We and the people haven't seen stream everywhere. And all we have heard of is CUDA everywhere. NVIDIA CUDA is known as graphics plus. It's more than just graphics. This has been taught at over 100 Universities now. I'd like to see ATI puts stream everywhere like what was mentioned in the article, but this is the next step. Now I think ATI/AMD has trouble of competing with Nvidia CUDA. Eventhough they are able to put stream out there in the market, it will be very hard to convince people and turn the market around due to the efficiency and popularity of CUDA. I am using CUDA on my labtop and workstation. It's amazing.

played with Badaboom on rather low end 8500GT and it works fine. Clearly faster than using the CPU (Q6600). Read some reviews about the AMD Avivo, and it seems that there are some artifacts and high CPU useage.

"AMD is doing something brilliant here, with the release of Catalyst 8.12 in early December, AMD is going to roll the CAL into the mainstream consumer driver. When you get the graphics drivers, you get GPGPU functionality for free, no download, no install... it just works."

What the heck is he talking about? CUDA is built into nVidia drivers by default. nVidia GPUs obliterate AMD GPUs in Folding@Home. Disproportionally so.

I still wonder who is giving the reach around in all this FUD, Charlie or AMD? Maybe it's a mutual circle jerk love fest.

What will the noticable differences be for users?

If I have a dual or quad core cpu and mid range gpu, what benefit will I see?

If I have a mid range CPU and low-end or on-motherboard GPU, what benefit will I see?

I was using some DELL pc's the other day that had on-board GPU, tiny cache on CPU and slow hard drives, with 256MB of RAM for XP. The customer thought they had bought a good pc, after all it was a DELL and that's good, right? Would this help them, the masses?

Seriously, can you try to be less objective about nVidia? GPGPU has been touted as the future for years, and ATI/AMD has been far behind, because they didn't dedicate actual hardware in silicon to it. CUDA is different from the past because it offers the graphics hardware as an alternative pipeline for general-purpose computing, so one doesn't have to know anything about graphics (e.g. OpenGL or Cg) to program it.

ATI/AMD keeps changing their mind about all of this. First, it was CTM (Close to the Metal), which required some assembler, and no one adopted it. Then came Brook+, based on what the CS department at Stanford did, and again, no one really caught on. OpenCL---which nVidia will support---doesn't yet exist, and when it does, it will reflect a lot of the features that are already in CUDA, simply because of market share.

When it comes to actually talking about real market share of GPGPU programs, the entire scene is about CUDA. No one I've ever heard of actually does real work with anything else. It's not because CUDA is perfect (far from it) but because AMD/ATI's solutions have NEVER caught on generally.

Writing that they're going to take over the market with this is just a total pile of crap. And to suggest that this has anything to do with their professional cards is even dumber. The code runs exactly the same on the GeForce GTX280 and the Tesla---and I should know, since I have both.

I generally like reading the Inq because it's generally a lot more interesting and honest than other sites, but this article about nVidia is just total garbage. You may have your reasons for hating the company, but next time try to look less like a total fool when writing blatantly incorrect and idiotic things.

I hope that ATI will also ship a Directshow-based H.264 decoder (non-DXVA) instead of just an encoder. Even nVidia does not have this one yet.

" Guess which one tends to win in markets, expensive and restricted or cheap and everywhere? If you are still confused, go look up this little company from Redmond called Microsoft..."

So you're saying expensive and restricted wins in the market? How does this support your thesis exactly?? 

Perhaps you're harkening back to days of yore, old fella. At least one entire generation of humans has been borne since MS was considered cheap. Of course as fast as the years must go for you that was just yesterday, wasn't it?

"there are some things that even bacon can't make better"

This is blasphemy and an affront to pig-loving folk everywhere! Shame on you Charlie for even making such an unfounded statement in an attemot at journalistic hyperbole... tsk, tsk,tsk...

AMD, I love this company... who doesn't? in the deep of your soul?

AMD's philosophy is so user oriented now... but they also know that when a company benefits the user, the company gets benefit back from the user. That's how it works for AMD. 
I would love to buy an ATI 4000. 
I would love to buy an AM3 CPU and use it on my AM2 motherboard. MSI and Asus just released a list of actual mobos that will be compatible with AM3 CPU.
4830 on XF? perfect!

And I probably would buy AMD, despite Intel has the greatest CPU now, but for a price.

Intel... that's another beast altogether

"If you are still confused, go look up this little company from Redmond called Microsoft..."

Did I almost hear a compliment to Microsoft on the INQ? Getting chilly around hell.

NJDevil.com

Once Again, Charlie D(Mr. anti-NVidia), great article.

to see, that my one year old combi of 690 mobo with integrated 1250 plus hd2400 might not get this enhencements

:-( 
grrrrrrhh

I, too, cannot wait to sniff around my 4870 :D

Access to such high performance hardware makes many a geeky software engineer weak at the knees! :D

I agree that amd has better products than nvidia right now, but, apart from that, I can't trust the rest of the article...

and not because I think charlie is helplessly biased, which he may or may not be: it's because those promises of widespread acceleration have been made before and not fulfilled

also, it's nice to see AMD/ATI trying to push mainstream cards instead of forcing users into buying the super-expensive pro versions, but AMD had better solve the many bugs in their firegl/firepro drivers if they want pro users to use their products (I know about the Maya bugs: they're awful, and have been there for over a year, untouched)

That's another proof that ATi is the best.

Thanks Charlie for this early-on information.

I have been wondering about when to buy the HD4670, but this news makes me want to buy it even sooner!

Cudo's to ATI/AMD they are really thinking about the customer!

Try to get this clarfied:
"It will work with all 4xxx series cards, and possibly older versions, but that is not a blanket statement. Stream will be in everything they make going forward, from integrated chipsets to 4870X2s.

Does that mean they do not plan to support current generation 780G (HD 3200) chipsets and that you have to wait for the 8XX series of chipsets for HTPC?

Nvidia seems better with 32 to 48 Pips, Ati has 16. Ati has 3X redundancy, while Nvidia has straight shot. Yet, through ALL of reposts from ati1950 on, Little mention is made of vista Ultimate. whad'ya gonnaplay it.on?

7 won't work any easier for Gzmes than Ultimate. So Chuck, why Not Hurl about how Vantage do in 64 bit(Nessessary extra, these days) On These Units?.

Ati brings sub $300 price into focus, God, Entire computer isn't worth too much more. Pubes await GtX290, while lapping game pad up&up. 
Public also is sleeping on 800 based chipset for Ultimat. Cram it All in Box, ADD Ultimate64 & Game. Its Developing market, NT6 is Mandatory,NOW....

So Charles, Your Assignment, If You Accept it, Is Make NEW Cards Soundly(hdmi) Beat xp with Ultimate/7.Yeah, Soundly, That Reads Well.
dsl Drashek

How do you get Catalyst 8.12 onto your computer without a download and install?

Looks like AMD is doing to nVidia what my dad told my wife to do, Grab, Twist and Pull

Ouch!

.. but now all you can see in GPGPU processing done on mainstrean VGA is CUDA. I have done some serious research and development in this. 

CUDA has one big advantage over Stream - Usable version is out on the market for about a year and many developers are quite familiar with its toolkit. An example of that can be seen at CUDA forum swhere you can find peretty good NV CUDA sanctuary :)

But I still wish for new open toolkit which will be supported by both NV/ATI and i don't like to be forced to write two different parts of code for one algorithm :(

If Charlie is correct on all of this, I will shed a tear. It's my Computer Engineering degree's dream come true. Ubiquitous parallel processing. I'm so happy...