Welcome to the MacNN Forums.

If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below.

You are here: MacNN Forums > Community > MacNN Lounge > IBM = 500 Ghz

IBM = 500 Ghz
Thread Tools
Jerk_circus
Junior Member
Join Date: Jul 2004
Status: Offline
Reply With Quote
Jun 22, 2006, 10:04 PM
 
I dont know if this is a repost. I searched, but found nothing, but the search function usually sucks for some reason.

IBM has developed a new transistor that can run up to 500 GHZ, 300 GHZ at room temp.
And Apple switched to intel J/k, I'm sure all chip manufacturers will us this new technology and not just IBM

And yes, I know, a 500GHZ computer is still only as fast as its slowest component. so unless other things speed up, there is not going to be anything really exciting. Still, the possibilities are there

http://www.msnbc.msn.com/id/13434023/
Jerk_circus | Toronto Web Development
     
Chuckit
Clinically Insane
Join Date: Oct 2001
Location: San Diego, CA, USA
Status: Offline
Reply With Quote
Jun 22, 2006, 10:08 PM
 
Pretty impressive. Even if this were an IBM-only thing, since Apple is now encouraging everybody to make universal binaries, there's no good reason why they couldn't just jump back once these puppies are put into production.
Chuck
___
"Instead of either 'multi-talented' or 'multitalented' use 'bisexual'."
     
Jerk_circus  (op)
Junior Member
Join Date: Jul 2004
Status: Offline
Reply With Quote
Jun 22, 2006, 10:12 PM
 
Yeah, it wouldn't be the first time they switched
Jerk_circus | Toronto Web Development
     
Kerrigan
Addicted to MacNN
Join Date: Apr 2005
Status: Offline
Reply With Quote
Jun 22, 2006, 10:24 PM
 
Clay Ryder, president of Sageza Group, a technology market research firm, said the breakthrough should lead to faster processors, but ones that will run far below the top speed demonstrated by IBM.
Not very encouraging. Sounds like the Cell hype.
     
Gamoe
Mac Elite
Join Date: Sep 2000
Status: Offline
Reply With Quote
Jun 22, 2006, 11:29 PM
 
Clay Ryder, president of Sageza Group, a technology market research firm, said the breakthrough should lead to faster processors, but ones that will run far below the top speed demonstrated by IBM.
Originally Posted by Kerrigan
Not very encouraging. Sounds like the Cell hype.
100 GHz would be "far below" this top speed, but that would still be incredibly impressive considering current processors top out below 5 GHz. Still, we've yet to see what will become of this either way.
     
Salty
Professional Poster
Join Date: Jul 2005
Location: Winnipeg, MB
Status: Offline
Reply With Quote
Jun 22, 2006, 11:44 PM
 
This is room temp?

"That speed was hit only when IBM researchers, working with counterparts from the Georgia Institute of Technology, cooled the transistor to near absolute zero, but Meyerson said the device still ran at 300 gigahertz at room temperature."
     
GSixZero
Mac Elite
Join Date: Aug 2004
Location: Seattle, WA
Status: Offline
Reply With Quote
Jun 22, 2006, 11:58 PM
 
While I don't know tons about processor design, I'm guessing that having transistors that run at those high speeds doesn't proportionally correlate to processors that run at those high speeds.

The article compares transistor speed with chip speed, which is apples and oranges as far as I'm concerned. I can't find how fast transistors are in current day chips, but I'm guessing that individual transistors are way faster than 5 ghz.

Although I admit what I wrote above might be total hogwash.

ImpulseResponse
     
©öñFü$íóÑ
Mac Enthusiast
Join Date: Jan 2006
Status: Offline
Reply With Quote
Jun 23, 2006, 01:13 AM
 
what could one individual person do with 500 GHz?

what...? completely digitize the entire solar system, one subatomic particle at a time and then compress it all in Stuffit? Eh... it'd probably take about 4 minutes...

Don't bully me, I got an Uzi... HOO-HAH!
     
gethigh
Forum Regular
Join Date: Nov 2002
Status: Offline
Reply With Quote
Jun 23, 2006, 01:47 AM
 
Originally Posted by GSixZero
While I don't know tons about processor design, I'm guessing that having transistors that run at those high speeds doesn't proportionally correlate to processors that run at those high speeds.

The article compares transistor speed with chip speed, which is apples and oranges as far as I'm concerned. I can't find how fast transistors are in current day chips, but I'm guessing that individual transistors are way faster than 5 ghz.

Although I admit what I wrote above might be total hogwash.
Yes, individual subsections can go faster, but are limited due to a limiting slow path (critical path) when integrated in a larger design. For example, Intel have made 10GHz ALUs (basic math block that can do add/sub, etc.) in research, but of course there are probably things in the pipeline that are slower than that which limit the speed of the overall processor--you can only go as fast as the slowest member.

So technically, an unloaded subsection of that 10GHz ALU could run even faster. The transistor, being the smallest functional unit you can break a circuit into can probably run much much faster...

This is based on my crude understanding of computer architecture and VLSI/ULSI design.


EDIT: I did some googling...I think IBM didn't break any records at all:

In 2000 Intel got 10GHz 30nm CMOS transistors working at 1V
http://www.findarticles.com/p/articl...46/ai_69237333

In 2001 AMD got 3.33TERAHz 15nm CMOS transistors working at 0.8V
http://www.pcstats.com/releaseview.cfm?releaseID=739

In 2005 Some researchers at Univ. of Illinois got 500nm Bipolar transistors (BJT) to run at 604GHz
http://www.newscientist.com/article....ine-news_rss20

Also arstechnia did an article clarifying some of the Hype on IBM/GAtech's chip:
http://arstechnica.com/news.ars/post/20060622-7117.html

The key thing to note is that we are not getting all the facts. For all we know these supposedly groundbreaking transistors only last a few milisecs before burning out from running at these speeds and voltages...
( Last edited by gethigh; Jun 23, 2006 at 02:12 AM. )
     
goMac
Posting Junkie
Join Date: May 2001
Location: Portland, OR
Status: Offline
Reply With Quote
Jun 23, 2006, 09:46 AM
 
Apparently it wasn't really a 500 ghz Processor:

http://arstechnica.com/news.ars/post/20060622-7117.html
8 Core 2.8 ghz Mac Pro/GF8800/2 23" Cinema Displays, 3.06 ghz Macbook Pro
Once you wanted revolution, now you're the institution, how's it feel to be the man?
     
Lateralus
Moderator Emeritus
Join Date: Sep 2001
Location: Arizona
Status: Offline
Reply With Quote
Jun 23, 2006, 10:04 AM
 
Originally Posted by goMac
Apparently it wasn't really a 500 ghz Processor:
And those who actually bothered to look at the article already knew that it wasn't...
I like chicken
I like liver
Meow Mix, Meow Mix
Please de-liv-er
     
kick52
Baninated
Join Date: May 2005
Location: England
Status: Offline
Reply With Quote
Jun 23, 2006, 03:26 PM
 
do nasa use these kinds of chips? shouldnt they buy loads of them to do calculations and stuff. or juct play a game of UT with a really good FPS.
     
   
Thread Tools
 
Forum Links
Forum Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts
BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Top
Privacy Policy
All times are GMT -4. The time now is 05:29 AM.
All contents of these forums © 1995-2017 MacNN. All rights reserved.
Branding + Design: www.gesamtbild.com
vBulletin v.3.8.8 © 2000-2017, Jelsoft Enterprises Ltd.,