• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Ageia responds to GPU physics

I say hardware physics will never be needed. The comparison of hardware graphics versus hardware physics is apples to oranges. Graphics have a long, long way to go. We still haven't reached photo-realistic graphics, and it will be a long time before we truly do. Physics, on the other hand, is far simpler to calculate, and much, much less computationally expensive than graphics. There is only so far you can go with physics, and the Havok engine is pretty close to it (at least within sight of it). Our processing power is increasing at a rate far greater than the computational requirements of game physics. Quite simply, the power needed for physics is a joke compared to graphics. Unless you are trying to give complex physics to every drop of rain in a storm, it just isn't going to be needed.
 
jdLordHelmet said:
I say hardware physics will never be needed. The comparison of hardware graphics versus hardware physics is apples to oranges. Graphics have a long, long way to go. We still haven't reached photo-realistic graphics, and it will be a long time before we truly do. Physics, on the other hand, is far simpler to calculate, and much, much less computationally expensive than graphics. There is only so far you can go with physics, and the Havok engine is pretty close to it (at least within sight of it). Our processing power is increasing at a rate far greater than the computational requirements of game physics. Quite simply, the power needed for physics is a joke compared to graphics. Unless you are trying to give complex physics to every drop of rain in a storm, it just isn't going to be needed.

People said the same thing when 3D graphics cards came out...
And I don't even thing you have grapsed how many compuation just a 1000 real-time physics obejcts would require...

Terra...
 
jdLordHelmet said:
I say hardware physics will never be needed.....
We may have good physics in games, but those physics are only available on select objects in a game....i.e. a box, a car, etc. The processing in a ppu will allow games to be coded much more liberally, where there are much fewer static objects in a game world, and many more destructable, moveable objects. So yes, physics now are good enough, but the PPU will allow physics to be more widespread.
 
I think the PPU is coming out at the wrong time considering multicore processors are taking over, I think it might be easier for programmer just to dump physics processing onto an extra core. Look at the consoles that are coming out, none of them are using PPU's as far as I know, but they all have at least 3 cores. (at least 360 and PS3 do) This implies that the future of physics processing is not in an extra card but simply another advantage of multicore processors.
 
jdLordHelmet said:
I say hardware physics will never be needed. The comparison of hardware graphics versus hardware physics is apples to oranges. Graphics have a long, long way to go. We still haven't reached photo-realistic graphics, and it will be a long time before we truly do. Physics, on the other hand, is far simpler to calculate, and much, much less computationally expensive than graphics. There is only so far you can go with physics, and the Havok engine is pretty close to it (at least within sight of it). Our processing power is increasing at a rate far greater than the computational requirements of game physics. Quite simply, the power needed for physics is a joke compared to graphics. Unless you are trying to give complex physics to every drop of rain in a storm, it just isn't going to be needed.


Have you ever fired a rocket at a wall and wondered why it doesn't make a hole? Or why you can't make waves in a pool of water?
A ppu will make this, and many more things, possible.
 
Terra said:
People said the same thing when 3D graphics cards came out...
And I don't even thing you have grapsed how many compuation just a 1000 real-time physics obejcts would require...

Terra...


agreed

kinematics, Entropy, Fluidy Dynamics (since air is considered a fluid for aerodynamics purpose), etc

jdlordhelmet

you underestimate how much the GPU physics can be off loaded from the CPU.
 
stelleg151 said:
I think the PPU is coming out at the wrong time considering multicore processors are taking over, I think it might be easier for programmer just to dump physics processing onto an extra core. Look at the consoles that are coming out, none of them are using PPU's as far as I know, but they all have at least 3 cores. (at least 360 and PS3 do) This implies that the future of physics processing is not in an extra card but simply another advantage of multicore processors.
Yea I kind of agree, but supposedly a dedicated, specialized processor is much better for graphics. you could make the same argument that you could throw away all video cards and just use one of the CPU cores to do graphics, but 3d accelerators are so much better at rendering graphics that this isn't feasible.
 
jdLordHelmet said:
I say hardware physics will never be needed. The comparison of hardware graphics versus hardware physics is apples to oranges. Graphics have a long, long way to go. We still haven't reached photo-realistic graphics, and it will be a long time before we truly do. Physics, on the other hand, is far simpler to calculate, and much, much less computationally expensive than graphics. There is only so far you can go with physics, and the Havok engine is pretty close to it (at least within sight of it). Our processing power is increasing at a rate far greater than the computational requirements of game physics. Quite simply, the power needed for physics is a joke compared to graphics. Unless you are trying to give complex physics to every drop of rain in a storm, it just isn't going to be needed.

No way is Havoc even scratching the surface. There is no doubt that dedicated physics hardware is the best solution for the near or even not so near future. By the time CPUs have enough extra cycles and computational power laying around to do complex physics on a massive scale computer architecture will have likely changed so much that it doesn't even resemble what we have today.
 
I'd like to see a company like Ageia produce a less expensive product, or PhysX processors that could be added to a graphics card, rather than a separate product.

Are physics in games relevant? Yes, but so is price. Most gamers are already shelling $150-400 for a graphics card;tell a gamer they'll need to shell another $200 for a PPU card, and I'll bet that over two-thirds of them will balk.

If less than a third of gamers owns one of these cards, developers will be less likely to code support for them. They're in it for money like everyone else, and if 60% of people out there can't play a game because they don't have the hardware, that game isn't going to make its development money back. Sure, a separate code-path could be written for computers that have the PhysX card, but what will the additional development costs be to do so?

Even if the Ageia PhysX product is groundbreaking, without games to support it, it's just a pretty piece of hardware. One might point to it as the possible 3dfx Voodoo of today, but back when the Voodoo came out, a basic 2MB/4MB DRAM-based PCI graphics card cost far less than the cards of today, so having both the graphics card and the Voodoo wasn't nearly as hard on one's wallet as this will be. Ageia's product is one that I hope will do some neat things --but I'd like to see it within the realm of affordability.
 
LoneWolf said:
I'd like to see a company like Ageia produce a less expensive product, or PhysX processors that could be added to a graphics card, rather than a separate product.

Are physics in games relevant? Yes, but so is price. Most gamers are already shelling $150-400 for a graphics card;tell a gamer they'll need to shell another $200 for a PPU card, and I'll bet that over two-thirds of them will balk.
I don't think anybody knows the answer to this problem. I'm buying it, and I don't have unlimited funds, but who knows how many others will.
If less than a third of gamers owns one of these cards, developers will be less likely to code support for them. They're in it for money like everyone else, and if 60% of people out there can't play a game because they don't have the hardware, that game isn't going to make its development money back. Sure, a separate code-path could be written for computers that have the PhysX card, but what will the additional development costs be to do so?.
The way to program for non-ppu systems is so make explosions, etc, "dumber". In other words, you shoot a rocket at a wall, and a hole in the wall appears. I shoot the same rocket at the same wall, and I see all the particles, hunks of wall, shrapnel from the rocket, etc. rendered, and the same hole appears through the smoke.
 
jdLordHelmet said:
Unless you are trying to give complex physics to every drop of rain in a storm, it just isn't going to be needed.

but thats the point of a ppu, it will do the calculations neccessary to give realism to rain and other oblects, it will add that much more realism to games,

right now programmers have to do "pre-planned" reactions for certain actions, if it isnt "pre-planned" nothing will happen, a dedicated ppu will allow multiple reactions for actions without the "pre-planning"... so if you had a bridge that you shot an rpg at in todays game no matter where you hit it it would be destroyed or if it wasnr programed nothing would happen... with a ppu you would have to hit the bridge in a structurally critical area for it to be destroyed
 
wait till the card starts applying to games like wow, guildwars, and eq2. i think a ppu could greatly increase game play for games like this.
 
I'm an amateur graphics programmer. Some of the stuff you guys are talking about goes beyond what we think of when we say "physics" and gets into things that would require a complete overhaul of how we create the graphics that show on your screen. Graphics is about drawing polygons and mapping textures to them, and physics is about moving those polygons around in a realistic way. From that perspective, stuff like deformation, entropy, "blowing holes in walls", etc, is gonna take a lot more than just physics. If fact, blowing realistic holes in walls has nothing to do with physics, in the graphics programming sense of the word. At that point, you aren't even dealing with polygons, you would be dealing with some type of pixel-by-pixel mapping or some other kind of wacky, not-yet-created method. Which makes sense, if you look at graphics progression through a sort of calculus filter, as graphics get better, the number of polygons gets larger/the size of polygons get smaller - eventually we may end up with polygons 1 pixel large - in other words, just plotting billions of 3D pixels instead of polygons (this is already done, but not for entire scenes). The "physics" for such an engine would be insane, sure, but all of it would be insane. I still say a physics card will never be needed. Ok, let me rephrase that: a physics card should never be needed. Physics will always be a laughably inexpensive venture compared to graphics.
 
right now programmers have to do "pre-planned" reactions for certain actions, if it isnt "pre-planned" nothing will happen, a dedicated ppu will allow multiple reactions for actions without the "pre-planning"... so if you had a bridge that you shot an rpg at in todays game no matter where you hit it it would be destroyed or if it wasnr programed nothing would happen... with a ppu you would have to hit the bridge in a structurally critical area for it to be destroyed

That's just not true. We've had physics to do what you describe - shooting a certain part of a bridge to make it collapse due to physics - even before we had the Havok engine (Max Payne 2 even had stuff like that). Do I even need to mention some of the physics-based traps and such from HL 2?
 
Brent_Justice said:
oh noes, i see it now

ATI vs. NVIDIA = GPU as PPU vs. Dedicated PPU
Put me down as a "PPUP"--- a ppu phanboi!
 
jdLordHelmet said:
I'm an amateur graphics programmer. Some of the stuff you guys are talking about goes beyond what we think of when we say "physics" and gets into things that would require a complete overhaul of how we create the graphics that show on your screen. Graphics is about drawing polygons and mapping textures to them, and physics is about moving those polygons around in a realistic way. From that perspective, stuff like deformation, entropy, "blowing holes in walls", etc, is gonna take a lot more than just physics. If fact, blowing realistic holes in walls has nothing to do with physics, in the graphics programming sense of the word. At that point, you aren't even dealing with polygons, you would be dealing with some type of pixel-by-pixel mapping or some other kind of wacky, not-yet-created method. Which makes sense, if you look at graphics progression through a sort of calculus filter, as graphics get better, the number of polygons gets larger/the size of polygons get smaller - eventually we may end up with polygons 1 pixel large - in other words, just plotting billions of 3D pixels instead of polygons (this is already done, but not for entire scenes). The "physics" for such an engine would be insane, sure, but all of it would be insane. I still say a physics card will never be needed. Ok, let me rephrase that: a physics card should never be needed. Physics will always be a laughably inexpensive venture compared to graphics.
I have no idea what you just said, but I think you are saying that, essentially, if we have hella-insano physics, we will need hella-insano video cards, correct? Video cards already render things like grass waving in the wind, so why can't a PPU enable that grass to move realistically as a result of the wind, and me walking through it, etc?
 
Grass blowing in the wind realistically is far less computation than is needed to draw the grass in the first place - exponentially less. That's my point.

edit: Assuming you are rendering each blade of grass individually, as you would have to be in order to have realistic grass blowing in the wind.
 
jdLordHelmet said:
If fact, blowing realistic holes in walls has nothing to do with physics, in the graphics programming sense of the word.

Au contraire, it has everything to do with material physics. How a bullet interacts with wood compared to a stone wall, the ballistics of that interaction, is a physics issue.
 
I think jdLordHelmet is saying is that just how GPUs can sometimes be CPU limited, a PPU will often be limited by the GPU. Maybe hes not, but thats what im going to infer.

Either way I personally am all for this physics revolution, whatever obsticles it may face.
 
jdLordHelmet said:
I'm an amateur graphics programmer. Some of the stuff you guys are talking about goes beyond what we think of when we say "physics" and gets into things that would require a complete overhaul of how we create the graphics that show on your screen. Graphics is about drawing polygons and mapping textures to them, and physics is about moving those polygons around in a realistic way. From that perspective, stuff like deformation, entropy, "blowing holes in walls", etc, is gonna take a lot more than just physics. If fact, blowing realistic holes in walls has nothing to do with physics, in the graphics programming sense of the word.


You obviously havent seen the PPU in action. You should get out more.

I saw the demo at quakecon. I saw the holes in walls processed via the PPU and then via teh CPU (and it wasnt a slouch CPU either). Both demos were done on the same computer without even the highest end video card. The difference was nothing short of amazing. We are talking like 4-5 FPS without the PPU to about 100 FPS with it.

Your confused in thinking everything is done in the GPU. Todays GPU's can render almost anything very fast but, like the CPU, they just are not anywhere near optimized to do physics.
 
jdLordHelmet said:
I say hardware physics will never be needed. The comparison of hardware graphics versus hardware physics is apples to oranges. Graphics have a long, long way to go. We still haven't reached photo-realistic graphics, and it will be a long time before we truly do. Physics, on the other hand, is far simpler to calculate, and much, much less computationally expensive than graphics. There is only so far you can go with physics, and the Havok engine is pretty close to it (at least within sight of it). Our processing power is increasing at a rate far greater than the computational requirements of game physics. Quite simply, the power needed for physics is a joke compared to graphics. Unless you are trying to give complex physics to every drop of rain in a storm, it just isn't going to be needed.
Physics could be doing a lot more. I, for one, and tired of sprites. I want holes dammit! :p
 
jdLordHelmet said:
That's just not true. We've had physics to do what you describe - shooting a certain part of a bridge to make it collapse due to physics - even before we had the Havok engine (Max Payne 2 even had stuff like that). Do I even need to mention some of the physics-based traps and such from HL 2?

The physics-based traps in HL2 were pre-programmed (scripted) and very primitive compared to what would be possible with a PPU.

Up to now, shooting a certain part of a bridge and having it collapse was just the result of a scripted reaction to damage taken. With true physics, things would react according to realtime calculations of the interaction between objects, which brings a whole new level of immersion and realism.
 
Im still not happy with the proposed pricing of the physics cards, if there are games that use them and show signs that they will continue to use them I may buy one second hand. But I cant justify spending more for a ppu than I would for a normal processor.
 
Terra said:
People said the same thing when 3D graphics cards came out...
And I don't even thing you have grapsed how many compuation just a 1000 real-time physics obejcts would require...

Terra...

There's the matter of economy, while the average [H] user from these pages users might be hardcore enough to buy such an expensive card, how many of the 'normal' gaming population would be willing to pay for it? And there's still the catch22 to deal with.

Also, while i used to use the evolution of 3D cards as comparison, thinking some more, i realized that it really isn't proper. Thinking back to the development history before 3D became mainstream, the instances and situations back then were much different from the one PPU's are in now.

jdLordHelmet said:
I'm an amateur graphics programmer. Some of the stuff you guys are talking about goes beyond what we think of when we say "physics" and gets into things that would require a complete overhaul of how we create the graphics that show on your screen. Graphics is about drawing polygons and mapping textures to them, and physics is about moving those polygons around in a realistic way. From that perspective, stuff like deformation, entropy, "blowing holes in walls", etc, is gonna take a lot more than just physics. If fact, blowing realistic holes in walls has nothing to do with physics, in the graphics programming sense of the word. At that point, you aren't even dealing with polygons, you would be dealing with some type of pixel-by-pixel mapping or some other kind of wacky, not-yet-created method. Which makes sense, if you look at graphics progression through a sort of calculus filter, as graphics get better, the number of polygons gets larger/the size of polygons get smaller - eventually we may end up with polygons 1 pixel large - in other words, just plotting billions of 3D pixels instead of polygons (this is already done, but not for entire scenes). The "physics" for such an engine would be insane, sure, but all of it would be insane. I still say a physics card will never be needed. Ok, let me rephrase that: a physics card should never be needed. Physics will always be a laughably inexpensive venture compared to graphics.

I've done much lengthier explanations like this before. You're one of the few guys that actually understood it from the start. Few people outside of programming and 3D modeling know just how much particle animations can bog down the most powerful PC's. And that's not even including physics yet. They keep bragging about the physics demo videos that were downloadable from the site but neglect to find out exactly what cards were needed to render those. They seem to fail to realize that in order to make any kind of softbody animation (especially fluid animations), you need to increase the polygoncount dramatically. Also, the actual function for terrain deformation has NOTHING to do with physics. Blowing holes in the wall may initially take some of the values from physics calculations but the computation power to do that is a one time thing and very negligible calculations at that.
 
jdLordHelmet said:
I say hardware physics will never be needed. The comparison of hardware graphics versus hardware physics is apples to oranges. Graphics have a long, long way to go. We still haven't reached photo-realistic graphics, and it will be a long time before we truly do. Physics, on the other hand, is far simpler to calculate, and much, much less computationally expensive than graphics. There is only so far you can go with physics, and the Havok engine is pretty close to it (at least within sight of it). Our processing power is increasing at a rate far greater than the computational requirements of game physics. Quite simply, the power needed for physics is a joke compared to graphics. Unless you are trying to give complex physics to every drop of rain in a storm, it just isn't going to be needed.
What is the point of going after photorealistic graphics if each drop of rain won't move realistically?
 
Although I understand that tons of tiny particles flying every whichway would be much more graphically intensive than physics intensive, the evidence from previous games seems to indicate that physics really does require much more power than graphics people are giving credit for. Look at Source, which has the most advanced physics engine available now, and is much harder on CPUs than GPUs, compared to games like Farcry and Doom. This implies that the cpu is being overloaded with physics-related processes, even though the game is less graphically demanding. I do agree that in the extreme situations like grass flowing etc graphics would need much more power, but for a good amount of basic polygons to be effected by laws of physics will require lots of processing power. I still stick to my original thesis that multicore processors along with possible future multicore/multithreaded gpu assisted processors will elimanate any price-performance need for PPU's. And again, I use consoles, the ultimate gaming machines, as my evidence.
 
I'd like to see these physics card implemented in flight simulator games. Right now they are very cpu dependent but yet their physics are quite limited :(
 
LoneWolf said:
I'd like to see a company like Ageia produce a less expensive product, or PhysX processors that could be added to a graphics card, rather than a separate product.

Are physics in games relevant? Yes, but so is price. Most gamers are already shelling $150-400 for a graphics card;tell a gamer they'll need to shell another $200 for a PPU card, and I'll bet that over two-thirds of them will balk.

If less than a third of gamers owns one of these cards, developers will be less likely to code support for them. They're in it for money like everyone else, and if 60% of people out there can't play a game because they don't have the hardware, that game isn't going to make its development money back. Sure, a separate code-path could be written for computers that have the PhysX card, but what will the additional development costs be to do so?

Even if the Ageia PhysX product is groundbreaking, without games to support it, it's just a pretty piece of hardware. One might point to it as the possible 3dfx Voodoo of today, but back when the Voodoo came out, a basic 2MB/4MB DRAM-based PCI graphics card cost far less than the cards of today, so having both the graphics card and the Voodoo wasn't nearly as hard on one's wallet as this will be. Ageia's product is one that I hope will do some neat things --but I'd like to see it within the realm of affordability.


I have to disagree with the second paragraph...alot of what we see with games arent supported by more than a 1/3 of the gaming population...such things include sounds cards that support things like X-FI, EAX, Dolby Live but game companies still implement them for those that do. Most people dont even have the hardware to run alot of their games with the eye candy all on. If you look at Half Life 2 system survey ...most people still run Nvidia 5200's, ATI 9600 and 9800. These are barely capable of any AA or AF and other options at high resolutions. I dont believe for one second that game companies produce for the general population b/c that would only create and an average game for the average player. Instead they code for the highest end systems that can support the features that put their game on the map and those that cant run it just have to run the game sub-optimal and those that can will enjoy the game as the programmers intended (100% eye and ear candy).

Dont get me wrong, they keep the average player in mind but that is done simply with on/off options for AA AF, and different resolutions. THis I believe will be the same mechanism for implementing the physics processor. Just an option...

Since you brought up voodoo...i remmeber when i got my voodoo2 and some games would let me use it by selecting it optionally. This is the same picture im seeing for the PPU.
 
AndoOKC1 said:
I have to disagree with the second paragraph...alot of what we see with games arent supported by more than a 1/3 of the gaming population...such things include sounds cards that support things like X-FI, EAX, Dolby Live but game companies still implement them for those that do. Most people dont even have the hardware to run alot of their games with the eye candy all on. If you look at Half Life 2 system survey ...most people still run Nvidia 5200's, ATI 9600 and 9800. These are barely capable of any AA or AF and other options at high resolutions. I dont believe for one second that game companies produce for the general population b/c that would only create and an average game for the average player. Instead they code for the highest end systems that can support the features that put their game on the map and those that cant run it just have to run the game sub-optimal and those that can will enjoy the game as the programmers intended (100% eye and ear candy).

Dont get me wrong, they keep the average player in mind but that is done simply with on/off options for AA AF, and different resolutions. THis I believe will be the same mechanism for implementing the physics processor. Just an option...

Since you brought up voodoo...i remmeber when i got my voodoo2 and some games would let me use it by selecting it optionally. This is the same picture im seeing for the PPU.

seems to me that your saying the same thing as him. i could be misreading but it seems like the survey you linked to shows that a large population of gamers are not capable of some of the features of games but yet they still play them. the reson behind this is that the developers want to design games for the widest audience possible. making sure the game runs for the low end but also has the ability to run balls out with top end hardware is what they are trying to do.


as for the PPU i think some of the things people keep attributing to it are not something we cant do now with current hardware. one of these things would be the ability to blow holes in your environment. this is something ive actually done in a game and thought at the time it was going to be the new way for games to be. there was a game called red faction where it was possible, and at some points the entire idea, to blow holes in the rock and dirt of the mines in order to make your way through the level. there was even a mod made for the game that would allow you to go anywhere you wanted instead of being limited to the pre-set areas.

if you look at the age of that game you will see that this has been something we could do with games for a long time but was not used. im not the kind of person that plays every game that comes out so i cant say for sure but seems to me this hasnt been used since, or atleast not enough. what we need is for the focus to drop off of better graphics and to look more into the actual gameplay and the development of the game as a whole. seems an awefull lot of attention is spent on one section of the game while the rest suffers, and i highly doubt new hardware device is going to help us much in that department.
 
CPU manufacturers are churning out Dual-Core CPUs faster than Michael Jackson on his way to "Visit" an orphanage.

No-one's ever going let up on this are they? :p
 
It would be good if they started with a basic ppu card or a ppu on the graphics card or something, even if its shit, just so they start to program better for it so in the near future, it will all work really well.

Anyway, graphics cards today just arent good enough to need a separate ppu. When you have physics, the physics generator (software or hardware (ppu)), will ussually make a alot of graphics intensive effects and will increase polygon counts on bits of rubble and bent metal and whatever. So, people are talking about water, well, water is ussually round, so to make water look rounded, you need alot of polygons and for dynamic smoke or dust, you need alot of particles so it will slow down your card alot.

It would be good if they start now seeing the first ppu's will probably be really shit and software devolpers will fuck it all up, but if they do introduce ppu's now, atleast in 3 years time they will ahve worked out how to program for them properly.
 
If they make another card that cost $200+ just to calculate physics, I'm moving to consoles for gaming, period.
 
XSNiper said:
If they make another card that cost $200+ just to calculate physics, I'm moving to consoles for gaming, period.

whos saying you have to buy it?... just because sli/crossfire came along didnt mean i had to go out and get it
 
XSNiper said:
If they make another card that cost $200+ just to calculate physics, I'm moving to consoles for gaming, period.
Ok, see 'ya later
*blowes a hole in the wall with a rocket launcher to let XSNiper out of the thread*
 
I can already blow a hole in the wall to let someone out in Red Faction.
 
Back
Top