Ageia RealityMark™ (physics benchmark)

Tom|Nbk · 11 Oct 2006 at 15:52

rofl how totally ridiculous ill be running this on my high end none physx rig later on for a chuckle

.

Pottsey · 11 Oct 2006 at 16:00

”Unsurprisingly its just ridiculously crippled so it only runs well with Ageia's hardware ”
Have you ever thought for a second that perhaps its not ridiculously crippled and that’s how it is in real life? Games get the same results and there is no evidence its crippled.

Its seems a lot of people are in denial that hardware can be way faster the software on the CPU. Its not surprising it only runs well with hardware CPUs have always been super slow at liquid and cloth.

Why are so many people surprised hardware is faster then software?

“I wonder if the graphics are in software too, like the cpu tests in 3d mark.“
Graphics are fully in hardware as soon as you turn off the high end physics like cloth the FPS jump up. The more you turn down the physics the higher the FPS go.

The benchmark is based off a map in Cellfactor. You can test it your self with different effects turn on and off.

Minstadave · 11 Oct 2006 at 16:04

Pottsey said:
Have you ever thought for a second that perhaps its not ridiculously crippled and that’s how it is in real life? Games get the same results and there is no
evidence its crippled.

Its seems a lot of people are in denial that hardware can be way faster the software on the CPU. Its not surprising it only runs well with hardware CPUs have always been super slow at liquid and cloth.

Why are so many people surprised hardware is faster then software?

I thought about it, I also though "Would Ageia sell their own mother to boost sales..", so far I've been unimpressed with their business model and their product.

I fail to see why software running on the PPU should be hugely faster than software running on a second core. The possibility that they've designed this cloth/liquid effect software to run poorly on anything but their own hardware seems much more likely. I see no reason at all why advanced physics effects can't be done on a second core, there's plenty of CPU power available there not being used.

locutus12 · 11 Oct 2006 at 16:09

Minstadave said:
Can you stop posting that in every PPU thread please? Its got old.

i dont post it in every physics processing unit thread, only in ageia`s, and it makes my point for me with regards to Agiea regardless of whether you believe its old or not.

squiffy · 11 Oct 2006 at 16:10

On one hand this demo shows the power of physics chip over the CPU doing the work. However this is all nice and dandy, whether or not games have code for this, and whether framerate suffers because of this is another matter. I think at the present time physics PPU should do "background" processing such as AI and body movement. That way it won't hit the framerate, in fact it'll improve it if the redirects the workload to the GPU. Could be used for SFX. Perhaps a "total CPU power" allocated and DX uses whatever it needs to do the job, so if you have multi-core CPU, PPU it'll pool resources, not just use PPU for one thing only. Also desireable for general maths work ie co-processor like the XT/AT timeline (co-processor could be aded later which improved things like spreadsheets/database)

It's like comparing software 3d to hardware 3d now. A few years ago it was all in software, the video card had no 3d acceleration (before Voodoo1) It could take a similar amount of time for physics to be included/required in all game, but also included onto CPU core/GFX cores.

Minstadave · 11 Oct 2006 at 16:16

squiffy said:
On one hand this demo shows the power of physics chip over the CPU doing the work.

It's like comparing software 3d to hardware 3d now. A few years ago it was all in software, the video card had no 3d acceleration (before Voodoo1) It could take a similar amount of time for physics to be included/required in all game, but also included onto CPU core/GFX cores.

Thats where I have the problem. Is it really showing the power of Ageia's hardware? Or is it just a fiddle to cripple a non-Ageia system that is completely capable of producing such effects.

And is it really like comparing software 3D to hardware 3D? The CPU should easily be capable of the physics calculations being done, I can't see why a seperate co-processor is needed.

Combat squirrel · 11 Oct 2006 at 17:03

lol, how far would have the 3d industry got if people had reactions the same as this to them, 3dmark that ONLY runs on 3d accelerators ? what a load of tosh !, not exactly sporting is it

Pottsey · 11 Oct 2006 at 17:14

“I fail to see why software running on the PPU should be hugely faster than software running on a second core.”
CPU only run 1 or 2 threads at once meaning the CPU must do instructions in a sequential manner while PPU’s and GPU run in parallel letting them run lots of threads at once. Phsyics needs lot of threads running this is why CPU’s are not the best choice for physics.

CPU’s just cannot match the physics power on a PPU or GPU. There is no way 1 CPU core is going to beat dedicated hardware at its job.

“The possibility that they've designed this cloth/liquid effect software to run poorly on anything but their own hardware seems much more likely. I see no reason at all why advanced physics effects can't be done on a second core, there's plenty of CPU power available there not being used.”
Look around for fully destructible 3d cloth in games on the CPU only. It not done as it’s not possible at playable speeds. The few games to use none destructible cloth that’s simplified over what the PPU does, suffer slow downs on the CPU. Backing up that Cellfactor is no different from other games. This also proves that cloth/liquid are not made to run poorly on anything apart from Ageia hardware. Unless you think Ageia bribed every developer in the world to make liquid and cloth run slow on the CPU. The same goes for 3d liquid you dont get it at useable speeds on CPU's.

Minstadave · 11 Oct 2006 at 17:23

Pottsey said:
CPU’s just cannot match the physics power on a PPU or GPU. There is no way 1 CPU core is going to beat dedicated hardware at its job.

I've never seen any evidence to actually prove a CPU isn't capable of producing realistic physics, the only comparison really available is cell factor and I can't tell what is the PPU doing well or simply rubbish coding for CPU physics. I can understand why a dedicated PPU could be better at producing physics than a CPU, but as we have plenty of CPU speed to spare, I'm sure there's plenty of scope for it to produce effective physics.

Look around for fully destructible 3d cloth in games on the CPU only. It not done as it’s not possible at playable speeds. The few games to use none destructible cloth that’s simplified over what the PPU does, suffer slow downs on the CPU. Backing up that Cellfactor is no different from other games. This also proves that cloth/liquid are not made to run poorly on anything apart from Ageia hardware. Unless you think Ageia bribed every developer in the world to make liquid and cloth run slow on the CPU. The same goes for 3d liquid you dont get it at useable speeds on CPU's.

I can't really answer that as there aren't any games out there with physics engines that try physics to the extent as Cell Factor does that don't support Ageia's hardware. I've never seen any evidence why cloth and liquids can't be done effectively on a CPU, its just never been a major priority. Ageia have made it their priority because they need to sell their hardware.

metalmackey · 11 Oct 2006 at 19:56

Look what I just did. Not as impressive as the benchmark but at least it aint flip screen

http://jasonshome.com

It will take advantage of the card and duel-core too (I aint got either so let me know how it runs with either/both).

xsnv · 11 Oct 2006 at 20:20

"Shortly after joining Futuremark's 3DMark Benchmark Development Program, the company behind the PhysX physics accelerator card has introduced a benchmark of its own. Dubbed RealityMark, Ageia's new app is essentially a version of the original Cell Factor demo turned into a benchmark. RealityMark runs a 38-second scripted Cell Factor sequence twice in a row: once with hardware PhysX acceleration enabled, and then a second time using software physics. Average frame rate numbers for each run are then computed and displayed in a chart at the end. Oddly, though, this chart displays a "default" hardware-accelerated result of 35.23 FPS if RealityMark is run on a system without a PhysX card installed

I think the text in bold just about sums it up. There's no shadow of a doubt this so called benchmark is heavily biased anyone who thinks it's not is living in la la land.

Iirc actually using the physicx card produced lower frame rates for a while Once a patch was made, cell factor ran perfectly well (minus a few cloth effects) on "normal" pc's.

So, £180 to see moving cloth? Me don't think so. If agei is in the future then i'm more than happy to stay in the present.

Pottsey · 11 Oct 2006 at 21:33

“Average frame rate numbers for each run are then computed and displayed in a chart at the end. Oddly, though, this chart displays a "default" hardware-accelerated result of 35.23 FPS if RealityMark is run on a system without a PhysX card installed”
That makes no since at all. Every system I have seen gets less then 3fps on average without a PhysX card installed. How on earth did they get 35.23fps did they disable the cloth? Can you give a link to that quote? How does that quote prove the benchmark is heavily biased? If its due to the cloth being turned off all it proves is the CPU is not good enough for full cloth. Also you didnt compare the PPU with cloth to the CPU without cloth? Could that be because as the PPU is still faster?

“So, £180 to see moving cloth? Me don't think so. If agei is in the future then i'm more than happy to stay in the present.”
Its more then just cloth it’s also liquids and a 30 to 60% performance boost. Look at COH that gets a large performance boost and new effects with a PPU. BOS gets nice chemical and other liquid effects as well as a speed boost.

Minstadave · 11 Oct 2006 at 21:53

Pottsey said:
“So, £180 to see moving cloth? Me don't think so. If agei is in the future then i'm more than happy to stay in the present.”
Its more then just cloth it’s also liquids and a 30 to 60% performance boost. Look at COH that gets a large performance boost and new effects with a PPU. BOS gets nice chemical and other liquid effects as well as a speed boost.

From another site:

"You may wish to look at this.

To summarize: Going to www.ageia.com and downloading the software package increases game performance, even if you DO NOT have the card itself.

The current theory is that installing the runtime engine, which is different than the card drivers themselves, allows your computer to create a 'virtual' software-based PhysX card. CoX is then able to offload the physics processing from it's own process thread to the virtual machine.

Testimonial: I do not have the card, and I run on a quite suboptimal computer (Athlon XP 1900+, Radeon 9600XT 128MB, one gig of RAM). Of late, I have had to run with no physics, and my particles turned down to 2000 or so, or I would risk crashing with heavy particle effects going off.

I am presently running with full particles, and full (not recommended without a PhysX card) physics, and I am fully stable. I have not gotten a huge fps jump, but my game is now much, much prettier and a bit more stable.

Notice that the devs have yet to say anything in that thread, however, so this is at your own risk.

Should you choose to go this route, however, take the following steps:

1) Download the drivers.
2) Select 'custom install'
3) Check ONLY the Runtime Engine and System Tray boxes, leave all others unchecked.
4) Install.

That's all there is to it.

Take it or leave it at your option, comrades."

metalmackey · 11 Oct 2006 at 22:20

Pottsey, if you have a PhysX card, run my little test Here and tell me what your lowest fps is while holding down space. I get about 30fps minimum with out a PPU.

juno_first · 11 Oct 2006 at 22:59

With cloth turned on it really kills a non physics rig as the game is obviously coded to use a physics card for certain things which makes it a poor benchmark.

If a game is coded properly as I guess crisis will be then I can’t see the need for a physics card.

Just a gimmick I think as cell factor runs fine without a physics card (less cloth) although per pixel motion blurring is a league above any current graphics card.

Oh a nice cloth demo from above, I really butchered Jason, hey hey. with no physics card I was getting 100+ fps & after making many hole in the cloth & still firing balls I was getting around 30fps though I recon this was because of the balls flying around not the holes in the cloth.

kitten · 11 Oct 2006 at 23:03

metalmackey said:
Pottsey, if you have a PhysX card, run my little test Here and tell me what your lowest fps is while holding down space. I get about 30fps minimum with out a PPU.

I think a set time to hold space would be useful. My fps fell from at least 200 to 27 fps over quite sometime. I got bored when half of Jason was shreded :eek:

The longer space is held the more balls are shot at the cloth, each extra ball costs more CPU clocks.

Perhaps this could be coded to fire a set number of balls on a single press of space. The benchmark would be then more quantative, and thus comparable.

Nice work btw.

metalmackey · 11 Oct 2006 at 23:20

It was only a quick demo (took about half an hour to code). The balls are 'deleted' if they fall off the ground. I will make a better one soon.

Thanks for the praise

rippling · 11 Oct 2006 at 23:22

very nice demo m8 , as said fixed time to hold space would be good , i went from 200fps to 20 with a fx53 ....

metalmackey · 12 Oct 2006 at 02:01

Its the balls shadows that make the framerate get so low. If I get rid of the shadows i get 160fps min. I would like someone with a PPu to test it to see if the framerate drops as far (if it does there aint any point in one).

Pottsey · 12 Oct 2006 at 07:25

”Pottsey, if you have a PhysX card, run my little test Here and tell me what your lowest fps is while holding down space. I get about 30fps minimum with out a PPU.”
Sure when I get home from work. Did you have FSAA or AF on? What settings?

“From another site:
"You may wish to look at this.
To summarize: Going to www.ageia.com and downloading the software package increases game performance, even if you DO NOT have the card itself.”
I am presently running with full particles, and full (not recommended without a PhysX card) physics, and I am fully stable. I have not gotten a huge fps jump, but my game is now much, much prettier and a bit more stable.
The Ageia API is for both software and hardware its not surprising new versions give a speed increase. Lots of games only use the API for software and some games don’t even work unless its installed even witout the PPU. Still the PPU is 30% faster then a dual core CPU in that game.

http://images.anandtech.com/graphs/physx performance update city _090506100924/12955.png

Sure you don’t need a PPU to run max settings but you get a nice speed increase.
EDIT Just remembed without the PPU the liquid effects are missing. Need to double check that though. If liquids are on and missing then he is not running on full without the PPU like he thinks he is.