Forums | MacLife

ATi Linux drivers are crap, Rob?

Now, when I saw the 24 display setup, I thought that the displays were Dell's 22" displays. However, AMD's demonstration utilized 24 Dell 2408WFP displays, the very same display I am looking at every day… and it looked quite small.

What you're seeing in pictures inside this article is a single PC based on AMD Phenom II 955 processor, Dragon platform and four graphics cards, running X-Plane from Laminar Research using Linux operating system. You've read it correctly, Linux support is out of the box, which is going to make penguin lovers quite happy. Unlike Windows and its limitations due to built-in DRM schemes, Linux has no problems to do a massive multi-scale display experience such as the aforementioned 24 display setup.

The 24 panel setup is running four instances of X-Plane, occupying each CPU core, using the latest beta version which is going to be available soon.

The caveat of avoiding screen overlapping is very interesting. According to AMD people we spoke with, the driver is making a 120 pixel vertical and horizontal adjustment, e.g. rendering each display as 1920+120 pixel horizontally and 1200+120 pixel vertically [2040x1320 pixels], achieving near-perfect alignment.

By rendering those 120 pixels extra, the resolution load was significantly increased for this 24 display setup [12240x5280], i.e. the next-generation GPU from AMD has to render 64.63 million pixels in order to show perspective-corrected 55.29 million pixel image.

But the end result is more than impressive - flying the plane in 12240x5280 resolution is nothing [less than] breathtaking. Even though the banding between the two displays reduces the immersive experience, the fact of the matter is that this technology reduces the cost of multi-monitor technology at least by a factor of five.

You will still have to wait for later in the year to be able to immerse yourself in multiple display setups, but the technology shown here is quite impressive.

http://brightsideofnews.com/news/2009/9 … puter.aspx

AMD delivers world's first WHQL-certified DX11 driver

ATI Radeon 5870 X2/5850 X2 cards spotted

Now that the 5870 "Cypress" launch is behind them, ATI's engineers are putting the finishing touches on their dual-GPU "Hemlock" boards, which are expected to debut before the end of the year. A couple of shots of the board have hit Xtremesystems.org. In one of the images you can clearly see the 8-pin and 6-pin PCIe power connectors required to power the card.

Meanwhile VR-Zone managed to check out an ATI demo system outfitted with a 5850 X2 GPU running Alien vs Predator DX11. They said the Hemlock board was slightly longer than 5870, perhaps as long as 12" PCB. Performance was "encouraging", although specific frame rates aren't mentioned.

http://www.firingsquad.com/news/newsart … chid=22167

From the above, p.7- NV 'fesses up, somewhat.

The RV770 Lesson (or The GT200 Story)

It took NVIDIA a while to give us an honest response to the RV770. At first it was all about CUDA and PhsyX. RV770 didn't have it, so we shouldn't be recommending it; that was NVIDIA's stance.

Today, it's much more humble.

Ujesh is wiling to take total blame for GT200. As manager of GeForce at the time, Ujesh admitted that he priced GT200 wrong. NVIDIA looked at RV670 (Radeon HD 3870) and extrapolated from that to predict what RV770's performance would be. Obviously, RV770 caught NVIDIA off guard and GT200 was priced much too high.

Ujesh doesn't believe NVIDIA will make the same mistake with Fermi.

Jonah, unwilling to let Ujesh take all of the blame, admitted that engineering was partially at fault as well. GT200 was the last chip NVIDIA ever built at 65nm - there's no excuse for that. The chip needed to be at 55nm from the get-go, but NVIDIA had been extremely conservative about moving to new manufacturing processes too early.

It all dates back to NV30, the GeForce FX. It was a brand new architecture on a bleeding edge manufacturing process, 130nm at the time, which ultimately lead to its delay. ATI pulled ahead with the 150nm Radeon 9700 Pro and NVIDIA vowed never to make that mistake again.

With NV30, NVIDIA was too eager to move to new processes. Jonah believes that GT200 was an example of NVIDIA swinging too far in the other direction; NVIDIA was too conservative.

The biggest lesson RV770 taught NVIDIA was to be quicker to migrate to new manufacturing processes. Not NV30 quick, but definitely not as slow as GT200. Internal policies are now in place to ensure this.

Architecturally, there aren't huge lessons to be learned from RV770. It was a good chip in NVIDIA's eyes, but NVIDIA isn't adjusting their architecture in response to it. NVIDIA will continue to build beefy GPUs and AMD appears committed to building more affordable ones. Both companies are focused on building more efficiently.

Also, if you didn't read as you should've , much of Fermi is architected to a market other than games, and its more demanding requirements, like ECC memory and more.

NVIDIA's architecture is designed to address its primary deficiency: the company's lack of a general purpose microprocessor. As such, Fermi's enhancements over GT200 address that issue. While Fermi will play games, and NVIDIA claims it will do so better than the Radeon HD 5870, it is designed to be a general purpose compute machine.

ATI's approach is much more cautious. While Cypress can run DirectX Compute and OpenCL applications (the former faster than any NVIDIA GPU on the market today), ATI's use of transistors was specifically targeted to run the GPU's killer app today: 3D games.

Intel's take is the most unique. Both ATI and NVIDIA have to support their existing businesses, so they can't simply introduce a revolutionary product that sacrifices performance on existing applications for some lofty, longer term goal. Intel however has no discrete GPU business today, so it can.

Larrabee is in rough shape right now. The chip is buggy, the first time we met it it wasn't healthy enough to even run a 3D game. Intel has 6 - 9 months to get it ready for launch. By then, the Radeon HD 5870 will be priced between $299 - $349, and Larrabee will most likely slot in $100 - $150 cheaper. Fermi is going to be aiming for the top of the price brackets.

The motivation behind AMD's "sweet spot" strategy wasn't just die size, it was price. AMD believed that by building large, $600+ GPUs, it didn't service the needs of the majority of its customers quickly enough. It took far too long to make a $199 GPU from a $600 one - quickly approaching a year.

Clearly Fermi is going to be huge. NVIDIA isn't disclosing die sizes, but if we estimate that a 40% higher transistor count results in a 40% larger die area then we're looking at over 467mm^2 for Fermi. That's smaller than GT200 and about the size of G80; it's still big.

I asked Jonah if that meant Fermi would take a while to move down to more mainstream pricepoints. Ujesh stepped in and said that he thought I'd be pleasantly surprised once NVIDIA is ready to announce Fermi configurations and price points. If you were NVIDIA, would you say anything else?

Jonah did step in to clarify. He believes that AMD's strategy simply boils down to targeting a different price point. He believes that the correct answer isn't to target a lower price point first, but rather build big chips efficiently. And build them so that you can scale to different sizes/configurations without having to redo a bunch of stuff. Putting on his marketing hat for a bit, Jonah said that NVIDIA is actively making investments in that direction. Perhaps Fermi will be different and it'll scale down to $199 and $299 price points with little effort? It seems doubtful, but we'll find out next year.

[p8] Today's launch is strange. I tried to convince NVIDIA to release more information about Fermi but was met with staunch resistance from the company. NVIDIA claims that by pre-announcing Fermi's performance levels it would seriously hurt its existing business. It's up to you whether or not you want to believe that.

Last quarter the Tesla business unit made $10M. That's not a whole lot of money for a company that, at its peak, grossed $1B in a single quarter. NVIDIA believes that Fermi is when that will all change. To borrow a horrendously overused phrase, Fermi is the inflection point for NVIDIA's Tesla sales.

By adding support for ECC, enabling C++ and easier Visual Studio integration, NVIDIA believes that Fermi will open its Tesla business up to a group of clients that would previously not so much as speak to NVIDIA. ECC is the killer feature there.

While the bulk of NVIDIA's revenue today comes from 3D graphics, NVIDIA believes that Tegra (mobile) and Tesla are the future growth segments for the company. This hints at a very troubling future for GPU makers - are we soon approaching the Atom-ization of graphics cards?
..

So... go read the rest.

NightCougar_37 wrote:

Wow so NV fails the GT200 cause they expected another 3870...lol, do they even try to test ATI's chips or just make wild guesses? You'd think with your top competitor coming out with a new chip, that you'd actually want to investigate it enough to find out the best way to counter it. The sheer arrogance of NV just reeks in that part. Its like waving a juicy steak of market share in front of a teased and injured doberman (ATI). Pretty soon its gonna attack and rip that arm off along with the steak.

Well keep in mind that they're designing these chips years in advance, so it's more like consulting Ms. Cleo...

Booksley wrote:

NightCougar_37 wrote:

Wow so NV fails the GT200 cause they expected another 3870...lol, do they even try to test ATI's chips or just make wild guesses? You'd think with your top competitor coming out with a new chip, that you'd actually want to investigate it enough to find out the best way to counter it. The sheer arrogance of NV just reeks in that part. Its like waving a juicy steak of market share in front of a teased and injured doberman (ATI). Pretty soon its gonna attack and rip that arm off along with the steak.

Well keep in mind that they're designing these chips years in advance, so it's more like consulting Ms. Cleo...

Now you can gamble more safely on stocks.

Also, NV is close to betting the farm on the HPC field for its future. Games aren't the focus anymore, and their head of dev relations/ TWIMTBP jumped to AMD. 'Bullet Physics' is AMD's 'Physics on the GPU' rival to PhysX and Havok, and is all open standards-based (e.g. OpenCL). Hard to believe NV will have equal bang/buck on games going forward, with C++, ECC and all baked into huge chips.

Nothing is really final unless/until a company goes out of business/is acquired/ leaves a given market (e.g. PowerVR still makes videochips, just not for PCs), and NV's DX11 hardware won't be out for awhile yet. It seems likely ATi'll have the better solution[s] for 3D gaming this gen is about the most one can say at this point, besides 'you kan haz ATI now.' That's better as in value- NV's best may still be faster as it ought, it does have 40% more transistors- but that can't come cheap. Bang/buck will likely favor ATI.

NV's do look very promising if you're putting together a HPC supercomputing cluster to do seismographic work, but that's not most of us.

Longer demo sans focus on tesselation: http://www.youtube.com/watch?v=9F6zSgtRnkE