A CPU cannot match a PPU or GPU for physics!

[HOCP4ME]

That statement I disagree with a lot less. I think your attempts to predict where the industry will be in 8 years are pretty wild though.

It's not that I didn't understand what you meant, but that I couldn't possibly agree with a statement that was completely false. You should try and say what you mean. I assure you again that I am not being pedantic.

You also needn't concern yourself with being compared to Terra. This is at worst a mildly interesting discussion.

Okay then, I guess a little clarification is all that I needed. And as for perdicting CPUs for the next 4-8 years, there was a typo in my post. I meant to say "if there is not a huge technological breakthrough", meaning that things continue to improve at the pace they are right now. If Intel meets its goal of 64 cores in 2010, however, then we might not need a GPU at that point. Unless, of course, a better but more resource-intensive way to do graphics is dsicovered (raytracing is one of these, so a raytracing GPU might become a reality someday), new display technologies increase resolution, or larger games demand more polygons to be drawn at once.

you are aware that raytracing graphics are generally more realistic than shader graphics. Also raytracing can do some things that shader graphics cannot, such as multiple refrelections.

Yes, I am aware of that. I am not, however, aware of how your statment has anything at all to do with what we are talking about.

Apparently you didn't try the demo I linked - the quality is pretty dang good, even if the resolution is really low. The framerates are tolerable, the scene is pretty amazing, the curved surfaces are really curved, that kind of thing. And raytracing is pretty dang parallelizable - POV-Ray (a non-realtime raytracer with much, much higher quality!) gets like 99% improvement from one CPU to two. Thus, I think in the days of quad/octal/many-core CPUs, doing realtime raytracing at "modern" resolutions will be entirely practical.

It might be practical someday. Actually, it will be practical someday. But it isn't right now, and won't be for at least a few more years.

Also, raytracing really has nothing to do with my original logic argument, which should have stated:

If a CPU can do physics efficiently, then it can do shader graphics efficiently.
A CPU cannot do shader graphics efficiently.
Therefore, it cannot do physics efficiently.

Premise two is obvious. Premise one is provided by substitution, since we know that shader graphics ~ physics when it comes to required processng type/power.

Adding specific-purpose *PUs to a computer seems counterproductive when you could put in more generalized units. For example, the APU and PPU and GPU could all be implemented as floating-point units, with an integer-based unit or two to control the whole mess. Then if you've got a more strategy-based game (Half-Life 3?) you can dedicate more resources to the AI; with a more action-based game like the one the PPU makers are showing off you can allocate for physics; and Myst Eleven can have uber leet graphics. Thus, the application devs decide what is most important for good gameplay, rather than (indirectly) you by what hardware you buy. With a common high-speed bus (like HyperTransport) on your system, you could plug in an upgrade module that makes every game faster, rather than just ones that use the [ACGP]PU.

That's a good idea. Too bad we don't have it right now. Until we do, I agree with the poster below you in that a PPU can at least work as a temporary solution while we wait for 16-core processors.

EXACTLY what i was thinking. Before the world of 3D accelerators, all gfx computations were done on the cpu. But the OP completely ignored this fact since it is detremental to his/her argument. Also the demo scene is awash with amazing looking gfx and physics demos which use ONLY the cpu. These demos sometimes also use most of the effects we see on gfx cards, such as texture filtering, bump/normal mapping, realistic water, Anti-aliasing etc. There are also numerous demos which use raytracing engines to provide hyper realistic reflections/refractions/caustics and true spherical geometry (i.e real curves and spheres NOT made from polygons). Again entirely done on the CPU. But the single biggest killer of the OPs point is a little game from 2000, called OUTCAST which was rendered ENTIRELY ON THE CPU. This game had a voxel generated landscape, with high polygon characters (for the time), and effects such as triliniear filtering, bump mapping, anti-aliasing and depth of field.

Also if the CPU cannot do physics calculations then how the hell did the Havoc/Novodex API's run? Exactly. They are software physics engines calculated with the CPU. PhysX is based on the novodex engine.

While its true that the CPU cannot match the PPU for the shear number of physics calculations per second. Saying a CPU cannot do it at all is just plain retarded.

Please read revised argument above.

There is nothing wrong with people asking for physics calculations to be done on the extra core of a cpu because hardly any games out there actually take advantage of the extra processing power of dual core setups. So the extra core is sitting there idle when it COULD be put to use doing extra physics calculations. Nothing wrong with wanting that. Not to mention that all dual core cpu's are 64bit. So they will be even faster on a 64bit OS with a properly written software physics API, closing the gap with the PPU again.

No, there's nothing wrong with it. But is it really worth the trouble when we have technology to do 30 times better? If you have 30,000 objects do those extra 1,300 really matter that much?

It's like the current situation with fuel-efficient cars. Hybrid cars give you an extra 10-20 MPG. That's probably enough to extend oil reserves for another 5-10 years. But is it really worth it when we have the technology (now = coal > ethanol, 2012 = nuclear > hydrogen) to virtually eliminate oil usage?

One problem I dont like about PPU's that nobody has mentioned, and dooms them in my eyes, is that apparantly they introduce another latency loop. That is why you typically LOSE frames with a PPU, even if it's just a few after heavy optimization by Ageia, over not using one at all (even if you might get better physics with it on, you still get a slightly SLOWER framerate).

Because the CPU has to send data to the PPU (over a slow external bus, at least compared to the internal speeds of chips) and then wait to get it back. There's just no way around this additional game instruction loop that slows you down.

That is why I prefer physics on a CPU. You dont have that latency because it's internal. I'd rather have less physics than latency.

AGEIA has pretty much solved that problem with updated drivers. Also, some of the latency is caused by extra load on the GPU - something that will occur with CPU physics as well.

As well I harken to Carmack's complaint: It isn't clear that large amounts of physics make a game better, in fact, they make a game easy to "break" (tons of boulders that can realistically roll anywhere sounds great..until you get randomly accidentally stuck behind them). Carmack has been correct so far in predicting a lot of the problems a PPU would have, such as making games run slower.

You're just being ignorant. You don't want to pay for a PPU, so you are trying to convince yourself that it would make the game worse anyway. Realistic physics = realistic game = better game. Which would you prefer? That a rolling boulder crushes and kills you? Or that you pass right through the rolling boulder as if it wasn't there?

Physics are "politically correct", like AI, but they are vastly overblown. The physics in half life 2 certainly aren't very impressive in practice, despite claims to the contrary. They were "meh" after 5 minutes. They're ok. They didn't make the game.

Thanks for supporting my argument. You just denounced physics that were rendered by a CPU.

I apologize if my earlier post implied that EE's are less intelligent than CS folk. I dont think either is smarter at all. I was just saying that generally we hardware enthusiasts are relatively ignorant about the programming that makes all the hardware go. Just as people who focus much more on software are relatively ignorant to how that software is being implemented at a hardware level. Thus arguing for one architecture over another without considering things on both a hardware and software level is flawed.

But that's the way it has always been and always will be in information technology. When we need faster performance, the hardware gets upgraded, then the software is developed to utillize that hardware. Developers usually don't try to improve the efficiency of their code since the hardware provides more than enough headroom anyway.

ANNOYING AS HELL

Your lack of meaningful comments tells me that you didn't read the post. How can it be annoying if you didn't read it?

 

[Chernobyl1]

This might help
http://www.penstarsys.com/editor/company/amd/gpgpu/index.html

Its a good speculative look at what AMD could be up to.

 

[GreenMonkey]

I'll elaborate on something said in the "how much will you pay" thread.

A physics card is useless in a game like Civilization. For that matter I don't think it would be very useful in an RTS game either (you are too far away from the action to see small objects flying around). Useful in an RPG? Nope, not likely...perhaps an action-RPG. I don't see a lot of need for it in a MMORPG either (bandwidth concerns, central server would have to know where the objects are as well...?).

Until that changes I can't see spending money on this. I only play a few FPS games, and none religiously. Get me a high-speed hardware card to speed up Civ 4 AI Is that what's next, an AI acceleration card?

Audio card is useful for many Windows apps (mp3s, videos, etc) for its superior sound quality and sometimes audio acceleration. Graphics cards are pretty much useless in Windows but will be useful in Windows Vista for fancy window effects. Physics card = useful only for 3D games.

 

[Hvatum]

I'll elaborate on something said in the "how much will you pay" thread.

A physics card is useless in a game like Civilization. For that matter I don't think it would be very useful in an RTS game either (you are too far away from the action to see small objects flying around). Useful in an RPG? Nope, not likely...perhaps an action-RPG. I don't see a lot of need for it in a MMORPG either (bandwidth concerns, central server would have to know where the objects are as well...?).

Until that changes I can't see spending money on this. I only play a few FPS games, and none religiously. Get me a high-speed hardware card to speed up Civ 4 AI Is that what's next, an AI acceleration card?

Audio card is useful for many Windows apps (mp3s, videos, etc) for its superior sound quality and sometimes audio acceleration. Graphics cards are pretty much useless in Windows but will be useful in Windows Vista for fancy window effects. Physics card = useful only for 3D games.

Apparently at first, but there may very well be other uses which are not immediatly apparent to you or me. And even for strategy games, let's say something like C&C Generals or Total Annihilation (one of the best RTS ever IMHO), a physics card could add a great deal. If you could do a huge amount of physics calculation practically for free there are many possibilities. You could add much more realistic terrain and make everything destructable.

For example, instead of having buildings light of fire and explode they might actually fall apart in a realistic manner, leaving behind rubble which your Panzers could then drive over and crush. Admit it, that would be sweet - I'd pay at least $100 extra to add that much depth to all my games. Or you could order your men to move small objects (rocks, debris) to construct a make-shift barrier to hide behind. In something like Stronghold Crusader catapults could actually smash apart stone battlements instead of making them smaller. These are just a few ideas which I hashed out over five minutes, I'm sure a professional could think of many more.

Granted, a physics card would add practically nothing to flat interface games such as HOI2 or Europa Universalis, but then again neither do graphics cards.

And in MMORPGs you could add physics effects to water, trees or even objects as long as the players interaction with the objects doesn't matter to those around the player. To be really conservative you could have all physics accellerated effects trivial to the actual game, but they would still add some depth.

 

[HOCP4ME]

I'll elaborate on something said in the "how much will you pay" thread.

A physics card is useless in a game like Civilization. For that matter I don't think it would be very useful in an RTS game either (you are too far away from the action to see small objects flying around). Useful in an RPG? Nope, not likely...perhaps an action-RPG. I don't see a lot of need for it in a MMORPG either (bandwidth concerns, central server would have to know where the objects are as well...?).

Until that changes I can't see spending money on this. I only play a few FPS games, and none religiously. Get me a high-speed hardware card to speed up Civ 4 AI Is that what's next, an AI acceleration card?

Audio card is useful for many Windows apps (mp3s, videos, etc) for its superior sound quality and sometimes audio acceleration. Graphics cards are pretty much useless in Windows but will be useful in Windows Vista for fancy window effects. Physics card = useful only for 3D games.

Let's use common sense:

If you only want to play CPU-intensive strategy games, do you spend you money on a high-end GPU? No. Does that mean that high-end GPUs shouldn't exist? No.

If you only want to play GPU-intensive FPS games, do you buy a quad-core processor? No. Does that mean that quad-core processors shouldn't exist? No.

If you only want to surf the Internet, do you buy an audio card? No. Does that mean that audio cards shouldn't exist? No.

If you only want to play MMORPG, do you buy a physics card? No. Does that mean that physics cards shouldn't exist? No.

Also, "physics = only useful in 3D games" is not what I consider an argument against the PPU. Just because something isn't useful in every aspect of computing doesn't mean it is a bad idea, and 3D games make up a very wide sector of the gaming market.

Finally, the GPU is also "only useful in 3D games" ('fancy window effects" not included, but I don't think that qualifies as "useful").

 

[Hvatum]

Let's use common sense:

If you only want to play CPU-intensive strategy games, do you spend you money on a high-end GPU? No. Does that mean that high-end GPUs shouldn't exist? No.

If you only want to play GPU-intensive FPS games, do you buy a quad-core processor? No. Does that mean that quad-core processors shouldn't exist? No.

If you only want to surf the Internet, do you buy an audio card? No. Does that mean that audio cards shouldn't exist? No.

If you only want to play MMORPG, do you buy a physics card? No. Does that mean that physics cards shouldn't exist? No.

Also, "physics = only useful in 3D games" is not what I consider an argument against the PPU. Just because something isn't useful in every aspect of computing doesn't mean it is a bad idea, and 3D games make up a very wide sector of the gaming market.

Finally, the GPU is also "only useful in 3D games" ('fancy window effects" not included, but I don't think that qualifies as "useful").

I don't understand! Unless you can explain to me how this physics card thing will improve my Solitaire playing experience it's useless. I mean, obviously if something isn't useful in solitaire then it can't possibly have a use anywhere else. Solitaire is the gold-standard for benchmarking the usefulness of computer components.

I also fail to see how a CD-Burner improves my ping in BF2, for that reason I think CD-Burners are useless also.

BTW: Jackhammers are also a dumb invention, I mean they can't even improve your math grade. What kind of useless tool is that?

 

[HOCP4ME]

Jackhammers are also a dumb invention, I mean they can't even improve your math grade. What kind of useless tool is that?

LOL! Thanks for the great laugh man.

Very effective tool at convincing someone that their logic is flawed; give them an absurd example that follows the same logic.

 

[Spewn]

Quote:
Physics are "politically correct", like AI, but they are vastly overblown. The physics in half life 2 certainly aren't very impressive in practice, despite claims to the contrary. They were "meh" after 5 minutes. They're ok. They didn't make the game.

Thanks for supporting my argument. You just denounced physics that were rendered by a CPU.

Err, I'm pretty sure he was just denouncing the idea that the physics actually made the game more enjoyable. He didn't state that it was poorly executed, or that it detracted from the game in its inaccuracy; he simply said their inclusion isn't what made the game.

I don't know what future games could bring, but I've yet to see something I'd pay money for. I was ready to pay money for a 3d accelerator card as soon as I found out they existed.

 

[drizzt81]

Err, I'm pretty sure he was just denouncing the idea that the physics actually made the game more enjoyable. He didn't state that it was poorly executed, or that it detracted from the game in its inaccuracy; he simply said their inclusion isn't what made the game.

I don't know what future games could bring, but I've yet to see something I'd pay money for. I was ready to pay money for a 3d accelerator card as soon as I found out they existed.

Well, he is incorrect in that statement. A good amount of the puzzles in HL2 are physics based.

 

[jimmyb]

For me that was the worst part of HL2. I know some people enjoyed them however. In FPSes, I tend to prefer id software style games (i.e. just shooting people and exploring the level, or as some of you would call them: boring games).

 

[GreenMonkey]

I don't understand! Unless you can explain to me how this physics card thing will improve my Solitaire playing experience it's useless. I mean, obviously if something isn't useful in solitaire then it can't possibly have a use anywhere else. Solitaire is the gold-standard for benchmarking the usefulness of computer components.

I also fail to see how a CD-Burner improves my ping in BF2, for that reason I think CD-Burners are useless also.

BTW: Jackhammers are also a dumb invention, I mean they can't even improve your math grade. What kind of useless tool is that?

Thanks for making a stupid counterpoint.


My point was that all the other add-in cards are useful in multiple different applications, gaming or not. Physics cards are only useful for games, and only for those 3D games that would benefit from physics - FPS, maybe RTS games, and maybe MMORPGs (I doubt that one).

Like I said, audio & graphics cards (and higher speed CPUs) have uses beyond just a handful of 3D games. I've yet to see any use for a Physics card outside of a certain niche of 3D games, primarily FPS games.

That's a lot different argument that saying my CD burner doesn't help my ping times

 

[Hvatum]

Thanks for making a stupid counterpoint.

Ok, here's a new one.

This Geforce 7950 is SO USELESS, I don't see any improvement in the FPS that my Windows Vista desktop is getting. I thought this would make Microsoft word run better! Obviously it doesn't so I therefore think it's useless.

My point was that all the other add-in cards are useful in multiple different applications, gaming or not. Physics cards are only useful for games, and only for those 3D games that would benefit from physics - FPS, maybe RTS games, and maybe MMORPGs (I doubt that one).

Like I said, audio & graphics cards (and higher speed CPUs) have uses beyond just a handful of 3D games. I've yet to see any use for a Physics card outside of a certain niche of 3D games, primarily FPS games.

That's a lot different argument that saying my CD burner doesn't help my ping times

Graphics cards, have very limited use outside of games. Anything beyond a Radeon 9600 provides more then enough GPU power to run OSX and probably windows Vista (unless they add artifical limitations). Furthermore all of the gaming related features of Audigy and X-Fi cards have no significant application outside of gaming. Face it, your argument is bunk.

For example: Creative soundcards are very succesful despite the fact that they really (at least until the X-Fi) only had an advantage in gaming. If you were right that consumers have no interest in paying for something which has a single function there would be absolutely no market for creative soundcards.

 

[BinarySynapse]

there are other potential uses for the number crunching power of a PPU. various sciences simulation, cryptography, folding, etc.

 

[GreenMonkey]

For example: Creative soundcards are very succesful despite the fact that they really (at least until the X-Fi) only had an advantage in gaming. If you were right that consumers have no interest in paying for something which has a single function there would be absolutely no market for creative soundcards.

Most of the dedicated soundcard solutions provide much better audio than integrated audio. Better SNR, THD, frequency response, DACs, etc.

Video cards admittedly don't have a lot of use beyond games, but there is HD video acceleration and Windows Vista is imminent. 2D video quality on a dedicated card tends to be a shade better than integrated. But a video card is useful in almost ALL games, whereas a physics card is only useful in some games.

In any event, both audio and video cards do have some benefit system wide - a computer is pretty much always producing video and audio.

there are other potential uses for the number crunching power of a PPU. various sciences simulation, cryptography, folding, etc.

That sounds reasonable. Not that I'm big into cryptography (someone alert the FBI! ). Although I've yet to see this number crunching potential used for anything else yet.

 

[SuperGee]

And your points? There only FPS and MMO games that make a difference? You pick a well known genre and think that is the only one PPU can be used for or is a posible Phyisics need to fullfill. Wrong.
Singleplayer still is alive. MMO and any online thing can use extensivly effects Physics. Offcourse there are pure online games like UT series every MMO things.
So manny genres where they all already went for 3D worlds and in all of them there could be some heavy use of Physics. Like Damage detail and interaction of race games.
RTS mass rigidbody Physics and a lot more realistic dustructive enviorment by attillery.
Second point.
It's only usable for game. So what if you don't game you don't buy one. But more peple need a sound card. So a lot of people buy a sound cards. That's no problem at all. Good for sound card makers. Bit if something is pure ment for gaming. That exlude all nongamers. Just like a joystick.gamepad.
If something is pure ment for gamers it must not excist? Makes no sense to me.
It would sell a lot less. But could still be a vaible market.

 

[GreenMonkey]

And your points? There only FPS and MMO games that make a difference? You pick a well known genre and think that is the only one PPU can be used for or is a posible Phyisics need to fullfill. Wrong.
Singleplayer still is alive. MMO and any online thing can use extensivly effects Physics. Offcourse there are pure online games like UT series every MMO things.
So manny genres where they all already went for 3D worlds and in all of them there could be some heavy use of Physics. Like Damage detail and interaction of race games.
RTS mass rigidbody Physics and a lot more realistic dustructive enviorment by attillery.

I'm willing to be proven wrong. I see what, one RTS with Ageia supported so far? Give me a call when a game like Guild Wars, BFME or CnC use it. And how much benefit is realistic physics for an RTS game? You're zoomed out at a distance most of the time overseeing the action. Might be good for an RTS/action hybrid type game (I'm thinking something like Battalion Wars for Gamecube)

Second point.
It's only usable for game. So what if you don't game you don't buy one. But more peple need a sound card. So a lot of people buy a sound cards. That's no problem at all. Good for sound card makers. Bit if something is pure ment for gaming. That exlude all nongamers. Just like a joystick.gamepad.
If something is pure ment for gamers it must not excist? Makes no sense to me.
It would sell a lot less. But could still be a vaible market.

No arguments here. But a gamepad doesn't cost $200. I'm willing to spend a minor amount like that (sub-$50ish) given that the physics offer up some useful gameplay improvements.

 

[SuperGee]

I'm willing to be proven wrong. I see what, one RTS with Ageia supported so far?

Yes you are. Think? 6 games out now!. And there are more Genres then Ageia has games out. So might it be that they must still come? And FPS is in the lead because the game market is more focused on FPS. So get back wenn those 60plus games are out. A part of those will be other then FPS games. Only that take a while because games are made in years not day or instantly. The Software migration or acceptation prosces is a slow thing. If it will come.
So it's to early to judge.

Give me a call when a game like Guild Wars, BFME or CnC use it. And how much benefit is realistic physics for an RTS game? You're zoomed out at a distance most of the time overseeing the action. Might be good for an RTS/action hybrid type game (I'm thinking something like Battalion Wars for Gamecube)

Well all genres have to deal with the impact between effects Physics and gameplay Physics on the Design requierment and adoption. Like effect is the easy smeasy way.
Gameplay phsyics for RTS also FPS to influence Pathing so the AI part. If the enviorment is dynamical and interactive. It need more work and AI specialist to overcome this. Most games don't have the time and expertise. So expect CF'ish and Graw'ish Games for each genre.
The few good and the more bad once.

JTF is The first PPU RTS game and it Doesn't put Pshyics to good use that it stand out the crowed, its more effect Physic. Doesn't mean it isn't possible and a other RTS game would do better.

No arguments here. But a gamepad doesn't cost $200. I'm willing to spend a minor amount like that (sub-$50ish) given that the physics offer up some useful gameplay improvements.

Oh the money whining point again. That's a old one. We know that a lot people will be on the front row for a few cents.

If PPU will be succesfull. well
$50 will make 100000 units. Ageia must put like PPU chips for $5 per 1000
$200 will make 20000 units The chip could cost $35

The other would use slow 64 GDR3 the other more. 128MB and faster GDDR4.

More for less isn't always good for the long run. Look at AMD thunderbird. Low prices very low margins
I wouldn't mind, bought a thinderbird fl 349 while the direct competition cost fl 2000. ($1000)

 

[Hvatum]

Most of the dedicated soundcard solutions provide much better audio than integrated audio. Better SNR, THD, frequency response, DACs, etc.

Video cards admittedly don't have a lot of use beyond games, but there is HD video acceleration and Windows Vista is imminent. 2D video quality on a dedicated card tends to be a shade better than integrated. But a video card is useful in almost ALL games, whereas a physics card is only useful in some games..

Yes, I agree that they have limited use beyond games. But if consumers were interested only in spending money for features that can be used for at least two applications we would have nothing besides soundquality oriented soundcards such as the EMU. Of course, people would still purchase dedicated soundcards, but they would have no reason to spend $100(s) of dollars for features which are utterly useless outside of games such as EAX. Especially when cards when with better SNR, THD, frequency response and DACs can be had for significantly less money.

Furthermore graphics card development would have little reason to advance past roughly a Geforce 6800. Are people upgrading to Geforce 7950s because they also want to finally be able to watch HD video and speed up their Windows XP desktop, nope. Face it, your argument is absurd. People will, have and will continue to purchase things which have no use outside of games, and spend a lot of money doing so too.

 

[Murtrude]

very scientific, nice

 

[HOCP4ME]

If you don't play the games that would use it, no one is saying you have to buy a PPU. But why does that mean that the PPU should never become useful in the types of games it was meant for? If you only play RPG, and you are correct in saying that the PPU will never be utillized in RPG, then whether it succeeds or fails will have no effect on you.

Trust me, Terra is (was) the only person here who thinks that a PPU is worth buying right now. Unless, of course, you really like the games that are out for it right now, or you are an early-adopter.

 

[GreenMonkey]

Yes, I agree that they have limited use beyond games. But if consumers were interested only in spending money for features that can be used for at least two applications we would have nothing besides soundquality oriented soundcards such as the EMU. Of course, people would still purchase dedicated soundcards, but they would have no reason to spend $100(s) of dollars for features which are utterly useless outside of games such as EAX. Especially when cards when with better SNR, THD, frequency response and DACs can be had for significantly less money.

Furthermore graphics card development would have little reason to advance past roughly a Geforce 6800. Are people upgrading to Geforce 7950s because they also want to finally be able to watch HD video and speed up their Windows XP desktop, nope. Face it, your argument is absurd. People will, have and will continue to purchase things which have no use outside of games, and spend a lot of money doing so too.

Sorry, been gone for a while, no internet at home until yesterday...postings have been from school/work only...

I was just pointing out that the other expansions have SOME fringe benefits as well as being useful for gaming, and that it does make a difference. There may be better cards for sound quality, but is there a better card that offers gaming performance AND sound quality? (BTW: EAX is supposedly used for music processing: stereo-to-surround sound, reverb, etc - not my cup of tea, but plenty of folks do)

I will buy the argument that video cards past a certain extent are only used for gaming. Vista will use some hardware acceleration, but admittedly nothing that something like a GF6200 couldn't handle.

Yes you are. Think? 6 games out now!. And there are more Genres then Ageia has games out. So might it be that they must still come? And FPS is in the lead because the game market is more focused on FPS. So get back wenn those 60plus games are out. A part of those will be other then FPS games. Only that take a while because games are made in years not day or instantly. The Software migration or acceptation prosces is a slow thing. If it will come.
So it's to early to judge.

Agreed. I do see UT2007 on the radar for physx support on their website, and that does look interesting. But there's no way in hell I'm spending even $50 on hardware just for one game. I need game support and an awfully good demonstration of why I should be buying hardware for it.

 

[Talz]

I'm a bit late on this thread but the original post seemed like one of the better simple explanations of the advantages of a dedicated PPU. I'm not sure the value is there but that's another discussion.

 

[BigDH01]

Maybe it's because they don't want to buy anything, or maybe it's because they don't understand the technology, but every day there are several posts on this forum that follow the same old lines "I won't buy anything until they utillize my extra CPU core". So here are the reasons why that just doesn't work:

1. People keep saying "just use the CPU for physics". Well, that's what developers are doing right now! Physics are nothing new, and they do exist in today's games, calculated on the CPU. But we've hit a wall with this method of physics procesing. A CPU simply doesn't have the required power to do physics any better than what we have now. But what about dual-core? Well, take the number of objects a CPU can handle (around 2,000) and add 80% (dual-core CPUs aren't 100% efficient). Add 280% for quad-core. You still will be nowhere near the 30,000+ objects that a PPU or GPU can handle.

2. There are technical reasons why a CPU cannot do physics while a GPU can. It's all about pipelines. A typical GPU has between 24 and 48 pipelines. This allows it to do many calculations all at once or in parallel. A CPU, however, has very few pipelines. This means that a CPU must do instructions in a sequential manner. Physics calculations require massively parallel processing to perform well. Ideally, every object should be tracked at the same time. A GPU and PPU can do parallel processing, but a CPU isn't very good at it.

3. Here is a constructed mathematical argument:

We know that physics calculations and graphics calculations require the same type of processing power. This is why a GPU can be used to do accelerated physics.

It is obvious that we can make the statement "If a CPU can do physics, then it can do physics" using the reflexive property.

Since we know that graphics = physics as far as processing goes, we can substitute "graphics" for "physics" in that statment: "If a CPU can do physics, then it can do graphics".

We know that a CPU cannot do graphics in real time. You can verify this by attempting to run any game without a GPU installed, or with hardware acceleration disabled.

So then, we have this:

If a CPU can do physics, then it can do graphics.
A CPU cannot do graphics.
Therefore, it cannot do physics.

Now, for all you math geeks out there, that is called "denying the consequent" or the Modus Tollens argument method. It is one of two valid ways to draw a conclusion when given two premises, one of which is a conditional.


So that's why a CPU is no substitute for a GPU or PPU when it comes to physics. Can something at least be put in the FAQ about this? I have to restate this argument every day because someone else comes along and says "use the CPU'".

Disclaimer: When I say "a CPU cannot do graphics", I am not referring to raytracing or pong. I am referring to shader graphics of the quality and quantity found in today's games (not including turn-based and/or 2D games, obviously). I understand that raytracing technologies are being developed that work on a CPU and that very old games used the CPU for rendering. Likewise, when I say "a CPU cannot do physics", I am referring to accurate, realtime physics of the type and quantity promised by AGEIA, NVIDIA, Havok, and ATI (i.e. cloth, friction, tens of thousands of objects...). This has confused a few people, so I thought I would clear it up right here.

Sorry, misread... long work day.