Science > Physics > 350 Ghz room temp chips will transmit movie in five seconds
| Topic: |
Science > Physics |
| User: |
"hi@anony habshi" |
| Date: |
20 Jun 2006 05:02:10 PM |
| Object: |
350 Ghz room temp chips will transmit movie in five seconds |
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
excerpt bbc.co.uk
Germanium is already added to the silicon chips used in mobile phones
to make them operate more efficiently.
Meyerson forecasts that the advances will show up in real products
within a couple years, probably in chips to power super-fast wireless
networks capable of transmitting a DVD-quality movie in as little as
five seconds.
A decade ago we couldn't even envisage being able to run at these
speeds
Professor David Ahlgren, IBM
Adding the element allows chips to run faster and use less power.
Importantly, they can also be fabricated using existing silicon
techniques.
These chips are already known to operate at faster and faster speeds
as they are cooled.
To break the speed record, the researchers super-cooled an IBM
prototype of a new "high frequency" device to -268.5 degrees Celsius,
using liquid helium.
This temperature is just above absolute zero, the theoretical minimum
temperature possible. When cooled, the chips were able to perform half
a trillion calculations every second, a speed of 500 GHz.
By comparison, a powerful desktop PC is capable of about five billion
calculations per second.
"A decade ago we couldn't even envisage being able to run at these
speeds," said Professor Ahlgren.
Next generation
At room temperature the chips still managed to outperform standard
silicon chips, running at about 350 billion calculations per second.
However, the researchers say they can push the chips even further.
"We observe effects in these devices at cryogenic temperatures which
potentially make them faster than simple theory would suggest," said
Professor John Cressler of the Georgia Institute of Technology.
The team believe it is possible to make chips run at 1,000 Ghz, or one
Terahertz, at room temperature.
"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," said Profeesor Cressler.
.
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
20 Jun 2006 05:35:02 PM |
|
|
In sci.physics habshi <hi@anony> wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
They same applications that exist today; they just finish a bit
faster.
<snip>
The team believe it is possible to make chips run at 1,000 Ghz, or one
Terahertz, at room temperature.
With "room temperature" maintained by a whole lot of add on cooling.
<snip remaining>
Do you have a foil covered cardboard box where you keep the shiny
things you find?
--
Jim Pennino
Remove .spam.sux to reply.
.
|
|
|
| User: "Edward Green" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
20 Jun 2006 06:16:58 PM |
|
|
wrote:
In sci.physics habshi <hi@anony> wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
They same applications that exist today; they just finish a bit
faster.
No. Qualitative increases in speed produce qualitative difference in
applications: it would never have occured to a reasonable person first
to store and view photos on a PC, then to store and edit movies. Tasks
which can be finished in a humanly relevant time scale may be
qualitatively different from those which would take millenia on some
generation of machines.
Yes. But whatever the application, it will in some sense be more of
the same crap, designed so that the fastest consumer machines do
whatever it is that it is now indispensible for us to do with finesse,
the cheaper machines barely adequately, so we will all covet the new
boxes, which will not make a damn bit of difference in the quality of
life, since 99.9% of everything -- even terabytes of everything --
is... you know.
<snip>
The team believe it is possible to make chips run at 1,000 Ghz, or one
Terahertz, at room temperature.
With "room temperature" maintained by a whole lot of add on cooling.
I must have a machine the size of a walnut which requires a cooling
unit the size of a piece of furniture! I don't care what it does!
Obviously it will be important, because it is doing so much of it so
fast.
.
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
20 Jun 2006 06:55:02 PM |
|
|
Edward Green <spamspamspam3@netzero.com> wrote:
jimp@specsol.spam.sux.com wrote:
In sci.physics habshi <hi@anony> wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
They same applications that exist today; they just finish a bit
faster.
No. Qualitative increases in speed produce qualitative difference in
applications: it would never have occured to a reasonable person first
to store and view photos on a PC, then to store and edit movies. Tasks
which can be finished in a humanly relevant time scale may be
qualitatively different from those which would take millenia on some
generation of machines.
Digital "pictures" were being done long before the average slub could
buy a PC capable of doing it in any reasonable time. The only thing
that has changed is now it only takes one computer and you don't
have to have backing by a government agency or a film studio to be
able to buy the hardware.
Yes. But whatever the application, it will in some sense be more of
the same crap, designed so that the fastest consumer machines do
whatever it is that it is now indispensible for us to do with finesse,
the cheaper machines barely adequately, so we will all covet the new
boxes, which will not make a damn bit of difference in the quality of
life, since 99.9% of everything -- even terabytes of everything --
is... you know.
Agree there.
<snip>
The team believe it is possible to make chips run at 1,000 Ghz, or one
Terahertz, at room temperature.
With "room temperature" maintained by a whole lot of add on cooling.
I must have a machine the size of a walnut which requires a cooling
unit the size of a piece of furniture! I don't care what it does!
Obviously it will be important, because it is doing so much of it so
fast.
One of the computer trade pubs ran an article about cooling problems
in some of the new, really dense, blade racks.
Seems some of them when loaded would burst into flames in spit of the
fans, which only served to spread the flames once they went up.
The fix? Good, old fashioned, water cooling.
Ignore the laws of thermodynamics at your own risk. Violaters will
be immolated.
--
Jim Pennino
Remove .spam.sux to reply.
.
|
|
|
| User: "Edward Green" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
21 Jun 2006 06:02:18 PM |
|
|
wrote:
Edward Green <spamspamspam3@netzero.com> wrote:
wrote:
In sci.physics habshi <hi@anony> wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
They same applications that exist today; they just finish a bit
faster.
No. Qualitative increases in speed produce qualitative difference in
applications: it would never have occured to a reasonable person first
to store and view photos on a PC, then to store and edit movies. Tasks
which can be finished in a humanly relevant time scale may be
qualitatively different from those which would take millenia on some
generation of machines.
Digital "pictures" were being done long before the average slub could
buy a PC capable of doing it in any reasonable time. The only thing
that has changed is now it only takes one computer and you don't
have to have backing by a government agency or a film studio to be
able to buy the hardware.
That doesn't change my mind. When something becomes just barely
possible, first only people with very deep pockets will be able to do
it, then it gradually slides down the economic scale. You just point
out that the threshold of qualitative change starts at the budget of
NASA, and runs down. Although digital data processesing is perhaps one
of the few technologies where it routinely runs down from the top to
the bottom. Now, Moon trips, for example, reached the barely possible
stage, were done essentially once, and are no nearer being a feasible
weekend trip for Joe Everyman than they were 30+ years ago.
I've had this discussion before (with you?), and generally sides split
off into "qualitative change" vs. "more of the same". I tried to
suggest there was something to be said for both POV's (or is that
P'sOV). The things represented by the files change qualitatively, but
the paradigm of processing larger and larger files changes
qualitatively.
Some things only change assymptotically... certain species of games
were essentially fully developed by the stage of the C64. The graphics
were crude, to use the usual cliche, but more than good enough to draw
the person with imagination into the simulated world. I don't find
modern versions more engaging because objects are drawn with more
resolution -- does chess require a huge high resolution battle sequence
everytime a piece takes a piece?
One of the computer trade pubs ran an article about cooling problems
in some of the new, really dense, blade racks.
Seems some of them when loaded would burst into flames in spit of the
fans, which only served to spread the flames once they went up.
The fix? Good, old fashioned, water cooling.
Ignore the laws of thermodynamics at your own risk. Violaters will
be immolated.
I like it.
.
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
21 Jun 2006 07:15:02 PM |
|
|
Edward Green <spamspamspam3@netzero.com> wrote:
jimp@specsol.spam.sux.com wrote:
Edward Green <spamspamspam3@netzero.com> wrote:
jimp@specsol.spam.sux.com wrote:
In sci.physics habshi <hi@anony> wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
They same applications that exist today; they just finish a bit
faster.
No. Qualitative increases in speed produce qualitative difference in
applications: it would never have occured to a reasonable person first
to store and view photos on a PC, then to store and edit movies. Tasks
which can be finished in a humanly relevant time scale may be
qualitatively different from those which would take millenia on some
generation of machines.
Digital "pictures" were being done long before the average slub could
buy a PC capable of doing it in any reasonable time. The only thing
that has changed is now it only takes one computer and you don't
have to have backing by a government agency or a film studio to be
able to buy the hardware.
That doesn't change my mind. When something becomes just barely
possible, first only people with very deep pockets will be able to do
it, then it gradually slides down the economic scale. You just point
out that the threshold of qualitative change starts at the budget of
NASA, and runs down. Although digital data processesing is perhaps one
of the few technologies where it routinely runs down from the top to
the bottom. Now, Moon trips, for example, reached the barely possible
stage, were done essentially once, and are no nearer being a feasible
weekend trip for Joe Everyman than they were 30+ years ago.
To be really pendantic about image processing, it was done by hand
long before computers were even invented.
So really all that has happened is an old, existing, arduous, manual
process has been automated and improved by the use of a new tool.
I've been trying to think of an application whose essence didn't
exist before computers. By essence, I mean at least the theory of
it didn't exist, whether it was possible to do or not.
I can't think of one.
I'm open to suggestions.
<snip>
--
Jim Pennino
Remove .spam.sux to reply.
.
|
|
|
| User: "Edward Green" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
21 Jun 2006 07:45:54 PM |
|
|
wrote:
To be really pendantic about image processing, it was done by hand
long before computers were even invented.
So really all that has happened is an old, existing, arduous, manual
process has been automated and improved by the use of a new tool.
I've been trying to think of an application whose essence didn't
exist before computers. By essence, I mean at least the theory of
it didn't exist, whether it was possible to do or not.
I can't think of one.
I'm open to suggestions.
You, sir, are a no-qualitative-changelist. I cannot change your sect,
and it would be foolish of me to try.
For the record: I never claimed that computers made possible data
manipulations which were never conceivable before, even in principle,
nor did I claim that manipulations now available to consumers may not
have been available earlier to professionals. I merely argued that as
processing power grows the kind of object which it is feasible to
manipulate (implied -- in a given time for a comparable cost)
occasionally undergoes qualitative change.
I have the feeling that if you allowed yourself to nod your head and
say "yeah, I can see that point of view" it would be tantamount to
saying "Yes, my ex-wife was right all along; I was a boor, and she
deserved all my money". (I am not saying sir, that you are either a
boor, nor have an ex-wife, as in truth I know nothing about you
personally. I am merely saying that the inflexability of your
convictions here is comparable to what would be expected in such
circumstances.)
Go in peace, and keep whatever rituals seem proper to you.
.
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
21 Jun 2006 08:05:02 PM |
|
|
Edward Green <spamspamspam3@netzero.com> wrote:
j...@specsol.spam.sux.com wrote:
To be really pendantic about image processing, it was done by hand
long before computers were even invented.
So really all that has happened is an old, existing, arduous, manual
process has been automated and improved by the use of a new tool.
I've been trying to think of an application whose essence didn't
exist before computers. By essence, I mean at least the theory of
it didn't exist, whether it was possible to do or not.
I can't think of one.
I'm open to suggestions.
You, sir, are a no-qualitative-changelist. I cannot change your sect,
and it would be foolish of me to try.
So you can't think of any computer application that didn't exist
in some form before computers and therefor all computer applications
are nothing more than automation of existing applications?
For the record: I never claimed that computers made possible data
manipulations which were never conceivable before, even in principle,
nor did I claim that manipulations now available to consumers may not
have been available earlier to professionals. I merely argued that as
processing power grows the kind of object which it is feasible to
manipulate (implied -- in a given time for a comparable cost)
occasionally undergoes qualitative change.
That I agree with.
However, the original question was what new applications will appear
because of faster CPUs.
My answer was none and you seemed to think that incorrect.
I have the feeling that if you allowed yourself to nod your head and
say "yeah, I can see that point of view" it would be tantamount to
saying "Yes, my ex-wife was right all along; I was a boor, and she
deserved all my money". (I am not saying sir, that you are either a
boor, nor have an ex-wife, as in truth I know nothing about you
personally. I am merely saying that the inflexability of your
convictions here is comparable to what would be expected in such
circumstances.)
Pot, kettle, black.
Go in peace, and keep whatever rituals seem proper to you.
OK, we disagree.
--
Jim Pennino
Remove .spam.sux to reply.
.
|
|
|
| User: "Edward Green" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
22 Jun 2006 05:30:48 PM |
|
|
wrote:
So you can't think of any computer application that didn't exist
in some form before computers and therefor all computer applications
are nothing more than automation of existing applications?
I can't tell if that is a precis of an admission you feel you have
triumphantly manuvered me into making or a carefully baited trap you
wish me to fall into. I don't believe I expressed an opinion on that
claim though, yeah or nay.
Edward Green <spamspamspam3@netzero.com> wrote:
For the record: I never claimed that computers made possible data
manipulations which were never conceivable before, even in principle,
nor did I claim that manipulations now available to consumers may not
have been available earlier to professionals. I merely argued that as
processing power grows the kind of object which it is feasible to
manipulate (implied -- in a given time for a comparable cost)
occasionally undergoes qualitative change.
That I agree with.
Then we have no disagreement. Sheesh.
.
|
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
22 Jun 2006 06:10:12 AM |
|
|
In article <vp6pm3-sts.ln1@mail.specsol.com>, wrote:
Edward Green <spamspamspam3@netzero.com> wrote:
j...@specsol.spam.sux.com wrote:
To be really pendantic about image processing, it was done by hand
long before computers were even invented.
So really all that has happened is an old, existing, arduous, manual
process has been automated and improved by the use of a new tool.
I've been trying to think of an application whose essence didn't
exist before computers. By essence, I mean at least the theory of
it didn't exist, whether it was possible to do or not.
I can't think of one.
I'm open to suggestions.
You, sir, are a no-qualitative-changelist. I cannot change your sect,
and it would be foolish of me to try.
So you can't think of any computer application that didn't exist
in some form before computers and therefor all computer applications
are nothing more than automation of existing applications?
That is the sole job of the computing biz. It always has been,
and it always will be. (I don't give a ***** what the so-called
leaders say; they're insane.) A computer system will never
innovate without human intervention.
For the record: I never claimed that computers made possible data
manipulations which were never conceivable before, even in principle,
nor did I claim that manipulations now available to consumers may not
have been available earlier to professionals. I merely argued that as
processing power grows the kind of object which it is feasible to
manipulate (implied -- in a given time for a comparable cost)
occasionally undergoes qualitative change.
That I agree with.
However, the original question was what new applications will appear
because of faster CPUs.
My answer was none and you seemed to think that incorrect.
/erg is correct. I'm working hard on this aspect. There
are other countries who are doing 10-, 20-, and 30-year
planning.
<snip zen and black kettles>
/BAH
.
|
|
|
| User: "Bill_Vajk" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
08 Jul 2006 12:54:25 AM |
|
|
wrote:
In article <vp6pm3-sts.ln1@mail.specsol.com>, wrote:
Edward Green <spamspamspam3@netzero.com> wrote:
That is the sole job of the computing biz. It always has been,
and it always will be. (I don't give a ***** what the so-called
leaders say; they're insane.) A computer system will never
innovate without human intervention.
The process involved in successful innovation is invariably illogical.
That's
the inherent art and beauty in it.
snip
My answer was none and you seemed to think that incorrect.
/erg is correct. I'm working hard on this aspect. There
are other countries who are doing 10-, 20-, and 30-year
planning.
Understanding the "cone of possibilities" precludes reasonable
individuals
from planning too far ahead. Correctness itself is a temporary state.
Bill Vajk
Just slumming this evening
.
|
|
|
|
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
22 Jun 2006 06:03:14 AM |
|
|
In article <ki3pm3-eul.ln1@mail.specsol.com>, wrote:
Edward Green <spamspamspam3@netzero.com> wrote:
wrote:
Edward Green <spamspamspam3@netzero.com> wrote:
wrote:
In sci.physics habshi <hi@anony> wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
They same applications that exist today; they just finish a bit
faster.
No. Qualitative increases in speed produce qualitative difference in
applications: it would never have occured to a reasonable person first
to store and view photos on a PC, then to store and edit movies. Tasks
which can be finished in a humanly relevant time scale may be
qualitatively different from those which would take millenia on some
generation of machines.
Digital "pictures" were being done long before the average slub could
buy a PC capable of doing it in any reasonable time. The only thing
that has changed is now it only takes one computer and you don't
have to have backing by a government agency or a film studio to be
able to buy the hardware.
That doesn't change my mind. When something becomes just barely
possible, first only people with very deep pockets will be able to do
it, then it gradually slides down the economic scale. You just point
out that the threshold of qualitative change starts at the budget of
NASA, and runs down. Although digital data processesing is perhaps one
of the few technologies where it routinely runs down from the top to
the bottom. Now, Moon trips, for example, reached the barely possible
stage, were done essentially once, and are no nearer being a feasible
weekend trip for Joe Everyman than they were 30+ years ago.
To be really pendantic about image processing, it was done by hand
long before computers were even invented.
So really all that has happened is an old, existing, arduous, manual
process has been automated and improved by the use of a new tool.
I've been trying to think of an application whose essence didn't
exist before computers. By essence, I mean at least the theory of
it didn't exist, whether it was possible to do or not.
I can't think of one.
I'm open to suggestions.
Objective knowledge cross-pollination.
/BAH
.
|
|
|
|
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
21 Jun 2006 05:39:52 AM |
|
|
In article <1150845418.326844.204570@c74g2000cwc.googlegroups.com>,
"Edward Green" <spamspamspam3@netzero.com> wrote:
jimp@specsol.spam.sux.com wrote:
In sci.physics habshi <hi@anony> wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
They same applications that exist today; they just finish a bit
faster.
No. Qualitative increases in speed produce qualitative difference in
applications: it would never have occured to a reasonable person first
to store and view photos on a PC, then to store and edit movies. Tasks
which can be finished in a humanly relevant time scale may be
qualitatively different from those which would take millenia on some
generation of machines.
Yes. But whatever the application, it will in some sense be more of
the same crap, designed so that the fastest consumer machines do
whatever it is that it is now indispensible for us to do with finesse,
the cheaper machines barely adequately, so we will all covet the new
boxes, which will not make a damn bit of difference in the quality of
life, since 99.9% of everything -- even terabytes of everything --
is... you know.
The computing biz is always in the business of compensating
for the last improvement. If you increase the "speed" of the
CPU, your next project is going to be increasing the speed
of either disks or memory, but not both.
Another aspect of seemingly infinite resources is that 90%
of it will always be wasted. So no matter how much
improvement you have in physical terms, it won't give
any more computing services/Hertz. That's why slop happens.
/BAH
.
|
|
|
| User: "Edward Green" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
21 Jun 2006 06:10:42 PM |
|
|
wrote:
The computing biz is always in the business of compensating
for the last improvement. If you increase the "speed" of the
CPU, your next project is going to be increasing the speed
of either disks or memory, but not both.
Another aspect of seemingly infinite resources is that 90%
of it will always be wasted. So no matter how much
improvement you have in physical terms, it won't give
any more computing services/Hertz. That's why slop happens.
Yes, yes, yes. Being such smart people, we worked this out in
discussion a long time ago, you and I and unsung others, but, like the
guys doing the incisive social analysis just about the time of the Fall
of the Roman Empire, just what bloody good does it do us?
.
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
22 Jun 2006 05:48:19 AM |
|
|
In article <1150931442.359378.314380@c74g2000cwc.googlegroups.com>,
"Edward Green" <spamspamspam3@netzero.com> wrote:
jmfbahciv@aol.com wrote:
The computing biz is always in the business of compensating
for the last improvement. If you increase the "speed" of the
CPU, your next project is going to be increasing the speed
of either disks or memory, but not both.
Another aspect of seemingly infinite resources is that 90%
of it will always be wasted. So no matter how much
improvement you have in physical terms, it won't give
any more computing services/Hertz. That's why slop happens.
Yes, yes, yes. Being such smart people, we worked this out in
discussion a long time ago,
And I'm still trying to work it out elsewhere.
you and I and unsung others, but, like the
guys doing the incisive social analysis just about the time of the Fall
of the Roman Empire, just what bloody good does it do us?
Did you not watch a certain project (name withheld to try
to prevent rabid thread drift to the nether regions) over the last
four years which involved serious computing practices? The
computing piece of the project could not have been done
five years ago. Now extrapolate. People do not have to
have a million dollar passkey to get access to compute-
intensive work. They don't need to hire a dozen babysitters
with a billion dollar infrastructure in place to get
computing access.
I predict (and I'm always off by a decade) that we'll see
effects in 5 years. I'm working on it. I also predict that
the meat of all this work won't be done by the US. The
US is pricing itself out of the business. Beware of any
legislation that is advertised as "helping" the networking
biz.
/BAH
.
|
|
|
|
|
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
20 Jun 2006 08:47:45 PM |
|
|
Let's not loose site the the fact that, no matter how fast the
computer, the fundamental limit on the speed of image transmission is
the data communication infractructure, which today tops out at between
4 and 5 Mbytes/second (using high-speed cable internet).
Today digital TV subscription service runs at probably twice this rate
over cable, and the optical versions of SONET at about 10 times that,
but then this raised the question of "what is the point".
Quite clearly the difference between downloading a movie in 5 seconds
vs. 360 seconds is a bit moot. What is interesting conjecture is what
new and unimagined applications exist that such computer and data
communication performance capabilities will generate.
Fact is, I'm right at this moment typing this message using a 2.7 Ghz
processor, and shipping it out to the internet over a 4 Mhz connection.
I did precisely the same sort of thing back around 1985 using an
incredibly slow Atari 800 computer over a 1200-baud dial-up modem, with
precisely the same result, and even before that employed a ASR33
teletype for a teminal over a 300-baud acoustic modem, again with the
same bottom line.
I suppose my point is just this: What new applications warrant this
extraordinary increase in both computing speed and data communication
bandwidth? Quite frankly, during the past 20 or so years, I haven't
seen many, but hope eternally that they will come.
Harry C.
Harry C.
habshi wrote:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
excerpt bbc.co.uk
Germanium is already added to the silicon chips used in mobile phones
to make them operate more efficiently.
Meyerson forecasts that the advances will show up in real products
within a couple years, probably in chips to power super-fast wireless
networks capable of transmitting a DVD-quality movie in as little as
five seconds.
A decade ago we couldn't even envisage being able to run at these
speeds
Professor David Ahlgren, IBM
Adding the element allows chips to run faster and use less power.
Importantly, they can also be fabricated using existing silicon
techniques.
These chips are already known to operate at faster and faster speeds
as they are cooled.
To break the speed record, the researchers super-cooled an IBM
prototype of a new "high frequency" device to -268.5 degrees Celsius,
using liquid helium.
This temperature is just above absolute zero, the theoretical minimum
temperature possible. When cooled, the chips were able to perform half
a trillion calculations every second, a speed of 500 GHz.
By comparison, a powerful desktop PC is capable of about five billion
calculations per second.
"A decade ago we couldn't even envisage being able to run at these
speeds," said Professor Ahlgren.
Next generation
At room temperature the chips still managed to outperform standard
silicon chips, running at about 350 billion calculations per second.
However, the researchers say they can push the chips even further.
"We observe effects in these devices at cryogenic temperatures which
potentially make them faster than simple theory would suggest," said
Professor John Cressler of the Georgia Institute of Technology.
The team believe it is possible to make chips run at 1,000 Ghz, or one
Terahertz, at room temperature.
"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," said Profeesor Cressler.
.
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
20 Jun 2006 09:15:03 PM |
|
|
In sci.physics wrote:
<snip>
I suppose my point is just this: What new applications warrant this
extraordinary increase in both computing speed and data communication
bandwidth? Quite frankly, during the past 20 or so years, I haven't
seen many, but hope eternally that they will come.
Home based break-ins to encrypted sites, financial sites in particular.
<snip remaining>
--
Jim Pennino
Remove .spam.sux to reply.
.
|
|
|
|
| User: "bobber" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
20 Jun 2006 09:02:11 PM |
|
|
One application could be faster wireless communication, such as a
speedier version of Wimax.
.
|
|
|
| User: "" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
20 Jun 2006 09:15:03 PM |
|
|
In sci.physics bobber <musicboy333@yahoo.com> wrote:
One application could be faster wireless communication, such as a
speedier version of Wimax.
CPU speed has nothing to do with the bandwidth of wireless communication.
--
Jim Pennino
Remove .spam.sux to reply.
.
|
|
|
|
|
|
| User: "Jan Panteltje" |
|
| Title: Re: 350 Ghz room temp chips will transmit movie in five seconds |
21 Jun 2006 04:37:50 AM |
|
|
On a sunny day (Tue, 20 Jun 2006 22:02:10 GMT) it happened hi@anony (habshi)
wrote in <44986b4a.1239602@news.clara.net>:
Very good , its 100 times faster than today's Intel chips.
What applications would be possible ?
excerpt bbc.co.uk
Germanium is already added to the silicon chips used in mobile phones
to make them operate more efficiently.
Meyerson forecasts that the advances will show up in real products
within a couple years, probably in chips to power super-fast wireless
networks capable of transmitting a DVD-quality movie in as little as
five seconds.
Perfessor:
1000GHz corresponds to 1 picosecond period time.
Light travels 1 meter in 3.3 nano seconds.
In 1 ps it travels 1 / 3300 meter = .33 mm
****HOW**** are you going to connect memory chips, and take advantage
of that speed? (send address to memory, send read pulse, read data,
add al setup times, no memory is fast enough, PCB traces are orders of
magnitude too long, even .33 mm makes on chip memory impossible.
Not Very Soon Do Not Hold Breath.
So forget it for computing in the near future.
It may up processor speed to 10GHz, but here we run into the 'Cray' problem
of speed of light.
.
|
|
|
|
|
Related Articles |
|
|
