Free Republic
Browse · Search
General/Chat
Topics · Post Article

Skip to comments.

NVIDIA's Fermi: Architected for Tesla, 3 Billion Transistors in 2010
Anandtech ^ | September 30th, 2009 | Anand Lal Shimpi

Posted on 10/01/2009 9:17:53 AM PDT by Ernest_at_the_Beach

The graph below is one of transistor count, not die size. Inevitably, on the same manufacturing process, a significantly higher transistor count translates into a larger die size. But for the purposes of this article, all I need to show you is a representation of transistor count.

See that big circle on the right? That's Fermi. NVIDIA's next-generation architecture.

NVIDIA astonished us with GT200 tipping the scales at 1.4 billion transistors. Fermi is more than twice that at 3 billion. And literally, that's what Fermi is - more than twice a GT200.

At the high level the specs are simple. Fermi has a 384-bit GDDR5 memory interface and 512 cores. That's more than twice the processing power of GT200 but, just like RV870 (Cypress), it's not twice the memory bandwidth.

(Excerpt) Read more at anandtech.com ...


TOPICS: Business/Economy; Computers/Internet
KEYWORDS: hitech; nvidia; tesla
Navigation: use the links below to view more comments.
first 1-2021-4041-47 next last

1 posted on 10/01/2009 9:17:53 AM PDT by Ernest_at_the_Beach
[ Post Reply | Private Reply | View Replies]

To: ShadowAce

fyi


2 posted on 10/01/2009 9:18:26 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 1 | View Replies]

To: Ernest_at_the_Beach

Whoa.


3 posted on 10/01/2009 9:19:52 AM PDT by Mr. Jazzy ("I AM JIM THOMPSON!!!")
[ Post Reply | Private Reply | To 1 | View Replies]

To: Ernest_at_the_Beach

>>Fermi has a 384-bit GDDR5 memory interface and 512 cores. That’s more than twice the processing power of GT200 but, just like RV870 (Cypress), it’s not twice the memory bandwidth.<<

And Vista will still be a dog on it.

Sort of brings up the question, if something sucks with a lot of power, does it blow?


4 posted on 10/01/2009 9:20:05 AM PDT by freedumb2003 (Communism comes to America: 1/20/2009. Keep your powder dry, folks. Sic semper tyrannis)
[ Post Reply | Private Reply | To 1 | View Replies]

To: rdb3; Calvinist_Dark_Lord; GodGunsandGuts; CyberCowboy777; Salo; Bobsat; JosephW; ...

5 posted on 10/01/2009 9:24:24 AM PDT by ShadowAce (Linux -- The Ultimate Windows Service Pack)
[ Post Reply | Private Reply | To 1 | View Replies]

To: freedumb2003; Mr. Jazzy; blam; SunkenCiv; Marine_Uncle; neverdem
Well,...technically Vista doesn't run on the Graphics processing unit...but further into the article....Tesla is a processor that Nvidia is building for special applications....see this :

***********************EXCERPT***************************

The Evolution of GPU Computing

When matched with the right algorithms and programming efforts, GPU computing can provide some real speedups. Much of Fermi's architecture is designed to improve performance in these HPC and other GPU compute applications.

Ever since G80, NVIDIA has been on this path to bring GPU computing to reality. I rarely get the opportunity to get a non-marketing answer out of NVIDIA, but in talking to Jonah Alben (VP of GPU Engineering) I had an unusually frank discussion.

From the outside, G80 looks to be a GPU architected for compute. Internally, NVIDIA viewed it as an opportunistic way to enable more general purpose computing on its GPUs. The transition to a unified shader architecture gave NVIDIA the chance to, relatively easily, turn G80 into more than just a GPU. NVIDIA viewed GPU computing as a future strength for the company, so G80 led a dual life. Awesome graphics chip by day, the foundation for CUDA by night.

6 posted on 10/01/2009 9:26:45 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 4 | View Replies]

To: Ernest_at_the_Beach

I’ve got a GTS250 on one machine and a GTX280 on another. Both cards rock. The GTX280 also works well as a space heater.

Can I put a plug in for FR’s Folding Team? http://www.freerepublic.com/focus/f-chat/2316710/posts .....C


7 posted on 10/01/2009 9:27:42 AM PDT by colinhester
[ Post Reply | Private Reply | To 1 | View Replies]

To: freedumb2003

To describe VISTA I will quote Bart Simpson “I didnt think it was physically possible, but this sucks and blows at the same time”

same for Microsoft Office with the new ‘ribbon’ bar that takes up 1/3 of your screen with commands you never use, and moves all the commands somewhere that you can’t find them


8 posted on 10/01/2009 9:28:00 AM PDT by Mr. K (THIS ADMINISTRATION IS WEARING OUT MY CAPSLOCK KEY DAMMIT DAMMIT DAMMIT!!!!!)
[ Post Reply | Private Reply | To 4 | View Replies]

To: freedumb2003
And Vista will still be a dog on it.

Windows 7 out this month.
9 posted on 10/01/2009 9:29:48 AM PDT by Signalman
[ Post Reply | Private Reply | To 4 | View Replies]

To: Ernest_at_the_Beach
Most of the software will be bloatware and most data will be GIGO!
10 posted on 10/01/2009 9:30:45 AM PDT by HuntsvilleTxVeteran ((B.?) Hussein (Obama?Soetoro?Dunham?) Change America Will Die From.)
[ Post Reply | Private Reply | To 1 | View Replies]

To: All; neverdem
And it was less than 70 years ago when Bell Labs invented the Transistor and about 10 years later when the Integrated Circuit was invented...FR Thread on that :

Transistors, 1948

11 posted on 10/01/2009 9:31:09 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 6 | View Replies]

To: Mr. K

Open Office user here...but usually just the Text Editor on Ubuntu.


12 posted on 10/01/2009 9:33:18 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 8 | View Replies]

To: Bobkk47

>>Windows 7 out this month.<<

IIRC, there was an article posted here that Best Buy was told/told its employees “do NOT call Windows 7 ‘Vista that works.’”

LOL.


13 posted on 10/01/2009 9:33:52 AM PDT by freedumb2003 (Communism comes to America: 1/20/2009. Keep your powder dry, folks. Sic semper tyrannis)
[ Post Reply | Private Reply | To 9 | View Replies]

To: colinhester

Thanks... if some of those Graphic cards get reasonable prices I might join in.


14 posted on 10/01/2009 9:35:13 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 7 | View Replies]

To: freedumb2003

Now that’s funny!


15 posted on 10/01/2009 9:36:00 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 13 | View Replies]

To: Mr. K
To describe VISTA I will quote Bart Simpson “I didnt think it was physically possible, but this sucks and blows at the same time”


16 posted on 10/01/2009 9:37:18 AM PDT by freedumb2003 (Communism comes to America: 1/20/2009. Keep your powder dry, folks. Sic semper tyrannis)
[ Post Reply | Private Reply | To 8 | View Replies]

To: colinhester
I've no idea what this baby costs....:


A GeForce GTX 280 with 4GB of memory is the foundation for the Tesla C1060 cards

And then:


Four of those C1060 cards in a 1U chassis make the Tesla S1070. PCIe connects the S1070 to the host server.

17 posted on 10/01/2009 9:39:43 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 7 | View Replies]

To: Ernest_at_the_Beach
Vista sucks -- mildly NSFW (sorry if I have posted this to you before: I do it as a public service to folks on the thread)
18 posted on 10/01/2009 9:39:59 AM PDT by freedumb2003 (Communism comes to America: 1/20/2009. Keep your powder dry, folks. Sic semper tyrannis)
[ Post Reply | Private Reply | To 15 | View Replies]

To: Ernest_at_the_Beach

1U??? Holy Moley!

How long before it fits into a PDA?


19 posted on 10/01/2009 9:41:36 AM PDT by freedumb2003 (Communism comes to America: 1/20/2009. Keep your powder dry, folks. Sic semper tyrannis)
[ Post Reply | Private Reply | To 17 | View Replies]

To: All
Narrative between pics just above:

***************************EXCERPT***************************

NVIDIA loves to cite examples of where algorithms ported to GPUs work so much better than CPUs. One such example is a seismic processing application that HESS found ran very well on NVIDIA GPUs. It migrated a cluster of 2000 servers to 32 Tesla S1070s, bringing total costs down from $8M to $400K, and total power from 1200kW down to 45kW.

20 posted on 10/01/2009 9:41:51 AM PDT by Ernest_at_the_Beach (Support Geert Wilders)
[ Post Reply | Private Reply | To 17 | View Replies]


Navigation: use the links below to view more comments.
first 1-2021-4041-47 next last

Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.

Free Republic
Browse · Search
General/Chat
Topics · Post Article

FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson