Ageia PhysX First Look
Ageia's PhysX started out as a killer concept but now that concept is reality. Today we take a look at that reality and touch on what it offers and what it will offer in the future.
Read the story here then talk about it here.
Ageis PhysX...The true future of PC Physics?
I am an ardent follower of PC Hardware and Software developments, To the degree that I have, in the past, been burned too many times investing in 'The Next Best Thing'...
I have followed the Ageis PhysX idea for quite some time, from when I first heard of the concept of a dedicated Physics Processing Unit (PPU) to now when the products are being marketed. I notice that a few online retailers have them on sale for £218 for the OEM 128MB version.
I have been scouring the net for any info I can get about this innovative solution to the restrictions software physics rendering places on games.
I read a pre-review of this card on AnandTech and I must admit that I am quite dissapointed by their initial findings and I'm not talking about the issues with having to re-boot the system after installation for the card to be detected by the drivers, this should be easily fixed with a driver revision. I am talking about the fact that Frame Rates DROP?!?! when the PPU is enabled on a very high spec system;
AMD Athlon 64 FX-57
AMD Opteron 144 (simulated)
ASUS NVIDIA nForce4 SLI X16 Motherboard
2GB OCZ DDR RAM
ATI Radeon X1900 XTX
ASUS PhysX PPU
Windows XP SP2
OCZ PowerStream 600W PSU
They tested the card with the CPU running full pelt and then again with it underclocked to simulate a slower CPU and the results were not at all what I was expecting.
The marketing of the Ageis PPU paints the picture that with the card installed in your machine it will free up the GPU and CPU to do the tasks they were designed for but in reality it seems that this card becomes a bottleneck, perhaps due to the fact that it is running over the PCI bus.
The in game framerates drop under all conditions of testing with the PPU enabled and after viewing the comparison videos I do not see why. Both videos (ingame footage of GRAW with and without PPU) show similar eyecandy, with the PPU version having slightly more smoke and debris, of which most dissapear as soon as they touch the ground. Not groundbreaking stuff, quite literally ;-)
I must admit to being blown away by Cell Factor and am willing to believe that performance in GRAW is due to driver issues or similar. Although I would need proof of this before even thinking about shelling out any money for this card.
From what I have seen, I honestly don't believe it's worth the £218 for the OEM version!!! And coming from me, those are not words I often utter regarding new tech ;-)
I totally agree with you. I think it is going to take at least another year for PPU's to get to the point where:
(a)the majority of games (<75%) can take advantage of it
(b)the cost is $50 - $100
(c)game performance is actually improved
Well, there you have it. As i suspected. Poor performance via the outdated PCI bus, throttling back the data through put of the PCIe bus. And lack of truely improved graphics content, due to the fact that reguardless of how much phycis processing you offload from the CPU, the video card can only render so many pixels onscreen reguardless.
I still belive that this product is a joke, as notied in this thread...
And aparently the Havok over at Firing squad thinks so as well.
If that isnt the biggest bunch of marketing spin ive ever heard i dont know what is.
In translation, they are saying our product doesnt need a fast processor or a high end video card to work...we didnt say work right, or actually improve your game play...we just said "work". And we want the consumer to draw his own conclusion, which really means, we will jsut have to double our marketing effort.
If you want to read the full FS article, its here.
Agias retort to that articles is here.
Its really sad to see a company struggle so hard to keep their head above water. But, given all the BS they shoveld from the get go about how great the product was, i cant say i really feel sorry for them.
Yep I would have to see a frame rate improvement before buying this product,I mean WTF its supposed to be doing the physics to free up the cpu from doing the task and should improve frame rate not drop it. If its because of the pci bus they should have known that and offered it in two versions one for pci-e and the other for pci. Right now im thinking this company wont last long if theres no frame rate improvement as not to many are going to fork out the cash just because thier spin on how great this is.
Ageis PhysX...The true future of PC Physics? Serious Doubts...
I have read all your posts with great interest, I feel that some very good points are being made, so here's my 2 cents worth ;-)
I believe the 'IDEA' of having a dedicated PPU in your increasingly expensive monster rig is highly appealing, even intoxicating and I believe this 'IDEA' coupled with some clever marketing will ensure a good number of highly overpriced, or at least expensive, sales of this mystical technology in it's current (ineficient) form.
For some, the fact that it's expensive and also holds such high promises will ensure it's place as a 'Must have' component for the legions of early adopters. The brilliant idea of launching them through Alienware, Falcon Northwest and the top of the line Dell XPS600 systems was a stroke of marketing genius as this adds to the allure of owning one when they finally launch to the retail market...If it's good enough for a system most of us can never afford but covet none the less it's damn well good enough for my 'monster RIG'. This arrangement will allow the almost guaranteed sales of the first wave of cards on the market. I have noticed that some UK online retailers have already started taking pre-launch orders for the £218 OEM 128MB version I just have to woner how many of these pre-orders have actually been sold?
The concept of a dedicated PPU is quite simply phenominal, We spend plenty of money upgrading our GPU's, CPU's and quite recently Creative have brought us the first true APU (X-Fi series) that it makes sense for there to be a dedicated PPU and berhaps even an AiPU to follow.
The question is, will these products actually benefit us to the value of their cost?
I would say that a GPU, or in fact up to 4 GPU's running over PCIe x32 (2xPCIe x16 channels) become increasingly less value for money the more GPU's added to the equation. i.e. a 7900GTX 512MB at £440 is great bang for the buck compared to Quad SLI 7900GTX 512MB at over £1000. The framerates in the Quad machine are not 4x the single GPU. Perhaps this is where GPU's could trully be considered worthy of nVidia or ATI's Physics SLI load balancing concept. SLI GPU's are not working flat out 100% of the time...Due to the extremely high bandwidth of Dual PCIe x16 ports there should be a reasonable amount of bandwidth to spare on Physics calculations, perhaps more if Dual PCIe x32 (or even quad x16) Motherboards inevitably turn up. I am not saying that GPU's are more efficient than a DEDICATED and designed for PPU, just that if ATI and nVidia decided the market showed enough potential, they could simply 'design in' or add PPU functionality to their GPU cores or GFX cards. This would allow them to tap into the extra bandwidth PCIe x16 affords.
The Ageis PhysX PPU in it's current form runs over the PCI bus, a comparitively Narrow bandwicth bus, and MUST communicate with the GPU in order for it to render the extra particles and objects in any scene. This in my mind would create a Bottleneck as it would only be able to communicate at the bandwidth and speed afforded by the Narrow bandwidth and slower PCI bus. The slowest path governs the speed of even the fastest...This would mean that adding a dedicated PPU, even a very fast and efficient one, would be severely limited by the bus it was running over. This phenomenon is displayed in all the real world benchmarks I have seen of the Ageis PhysX PPU to date, The framerates actually DROP when the PPU is enabled.
To counter this, I believe, Ageis through ASUS, BFG and any other manufacturing partner they sign up with will have to release products designed for the PCIe bus. I believe this is what Ageis knows as the early manufacturing samples were able to be installed in the PCI bus as well as the PCIe bus (although not at the same time ;-) ). I believe the PCI bus was chosen for launch due to the very high installed user base of PCI motherboards, every standard PC I know of that would want a PPU in their system. I belive this is a mistake, as the users most likely to purchase this part in the 'Premium price' period would likely have PCIe in their system, or at least would be willing to shell out an extra £50-£140 for the privelage. Although I could be completely wrong in this as it may allow for some 'Double Selling' as when they release the new and improved PCIe version, the early adopters will be forced to buy into it again at a premium price.
This leads me neatly onto the price. I understand that Ageis, quite rightly, are handing out the PhysX SDK freely, this is to allow maximum compatibilty and support in the shortest period of time. This does however mean that the end user, who purchases the card in the beginning will have to pay the full price for the card...£218 for the 128MB OEM version. As time goes by and more units are sold, the installed userbase of the PPU will grow and the balance will shift, Ageis will be able to start charging the developers to use their 'must have' Hardware Physics support in their games/software and this will subsidise the cost of the card to the end user, therefore making them even more affordable to the masses and therefore making it a much more 'Must Have' for the developers. This will take several generations of the PPU before we feel the full impact of this I believe.
If ATI and nVidia are smart, they can capitalise on their high installed initial userbase and properly market the idea of Hardware physics for free with their SLI physics, they may be able to throw a spanner in the works for Agies while they attempt to attain market share. This may benefit the consumer, although it may also knock Agies out of the running depending on how effective ATI and nVidias driver based solution first appears. It could also prompt a swift buy out from either ATI or nVidia like nvidia did with 3DFX.
Using the CPU for Physics, even on a multicore CPU, in my opinion is not the way forward. The CPU is not designed for physics calculations, and from what I hear they are not (comparitively) very efficient at performing these calculations. A dedicated solution will always be better in the long run. This will free up the CPU to run the OS and also for Ai calculations and well as antivirus, firewall, background applications and generally keeping the entire system secure and stable. Multicore will be a blessing for PC's and consoles, but not for such a specific and difficult (for a CPU) task.
"Deep breath" ;-)
So there you have it, My thoughts on the PPU situation as it stands now and into the future. Right now I will not be buying into the dream, but simply keeping the dream alive by closely watching how it develops until such a time as I believe the 'Right Time' comes. £218 for an unproven, generally unsupported, and possibly seriously flawed incarnation of the PPU dream is not in my opinion The Right Time, Yet ;-)
I do not really have the time to reply as I would like but I have been told by Ageia that they are addressing the PCI-E issues and should have a response to it in the near future. I would be happy with a PCI-E 4x or something like that. I dont know if it would need the full bandwidth of a 16x slot but they do need to move away from PCI.
I'll keep it really simple.
PPE in a PCIe configuration, as a stand-alone card, will not fly. You'd have to choose between a single vid card and a PPE card, rather than SLI with a PPE card (or Crossfire with PPE).
I don't see the PPE increasing framerates, but rather increasing realism...which is what they're going for. I mean, c'mon......when you're topping 200FPS in a game, what the heck are you complaining about??
Where I DO see PPE heading is an integration into the video card, which would make the most sense. I can definitely see the allure, in the current format. Let's take me, for example. I don't have an SLI motherboard, nor do I have $500 to spend on a single video card. However, I can drop $200 on a BFG PPE card, pop it into one of the gazillion PCI slots I have available, and make my X800GT look a hell of a lot better............and for less money than an X1900. It's all in the market.
At any rate, I don't see this new development as really aimed at hardcore gamers, but it is a plausible add-in for the other 90% of the computer user world.
In regards to PhysX in general, I am two-side on the subject. I had very high hopes in the card, and have been following it since early last year. Currently, GRAW and Cell Factor are the 'killer-apps' for the card, but two doesn't exactly make anyone want to run out and spend a huge wad of cash on it.
Currently, GRAW doesn't offer a mindblowing experience if you add-in a card, and Cell Factor seems to be more of a tech demo than anything. I anticipate UT2007, because that may be the official killer-app for the card.
It's evident that AGEIA has the support of many companies out there, so now it seems like it's just a matter of time before the support will actually get released.
Weither or not the PCIe1x slot has more bandwidth, its bus speed is certaintly much faster then that of legacy PCI, and that alone would be a great improvment from its current implimentation.
It is easy to complain very quickly. Frame rate is not a measure of realism or physics. It just happens frame rate is important for rendering graphics (for the graphics cards). It should not be bad, however. I understand the boards tested by Anandtech, et al. had old drivers and they didn't use the latest, which easily overcomes the frame rate issue. But some forums find it hard to swallow their pride and they won't retract the story. Second, the graphics cards at the high end cost over $400. the price of the PPU is between $249 and $299. If you want to experience something new - you are only certain to get more games on Ageia PPU. Stop complaining so easily.
Yes. The frame rate issues have been fixed with the updated drivers and we all know the games will be there. Whether or not they are blockbusters are another thing. I am honestly bored with all the reviews that I have read so far and tired of certain other sites bashing the hell out of it. I am currently out on my opinion of the card but it is extremely promising. I am holding off on releasing my review untill I get RoN: RoL tomorrow. There are also copies of the retail GRAW and Bet on Soldier coming in to review the PPU with so it will be the end of the week or early next untill I reach my conclusion. I just don't want to have my review look EXACTLY like every other review so stay tuned...
Well DS...im sorry, but unfortunately your review WILL be like every other review of the card.
Not becuase of lack of creative writing skill, But for the simple fact that you will get the exact same results. Weak, crappy, "particle acceleration".
All of the games you mentioned, though "fully supporting" the PhysX PPU, are ntohting more then some aditional bursts of particles, and flack. ANd im sorry, but you dont need a $300 add in card for that. And that sort of thing could easily be done elsewhere.
The fact still remains, the only truely killer app, is that stupid tech demo that Agia has. And who bought their last video card bassed on the tech demo that nVidia or ATi demoed it with? I sure as hell know i didnt.
Untill Agia gets a TRUELY killer app, it will go no where.
And no game developer is going to go out onto a limb with game that will only support working on an as wet unproven piece of hardware. Its simply to much of a risk. WHich means that the games will be built to run on standard hardware, the lowest common denominator. Sure there might be some blowing trash, or maybe even a potted plant getting into the mix, but is it really improving your gameplay experience...i mean really adding an extra dimension? In most cases, probibly not. Well, maybe to some people, but i doubt most will justify $300 worth of better.
WHich perhaps leads me to wonder if Ageia should take a new approach with the PPU. And perhaps Rename it, PEPU. Or Particle Effect Processing Unit. Becuase so far, we have seen any physics calculation worth writing home about. And wont for at leat another 10 months...and whos going to care about the hardware they bought ten months ago? Certaintly not the game that would shell out $300 on impulse to buy a PPU to begin with.
Perhaps you would like to write it since you know what it will say. JK
I am partially blaming the game publishers for half assing the coding for the games because so far. Physics will come into it's own eventually but I honestly dont think it will be for another couple of years.
Well, i dont think the game publishers can really be blamed for the shortcomings of Agias own bad marketing, and failure to provide development kits earliy int eh development process of the game.
From everything ive heard they have bought up some physics properties, then showed up on everyones door step and said "heres a new physics development tool, and heres this acceleration card, heres our press kit, its all free, so do with it what you can, just as long as you can get a game that supports it out to market sooner then later."
When your put on the spot like that, and have at a very early stage of the development process already taken advantage of a software physics engine (like havok), you have to go back, write excess code, and find some way to actually blend it into the current game quickly. And at the same time, not add so much graphical content that it puts the game out of reach for people with average graphics systems, or makes the physics accelerated version look so good that the majority of gamers without it will overlook teh game completely. That alot of decision making, planning, and orchestration to have happen in less then 8 months.
You simply cant make a fantastic product with such poor planning.
As ive said before, timing was everything. And they screwed the pooch on it.
Had they held the card back fromt eh market untill the developers where able to take full advantage of their hardware, it would have been much better. Instead, for the first year of this card product cycle, all we are going to see is patched up games with accelerated particle effects, and some secondary physics calculations in specific situations only.
Just imagine if they had their head on straight and got these development kits out 16-18 months ago what a game like Oblivion would look like with physics acceleration.
Somthing needs to happen real soon that will wow the gaming public, or this card will become forgotten overnight.
|All times are GMT -4. The time now is 11:54 AM.|
Powered by vBulletin® Version 3.8.7
Copyright ©2000 - 2014, vBulletin Solutions, Inc.
Copyright © 2005 - 2014, Techgage Networks Inc.