Ghost Recon Advanced Warfighter Tests
And the short story is that the patch released by AGEIA when we published our previous story didn't really do much to fix the performance issues. We did see an increase in framerate from our previous tests, but the results are less impressive than we were hoping to see (especially with regard to the extremely low minimum framerate).Here are the results from our initial test, as well as the updated results we collected:
There is a difference, but it isn't huge. We are quite impressed with the fact that AGEIA was able to release a driver so quickly after performance issues were made known, but we would like to see better results than this. Perhaps AGEIA will have another trick up their sleeves in the future as well.
Whatever the case, after further testing, it appears our initial assumptions are proving more and more correct, at least with the current generation of PhysX games. There is a bottleneck in the system somewhere near and dear to the PPU. Whether this bottleneck is in the game code, the AGEIA driver, the PCI bus, or on the PhysX card itself, we just can't say at this point. The fact that a driver release did improve the framerates a little implies that at least some of the bottleneck is in the driver. The implementation in GRAW is quite questionable, and a game update could help to improve performance if this is the case.
Our working theory is that there is a good amount of overhead associated with initiating activity on the PhysX hardware. This idea is backed up by a few observations we have made. Firstly, the slow down occurs right as particle systems or objects are created in the game. After the creation of the PhysX accelerated objects, framerates seem to smooth out. The demos we have which use the PhysX hardware for everything physics related don't seem to suffer the same problem when blowing things up (as we will demonstrate shortly).
We don't know enough at this point about either the implementation of the PhysX hardware or the games that use it to be able to say what would help speed things up. It is quite clear that there is a whole lot of breathing room for developers to use. Both the CellFactor demo (now downloadable) and the UnrealEngine 3 demo Hangar of Doom show this fact quite clearly.
Facebook
Twitter
RSS
67 Comments
View All Comments
apesoccer - Wednesday, May 17, 2006 - link
That's a good question as well...especially for those of us using other additional pci cards...mbhame - Wednesday, May 17, 2006 - link
You guys are giving Ageia WAY too much slack. :(Call a spade a spade and save face.
apesoccer - Wednesday, May 17, 2006 - link
There's no use in throwing in the towel before we get in the ring...mbhame - Wednesday, May 17, 2006 - link
Throwing in the towel...? How do you infer that from what I said?I said "Call a spade a spade". Whether Anandtech.com chooses an easy-out path of "Currently the PPU sucks..." (not in so many words) or not, there is tremendous grace extended to Ageia around here, and frankly, it stinks.
Obviously there is a fine line between journalism with respect (which 99% of other websites are ignorant of) and brown-nosing, or needing to get a pair. All I'm saying is it's not very clear where this site's stand is amongst these possibilities.
Trisped - Wednesday, May 17, 2006 - link
I think everyone is being cautiously optimistic that the tech will improve. I wasn't on the 3d accelerator screen when that first happened, but from what I hear those cards were expensive and actually were worse then not having them. But now they are required for every game and windows vista.We want to wait to see if they can work out the bugs, give us better comparisons, and to compare it to the GPU only systems that are suppose to be coming. Once we have all the facts we can pass a final verdict, until then everything is guess work.
apesoccer - Wednesday, May 17, 2006 - link
There's alot of grace given to it everywhere...I have yet to see an article bash them. There has been a lot of interest in this product, and frankly, the general concensis is that we want to see it succeed. That aside, i don't think they can make a precise statement saying...This product is going to suck balls...or this is going to be the next Sliced Bread...My problem with it, is the lack of depth to the findings (and your statement "Call a spade a spade"...), I wish they had tried more kinds of CPU's with different kinds of GPU's, at several resolutions at both the same settings hardware/software and different ones. Without those tests, you can't really say you've tested the product.
Basically...because they haven't done enough work with it yet [imo](due to time restraints or whatever...), we can't make any real statements about this product. Other then, at the one hardware setting they ran it at, compared to the different software setting ( >< ), the software setting scored better in fps. Which tells us what? The ppu uses overhead cpu cycles when doing at least 3x the amount of work the cpu would be doing at the lower sofware settings. So lets see some different settings (and some of the hardware/software running at the same), so we can get a better idea of the big picture.
mbhame - Wednesday, May 17, 2006 - link
I don't agree with your assessment on the general consensus. My circles vehemently want it to fail as it's an additional cost to our PCs, an additional heat source, an additional power requirement... and for what?I think you're kidding yourself if you think some other CPU:GPU combination would yield appreciably-different results.
DerekWilson - Wednesday, May 17, 2006 - link
we're working very hard to find ways to more extensively test the hardware. you've hit the nail on the head with why people haven't been tearing this part up. we are certainly suspicious of its capabilities at this point, but we just don't have the facts to draw a hard line on its real value (exept in the context of "right now").mbhame - Wednesday, May 17, 2006 - link
Well then make stronger statements in the present-tense. Just because someone makes a product designed to do "X", it doesn't mean that they'll succeed in doing so. You guys come across as if it's a given the PPU *will be* a success and in doing so generate a level of expectation of success. As it stands now this is a total flop - treat it as such. Then IF and when they DO make it worthwhile for some appreciable reason then we can marvel at their about-face collectively.It's not cynicism, it's reality.
AnnonymousCoward - Friday, May 19, 2006 - link
Why do you need stronger criticism? You've been able to determine what's going on, and that's because the performance charts speak for themselves. I'd rather read what's currently on the conclusion page, instead of the obvious "This product's performance sucks with current games."