What's NVIDIA up to...? v2

[Tabajara]

Greetings!

Nvidia posts $141-million loss for second fiscal quarter

They seem to have blamed their loss in all the wrong reasons, like weakness of the euro, and said to shareholders that all was fine, because they still have apple's chipset business and such.

[powerarmour]

Details emerge about Nvidia's x86 CPU :-

http://www.semiaccurate.com/2010/08/17/ ... s-x86-cpu/

[impar]

Greetings!

This won't stop Nvidia though, their one managerial tactic when confronted with something they're not allowed to do is to simply do it anyway then figure out how to make it legal later.

[impar]

Greetings!

Nvidia preparing to lose millions
Price war coming on cards

The rumour mill has manufactured a yarn which claims that Nvidia is preparing to write off millions and slash the costs of its graphics cards...

Source of the rumours is a magazine called KitGuru, which initially thought that the cuts of Nvidia's fastest selling Fermi card, the Geforce GTX 460, were going to drop by $20. Now the magazine it thinks that $20 will not be enough to stem the tide of the Rise of the Radeons and an extra $10 will be needed.

[powerarmour]

Interesting little piece on CUDA/GPGPU etc :-

Compared to the old XPDM, WDDM was a big step up for GPU usage on Windows, but only for graphical purposes. With Windows’ iron-fisted control over the GPU and a focus on task scheduling for responsiveness over performance, it wasn’t ideal for GPGPU purposes. Case in point, with a WDDM driver NVIDIA was finding it took 30μs for a kernel to be launched, but if they had Windows treat the GPU as a generic device by using a Windows Driver Model (WDM) driver, that launch time dropped to 2.5μs. This coupled with the fact that a WDM driver is necessary to use Tesla cards in a Windows Remote Desktop Protocol environment (as any Folding @Home junkie can tell you, RDP sessions can’t access the GPU through WDDM) resulted in the birth of TCC mode.

http://www.anandtech.com/show/3924/nvid ... toolkit-32

[powerarmour]

Nvidia signs up with Global Foundries :-

http://www.semiaccurate.com/2010/09/21/ ... foundries/

[impar]

Greetings!

Nvidia signs up with Global Foundries :-
http://www.semiaccurate.com/2010/09/21/ ... foundries/

[powerarmour]

NVIDIA reveals Fermi's successor: Kepler at 28nm in 2011, Maxwell in 2013 :-

Not a lot of details to be had, but NVIDIA wants you to know Fermi isn't the company's be-all, end-all GPU -- "hundreds of engineers" are already hard at work on Codename Kepler, expected to go to production this year and ship in 2011. Kepler's based on a 28nm process, we're told, and will thankfully deliver an estimated 3 to 4 times the performance per watt compared to Fermi, and hopefully run cool. If you built your last PC to last, however, you might wait for Maxwell in 2013, supposedly bringing a sixteen-fold increase in parallel graphics-based computing just two years after that, including advanced features like the ability to autonomously process some content independent of a CPU.

http://www.engadget.com/2010/09/21/nvid ... 11-maxwel/

Kepler is due in 2011 and will be built on a 28nm process technology, though whether that is TSMC or GlobalFoundries is yet to be seen. Huang said that by the time of release the company will have invested about $2 billion in the design. Little information was given on performance, but Huang was adamant they there were targeting performance-per-watt, and that is what the scale on the left hand side represents. Kelper will have apparently have 4x the performance per watt in terms of double precision GFLOPS.

That is an important note as we don't expect the raw performance of the GPU in real-world applications and games to see that much of an increase in just a year. Double precision computing performance is more about high-performance and professional computing but is basically not used in any gaming environments.

But, if we base a Kepler GPU on a ~200 watt power envelope, we hope that this will still equate to at least a factor of 2x gaming performance compared to the results we see from Fermi today.

Maxwell is the following GPU architecture that is schedule for a 2013 release and will be built on a 22nm process technology. Compared to Fermi, Huang stated that Maxwell will bring a 10x performance per watt increase, again in double precision GFLOPS.

NVIDIA stated that with these new architectures they bring new features as well including things like pre-emption, virtual memory support, etc.

When asked about the move from annual architectures to bi-annual releases (as the Kepler/Maxwell roadmap indicates) Huang stated that they see little value in releasing new GPU architectures without also having a node process technology advancement. This means that as the progression in process technology advances, so will NVIDIA's GPU plans. Kepler is targeting 28nm and Maxwell 22nm. Huang also commented that is node process technology advances faster they may alter their plans in the future. Mid-architecture "refreshes" are still planned in between these releases so the GeForce group could still plan on annual products, etc.

This does present a little more risk for NVIDIA though - combining a new architecture with a new process has been known to cause some significant issues every once in a while. Ask ATI with the Evergreen 40nm GPU or AMD with the Llano 32nm APU.

We still have concerns about NVIDIA quoting "performance per watt" rather than just raw performance; it leaves open the idea that performance will remain mostly stable while power efficiency will come down. Huang stated several times that "performance per watt IS peformance" because transistors are free moving forward, but power is not. True enough, but gamers will want to get as much performance as they can in the 200 watt envelope of the PEG slot and aren't as interested in getting a GTX 480 at 50 watts. That feat would be impressive and is necessary for many other markets and areas, but let's hope the performance progression rate increases as well.

http://www.pcper.com/comments.php?nid=9281

[Tabajara]

Looks like twice the performance at half the current power. That can be done with a new architecture and a new process node if they have a lot of luck, but they haven't been lucky for a while. I'll be amazed if they can double their performance at 200w until the end of 2011...

[powerarmour]

Performance per watt is about the only measure left for Nvidia to beat AMD with, it's arguably worked even better for Intel since they switched to those tactics!