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 dont care how fast the card goes i would never buy an ATI graphics card!!!
Ack. I've never been so much as a "softcore" action gamer, but even so I really don't see the need for that much horsepower just to play shoot-em-up fantasies as hyper-realistically (oxymoron intended) as possible.
But deep end video chipsets do have a purpose just a short ways down the road. True immersive VR worlds. 3D gogglevision with lag time well below the perception threshold (10ms, perhaps?). Gibson-esque Cyberspace. The Matrix.
Between screaming video and fast wires, the technology is almost here. How long will it take for the content to follow?
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
The graphics market is starting to really heat up - check the earlier story about the Voodoo 4 &5.
Good god, where have you been? The acceleration of graphical capabilities of PCs over the past two years (starting with 3dfx's DooDoo) has been incredible. Even last years games were aeons beyond those games of a year before them, and before that improvements in graphics technology and 3D were dog slow. We have been in the middle of a revolution in 3D graphics speed and quality for more than two years now. Hardly "just starting to heat up"
That was a typo! I swear! ;)
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. :)
DAMMIT!!! I just got a Voodoo2 1000 PCI card (because of the @!$#%* built in ATI Mach64 I have there isn't an AGP slot - my mobo SUCKS) for $50... now they're coming out with cards that new games will need them to play! Dammit, dammit, dammit! *sigh* there's always Quake 3 and Unreal Tournament... ;)
If you think you know what the hell is really going on you're probably full of shit.
If you think you know what the hell is really going on you're probably full of shit.
jdube is who I am.
Now, comparing that FireGL card to other things available, it's quite lackluster.
- -It won't do 3D in a window
I don't know exactly how much of the setup this new hardware will do... This could be interesting!-It's geometry setup actually slows down what my dual PIIs could do by themselves (at least, it feels that way)
"...America's great minds of today, teaching America's great minds of tomorrow. Poor bastards." -- A Beautiful Min
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))
How come I always have to be the one that points out the really obvious errors???
I liked everything about your post until you got to the point of where without XFree86 acceleartion, this card will sit around doing nothing... So long as MSFT and Apple incorporate the drivers into their respective OS's, there's a huge market for this card.
There'll be a slighlty larger one if XFree86 has drivers for it too, but in the short term, the markets already here.
Again, apologies for the anonimity, but i seem to have lost almost 10% of my karma due to misunderstandings today!
See the thread on Glide being open-sourced. If we had some specs, maybe there's more than meets the eye here.
But, essentially, an implementation is available.
Pan
I said no... but I missed and it came out yes.
First it's OS of the month (Win 2k, win98, win ce) then cpu of the day (PIII, Athlon, K6-3) and now gfx card of the week. It's all talk for a computer that may never be seen in stores. MS doesn't do computers-if they did, even gateway and Dell would go nuts at the idea that MS is competing with them.
---
Think of it as a hardware-interpreting-coprocessor!
"...America's great minds of today, teaching America's great minds of tomorrow. Poor bastards." -- A Beautiful Min
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.
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.
Let's not forget my new product... it's a 4D accelerator. Everything is purely theoretical, and the "graphics" exist in an infinite amount of places at an infinite amount of times. How's that for fill-rate?
I find the current obsession with 3d graphics and 3d sound rather odd.
/bastard/ of a computer.
I myself am a casual gamer and played my share of Half Live, Descent and Freespace (try Freespace, it's good).
Now if I look at any current game-capable home PC, I think those are quite a
- A graphics card that generates a LOT of heat, so much that it needs its own fan.
Some graphics cards consume that much power that the mainboard's chipset starts behaving flaky. Some graphics cards consume more power than supported by not-that-old chipsets and can indeed create actual hardware defects on a mainboard.
- My desktop's graphics card has 32 MB of RAM. Come on, my laptop has 32 MB of system RAM and I do close to everything on it, including word processing, database development, web server stuff...
- Yet, the graphic's card awesome processing power and its RAM are being used for gaming only. I mean, most of the time at a computer I spend my time programming or using office applications. At these times, these resources are just idly wasting power.
- What do these modern graphics cards do? They speed up 3D related calculations.
- Isn't that more or less a specialized variant of what a digital signal processor does? Or am I naiive when it comes to a DSP?
- Why do we have to have specialized chips for graphics, sound, win-modems and whatever when we could have used a single type of add-on chip to help the CPU? Why did the industry still not decide to put at least *one* versatile, programmable DSP on every modern computer mainboard? Those things are cheap, they are versatile, they could be programmed to speed up a whole bag of different algorithms such as audio (think live MP3 encoding, that was possible years ago with a DSP), graphics (Photoshop filters), encryption. Again: Or am I naiive when it comes to a DSP's capabilities?
- Another related question: Why this odd decision to push 4-way sound cards for 3D sound? 5 channel home movie theatre stereos exist since a long time, why did noone in the industry decide to offer a simple card to connect with those.
Oh my. I don't claim to be an expert on DSPs or 3D audio. But still, from the little I know, I think that the last two years in PC hardware design went terribly wrong...
------------------
------------------
You may like my a cappella music
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
Will I have to connect your company's graphics card to a cup of tea? Now that would be a change.
------------------
------------------
You may like my a cappella music
"I long for the days of nes, snes, and genesis, where game programmers had to come up with ORIGINAL ideas. "
And frequently didn't. Can we say Mortal Kombat and [insert SNES Street Fighter clone here]?
"Now it's almost always shoot-em-ups!" ;)
Please don't confuse 3D first-person-shooters with the traditional shoot-em-ups; as defined at Shmups.
--
It is basically a gutted PC. Wow. It is just a way to build hype. And the more they don't say about, the more people will just get annoyed and go away.
Like Nintendo with their Project Reality, Ultra 64, etc. Even Nintendo now discloses more than MS. Nintendo has to be the most secretive and strange company. They do some of the strangest things, but they can pump out the games. They can make a good game and find companies that can make fun games for them.
Can Microsoft do that? Unless they basically try buying their way in, they will have more of a problem than they expect. Nintendo and Sony have deep pockets. And they have no series characters. Like Pokemon, Mario, or Crash. And no Square.
And at least Nintendo basically has disclosed general info. Like the IBM copper CPU, etc.
I don't really care too much. Good games make people buy consoles, not the processor or the damn graphics card.
"I disapprove of what you say, but I will defend to the death your right to say it" - F. Voltaire.
- My desktop's graphics card has 32 MB of RAM. Come on, 1280x1024x(3bytes color + 1byte alpha + 4bytes Z)x2buffers = 20M, which leaves just 12M for texture, which is not much.
At these times, these resources are just idly wasting power.
The amount of power consumed is porportional to the work being done. An idle graphics chip is not burning much power.
- What do these modern graphics cards do? They speed up 3D related calculations.
They do transforms and texture mapping, which require gobs of number crunching.
Isn't that more or less a specialized variant of what a digital signal processor does? Or am I naiive when it comes to a DSP?
A DSP just a specialized chip (to do FIRs, IIRs, FFTs, etc), just like a 3D accelerator is a specialized chip
Why do we have to have specialized chips for graphics, sound
Because a specialized chip is always faster than a general purpose one
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 think that's a bit of a temporary situation, really. Right now, almost all the first person shooters are competing for 'wow factor' in the area of visuals. Some of them do include some cool features and all, but, all in all they are the same game with beefed up graphics. However - there are companies that do currently produce games that make use of 3D hardware that aren't just the same FPS over and over. Dungeon Keeper 1 & 2 is a good example. So is the upcomming 'God Sim' Black & White (something I am REALLY waiting for!). There's new flight sims making good use of the hardware, Bullfrog's expansion of the Theme Park series, RTS games, etc., etc., etc. I also think you should look back in the past a little more about those 'orginal' ideas - for each original game there were a dozen that came right after it that tried to do the same game, but better. Looking back even futher, look in the arcades at things like Galaga, Galaxians, and the tons of other games that were just like them. For now there isn't a whole lot of innovation, but there is some. But, as the FPS market gets more and more glutted, and becomes less viable for new developers looking for a part of the action, 3D hardware will get pushed in other directions instead. It's a cycle that happens all the time, this particular one being not very different from the rest of the game cycles that have occured before it.
Davis Ray Sickmon, Jr - looking for something to read? Check out my three free novels at MidnightRyder.org
ati may not be open source but it sure shows and proves how more advanced intel 3d cards are than the overpriced SGI stuff you always hear about but never really see...
i mean, i get about 85fps on quake2 with TNT/Linux but only about 19fps on one of those SGI O2 machines...talk about lame 3d...SGI is pisspoor.
also, titanic was done completely on Linux...where were those SGI big fancy machines then? nowhere because they cant stack up to Linux and Intel 3d.
case closed.
"Oh, but they're such a kinder, gentler company now! Why, only last month, they released ALL the Rage series programming info, and announced full support for Open Source!!"
OKAY, WHAT ABOUT THREE FSCKING YEARS AGO WHEN I DROPPED $179 FOR A ATI CARD THAT WAS "SUPPORTED UNDER LINUX", BUT IT WAS ONLY THE 2D SIDE?
AND WHEN I SENT THEIR MARKETING DEPT. A *NICE* LETTER ASKING THEN TO RECONSIDER SUPPORTING 3D AND TV ON LINUX, THEY SENT ME A HOSTILE EMAIL SAYING THEY WOULD "NEVER" SUPPORT OPEN SOURCE3D, OR TV IN, ON LINUX!
screw ATI. I would never buy a product from them again. i was poorer than shit back then, and I'll be damned if I'm gonna just "forget about it".
3dfx has been the leader in Linux/Open Source support from the beginning. ATI or some other company would have to seriously leapfrog 3dfx consistently -- for at least two years running (IE 3dfx would have to screw up BAD) -- before I'd consider change brands.
screw ATI and the bastards in their marketing dept. you ripped me off when i was poor.
get a job, gameboy. then you'll need a real machine.
This is supposed to say this:
Personally, I like the expanded colour range and on the fly hardware particle generation.
All you need to do is press down on the sockets to reseat the firmware for a minute or two.
Days of fun.
Thanks for watching. I'll spell better next time.
honest.
Pope
It doesn't mean much now, it's built for the future.
can you say EVERQUEST, massively multiplayer adventure game
can you say Tribes!
can you say Thief!
can you say Half Life!
theres more than just quake3 these days
:)
-I go to Rice, so figure out my email address
That's the way it's always been. How do you think Pokemon became so popular on a 1 MHz processor with 8K of RAM, while Dreamcast games like VF3tb flopped with a 200 MHz processor and 26 MB of RAM?
Isn't _anyone_ here concerned about where this story came from? Sharky isn't exactly known as a credible journalist..
a "minor" detail.. the article doesn't mention anything about an ATI chip with those specs. specifically, it says MS is looking for a card that can do 2 gigapixels/sec for its X-box, but it doesn't say which one. it speculates that nvidia and ATI have candidate products for the x-box, but it doesn't specifically say ATI has such a chip.
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...
Any information about the ancillary buffers available in the ATI card? I've been working with a TNT2 card and the results are pretty poor if you need stenciling or accumulation, using the 16 bpp X server provided by NVIDIA. I'm working with robotics simulation and I would be better served with an SGI box -- but most people (including the lab managers etc) can't see the difference between a high-end PC with a 3D card designed for games and a low end SGI workstation with a slightly higher price. And the 3D hacks in xscreensaver don't work in full screen mode with my card (in fact they work, but in single buffer mode). I've been offered an Ultra 1 box with a Creator card, which is slower than an average PC (ok, I guess an Elite 3D card would help me there). I'm now waiting for that workstation-class NVIDIA card, or perhaps this ATI card if it has the extra buffers.
I've worked in the graphics industry for years and the problem was never ``processing'' pixels. You could build DSP farms to do as many as you liked.
The problem has always been getting them out to the frame buffer. Memory is only so fast.
So let's do a little math. At 2Gigapixels per second you would need a framebuffer with 500ps memory to accept the data. That was 500 Pica Second. Does such memory exist? What does it cost?
And if that kind of memory is readily available and inexpensive enough to place 8MB of it on a graphics card, why can't I get it for system memory and do away with all that caching overhead?
I am not an Anonymous Coward; /. just refuses to acknowlege my registered account.
My name is Bob Washburne, rcwash@concentric.net
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)
Don't forget synth applications!
Most modern "analog modeling" synths use one or more DSP's as their sound-engines.
Clavia Modular series, Yamaha An1x, Virus, etc, etc.
/.Mattsson - My native language is not English, so please don't whine over linguistic errors. (That's lame anyway...)
Your description of graphics processors, including "XORs, fills, tight loops oriented towards shading" describes the bottlenecks in 2D graphics chips well, but does not describe the problems one would need to optimize in a 3D graphics chip. The 3D bottlenecks are not amenable to a Transmeta-style solution, IMHO.
I've done some research on the 3D graphics chips of UNIX workstations and PCs over the last five years and Transmeta's approach doesn't make any sense as a peak-performance graphics chip. While I must apologize to any real 3D chip designers out there for my generalizations and any misconceptions they may spot with their even greater experience,
I'll try to summarize why programmable chips don't make sense to accomplish fast 3D:
1) If the algorithm a chip must execute is fixed (as it generally is with 3D algorithms), nothing is faster than a well-designed hard-coded ASIC that lays down precisely the circuits needed for optimally accelerating that algorithm.
2) If the algorithm varies substantially, a general purpose processor is more useful. In cases where there is significant unpredictable branching in the algorithm, a general purpose CPU will be optimal. In cases where there is strong data parallelism, a DSP will be optimal.
3) Run-time programmable logic, such as FPGAs (field programmable gate arrays), microcode, or Transmeta-style programmable logic, has traditionally been best for cases where
3A) you want to trade off top-notch ASIC speed for programmability in case your algorithm isn't debugged or you get flaws in the silicon
3B) you wanted to accelerate a broad, flexible set of functions faster than, say, software, but didn't want the expense of a general purpose microprocessor
3C) you really want to accelerate one algorithm now, but in few minutes, you want to accelerate another. With 3D you're changing the path picked through the 3D pipeline multiple times per frame, at every state change. You wouldn't be able to reconfigure your chip fast enough to optimize for that type of changing; at best, you might reconfigure your logic for a particular 3D game and the 3D primitives it uses.
Transmeta and FPGA chips can of course accelerate 3D logic, but what you have to realize about 3D logic is that
1) it is very branchy- lots of special cases depending on just whatever mode you're in (This makes DSPs and rasterization a poor fit, although Intergraph has used DSPs for geometry acceleration)
2) the front end geometry processing is primarily floating point (vertex) matrix manipulation, the back-end rasterization is primarily integer (pixel) manipulation; your architecture must provide both types of execution units, in the right proportion
3) the process of shipping all the various vertex, texture and triangle-to-pixel data is very timing-sensitive, requiring lots of dedicated FIFO buffers for optimal acceleration
4) many pixel operations such as pixel walking or gouraud shading generally require very simple increment operations that don't require a full integer unit as one would find in a CPU or DSP (FPGAs would be better here, ASICs better still)
5) the data paths between circuits on the chip grows practically exponentially as you go through the 3D graphics pipeline. Megabytes of vertex data turn into gigabytes of pixels. A general purpose CPU or FPGA are not typically optimized for this.
6) moreso than FPGAs or CPUs, a 3D chip has to be optimized for huge output bandwidth to the frame buffer, both read bandwidth (for Z buffer and blending operations) and write bandwidth, with a separate set of data lines for reading in the initial vertex/texture primitives. The backend frame buffer bandwidth typically requires more pins than you'd have in a CPU/FPGA package. And most CPUs, DSPs, and FPGAs don't have such split memory controller setups integrated into the package, requiring a more expensive external chip.
If this got too technical; I apologize for not having time to make it simpler and/or more precise. But nothing I've seen about Transmeta rings any bells as having promise for making a faster 3D graphics chip, something I'd be very interested in.
--LP
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.
Get the TNT/TNT2 drivers from the glx CVS server, or snapshots. I guess you could find the website by looking for "glx", "mesa", and "tnt" on google.
Xscreensaver will work double buffered (which means it won't flicker, if anybody else has that problem), but, expect that you will have bugs in other GL apps. Also, will be a lot less stable. An unstable X can and will crash the entire system. To top off that, no matter how hard you try to optimize it with -mpentiumpro cflags and such, the CVS driver will be slower than the binary released by nvidia.
I know I will be moderated down for this, but . . . Vincent
Digital signal processing is a technology used to take an analog audio or video signal, convert it to digital format (duh), and then takes advantage of its digital state to perform modifications to the signal: ie filtering out noise, or enhancing a video stream, etc. I'm willing to bet that video cards that have some sort of video input or a TV tuner built on-board have DSP chips to process the information.
With 3D audio, there is a sound card that will output sound to a Dolby Pro-Logic Surround Sound capable receiver: Creative Labs' SoundBlaster Live! series, including the original card, the value edition, the MP3 edition, the platinum edition, etc. The first main software upgrade to the sound card (LiveWare 2.0) included the ability to encode audio in Dolby Surround format, so you can plug it right into your favorite home-theater stereo and blast yourself away. Believe me, it's fun. =)
This is exactly what the Bit Boys chip seeks to overcome when it ships (???) by putting the frame buffer on the same silicon as the rendering engine. It will be sweet if they deliver it.
1) take your Ritalin tablets 2) turn off your caps locks 3) you are not a gangster, you are a skinny white boy 4) re-read your grammar texts 5) try a spell checker 6) talk to your counsellor about anger management Have nice day :)