New IBM Chip clocks in at 250X faster than current chips.

Toggle sidebar Toggle sidebar
RafterManFMJ

RafterManFMJ

Distinguished
Apr 11, 2006
63
0
18,630
From the Drudge report Front Page:

RESEARCHERS SAY NEW CHIP BREAKS SPEED RECORD
Mon Jun 19 2006 22:57:25 ET



Researchers at IBM and the Georgia Institute of Technology are set to announce Tuesday that they have broken the speed record for silicon-based chips with a semiconductor that operates 250 times faster than chips commonly used now.

The NEW YORK TIMES reports: 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 IBM 's systems and technology group. He said developments like this one typically find their way into commercial products in 12 to 24 months.

Developing...
Click to expand...

...Guess I'll need to put off buying a new computer not until Conroe ships, but until THIS does!
 
Action_Man

Action_Man

Splendid
Jan 7, 2004
3,857
0
22,780
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).
Click to expand...

Nice of them to leave that part out.
 
croc

croc

Distinguished
BANNED
Sep 14, 2005
3,038
1
20,810
'Here is an interesting tid-bit, what happens when you pull liquid He down to a temperature below 4.5 K by pumping a vaccum above it (evaporative cooling)?'

I seem to recall from Uni days that it boils... Until it generates enough pressure to stop boiling.

If you put liquid HE into a cylindar with no vapor gap and then expand the volume of the cylindar, I think it freezes. But that was several sleeps ago, and my interest in supercooled magnetics has, well, cooled.

'I think tri-gate has a better chance of succeeding or AMD's double gate .... :wink:'

Hasn't tri-gate already been done? TI 9904a I think is an example. Useful in industrial apps where it was used as a controller. Zero crossing gates, +5 and -5 states. So it had two possible instructions per cpu cycle. AB's chips also did something similar, I recall.
 
Ycon

Ycon

Distinguished
Feb 1, 2006
1,359
0
19,280
Hmm... POWER 5 processors already consume well above 200W...
200W x 250 = 50.000W :lol: :lol:
I know it doesnt work out like that, but that CPU is certainly going to su*k sp*** outta your ba*** :!: 8)

@ the 300 GHz link:
The 300 GHz is a blatant lie (it has to be a lie).
If the transistor can handle 500 GHz at near absolute zero, near -273.16°C, how can it still pull out 300 GHz at 20-ish °C?
 
iterations

iterations

Distinguished
Apr 10, 2006
428
0
18,780
Yeah people need to keep in mind that this is a transitor switching testbed, cryogrenically frozen with liquid helium, not a CPU. This is cool tech but literally decades away from being anywhere near a consumer product.

You can always count on IBM for a great press release!

Cheers!
 
S

syn1kk

Distinguished
May 19, 2006
113
0
18,680
300 Ghz @room temp.
http://www.theinquirer.net/?article=32517
http://today.reuters.com/news/newsA...-20T043900Z_01_N19356979_RTRUKOC_0_US-IBM.xml

Do not buy Conroe, wait for Athlon64 1000000+
Click to expand...

once again... let me remind the crowd here that The Inquirer is not a really credible source. "The Inquirer has been accused of manufacturing rumours or speculating aimlessly in order to inflate its number of visitors. Others rebuke these claims, saying it is a byproduct of getting information early, that company's plans change which invalidates earlier information."

Although it does have some credible news... it does not follow the same standards as newspapers like NYTimes. (i.e. writing stories using actual facts...)
 
S

syn1kk

Distinguished
May 19, 2006
113
0
18,680
This kind of news does not directly pertain to desktop computing =P. It is important though for the semiconductor field because you can apply it to things that need lots of speed.

I could easily see this being used for supercomputing given a contract and 5 years. I could see this for high power servers given greater than 5 years. But for desktops??

Sounds too far fetched it would take a lotttt longer and billlions more of R&D. I mean the next cooling step to become standard is water cooling... having liquid nitrogen??!! Right now the only way to run your computer constantly is to buy big canisters of liquid nitrogen (in this case liquid helium)

-----------

So without further ado I present to everyone the new overclocking standard!!! (not drawn to scale, actual canister is 4 feet tall with a radius of 1 ft):
glorious_MSpaint.GIF


-----------

For the record IBM is a really good company. They have brought us things like the power PC (used in the XBox). They are also coming out with a solid state Harddrive. This would be great because harddrives REALLLLLYYY suck! It will be in production give or take a couple years. (or sooner)
 
You must log in or register to reply here.

TRENDING THREADS

Latest posts

Moderators online

Share this page

COMPANY
RESOURCES
FOLLOW
Top Bottom