Arkham City PhysX Multi GPU Comparison

So I see a lot of people saying no games use PhysX and that it's actually something of a novelty that never really took off just like EAX by Creative Labs not too long ago.  Seeing how phenomenally the recently released Borderlands 2 has made use of it I have to disagree with sceptics.  It isn't perfect, but it definitely makes for a much prettier and more realistic environment.

Above you see my set up of two GTX670 SLI with a GT430 and GTX480.  Unfortunately I no longer have access to the latter 2 cards used in this test, therefore I can't run a test measuring Borderlands 2 performance.  I do however have results testing Arkham City.  I've chosen to test under DX11 with everything else turned to maximum setting (obviously PhysX cranked all the way up as well) vsync off at 2560 x 1440 with 4xAA because it is the most intensive scenario within the limits of my system, and more importantly, its what I'd play the game using.

Click to enlarge.

The results were quite interesting.  The minimum fps was quite sporadic across the various combinations, but were consistent through multiple runs of each.  At first I thought it may have something to do with the two cards connected using an SLI bridge.  But after using multiple bridges and a test of dual GTX670s with one dedicated to PhysX and without a bridge, there were no differences in the minimum fps.  What also threw me off was the fact that a single GTX670 + GT430 for PhysX had just as low a minimum.  These must be anomalies though as there was never a point where I'd see it running at 1 fps for any sustained period of time.

Anyhow, apart from that little anomaly, the average frames and maximum frames give a much clearer indication of PhysX performance.  Running with a single GTX670 and offloading the PhysX to the CPU was surprisingly playable (Core i7 3820 @ 4.6GHz).  It would drop below 30 more often than I would deem acceptable but it definitely wouldn't come to a sustained crawl at any point.  But moving on to the more realistic usage scenarios and we find that a single GTX670 does a fair bit better on average than CPU PhysX.  Adding a dedicated PhysX card offered extremely incremental advantages over a single GTX670 with a GT430 actually lowering performance by a couple fps on average while the GTX480 showed 1-2fps increase over the lone card.

Moving onto SLI scores and we see a similar pattern.  Whilst the averages remained fairly lacklustre the maximum did  jump about 20fps.  Adding the GT430 to the SLI GTX670's again saw a lowered average score whilst showing no real world benefit.  The GTX480 on the other hand helped a hell of a lot more in SLI pushing the average above the 60fps threshold and the maximum above 100fps.

In conclusion, those opting for a dedicated PhysX card, especially the AMD users, don't bother with any card that would run significantly lower than your main GPU.  The GT430 did no good for PhysX at all and it'd be better saving that money and going single GPU.  For SLI users, a strong dedicated PhysX card does help, but the extra heat, noise and power draw from having a GTX4/5/670-80 solely for that purpose, not to mention the extra wad of cash you'd be without, is definitely relative to what you value most.

My pick?  No dedicated card at all.  But if you've got SLI and can afford it:

One of these might help =)

Build 99% complete

So the last thing I needed to set up the X79 came in and I was set to move everything over.  I took advantage of having no motherboard in the chassis and nibbled away the rear grill as per ehume in the air flow thread.

The nibbler is actually quite easy to use.  The blade runs at a 180 degree angle perpendicular to the surface being cut as opposed to the 90 degrees that a pair off scissors would.
















A downside to this is that its hard to see if your cuts are neat and straight.  I made a little mess of things.  I'll just throw some U-channel moulding on this later on instead.

Line up of the PCIe cards I would be testing on the new motherboard.  The Auzentech Hometheater HD turned out to be completely dead on the analogue ports.  I was foolishly hoping it was some sort of OS error on my previous build.

The monstrous NZXT Havik 140 with stock fans replaced with a couple of pwm Xigmatek XAF-F1452.  Pretty much the same fan with some silver accents.  It also seemed a tad noisier with a mechanical whirl amongst the air movement.  At the lowest speed of 800rpm its nonexistent but at the peak of 1300rpm it is there.  Not that its incredibly audible but the difference can be observed if you are listening for it.

The 2011 mounting screws save a tonne of time with this cooler as well as there is no need for a backplate whatsoever.

Here is pretty much the final build internally, although some more lights will be added later and the cables could be managed a little better.  I was wanting a way to show off the SSD a little more but it gets covered up by the side panel anyway.

A little something I had planned to test for a long time. My Blackmagic Intensity Pro mounted into the vertical expansion slot of my chassis.  The slot is usually reserved for extra rear USB slots or fan controllers but I figured that with the size of this card, it might just work.  I used a PCIe riser to get the card to have its signal sent to the motherboard.  It works like a charm! =D














 
The side panel fitted with the original Havik 140 fan mounted to the side as an intake for the multi GPU setup.














Money shot.  I plan to use smaller cold cathodes instead of the long LED so that I can better highlight the white UV components.