Moving back to software - when?

OpenGL OpenGL: Advanced Coding
41

Originally posted by RigidBody:

imho it does not make much sense to make the GPU do that work. if you want to display 30 frames/sec, you may have to compute 10-100 integration steps between each frame.
the gpu couldn’t do it, the general need though is for the ppu and gpu to have access to the same memory so you don’t have to download your finite element mesh or whatever from your ppu to system memory then back up to the gpu. i figure if the ppu is moderately successful hardware manufacturers will either concieve some sort of ppu>>gpu modem or start putting them on the same card somehow. the ppu would have its own memory, but it would be able to dma its final results per frame out to the gpu memory.

any idea where the ppu will go? will there be boards at the proposed december launch with 3 or 4 pcie16 ports? sometimes there docs talk as if there will be multi-processor mainboards with ppus right on the board presumably next to the cpu.

42

i don’t think memory transfer will be a big problem, because the PPU will compute only a few hundred trias/quads.

although i’m probably not going to buy one, i’m curious to see how it will turn out. 10 years ago there was a 3D accelerator card by 3dfx, which was an addition to an existent graphics board. as i remember, i did not know many people who had one. and i don’t think there will be many people who buy an extra PPU card. if they have some bright heads at ageia, they will try to find a mainboard manufacturer who will integrate their chip into a mainboard (if that’s possible).

43

Originally posted by RigidBody:
[b]i don’t think memory transfer will be a big problem, because the PPU will compute only a few hundred trias/quads.

although i’m probably not going to buy one, i’m curious to see how it will turn out. 10 years ago there was a 3D accelerator card by 3dfx, which was an addition to an existent graphics board. as i remember, i did not know many people who had one. and i don’t think there will be many people who buy an extra PPU card. if they have some bright heads at ageia, they will try to find a mainboard manufacturer who will integrate their chip into a mainboard (if that’s possible).[/b]
Well, I bought one of the original Monster3D cards, and I’d love to buy a physics board. Of course, my budget right now is a bit stretched, so that probably won’t be possible…

As for rendering only a few hundred quads… IIRC, they mentioned 50k discrete particles running at 200 fps on the board, but I’ll have to look up that info to be sure I’m remembering it correctly. I remember thinking at the time, “50k particles isn’t enough to accurately simulate anything!”

44

dont know if its of interest, but it seems that asus will be the first to start integrating this ppu
http://www.tomshardware.com/hardnews/20050517_202925.html
what i really wonder is if this additional processing unit will really be that useful since now everybody is jumping on the multicore cpu train…

45

bChambers, the world should be full of people like you :smiley: always buy the new stuff, keep the world turning…

i’m not too familiar with particle systems, i was thinking of something like this:

(as you see, the image comes directly from www.ageia.com )

there are many race games, and their developers would be keen on a PPU which can simulate a crash like
shown in the upper image. but for a crash like this i think you’ll need at least 2000-5000 trias (not considering
the flat tyres :slight_smile: )

Chuck0, thanks for the link. it confirms me in my opinion that a PPU will only sell if it is integrated in a mainboard.
like a 3d accelerated chip could not be sold for itself, but only integrated on a regular graphics board. asus will first
build an additional board with the PPU and thus get experience with the chip itself, and maybe later on they will
put it on one of their mainboards, as a feature like sound, s-ata or lan.

46

that image is total unfounded hype like 90% of the material in ageia docs and internet resources. notice the ‘getty images’… that is just stock footage of a real car probably after some kind of natural disaster if it isn’t obvious. the current generation ageia ppu can’t get close to that and probably won’t even be able to in a decades time.

47

well vodoo2 and especially vodoo1 cards were extremely succesufl mostly because they were head and shoulders above everything else which was available during their time… if this ppu would be able to accomplish the same, then i guess it would have a chance even as expansion card. but i doubt that since im quite sure that one core of modern dual core processors can alreay be utilized as physics (and ai) coprocessor and even if its not that highly specialized for the task i guess it could perform quite well in comparison to this ppu.

48

its difficult to take ageia seriously if they won’t release internal architecture details, but appearently they have industry partners backing the endeavor so presumably they have some inside information or at least some company shares… still looking at the SDK API, if someone doesn’t produce an opengl style wrapper for this i would either be turned off or decide to do it myself. apparently the SDK is built on DirectX conventions, but i wouldn’t know not being a microsoft champion myself.

49

well, i think that a single core cpu together with a ppu will have a higher performance than a dual core cpu without ppu. i think the instruction set will be very small compared to a normal cpu and thus highly accelerated- i read that the ageia ppu has about 125 million transistors.

the interesting part is about their physics api- i wonder if they will provide a non-accelerated version. if they do not- it should be hard to find a software developer who spends probably a lot of time and money creating a game which can be sold only to someone who has a ppu, which is a big financial risk.

but if they do provide a software-only api they run into the risk that someone can compare the performance of a ppu- with a non-ppu system and thus find out that a dualcore system without ppu could be a better buy.

50

It’s supposed to accelerate Novodex physics. So there’s your software physics engine.

But it would be nice if they opened up an API for others to use.

51

Originally posted by Chuck0:
im quite sure that one core of modern dual core processors can alreay be utilized as physics (and ai) coprocessor and even if its not that highly specialized for the task i guess it could perform quite well in comparison to this ppu.
But will developers want to use an entire cpu for physics? Personally I’m hoping that the next gen graphics cards are dual core gpus so we can have two graphics contexts and make full use of dual core cpus for graphics. It might go some way to explain why were having to wait a relatively long time for this next generation of cards. It also ties in with reports that the g70 is twice as fast as the gf6.

52

Originally posted by T101:
[b]It’s supposed to accelerate Novodex physics. So there’s your software physics engine.

But it would be nice if they opened up an API for others to use.[/b]
The PPU is designed around Novodex so no other API! It is pretty stable, fast and feature rich.
And yes, it’s suppose to be GL like. No hw drivers means soft emu, else use ICD.

53

Originally posted by Chuck0:
dont know if its of interest, but it seems that asus will be the first to start integrating this ppu
http://www.tomshardware.com/hardnews/20050517_202925.html
what i really wonder is if this additional processing unit will really be that useful since now everybody is jumping on the multicore cpu train…
Of course it will sell. It doesn’t have to be faster than a dual-core machine; it just has to take some work away from the CPU, allowing the CPU to do other things (like edge detection, AI, sound mixing, etc).

As for Novodex, you can get the SDK by registering with Ageia (it’s free). The SDK comes with a number of fun demos; what I’d like to see, though, is a video comparison of hardware accelerated and software run. The demos all ran great on my system (Athlon XP-1700), so the question is: how much faster will they run with the hardware?

The only thing that really bugs me, though, is that to use Novodex you have to pay for a licence, which is something I (as an independant wanna-be) will never do. If they really want people to accept it, they should let ANY developer use it for free, and then make their money off of having a kick-a** chip.

54

You’re talking a hard-wired rigid body integrator here, aren’t you?
So, how many stacked boxes is it going to take to impress joe puplic enough to buy a dedicated add on card for?
It’s just not neccessary, is it?
Half Life 2 had a fully fledged physics engine, but how much of the gameplay actually used it? Not much as I remember, see-saws and a crane was just about it. This is because there’s a limit to how much gameplay needs realistic physics. Valve had a sandbox, played in it for literally years, and came up with some see-saws and a crane. Doesn’t that tell us something?

55

Originally posted by knackered:
You’re talking a hard-wired rigid body integrator here, aren’t you?
So, how many stacked boxes is it going to take to impress joe puplic enough to buy a dedicated add on card for?
It’s just not neccessary, is it?
Half Life 2 had a fully fledged physics engine, but how much of the gameplay actually used it? Not much as I remember, see-saws and a crane was just about it. This is because there’s a limit to how much gameplay needs realistic physics. Valve had a sandbox, played in it for literally years, and came up with some see-saws and a crane. Doesn’t that tell us something?
they probably didn’t use much physics because it would subtract from other needs of the cpu. i’m sure anyone can think of a billion ways to use hardwired physics that are much more suddle than boxes. the chip right now only does rigid body collision detection and response, constrained joints, and simple spring dynamics as far as i can tell. right now peoples minds are probably just a tad narrowed by the fact that physics comes at a loss from the cpu.

as for the sdk demos, i believe the frame rates they show are projected frame rates if the hardware was installed… if you hit the zero key in the viewer it will display performance and considerably lower frame rates.

56

The core problem is one of content, unbounded complexity and game design.

Even the most flexible games rely on serious limitations to where you can go and what you can do with few exceptions.

It’s inherent to the robustness of the game and the production time involved in creating it.

If you have real physics you can break the gameplay, and it’s not that you couldn’t have different gameplay, you could but it would seriously affect the game design.

You also don’t have the data there nor do I think it’s feasible to have the data in the near term. If you cut a car in half you need to see the inside of the car, if you blow a building up it’s a lot more complex to make it real or even approximately real.

Half life could crunch the numbers for moving stuff around but the game design didn’t use it, even where it was used it was horribly contrived. There’s a lot you could have done in a real world scenario that couldn’t be done even when physics was used. Cut a rope and the barrel falls and squishes a guy, OK, but launch an RPG at a plank of wood and nothing. It’s ridiculous and it’s very intentionally ridiculous because of the limits of game logic and game design.

It’s not enough to naively say you can do arbitrary stuff or arbitrary complexity. Not every game can be FarCry w.r.t where you can wander (that had serious limitations too), it affects the gameplay in ways game designers don’t want it affected.

Moreover how often do you use physics in the sense a game engine does, apart from your own body motion, driving a car or throwing or catching something, really physics doesn’t get much of a lookin in driving everyday events more than stuff staying where it is most of the time and more than the stuff games do today anyway. It would be a very contrived and strange game where you had to use physics to solve problems. It’d be like lemmings but even more quirky.

So what does physics really get you? The power destroy everything you can see and have it break up in a realistic way and you can consequently go anywhere. Maybe someone will write a game like that now, it’s not entirely impractical to do a lot of that now but it would be pretty bad if every game let you do that with impunity, and you’d quickly run out of original data. Just imagine a game where you could go anywhere in a city block never mind a city, and destroy or cut open or break open everything and the complexity required, and think of the boredom. I don’t mean in a rigged contrived fashion, rigged is easy, that’s why all you get is rigged stuff. I mean go anywhere do anything see anything physics & data.

57

personally i can’t get into a game without ‘go anywhere’ mechanics. when i play a game i want to feel like i’m really in it… its not worth playing if it can’t be that convincing, and there are enough games that deliver that to keep anyone who can balance their game life and real life busy.

as for do anything physics, i guess i’m not really crazy about games that would give you a rocket launcher and unlimited ammo. i also don’t see the fun in just going deviant like the GTA game people can’t get enough of (which i’ve never played)

anyhow, i actually suggested suddle effects. walking on grass, wind effects, just general reactions, that sort of stuff.

as for solid stone and metal structures, i don’t think it is asking too much to not be able to rase them to the ground. but i wouldn’t think cutting and burning wood structures and trees would be too much to ask of a hollywood type funding game in the future.

i’m not really thinking in terms of destruction though. think unconstrained animation, garments, things like jewelry, hair, suddle side effects and that sort of stuff that really draw you in to the illusion.

personally i would rather watch a movie or read a book if the game can’t draw you into its world. i go for chess every now and then, but games for games sake are not really my bag. if you are drawn in though you are in a different world where you can forget that you are really wasting your time in the real world. it doesn’t have to seem real so much as anything that makes the world seem fake pulls you out.

in the end though i think its best to focus all the physics on the characters. fluids would be nice and a good wind hack is always cool.

58

The only thing that really bugs me, though, is that to use Novodex you have to pay for a licence, which is something I (as an independant wanna-be) will never do. If they really want people to accept it, they should let ANY developer use it for free, and then make their money off of having a kick-a** chip.
well, if i for one ever use it, i will build on opengl state machine type wrapper for it. i can’t imagine why you could not simply make such a wrapper agnostic and link it against whatever ppu drivers are out there. i figure this will happen anyhow if the ppu catches on and the drivers will not require a license similar to opengl. for what its worth, the novodex docs are advocating dynamic linkage, and the api though structured does appear quite ameniable for an opengl wrapper.

off topic, but i’m curious about how many ‘indapendant’ developers there are out there. that is not people who would like to be part of the publisher/studio system but have yet to be indoctrinated, but people who really don’t like the model and would prefer something different and probably more scalable. is there any place where these sorts would gather? i’m always walking at least three different lines as a developer, but my dream masterpiece is a free run-time configurable/programmable completely abstracted virtual reality environment, a sort of game ‘interpreter’. its something i’m always working toward in the back of my mind. i can produce specs for something very close to the optimal platform for anyone who is interested. my implimentation is probably about 50% complete. the idea is to allow a single person to rapidly realize their personal vision and render game design about as demanding as writing a book or a song. this can be made possible by users sharing their artistic data and virtual device drivers in a shared central repository. the basic model is give a little take a lot! everyone wins. zero design constraints.

‘personal message’ me if interested.

59

W.r.t. physics stuff:
I seem to remember reading about a supposed demo of either Doom3 or Duke Nukem Forever (I suppose that referred to how long we were supposed to wait for it by the way) where you were supposed to be able to blow holes in walls and individual bricks would be flying.

I suppose that’s the sort of stuff you could use it for. In theory.

Then again, flying bricks isn’t your primary concern when you’re busy blasting the opposition in a first-person shooter.

Maybe in a car-racing game you could have some more realism (twisting of the chassis).

But I have to say, I think it’s with more serious applications that something like this would be worthwile to have.

Michagl:

the idea is to allow a single person to rapidly realize their personal vision and render game design about as demanding as writing a book or a song.
What? And put all of us out of business? :wink:

60

What? And put all of us out of business? :wink:
no you just go into business for yourself like an author… or if you want to do something more complicated do something more like a rock band. smaller teams basicly where everyone might have a slight expertise.

i did some scouting around tonight though. it looks like all of the indapendant game communities aren’t interested in developing tools(engines)… according to them, they only want to use pre-built platforms, which i figure probably really hurts their cause. they say however that popular indie platforms like torque are still more complicated than what an indie movement really needs to work.

if nothing comes up i figure i can deliver a competive platform in about 3 more years, but i worry about slow adoption due to the platform being spec-ed and implimented by a single individual rather than a community. still there is nowhere to go to openly discuss the matter it would seem.
it has to be so much more solid and flexible than a disposable platform.
if there are indapendantly minded people here willing to develop platforms that would like to help out, the gesture could probably go a long way.