chip would be somewhere in the region of a tenth the speeds quoted here!
However, these new materials and structures still make for an impressive speed gain over traditional Silicon CMOS designs." (The speeds quoted in this article are maximum rated *switching* speeds of a single transistor. Synchronous logic designs of the type found in microprocessors involve synchronous cells (known as flip-flops) and asynchronous gates providing boolean functions on the signals passing between flip-flops. The maximum rated frequency of any design is limited by the slowest path between flip-flops and this is what the clock signal will be set at.
As the paths between the clocked flip-flops are typically anywhere between 2 and 10 logic cells deep and with each one comprising 10's of transistors (usually in complementary configuration to aid switching speed), the overall figure for an ASIC design such as a uProcessor would be at least 2-4 times slower than the maximum transistor switching speed (it's not quite cumulative, because as one transistor starts switching, the voltage at the at the `gate' of the next one has already started changing causing it to start conducting, and so on). I also have a suspicion that there would be other real-world constraints such as cross-talk (noise between transistors) and thermal problems. I'd hazard a guess that a production-quality chip would be somewhere in the region of a tenth the speeds quoted here!
However, these new materials and structures still make for an impressive speed gain over traditional Silicon CMOS designs." (http://www.physorg.com/news3662.html)
....For Duke Nukem Forever.
This article has more of the details correct. http://www.newscientisttech.com/article.ns?id=dn93 68
Slashdot +1 funny -4 Insightful +1 informative -2 Redundant
Karma: Somewhere between SCO and Microsoft
Sure lots of scientists use SI (although depending on the field they may use cgs instead), but many engineers in the US use the standard American units.
There are several reasons for this: 1) tradition, 2) tooling (especially on the manufacturing scale) is hard to change, and 3) engineers can handle the simple math required to convert between units.
Plus some units should never change. Who wants to know an automobile's horsepower in kilowatts?
Well, the bandwidth of the digital transmission isn't 2.4 GHz therefore one wouldn't need a 2.4 GHz DSP to generate the signal. Knowing little to nothing about the inner workings of cell phones, I would imagine the cell phones produce a digitally modulated signal at baseband and then using analog mixing and filtering to shift the baseband signal to RF.
That's only an over-clock of around 42%. My old Celeron 300a ran 500 MHz on air cooling, that's a 66% over-clock!
Get back to me when you hit 583 GHz, IBM!
in other news,ken kutaragi Announces that Playstation 3 Rev 2 will use a 500 Ghz SiGe Cell processor,and that will make the gigant crabs more real than the real life and that PS3 will suck you to inside the television where you will live a matrix like experience with toy story like graphics and yellow ducks
Coils are bad for high-speed circuits. They generate inductance, i.e. there's some energy stored in the magnetic field induced by the flow of electrons, and this energy resists changes in current.
If you think resisting changes in current is good, remember that current doesn't continually flow in these circuits, but instead ebbs and flows to charge/discharge load capacitance. So we essentially have resistance to overcome to start charging/discharging that cap.
Disclaimer: I only have a B.S. in Comp. Eng., so some of that may sound like BS to those who know way more than I do...but I'm pretty sure I got the explanation right.
:(){
who mods down people liking a post?
at first I read "500mhz" and I was like, "don't they run at 2.4ghz now? Is this a dupe from like 3 years ago?" then I read it again and did one of these O.O, then I read some of the article and relegated to one of these o.0.
disclaimer: I've been known to store numbers in my ass for which to dig out when quantities are required.
You're both wrong, although well intentioned. Saying it "increases with temperature" implies that as temperature increases, so does the clockspeed. Saying that it "decreases" with temperature decreases, so does the clockspeed, which is really the same thing, and also wrong.
It doesn't increase or decrease WITH temperature. It increases or decreases INVERSELY TO temperature.
I put the 't' in electrical engineering.
""a 500 GHz Silicon-germanium (SiGe) chip, operating at 4.5 Kelvins.""
"Imagine how fast it would run if they got it down to 0 Kelvins!"
Imagine how fast it would run if they got it down to -5 Kelvins!
http://lkml.org/lkml/2005/8/20/95
Does liquid helium really cost $24/gallon? If so, we might want to get ahead of the curve and see if we can run our cars on it.
Software sucks. Open Source sucks less.
There has to be code before it can be compiled...
Rob
After waiting around for what seemed like forever, I got my hands on one of these systems. I wiped off the stupid proprietary OS and installed a much leaner and faster Debian Sarge. I have been kicking ass playing Quake 3 through wine. It's almost as fast as native windows.
Hundreds of thousands of reporters found dead all over the world in a yet unexplained wave of shootings !
More details in our next edition !
Huh ? Wha..
BANG!
May contain traces of nut.
Made from the freshest electrons.
Why are we STILL waiting for 10GHz CPUS ?????
As said the thing may have its place in kinda fast real time processing of steady input, but that input would have to be supplied at a much greater rate. Until everything down the line from user input to disk/display output is quick enough to move that much data this proof of concept device is just an entry in the Guinness Book.
I'll be your candy shop of infinite deliciousity if you'll be my discotheque of endless rump-shaking.
And jeeze who knew that cellphones ran on 2Ghz processors nowadays... doh!
Well, seriously, it's a matter of perspective. The other day someone was presenting his results at our group meeting, and one of the post-docs looked at his plots:
What temperature is that at?
Errrh, 4 Kelvin.
Ohhh, it's high-temperature measurements!
The guy usually works in the milliKelvin range, so I guess it really was high-T for him. A couple of the rest of us exchanged glances...
Any sufficiently advanced libertarian utopia is indistinguishable from government.
C = 300,000,000 m/s. Ooops. Good grief but I need some coffee.
Weaselmancer
rediculous.
Considering the speeds that average at about 2GHz on current processors even at room temperature this is running 175 times faster. With this increase the drawbacks of interpreted languages and languages run on virtual machines, such as Java, will be null and void. I can't wait until this processor is mass produced, and available at a reasonable price, but at that point Windows will have system requirements that make it seem just as slow as the current processors.
The greatest of all weaknesses is the fear of appearing weak. ->JB Bossuet, Politics from Holy Writ. 1709
Except for extremely high end test equipment, I do not know of anything that performs signal processing at sample rates on the order of 1-2 GSPS (gigasamples/second) or higher.
Even modern cell phones are *at most* doing direct IF sampling and IF signal generation. Upconversion to/downconversion from a 1-2 GHz carrier frequency is still done in the analog domain. Most likely, upconversion to/downconversion from IF is also done in the analog domain, with the only digital portion being baseband processing. Direct IF sampling/transmission is still rather expensive, too expensive for your average cell phone.
Unfortunately the article is now Slashdotted so I can't tell whether this 500 GHz chip was RF circuitry operating at a 500 GHz carrier frequency (20-30 GHz plus is common nowadays in this domain), or digital circuitry operating at a clock speed of 500 GHz, and if it was digital, how complex a circuit it was. It's much easier to clock a simple circuit at very high frequencies than a complex one like a CPU.
retrorocket.o not found, launch anyway?
Where's the Doom3 frame rates?
In my opinion it is big chance for development AI, fast large neutral networks etc.
Good article but nothing beats a picture from This article
certainly, there are potato chips, corn chips, chocolate chips, ice chips, even banana chips.
"22 astronauts were born in Ohio. What is it about your state that makes people want to flee the Earth?" Stephen Colbert
You're probably right. It's likewise been a while since I've looked at the math closely. If you go to the page I linked in my original post, it probably has the answer on it somewhere.
"Ladies and gentlemen, my killbot features Lotus Notes and a machine gun. It is the finest available."
"500 gigahertz! 500 gigahertz! Great Scott!
:D
"How could I have been so careless? 500 gigahertz! Tom, how am I gonna generate that kind of power? It can't be done, can it?"
Ahh slashdot
~--~
Do not mind the one with the crazy, for he is sane
Interesting but I can not see much use in a 350ghz rf system. Talk about line of sight!
One word: Radar. I'm no RF engineer, but IIRC, a 300GHz signal has a wavelength of 1 millimeter, which would make it possible to detect radar reflective objects that size, in theory. That would have to be the holy grail of radar technology.
If one could resolve a signal that has millimeter or sub-millimeter resolution from a distance, it would be a breakthrough in military radar systems. It would make avionics not only be able to tell a fighter pilot exactly what kind of aircraft he was engaging, but also tell him what kind of ordinance the aircraft has mounted to external hardpoints, what the aircraft's attitude is, etc.
It could also be used to precisely detect incoming ordinance: imagine a mobile Phalanx type system that could detect the direction enemy fire was coming from, and possibly counter the effects of RPGs, missiles, and mortars!
A system that could react fast enough would be able to protect tanks from armor piercing missiles or DU rounds by shooting a projectile (or many) to intercept the incoming threat. Also, such a system mounted on a HMMWV could shoot RPGs down as they are in flight, or detect where enemy small arms fire is coming from and instantaneously direct fire to that location, and it might be able to detect firearms and other weapons concealed in the clothing of insurgent forces hiding in a crowd of non-combatants!
In addition, such technology would have civilian uses like supplanting screeners at airports, guidance of autonomous passenger vehicles, computer vision, it could be used for all kinds of applications.
Constitutional rights may be respected, repealed, or modified; but they must never be ignored.
Just imagine a beowulf cluster of these
Redundant by one minute...
HAW HAW!!!
From wikipedia entry on Moore's Law: And one (albeit imprecise) measure of computing power is clock speed. Certainly if one held everything else constant, and solved all the attendant problems like heat dissipation, etc. and increased clock speed of a CPU from 2.5 GHz to 500GHz, one would be greatly outpacing Moore's Law.
...the future crusty old bastards are already drinking the Kool-Aid.
My cellphone phone does not operate at 2.4GHz, it's braodcast frequency is 2.4GHz.
Am I to understand that the chips in the story are CPUs operating at 500GHz ?
Has anyone but myself thought of the implications this will have on encryption and security... or a lack there of?
As I'm sure most of you know, SHA-1 has been proven to show signs of collisions on todays computers. http://rsasecurity.com/rsalabs/node.asp?id=2738
Now imagine what would be possible with 500GHz. Amazing!
IBM engineers have just posted on the official Elder Scrolls forums regarding their "out of this world Oblivion frame-rates." One was caught on record as saying "CPU-limited my ass!" I guess all it takes is an artic-chilled CPU and you CAN play Oblivion smoothly.