News
 

Bookmark and Share

(10) 

At the Consumer Electronics Show Nvidia Corp.’s chief executive officer said that the highly-anticipated next-generation graphics processor known as GF100 (aka NV60, G300, GT300) had finally entered mass production. The company remained tight-lipped regarding the release time frame of the future product, which was first shown over three months ago.

“Everyone is dying to know when they can buy GF100. Happy to tell you that it is in volume production, ramping very hard and you can get a sneak peak of it here at CES,” said Jen-Hsun Huang, chief executive officer of Nvidia, at a press conference during CES 2010.

Earlier Nvidia said that it would ramp up production of its next-generation graphics processing units (GPUs) based on Fermi architecture starting in late January, hence, the comment by Mr. Huang may mean that the company is a couple of weeks ahead of the rather pessimistic scenario that the CEO presented back in November ’09. Still, the GF100 chip in general will be at least several months late to market compared to the company’s original plan.

Quite ironically, the announcement of the initiation of GeForce “Fermi” mass production coincides with the claim of arch-rival ATI, graphics business unit of Advanced Micro Devices, regarding shipment of second millionth DirectX 11 graphics processing unit. Nvidia hopes that its next-gen graphics chip will outperform ATI’s Radeon HD 5870 in video games and will also offer better functionality, which will make the delay justified.

The leading supplier of graphics processors has reportedly notified its partners that it would officially launch the GeForce “GF100” graphics chip in March ’10, according to a previous media report. In addition, Nvidia plans to release a rather mysterious code-named GF104 chip in Q2 2010. The GF104 graphics processing unit will target the high-end market, according to the media report.

The flagship Fermi graphics processor will feature 512 stream processing engines (which are organized as 16 streaming multi-processors with 32 cores in each) that support a type of multi-threading technology to maximize utilization of cores. Each stream processor has a fully pipelined integer arithmetic logic unit (ALU) and floating point unit (FPU). The top-of-the-range chip contains 3 billion of transistors, features 384-bit memory GDDR5 memory controller with ECC and features rather unprecedented 768KB unified level-two cache as well as rather complex cache hierarchy in general. Naturally, the Fermi family is compatible with DirectX 11, OpenGL 3.x and OpenCL 1.x application programming interfaces (APIs). The new chips will be made using 40nm process technology at TSMC.

Tags: Nvidia, Fermi, GF100, GT300, NV60, Geforce, 40nm

Discussion

Comments currently: 10
Discussion started: 01/10/10 12:48:36 AM
Latest comment: 12/05/10 05:47:13 AM

[1-10]

1. 
Some rumors said that it will be ~30% faster that ATI's 5870...
So what? Now almost all games gives ~60fps at 1920x1200 with 16xAA and 8xAA. Not to mention that on crappy console ports this number is almost double.
So who cares if one card can output ~60fps and the other one ~75FPS in the same game??
BTW, another rumor said that the price will be 30% more expensive than ATI's...
0 0 [Posted by: TAViX  | Date: 01/10/10 12:48:36 AM]
Reply

2. 
I have my doubts that Fermi will outperform ATI. Namely because nVidia has been silent on performance specs. If they really could outperform by 30% I think they would be advertising "Hey wait, don't buy ATI, We're going to be faster" Instead we have "Hey wait, don't be ATI, we have physx and cuda"
0 0 [Posted by: aethm  | Date: 01/10/10 08:18:53 AM]
Reply

3. 
Judging by TFlops at least, it will not beat ATI significantly.

Nitpick - it's "sneak peek" not "sneak peak".
0 0 [Posted by: martinw  | Date: 01/10/10 11:47:07 AM]
Reply

4. 
We will see ,but i have doubt also about Fermi perfomance ,may be Nvidia overvolt gpu like always do to achieve ATI HD5xxx series ,but that result in high temperature and higher TDP .
Anyway i be glad to see Nvidia DX 11 card on market.
0 0 [Posted by: Blackcode  | Date: 01/11/10 12:22:20 PM]
Reply

5. 
Yeah, I can echo Tavix's statements. I read that that Fermi will outperform the 5870 around 15-30 percent. However, the main this is that how will Fermi compete with ATi on the price/performance/watt?

I'm pretty sure ATi is cooking up something like a 5890 flavour or maybe a faster 5970. Furthermore, once the 40nm process is all good, prices would have finally dropped far enough to mkae it difficult for nVidia to fight in those price segments.
0 0 [Posted by: RtFusion  | Date: 01/11/10 04:59:24 PM]
Reply

6. 
I'm waiting to the new video card since November 2009.
if Nvidia don't start to sell GT300 series I will buy a XFX 5850...

0 0 [Posted by: samueldiogo  | Date: 01/12/10 03:09:57 AM]
Reply

7. 
a 30% performance advantage(if they can achieve that) does not compensate for a chip that's at least 50% bigger, even assuming that yields are going to be similar (and they wont be)
it will just be to expensive.

it'll be a great GPGPU chip, but not so much a great gaming chip. and if larrabee is ever released, thats going to be a even better GPGPU chip(and a even worse gaming chip).
gf100, jack of al trades, master of none.
0 0 [Posted by: Countess  | Date: 01/12/10 08:25:11 AM]
Reply

8. 
only about 20% faster than Cypress, while Hemlock smokes it...

Because of the situation a mole we know is suggesting that Nvidia may limit the sales of Fermi to consumers and instead use the chips for the Tesla and Quadro products where prices and margins are much better...

http://vr-zone.com/forums...n-the-state-of-fermi.html
0 0 [Posted by: Blackcode  | Date: 01/12/10 02:41:41 PM]
Reply

9. 
I'm not dying to purchase a GF100 just because it looks great on paper.

Being behind the 8-ball presents its unique problems...how to talk up a product in order to gain attention away from the current limelight of the competitors.

All I hear is promises, and broken deadlines & this is starting to sound no different than a political campaign in my view.

I can assure you...if Nvidia could of sold 800K graphic cards, they would not look in the mirror and say to themselves "insignificant" let alone playing it off as if it is not important in the DX11 race.

I just feel that Nvidia has lost its foresight and it shows.
0 0 [Posted by: aaaayes  | Date: 01/13/10 03:20:58 AM]
Reply

10. 
I'd take this story with a pinch of salt. TSMC are still having issues with their 40nm yields which will impact on GF100 and other Fermi based chips.

AMD must be coming close to two and half million 5000 series graphics card units sold by now too, their cards are now more widely available. I'd say it'll be mostly die-hard nVidia fans that are still hanging on for their GF100 cards.
0 0 [Posted by: GavinT  | Date: 01/13/10 04:47:23 AM]
Reply

[1-10]

Add your Comment




Related news

Latest News

Wednesday, October 8, 2014

8:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

12:22 pm | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

9:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

6:41 pm | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture

Monday, August 25, 2014

6:05 pm | Chinese Inspur to Sell Mission-Critical Servers with AMD Software, Power 8 Processors. IBM to Enter Chinese Big Data Market with the Help from Inspur