Last message on previous page:
A couple things I've been meaning to say.

First of all, StrangeStranger, you keep on saying that GPUs are really good for calculations, and that's all physics is, so GPUs should be really good at physics (although ask yourself, what processing part of the computer ISN'T good at some form of calculations?). Calculations are calculations after all, right? Fine, then explain to me the OTHER thing you keep saying (No, not "ur stupid read the article" ) : This picture here:

You keep on saying (not an actual quote, but I don't want the stupidity to look like it's my idea) "Look see if you read the article you'd know that the GPU has lots of extra processing power, see how the pixel and vertex shaders aren't always being used?" Here's what I want you to explain: If calculations is calculations is calculations, then WHY can't they simply balance the load between the vertex shader and pixel shader? Obviously you can't just stick calculations anywhere and expect them to be done, there are optimizations to be taken into consideration (my spoon is good for soup and my fork is good for salad, switching their roles doesn't work so well if it works at all). Think about it, if a GPU is at least 10 times as powerful as a CPU in terms of raw processing power, why don't they just stick 4 GB of DDR/DDR2 on a graphics card and offload all calculations onto there like a CPU? Maybe it's not so simple, maybe there are software/hardware/firmware things to take into consideration.

Speaking about this free processing power due to pixel shaders and vertex shaders sometimes being fully utilized while the other is twiddling its virtual thumbs, if I understand the Unified Shader concept it combines them which would essentially nullify that point. It's funny, now that I think about it, this relates back to me being an "idiot" and digging myself into a deep hole of stupidity. All I asked was that graphics cards companies work on exploiting that "hidden power" for graphics first. And you know what? If I'm given the choice between the Unified Shader architecture and what we have now, where I'm forced to lose potential processing power due to VS and PS being separate, I'm going to choose the Unified Shader stuff (which I believe ATi is using in the R600 chip and used in the Xbox 360 chip). Maybe I'm crazy for wanting my graphics cards power to be used for graphics, but it seems ATi at least is crazy in the same way, so I don't really mind.

So what have I tried to establish thusfar? First, in current processor architectures, not every piece of processed silicon can do everything as well as the next one; if this were the case we wouldn't have multiple processors with specialized uses in our computers. Second, the physics processing power that's sitting dormant in current graphics cards will hopefully be used in the next generation of GPUs.

One thing I realized the other day but didn't get around to posting in regards to random numbers in physics... first of all, one point of realistic physics would be to eliminate a great deal of randomness (in a current game, you might program 3 different ways that a window or vase might shatter, so as to add a bit of variety without complex calculations) by simulating, on a simplified level, "exactly" what happens. If all 30 computers of players on a map get informed that a grenade was thrown under a car, assuming the physics are done properly, the explosion should be the same each and every time, because each computer can calculate the trajectory of the grenade, its position and speed when it explodes, the resulting concussive force on the car above it, and if that is enough to blow off any parts. However, if you want random numbers this shouldn't be hard at all to do. You see, when a computer makes a random number, it's not really random. A computer can't just invent a number; random numbers can generally only be done by doing physical simulations. However, say we have a game and we want to have some random stuff going on. The game could have a pre-programmed table of 10,000 random digits, 0 through 9. When a multiplayer level starts up, it would tell every computer to start at a certain position in the table, and every time a random number needed to be used, the clients could all get it from that table. Maybe they pick every 7th number, or move forward x spaces (where x is the sum of the random number and the one before it on the table). The end result is that the computers all have a list of random numbers from which additional "random-enough" numbers can be picked, yet there's still a formula so every computer will always end up with the same result.

A final point, to people who keep insisting that Cell Factor is currently just a demo of "cloth tearing" and "liquid spilling". Did you not find destructable objects interesting in the slightest bit? Somebody tries to take cover behind something, and you blow it to pieces; not only does this add to the gameplay by forcing players to make intelligent choices about where to hide (YES behind the 2' thick concrete wall, NO behind the plywood) but it also populates the game with massive amounts of truly physics-driven rubble. It appears and behaves in the ways you would expect it to, as opposed to current games where a grenade or gunshot will make sparks and sprays of dust which promptly disappear. Destructable objects are very cool in my opinion, as is the magnitude of objects in general. Sure, it's neat to be able to hide behind a single box, but not anywhere as neat as hiding behind a stack of boxes. In earlier times, the stack of boxes would be treated as a single immobile object, probably to reduce physics computations. With the ability to calculate huge amounts of objects (throw a gravity grenade to see what I mean) it's feasible to make any and all objects physics-driven, adding to the dynamics of gameplay. This also goes hand-in-hand with destructable objects, because if you can use a grenade to turn a stack of crates and a car into thousands of independently animated fragments, you better be able to calculate them all. Granted, those could be done with software-only mode (as I did myself) but they're taking processing power from somewhere, and I have a feeling I could add more bots if my CPU wasn't bogged down with that.

In the end I'd have to say I hope it gets standardized like DirectX, which should make everyone happy: The pro-Ageia people would get their cards, the pro-GPU people would get their cards, and everybody would benefit from the competitive drive to crank up performance on the cards, as well as a standard way to compare them.

You call that clear? Lets take a look at your posts…

First you say:

Then you say:

The first quote is talking about unlocking potential within current cards, while the second says you don’t care about today’s cards and know that there is no potential to be unlocked. Hmm… Maybe this is would make it unclear? You can count two contradictions in your posts here. There are several others in your posts, but that will make this post too long.


Also, look at this sentence. Does this imply you are talking about FUTURE video cards?

Hmmmm… You refer to your graphics card, which you care about. Yet with the previous quote you DO NOT CARE about today’s cards. You also state that:

Current GPUs are not used for physics calculations within games, so it is not, as you say, “done now”.

This leads to two conclusions for your drivel:


A) You have developed a time machine and you currently own a future video card because you want the best graphics outcome for your current video card, but you don’t care about today’s video cards because you own the video card of the FUTURE!!!!! In this case, can you please use your time machine to go back in time and clarify your posts so that they would not cause this confusion?

or

B) You are confused and not sure what you previously wrote, and why people do not understand you. In that case, that effective communications class at your local community college seems very tempting now!

Hardly; ever heard of ray tracing? :?

tbh i don't know much about that (its been explained to me beofre but i've forgotten) but i have heard it takes quite a few comps or at least a super comp to do it in real time. i might be off about that though. what is it exactly hey you. i'm lazy and can't be bothered googling.

Hardly; ever heard of ray tracing? :?

Do you mean Raytracing as a alternative render methode.
Because you can do Raytrace collission to with simple straight gun fire Physics.

Currently Hardware is aimed at geometry Texture Pixel shading method.

What if there whas Specific a RT_VPU or VVPU
RaytraceVisual Proscesing Unit.
Voxel Visual PRoscesing Unit.

Problem with raytrace and Voxel it only excist in software so it is a CPU load.
Where the geometry Texture pixelshading Method has the Option software and Hardware Support.

Knowing The difference between a CPU and the latest GPU is in graphics prosesing. What could mean Hardware acceleration for Raytrace and voxel.

It's mayby possible with those GPGPU of today and unified nextgen. Those uniform shader could be mis-used for Voxel computation.
As there where Voxel and geometry hybrid Novalogic games.

Raytrac i don't know. But hardware accelerated with specialiced hardware.
Could make a big deal.

Just Like PPU for PhysX
And AIS1 for AI.

GPU is acting more as a general purpouse Parrallel Coprocesor

Alright, further clarification because you don't seem to get it. I'll go in order of what I posted.:

I did in fact say

This was a bit of a tongue slip on my part. It was a careless combination of two true statements: 1) Some people are advocating using CPUs and GPUs to do physics calculations, and 2) CPUs currently do the physics calculations. The point of the sentence was to say "People seem to think that CPUs and GPUs can handle complex physics, but if we look at modern game physics as they're implemented [using CPUs] there isn't nearly the level of physics detail we could hope for." Fortunately nobody else was tripped up by my unintentional statement (that GPUs currently do physics calculations) in the next 4 pages of posting otherwise they would've shouted "OMG I want your graphics card how well does it do physics??" Gimmie a break. It was a decently sized post, and I'm sorry if I didn't have an English professor proof-read every sentence to make sure it couldn't be picked apart by overly-hostile persons such as yourself.

The next time I posted, I said

You ask if this could talk about future cards, and it absolutely could. When I said "my graphics card" I didn't just mean my current card, I meant cards I might buy in the future as well. To demonstrate this, when I say "If my (current) graphics card has processing power to spare, I'd like to see my resolution hit 1600x1200 [etc]" and "If my (next) graphics card has processing power to spare, I'd like to see my resolution hit 1600x1200 [etc]" it still makes sense. Whether it's now or next year, I'd like my graphics card to do the graphics. The only scenarios I now envision for which I would approve of graphics cards doing physics is if I'm running at max graphics detail and resolution at fluid framerates and there's still processing power to spare, OR if some design issue with graphics cards means that they cannot and never will be able to use some of their power for graphics, but they CAN do other things on it.

Obviously, however, other people DID understand me, just not you, and just not until now it seems. With later posts I've tried to clear up what I'm saying, but you seem completely unable to deal with it. Due to your deliberate misinterpretation of what I was saying, negative and sarcastic attitude and conclusions, completely pointless personal attacks and utter refusal to let go of any way you might have to demean my valid opinion, I have to conclude that you're one of those people who enjoys getting a reaction by provoking somebody to no end rather than having a useful exchange of ideas. Instead of trying to come to the conclusion that I'm either from the future or that your inability to understand what everyone else can stems from my lack of communication skills, how about you try to address the pros and cons of hardware vs software physics, using past and present products, as well as possible future scenarios? I'm sure it would be much more useful and relevant to the article this thread was based off of.

I already did. Please read the thread before making conclusions.

*Sigh* Here we go again, more flaming, well, transistor count does not determine a chips prosessing power and how many instructions it can do per sec, take a 7800 GTX and a X1800XT for e.g. wait, a X1800 has a special instruction feature that enables every pixel and vertex engine to work almost every clock, the performance matches the 7800GTX, not so strange.

Heh, personally I don't really like my GPU to do Effects Physics and simple collision detection like ragdolls(It can do ragdoll, but the ragdoll won;t be able to hit you even you can hit it, get it?), I would like physics to be process on something like a PPU, I mean on paper, it would be nice see? like I got a bunch of ragdolls and other objects in my current viewing area and my FPS is 58, I put a nice little 'nade in the middle, then kaboom, FPS dropped to only 50, get it? Nothing is added, exp for the explosion effects and the granade model, since all the objects are already there, try spawning 30 ragdolls and other breakable stuff in Half-Life 2 Garry's Mod then put a granade in the middle and you would know what I really mean.

I think the limiting factor on physics simply lays in updating thousands of objects, both across the system bus and more importantly over the net. Most games deal with a few dozen objects and crap out with more.

I'm guessing the biggest growing market in PC games is MMOs or multiplayer and I can't fathom keeping thousands of objects syncronized over the net. Physics in games are good for a for a few interactive objects at a time and for graphical effects. I really hope physics improves, but I think the bottleneck is everything but the math itself.

[img]HERE[/url]
Getting quake-3 to work required 20 AMD 1800s. Notice the superior lighting, shadows, reflections, and refraction.,
I believe some special ray-trace cards already exist.
I won't be surprised if real-time ray-tracing becomes common this decade. (these examples are like over 2 years old already)

[img:b673f7365a]http://graphics.cs.uni-sb.de/~sidapohl/egoshooter/screenshots/mutlipleReflectiveSpheres.JPG[/img]
An old game, but seeing it in raytracing is one of the coolest things I ever seen.

Yes nice old stuf if you compared it with what is posible now Crysis.

Now imagine if there where no GPU only simple rasterizor chip.
You need a 40 conroe render farm to do Crysis on the software reference device. Emulating The shaders and pipelines.

RT & Voxel need Hardware acceleration. But the market has choosen for the other methode.

So I like the PPU solution it means a lot more Physics is posible in games.

And games get jet a lot more complex.

//edit

Link please? . It's a fictional example.
Point is with a 90nm 300Mill RTVPU you need one conroe and a way more advance game is possible then the old Q3. But Q4 or crysis. with a lot of extra unit to push the eyecandy up.
20 AMD CPu for Q3 is not a commercial sucses.

Link please.
Thanks...

I did'nt want this post to be a mile long,but something you've said really knocked me off: "The real killer app, here, is clearly the prospect of destructible terrain. A popular subject of war FPS titles, for instance, is blowing up bridges or other buildings; every title I've seen has an instance of it. However, as you mentioned, just like the tripod-created-craters in the "Follow Freeman" chapter, they're all, to put it that way, "pre-canned." (perhaps a better example would be the first campaign of Call of Duty 2, which used scripted destruction every few moments)

What would really enhance the believability of games is if such destruction could truly be handled in real-time, and be completely variable. In a word, what would really convince people would be a small-scale scientific-grade physics simulation on a card. "

No offense,but this is as stupid as it gets. In order not to script events in the game, you have to make an advanced AI. Now,in COD 2,for example, you are running through the trench, while the (scripted) destruction takes place around you. Imagine the writing of the code that would allow a great number of your opponents to interact,change opinions and experiences and THINK!!! They would then be able to spot you,tell the tank commander about it so he could fire a shell directly at you. This is something we've seen on a small scale in F.E.A.R. and other games, but i guess you wouldn't expect it to be possible with 100 (or more) artificially intelligent objects (enemies). Or,if You have,lets say,an gigantic underground worm that's "chasing you".He's supposed to jump out on a certain place,and kick something off (usually,to devastate something completely).You would NOT be able to destroy it yourself before that,with or without the physics card!!! If there wasn't for the trigger zones in the games,they would not be possible at all.You just cannot build a perfect universe inside your computer and just join and interact.
Imagine a machine You'd have to have for this.Also,this opens an issue of enormous media able of storing and transfering this data, and,of course,the sheer time and resources required to make such a game.

This post is more likely to be in Games section,but I couldn't help it. Sorry.

I already did. Please read the thread before making conclusions.
I have read the thread. If you're done making useful input, then fine. Just stop this pointless bickering because I think everyone is fed up with it.