DIGIT-ARC read-only archive · snapshot: July 23, 2026

500 Ghz Cpu. No Kidding

23 posts · originally from https://geek.digit.in/community/threads/500-ghz-cpu-no-kidding.30566/

S
supersaiyan Original post #1
Jun 21, 2006 at 1:44 AM
check this out-*www.ciol.com/content/developer/2006/106062001.asp?nl=6_19188_Jun20

NEW YORK: IBM and the Georgia Institute of Technology announced today that their researchers have demonstrated the first silicon-based chip capable of operating at frequencies above 500 GHz -- 500 billion cycles per second -- by cryogenically “freezing” the chip to 451 degrees below zero Fahrenheit (4.5 Kelvins).

IBM said in a statement that such extremely cold temperatures are found naturally only in outer space, but can be artificially achieved on Earth using ultra-cold materials such as liquid helium. (Absolute Zero, the coldest possible temperature in nature, occurs at minus 459.67 degrees Fahrenheit).

By comparison, 500 GHz is more than 250 times faster than today's cell phones, which typically operate at approximately 2 GHz. Computer simulations suggest that the silicon-germanium (SiGe) technology used in the chip could ultimately support even higher (near-TeraHertz – 1,000 GHz) operational frequencies even at room temperature.

The experiments, conducted jointly by IBM and Georgia Tech researchers, are part of a project to explore the ultimate speed limits of silicon-germanium (SiGe) devices, which operate faster at very cold temperatures. The chips used in the research are from a prototype fourth-generation SiGe technology fabricated by IBM on a 200-millimeter wafer. At room temperature, they operated at approximately 350 GHz.

“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,” said John D. Cressler, Byers Professor in Georgia Tech's School of Electrical and Computer Engineering, and a researcher in the Georgia Electronic Design Center (GEDC) at Georgia Tech. “This work redefines the upper bounds of what is possible using silicon-germanium nanotechnology techniques.”

"This groundbreaking collaborative research by Georgia Tech and IBM redefines the performance limits of silicon-based semiconductors," said Bernie Meyerson, vice president and chief technologist, IBM Systems and Technology Group.

"IBM is committed to working closely with our academic and industry partners to deliver the insight and innovation that will enable a new generation of high-performance, energy efficient microprocessors."

SiGe is a process technology in which the electrical properties of silicon, the material underlying virtually all modern microchips, is augmented with germanium to make chips operate more efficiently. SiGe boosts performance and reduces power consumption in chips that go into cellular phones and other advanced communication devices. IBM first announced its SiGe technology in 1989, and later introduced SiGe into the industry's first standard, high-volume SiGe chips in October 1998. Since that time, it has shipped hundreds of millions of SiGe chips.

Ultra-high-frequency silicon-germanium circuits have potential applications in commercial communications systems, defense electronics, space exploration, and remote sensing. Achieving such extreme speeds in silicon-based technology – which can be manufactured using conventional low-cost techniques – could provide a pathway to high-volume applications. Until now, only integrated circuits fabricated from more costly “III-V” compound semiconductor materials have achieved such extreme levels of transistor performance.

Better understanding the physics of silicon-germanium devices – and ultimately the circuits that can be built from them – will provide important clues to improvements needed in the future.

“We observe effects in these devices at cryogenic temperatures which potentially make them faster than simple theory would suggest, and may allow us to ultimately make the devices even faster,” Cressler explained. “Understanding the basic physics of these advanced transistors arms us with knowledge that could make the next generation of silicon-based integrated circuits even better.”

In addition to Cressler, the research team included Georgia Tech Ph.D. students Ramkumar Krithivasan and Yuan Lu; Jae-Sun Rieh of Korea University in Seoul, South Korea (formerly with IBM); and Marwan Khater, David Ahlgren and Greg Freeman of IBM Microelectronics in East Fishkill, N.Y.
gary4gar
Jun 21, 2006 at 1:52 AM
not possible in near hundered years
if they create such low temp it will lead to revolution.
the registance of eletrical wires will be zero.they'll act as a supeconducter.
india's power will be no more a problem
anispace
Jun 21, 2006 at 9:55 AM
temperatures upto 1 Kelvin are possible. Only zero kelvin(-273.15 deg celcius) which is called Absolute Zero is not possible practically.

check this out>>
Lowest Manmade Temperature
The lowest manmade temperature achieved so far is 450 picokelvin. It was achieved by a team of scientists at the Massachusetts Institute of Technologu in Cambridge, Massachusetts, USA: A.E. Leanhardt, T.A. Pasquini, M. Saba, A. Schirotzek, Y. Shin, D. Kielpinski, D.E. Pritchard and W. Ketterle. The results were published in Science magazine on September 12, 2003.

This remarkable temperature – which beats the previous record by a factor of six – is the latest achievement in the quest to reach absolute zero, or zero Kelvin, the lowest temperature possible. At such low temperatures, which are just a few billionths of a degree, matter takes on a new state called a Bose-Einstein condensate (the discovery of which earned Wolfgang Ketterle a share in the 2001 Nobel Prize for Physics). In this state, atoms behave as one "superatom". Scientists can then use magnetic fields to isolate and cool the atoms further.

Leanhardt and his team achieved the lowest temperature yet by using a "gravito-magnetic trap", which holds the isolated atoms more lightly than the magnetic fields used to date. In theory, even lower temperatures should be possible using the same technique.*www.guinnessworldrecords.com/index.asp?ID=52880

wow i guess what we learn in school really helps.
JGuru
JGuru #4
Jun 21, 2006 at 11:43 AM
How about PCs running at 500 GHZ? What would be fantastic. But really, these are
achieved at sub-zero temperatures, not in normal temperatures. In that case we
need a special freezer for the PC!! Maybe they can develop a freezer for the CPU
that can be fitted inside the cabinet. That would be cool
goobimama
Jun 21, 2006 at 1:45 PM
Well even if the CPU runs at 500 Ghz, your HDD still gives a maximum of 300 MBps...
nik_for_you
Jun 21, 2006 at 1:57 PM
It would be only on experimental basis as it is very difficult to achive such temp and maintain also. and it will be costly also ..
S
Jun 21, 2006 at 2:48 PM
dudes they have demonstrated it. so its possible but under special conditions
Saahib
Saahib #8
Jun 21, 2006 at 3:56 PM
Did anyone read it carefully, they are clearly saying that it worked at 350 GHZ at room temprature and the chip will be capable to achieve same 500 GHZ on room temprature in near future, don't expect that future as 100 years.. consider it 1 or 2 years and around 5 yrs for commercial production. About HDD giving max 300 mbps, why you are forgettting that we are soon going to give have HDD and will have some 3D memory chip etc.:)
C
cyrux #9
Jun 21, 2006 at 9:31 PM
So what happends if they go further down by 9F, would matter cease ?? That would be an intersting observation.....
S
surdy #10
Jun 23, 2006 at 10:37 AM
it make me :O :O :O ....but the worst thing is that such performance was attained only under not so practical conditions
prankie
prankie #11
Jun 23, 2006 at 8:49 PM
supersaiyyan said:
At room temperature, they operated at approximately 350 GHz.

that's also deadly!!!!
T
Jun 28, 2006 at 12:07 AM
@ surdy: 500 GHz is under impractical conditions but hey it is 350 GHz at room temperature. thats way tooooo fast than the 3.x GHz processors we r using today.
N
Jun 28, 2006 at 10:30 AM
Don't expect these kinda processors in india at least.Maybe possible after 2150ad.
Ankur Gupta
Jun 29, 2006 at 5:03 PM
well with technology advancing so fast and nanotechnology entering into the picture in every field with promising results i am sure tht a 500ghz processor at room temp.. is possible by 2015.
jamyang312
Jun 29, 2006 at 5:24 PM
man who needs such a computer??
look at me,i m satisfied with my 500 MHz cpu!!
T
Jun 29, 2006 at 11:10 PM
oh come on jamyang312. first thing these processors are not entirely meant for home use. and secondly, man this technology sector needs ppl who want more and more power. this craving is the factor which is making this sector grow at such lightning speeds. let me ask you why you purchased a 500 MHz cpu. why are u not using a 386 or a 286. they are good too.
mihirvashist
Jul 3, 2006 at 8:22 PM
gary4gar said:
not possible in near hundered years
if they create such low temp it will lead to revolution.
the registance of eletrical wires will be zero.they'll act as a supeconducter.
india's power will be no more a problem

everything is possible in this world,all we need is determination

supersaiyan said:
check this out-*www.ciol.com/content/developer/2006/106062001.asp?nl=6_19188_Jun20

NEW YORK: IBM and the Georgia Institute of Technology announced today that their researchers have demonstrated the first silicon-based chip capable of operating at frequencies above 500 GHz -- 500 billion cycles per second -- by cryogenically “freezing” the chip to 451 degrees below zero Fahrenheit (4.5 Kelvins).

IBM said in a statement that such extremely cold temperatures are found naturally only in outer space, but can be artificially achieved on Earth using ultra-cold materials such as liquid helium. (Absolute Zero, the coldest possible temperature in nature, occurs at minus 459.67 degrees Fahrenheit).

By comparison, 500 GHz is more than 250 times faster than today's cell phones, which typically operate at approximately 2 GHz. Computer simulations suggest that the silicon-germanium (SiGe) technology used in the chip could ultimately support even higher (near-TeraHertz – 1,000 GHz) operational frequencies even at room temperature.

The experiments, conducted jointly by IBM and Georgia Tech researchers, are part of a project to explore the ultimate speed limits of silicon-germanium (SiGe) devices, which operate faster at very cold temperatures. The chips used in the research are from a prototype fourth-generation SiGe technology fabricated by IBM on a 200-millimeter wafer. At room temperature, they operated at approximately 350 GHz.

“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,” said John D. Cressler, Byers Professor in Georgia Tech's School of Electrical and Computer Engineering, and a researcher in the Georgia Electronic Design Center (GEDC) at Georgia Tech. “This work redefines the upper bounds of what is possible using silicon-germanium nanotechnology techniques.”

"This groundbreaking collaborative research by Georgia Tech and IBM redefines the performance limits of silicon-based semiconductors," said Bernie Meyerson, vice president and chief technologist, IBM Systems and Technology Group.

"IBM is committed to working closely with our academic and industry partners to deliver the insight and innovation that will enable a new generation of high-performance, energy efficient microprocessors."

SiGe is a process technology in which the electrical properties of silicon, the material underlying virtually all modern microchips, is augmented with germanium to make chips operate more efficiently. SiGe boosts performance and reduces power consumption in chips that go into cellular phones and other advanced communication devices. IBM first announced its SiGe technology in 1989, and later introduced SiGe into the industry's first standard, high-volume SiGe chips in October 1998. Since that time, it has shipped hundreds of millions of SiGe chips.

Ultra-high-frequency silicon-germanium circuits have potential applications in commercial communications systems, defense electronics, space exploration, and remote sensing. Achieving such extreme speeds in silicon-based technology – which can be manufactured using conventional low-cost techniques – could provide a pathway to high-volume applications. Until now, only integrated circuits fabricated from more costly “III-V” compound semiconductor materials have achieved such extreme levels of transistor performance.

Better understanding the physics of silicon-germanium devices – and ultimately the circuits that can be built from them – will provide important clues to improvements needed in the future.

“We observe effects in these devices at cryogenic temperatures which potentially make them faster than simple theory would suggest, and may allow us to ultimately make the devices even faster,” Cressler explained. “Understanding the basic physics of these advanced transistors arms us with knowledge that could make the next generation of silicon-based integrated circuits even better.”

In addition to Cressler, the research team included Georgia Tech Ph.D. students Ramkumar Krithivasan and Yuan Lu; Jae-Sun Rieh of Korea University in Seoul, South Korea (formerly with IBM); and Marwan Khater, David Ahlgren and Greg Freeman of IBM Microelectronics in East Fishkill, N.Y.
great, i'm looking forward to this technology who knows maybe next 10 years and we'll be playing lara croft (trapped in a tomb fighting our way out ) in 3d thnx to these processors,only if they are available for massess at not toooo high prices
RCuber
RCuber #18
Jul 3, 2006 at 8:45 PM
If anyone has extra liquid helium , please send it to me . One tone will be sufficiant i guess :D
O
Apr 21, 2007 at 10:01 AM
Well I think that this is good for IBM and all us. A 500ghz single cpu, it’s a nice thing, but I what to see how far they take this. Keeping in mind that you can have the fastest cpu in the world but if you can only access the data at 300 mbps then that’s as fast as you’re going to work at, or if you motherboard in only transferring things at 200 mhz then once again a weak link in the chain. I’d like to see the optical processors and optical motherboards. There’s nothing like working at the speed of light.
goobimama
goobimama #20
Apr 21, 2007 at 1:29 PM
^^^ First of all welcome to the forums, secondly, stop digging out old threads! And that too, this if your first post...!
Zeeshan Quireshi
Apr 21, 2007 at 1:47 PM
goobimama said:
^^^ First of all welcome to the forums, secondly, stop digging out old threads! And that too, this if your first post...!

n i thought that posts in news section weren't counted :D
T
thunderbird.117 #22
Apr 21, 2007 at 1:53 PM
I got a wonderful idea. Let us bring the last post :D.
goobimama
goobimama #23
Apr 21, 2007 at 2:01 PM
They aren't? Didnt know this...I thought it was only in bandwidth wastage section...

Well of course they are counted. My post count just increased with this post...