Ageia PPU...maybe not so great after all.

Page 6 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

T2k

Golden Member
Feb 24, 2004
1,664
5
0
Wow, this thing gets HOT. *REALLY-REALLY H-O-T!* And without any use.

We took out of an always-open Antec mid-tower case and 4-5 mins later it still burns your finger.
 

Dethfrumbelo

Golden Member
Nov 16, 2004
1,499
0
0
Originally posted by: T2k
Wow, this thing gets HOT. *REALLY-REALLY H-O-T!* And without any use.

We took out of an always-open Antec mid-tower case and 4-5 mins later it still burns your finger.


Sounds like it needs a pretty serious cooling solution. The way you describe it, the chip could actually go well over 100C at load.


 

T2k

Golden Member
Feb 24, 2004
1,664
5
0
Yeah, I was already searching for a full-cover block for it, just to silence it but now it seems it's more than recommended anyway.
 

dfloyd

Senior member
Nov 7, 2000
978
0
0
Originally posted by: T2k
So until Ageia actaully delivers everyone has a right to point out that right now, Hardware Based Consumer Physics Proccessing Cards are less than desireable.

FYI: AGEIA's approach is just one solution - so the fact that currently it's still unproven and the only (barely) available one doesn't justify such claims like "Hardware Based Consumer Physics Proccessing Cards are less than desireable." We need another few months to see what this card can do but we can certainly say that hw-acc'ed PP cards would be more than welcomed by most of the gamers. A more interactive/interesting, better gameplay is much more important than a possible 10% framerate drop, I believe.

Obviously friend, so please reread my post and see where I stated "right now".
 

T2k

Golden Member
Feb 24, 2004
1,664
5
0
Originally posted by: dfloyd
Originally posted by: T2k
So until Ageia actaully delivers everyone has a right to point out that right now, Hardware Based Consumer Physics Proccessing Cards are less than desireable.

FYI: AGEIA's approach is just one solution - so the fact that currently it's still unproven and the only (barely) available one doesn't justify such claims like "Hardware Based Consumer Physics Proccessing Cards are less than desireable." We need another few months to see what this card can do but we can certainly say that hw-acc'ed PP cards would be more than welcomed by most of the gamers. A more interactive/interesting, better gameplay is much more important than a possible 10% framerate drop, I believe.

Obviously friend, so please reread my post and see where I stated "right now".

? Perhaps you should re-read my post...
 

dfloyd

Senior member
Nov 7, 2000
978
0
0
Actually I did reread your post, and your talking about future tech, nothing thats even out, I am speaking of cards that are in some peoples machines now and basing my opinion on that. Sorry you did not understand what I was posting.

So once one of those cards get out maybe Physics based processing will be impressive, but with the current card (Ageia as i stated) that is out, Physics based processing looks very unimpressive and in fact a huge and total joke. Pay two fifty plus to get lower fps? That makes sense :/ Maybe in Mxyzptlk's dimension.
 

Acanthus

Lifer
Aug 28, 2001
19,915
2
76
ostif.org
Originally posted by: BenSkywalker
But does anyone need all that debris to have a game with good physics?

That line of thought, more then anything, is the one most likely to slaughter PC gaming altogether. When the consoles are offering gaming generations beyond what the PC can approach, that will be when PC gaming is going to be facing complete failure for real.

If the PPU can provide effects like cars blowing up or getting damaged with realistic modeling, I'd be happy.

How about material modeling and interaction? Take a game with very, very weak physics like HL2- the game where a rocket launcher can't destroy plywood. How much more immersive would a game be if devs that had real talent were able to make completely accurate environments? You know, a hand grenade will actually take out that chain link fence that has been stopping your tank? Or how about secondary splash damage? Some dives for cover in a room and you fire a rocket into the room with them the concussion force of the rocket plus the debris it generates is going to cause serious damage to a normal person- they certainly won't be unscathed which is the norm as of today. How about sheetrock stopping slugs from dual 45s? I don't know about you, but I'm getting a bit tired of that. If PCs continue to rely on the snails pace advancement of CPUs then they are going to fail completely to be competitive with what consoles will be offering.

But how those capabilities will be used in actual games is a different matter, especially when a) the point of the game is not to just show off the physics, and b) the rest of the system can't handle the additional physics load without slow downs.

A) Not all developers are retarded

B) Not all developers are retarded

That covers those two problems.

Speaking of Aegia in particular I have no idea how good the chip is, I have yet to see a breakdown of it to have even a rough idea of how much power the part has. I certainly have not seen anything that indicates that it will outperform Cell, but the idea of a dedicated physics processor is one that PCs need or the platform is going to turn into an upgraded cell phone in terms of gaming. x86 CPUs as they stand right now are far too slow in vector performance to keep up with their counterparts, and those that think GPUs should be handling the load should really do something outrageous like think about that for more then a couple of seconds

The best description of the core is "Dozens of cores" dedicated to physics, and a memory subsystem that is more complex and faster than a 7800GTX-512.
 

Topweasel

Diamond Member
Oct 19, 2000
5,436
1,655
136
Originally posted by: T2k
So until Ageia actaully delivers everyone has a right to point out that right now, Hardware Based Consumer Physics Proccessing Cards are less than desireable.

FYI: AGEIA's approach is just one solution - so the fact that currently it's still unproven and the only (barely) available one doesn't justify such claims like "Hardware Based Consumer Physics Proccessing Cards are less than desireable." We need another few months to see what this card can do but we can certainly say that hw-acc'ed PP cards would be more than welcomed by most of the gamers. A more interactive/interesting, better gameplay is much more important than a possible 10% framerate drop, I believe.


I think part of the performance drop is due to either the Physx card or the CPU generating the extra "interactive" objects which again have to be rendered by the video card. In a perfect world these objects would already exist in the world and would then be rendered no matter what.

The onlly Problem would be.

A.) Gameplay would have to be different for PhysX systems and Non PhysX systems. With one person being able to break a dorr down and another not. It will be a while before our favorite Multiplayer games can do Multiplayer.

or

B.) The treat everything the same which means that we would be back to software acceleration. So Some people would play it where the CPU handles Physics (slow) and other would have the PhysX acceleration (fast). It would be like the good old days of GLQuake.
 

A554SS1N

Senior member
May 17, 2005
804
0
0
The PhysX card costs over £200 in the UK, which is only a little short of getting a card like a 7900GT, or an X2 3800+ processor. Tbh, I wouldn't want to pay that EXTRA for a new system to run all this crap. Over a standard system build I could get a much higher spec machine for general use. When these chips/cards become cheap, run cool, and don't bog down the system so much that they're unusable, then maybe it'll be worth considering. I'll expect that it be a few years yet though. I thought the whole point of this card was to speed up performance by taking the load of the CPU when performing 'normal' physics calculations; not just to increase the detail so much it's like a slide-show.
 

Markbnj

Elite Member <br>Moderator Emeritus
Moderator
Sep 16, 2005
15,682
13
81
www.markbetz.net
Pretty complete review and test of the Phys-X by HotHardware:

http://www.hothardware.com/viewarticle.aspx?articleid=816&cid=2

They look at GR:AW, and Cell Factor, and come away much less than impressed. The piece closes with some comments from a game developer and Ageia. The upshot is: GR:AW exhibits minor changes, while Cell Factor is more impressive but the technology kills frame rates. Only make sense given the extra crap you have to render.

Early versions of technology often flop, so I'm not writing off PPUs completely, but the $200 price point plus the cost in performance does not trade well against a few extra bits of stuff flying around.
 

Clauzii

Member
Apr 24, 2003
133
0
0
I found this on the german site Hartware.net. It´s the ASUS Physix P1 Card:

Processor Type: AGEIA PhysX
Bus Techonology: 32-bit PCI 3.0 Interface
Memory Interface: 128-bit GDDR3 memory architecture
Memory Capacity: 128 MByte
Memory Bandwidth: 12 GBytes/sec.
Effective Memory Data Rate: 733 MHz
Peak Instruction Bandwidth: 20 Billion Instructions/sec
Sphere-Sphere collision/sec: 530 Million max
Convex-Convex(Complex) collisions/sec.: 533,000 max

To mee it looks like the onboard 128MB memory is a bit on the slow side..
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |