Slashdot Mirror
New ATi 3D Chip
Cooper writes "Saw a piece on Sharky Extreme about a new ATI chip dubbed the Rage 6, which they say is going to be used on Microsoft's x-box as well as for PCs. It's got an on-board geometry processor like the NVIDIA GeForce. " Wow. 2 gigapixels per second? Wow. The graphics market is starting to really heat up - check the earlier story about the Voodoo 4 &5.
Seriously, though, sheer pixels per second is kind-of meaningless. (Actually, it'll be state changes per second. :) In most vector-based or polygon-based product, the bottle-neck is in calculating the outer perimiter of the shapes.
Personally, I think pixel-based displays are a dead-end, anyway. Aliasing is horrible, and the techniques to get round it do so by making the picture too blurred to tell.
What's needed is a pure analogue polygon-based display, capable of area fill and non-trivial shapes. 3D would be nice, too. Anyone got a holographic projector they could lend me?
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
Seem to be a lot of announcements to coincide with Christmas shopping. Some of them seem to be the usual vapourware i.e. don't buy a graphics card for Christmas because our sooper-dooper card will be out just after...HONEST!
:-)
Anyway which graphics card is "the business" both now, and which is expected to be ?
On another note, I'm not too enthusiastic about Microsofts X-Box - seems the forthcoming Sony PSX 2 is going to beat it into the ground, and the spec of Microsofts product doesn't look that different from a PC anyway. Anyone think any different ?
The Playstation 2 looks like it might be the first games console I'll buy since I bought one that played table tennis games in glorious black & white !
Donte Alistair Anderson Roberts - hi son!
Karma: Chameleon
I found it really funny that because each of the new chips uses 7 watts of power, if you have more than 3 it can't get enough from the bus (AGP provides 20W of power) ... so if you look at the picture there's a brick that you have to plug into your outlet in your wall, and then plug into the back of the card... /me is wondering how much heatsink/fannage you'll need for 4x7watt processors...
-- Erich
Slashdot reader since 1997
This may parallel (fatally, as is the case for automotive analogies) automobile mufflers; I find that the really powerful automobiles have extensive exhaust systems, whilst any car with a "wimpy" exhaust system is itself necessarily "wimpy."
A graphics card that requires inordinate amounts of power might, on the one hand, be making flashy use of electricity to make it seem cool, but might truly be providing a whopping lot of "rendering power."
Of course, the killer question is whether or not there will be XFree86 accelerator code that can actually harness this power... Otherwise, these monstrous, smoking-at-the-ears graphics boards may be paper dragons, parallelling the Intel MMX, where few if any programs actually made real use of the optimization...
If you're not part of the solution, you're part of the precipitate.
It is nice in a free market to vote with your $$.
A lot of people give a lot of hot air to Open Source in general and Linux in particular.
Nvidia did a very nice thing by providing an optimized, glx version of the SVGA X server for the TNT cards. 3Dfx has recently made some moves in this area, but I still tend to think they are "closed thinkers" (GLIDE).
The question, what has ATI done for me lately? Why should I even consider giving them my money?
Of course, larger textures, more polygons and features like full-screen antialiasing and enviornmental bump mapping and true color are great, but it is hard to get worked up over any particular video card when each of them only has bits and pieces of the really cool features, and when it comes down to it, all they really do is allow some minor improvements in image quality and allow you to up your screen resolution and get more frames. Great for the obsessed gamer, but game developers still have to make games with the low end in mind, so the games themselves aren't tremendously more impressive from a graphical perspective.
For those reasons I'm a lot more excited about the Dolphin and PSX2 than I could ever be about a mere video card, or even a new class of video cards (like those with on-board T&L, which is meeting with mixed enthusiasm from developers btw.)
But all these incremental advances and all the competition is great. It means that maybe in 3 or 4 years, there'll be PC games where the game developers aren't limited by hardware anymore, but rather the "developmer's bottleneck" will be the designer's creativity, effort and resources. That would be cool. :)
I call it the Eyeball(tm) and I've patented it and GPLed it. It can do over 3 quadrillion equivalent pixels (I say 'equivalent' because it deals in quantum elements, of which there are an uncountable number in a pixel) per millisecond and when combined with another Eyeball(tm) in a dual setup, can actually create realistic stereovisual effects. It can take input from the real world and give it to you in astonishing 3D quality, and with the new additions 'LSD', 'X' and 'Louisville Slugger', you can make it generate colors you may never have seen before. Unfortunately, such advanced technology comes at a price. The incredibly complex nature of the Eyeball(tm) is such that it requires a proprietary socket, the EyeSocket(tm) to interface with your system properly, and of course you'll need a brain (we realize that this excludes a vast majority of the world's game players, but the ones who do have one will greatly appreciate this invention).
.. TODAY!
Don't settle for wussy video cards that are limited to only 'pixels' and may or may not be out after Christmas. Use the Eyeball(tm) (or two) and enjoy true reality
(please note that overclocking the Eyeball(tm) or removing the Eyeball(tm) from the EyeSocket(tm) in any way voids the warranty and may damage said Eyeball(tm))
It's far more fun to forget about that... :-)
(No, there probably aren't many people with hundreds of karma points. My count is only in the "single" hundreds, not in multiple hundreds...)
If you're not part of the solution, you're part of the precipitate.
All of us in our shop have been reading reports of the "new-and-improved graphic" graphic chips that supposed to fly at this and that speed, in the giga-pixels-per-second range.
All is well, if those giga-pixels-per-second can be translated into SERIOUS USE.
For a gamer, the giga-pixels performance might be sufficient, but for other serious uses - like REALTIME SIMULATION for example, giga-pixels-per-second performance do us any good if it can't do simple refreshs at 30 frames/second or more, at the resolution of 2048*2048*32bits/pixel.
REALTIME simulations _ARE_ important to our shop, and the adage "A picture is better than a thousand words" rings very true to us, for there is no way we can catch faults by pour over the tera-bytes of data generated on a typical simulation.
We have reached our human capabilities in our demanding simulation environment, and when we _NEED_ the hardware to support us, all we see are marketing hypes that do not translate into real use for us.
My hope is that one day the marketing hype will go away, and serious users like us will get the products that we truly require.
Anyone know how long we have to wait until _REALLY USEFUL_ products will come to the market?
Muchas Gracias, Señor Edward Snowden !
- The former ("application processor") tends to involve grabbing bits of memory from here and there, comparing them to other bits of memory, jumping, often adding something, and sometimes calling subroutines.
- The latter ("graphics processor") will be doing a whole lot of operations involving XORs, filling regions with values, and even doing some tight loops oriented towards filling regions with "shading."
The graphics processor is rather more likely to find useful some operations that do "mass updates," which is rather like what a DSP does; that is quite different from the "lots-of-control-statements" that you'll get with a "conventional"/"application-oriented" CPU.That may be a gross oversimplification, but there you go...
The patents that Transmeta has been granted somewhat confirm this point of view; the patents represent ways of optimizing the emulation of those "lots-of-control-statements."
There may be a real killer graphics chip right around the corner, although it is easy to argue that the last three years have involved the continuous release of successive generations of "more-and-even-more-killer" graphics processors.
I'm not sure that there is a "Transmeta" of the graphics world; it's probably not appropriate to talk about such until next February when you might conceivably be able to buy some Transmeta product...
If you're not part of the solution, you're part of the precipitate.
Thank you for that incredibly well informed and wonderfuly articulated argument.
My ATI All-in-Wonder card works great for me. I've had absolutely no problems with it, and now that ATI has relased the specs for it, I'm really looking forward to being able to use it for video capture.
Is there any particular reason you don't like ATI?
I just wanted to mention that, IMHO, since graphics
have become so big, there's just more and more fighting
games.
Good Thing: Games are more flexible. Good ideas can become better.
Bad Thing: Since graphics have become less and less
of a barrier, there's been less originality in games.
I long for the days of nes, snes, and genesis, where
game programmers had to come up with ORIGINAL ideas. Now it's
almost always shoot-em-ups!
A number of companies have specialized in developing really unique and interesting graphics engines which they are marketing to the big makers in the form of logic cores. They range from faster engines to render more polygons per microsecond, to more unique designs that render blocks of the screen at a time, to really uniqe designs that take polygons completely out of the picture. These engines will find their way into the next generation graphics chips very shortly.
Additionally there have been a number of advances in the architecture of the systems themselves that will make significant advances in graphics. The advent of really high performance memory (Rambus, DDR, etc.) will certainly improve performance. And then there are some really uniqe designs coming that use copper-wire interconnect technology to give roughly the same performance as "system on chip" designs. And with all that, they die sizes of the chips themselves will keep shrinking (I think the new ATI chips are done on a .18 micron process). So suffice it to say, things are only going to get more interesting.
To answer myself: Yes, I know that some time ago, IBM manufactured a generic DSP card that was used as a modem and a soundcard, and yes, I know that it blew.
But I think that the concept is right, yet IBM failed to actually do it accordingly.
------------------
------------------
You may like my a cappella music
We're entering a time when the only way to program 3D cards is manipulating the registers directly. There's no way you can get these cards supported by a library in time for the next generation of cards. We're leaving the age of abstraction and it's becoming more important for software to access the graphics hardware directly.
I had the pleasure of ordering a ATI Rage Fury and a Nividia TNT 1 at the same time and running them to test them both on the same computer. Originally I was going to put the ATI In my prefered computer but was disappointed to discover that as much as the ATI Rage Fury had so many plus features and twice the memory the drivers were either not complete or the hardware was not as good as the TNT1.
I know what you might say: "Maybe your one card was bad..." I thought of that I ordered another one and had the same results.
The other thing was that It ran the first few months as the second closest thing to vapourware after Daikatana. The only people that could get a hold of them (after their release date) were people who review hardware.
Will the "New" ATi Rage Fury MAXX be the same story? If so then the niVidia GeForce will still be my First choice.
Conclusion: Wait till they both have been released. If you can get a hold of one for free test it and post your results for others to see. And for those who can't.. Check online before buying either.
Movie News - "Entertainment news, bitch!"
The OpenGL extension specification deals quite nicely with this problem. Hardware vendors can add new functionality through extensions without waiting for an official update to the library. (Non-extensible libraries like Direct3D will find themselves at a disadvantage.)
As 3D chipsets multiply, software abstraction becomes increasingly important. Application developers can't be expected to keep up with the onslaught of new hardware. If manufacturers want developers to take advantage of their new hardware, they have no choice but to support standard libraries.
I certainly wouldn't go out of my way to support a particular chipset if the manufacturer didn't bother to provide proper OpenGL support...
It's entirely possible to stack multiple processors onto one die.
(That's how the 486 and Pentium work, merging the 386 and 387 processors into a single unit. The CyrixGX went one step further, merging the graphics processor in as well.)
If Transmeta have a "universal instruction set" general CPU, merged with ultra-fast GPU and MPU, it would rip to shreds everything else out there.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
But that word "address" is the critical thing... In order to stack many processors together, and make use of them, you need considerable memory management hardware so that those CPUs can actually address memory, and not trample on one another whilst doing so. Parallelism isn't trivial to harness...
If you're not part of the solution, you're part of the precipitate.
That's certainly a fuller explanation of things than my knowledge can cover...
If you're not part of the solution, you're part of the precipitate.
The difference between a low end SGI and a high end PC is enormous. If you got a refurbished O2 with an R5200 you'd beat the pants off any PC box for the same price. With a relatively inexpensive upgrade you can get an R12000 instead. OpenGL support would of course be native and the graphics card would easily be comparable to a TNT2.
I'm a loner Dottie, a Rebel.