AMD Frame Pacing Explored: Catalyst 13.8 Brings Consistency to Crossfireby Ryan Smith on August 1, 2013 2:00 PM EST
For the purposes of our testing we’ll be looking at the 6 games we’ve adopted for use with FCAT due to their proven reliability. These are Total War: Shogun 2, HItman: Absolution, Sleeping Dogs, Battlefield 3, Bioshock Infinite, and Crysis 3. All of our results unless otherwise noted are using Catalyst 13.8b1 for the AMD cards, and NVIDIA’s 326.19 beta drivers for the GeForce cards.
Our metric of choice for measuring frame times and frame pacing is a metric we’re calling Delta Percentages. With delta percentages we’re collecting the deltas (differences) between frame times, averaging that out, and then dividing delta average by the average frame time of the entire run. The end result of this process is that we can measure whether sequential frames are rendering in roughly the same amount of time, while controlling for performance differences by looking at the data relative to the average frame time (rather than as absolute time). This gives us the average frame-to-frame time difference as a percentage.
In general, a properly behaving single-GPU card should have a delta average of under 3%, with the specific value depending in part on how variable the workload is throughout any given game benchmark. 3% may sound small, but since we’re talking about an average it means it’s weighed against the entire run, as the higher the percentage the more unevenly frames are arriving. For a multi-GPU setup we’d ideally like to see the delta percentages be equal to our single-GPU setups, but this is for the most part unreasonable. There is no hard number for what is or isn’t right here, but based on play testing we’d say 15%-20% is a reasonable threshold for acceptable variance, with anything under 10% being very good for a multi-GPU setup.
Finally, in our testing we did encounter an issue with Catalyst 13.8 that required we make some slight adjustments to FCAT to compensate for this bug, so we need to make note of this. For reasons we can’t sufficiently explain at this time but has been confirmed by AMD, in some cases in Crossfire mode AMD’s latest drivers are periodically drawing small slices of old frame buffers at the top of the screen. The gameplay impact is minimal-to-nonexistent, but this problem throws off FCAT badly.
To quickly demonstrate the problem, below we have two consecutive frames from one of our Battlefield 3 runs. The correct FCAT color order here is dark blue, green, light blue, and olive. The frames corresponding to dark blue and green occur on frame one, and light blue and olive on frame two. Yet looking at frame two, we see a small 6 pixel high stripe of dark blue at the very top of the image. At this point the dark blue frame should have already been discarded, as the cards have moved on to the green and later light blue frames. Instead we’re getting a very small slice of a frame that is essentially 2 frames old.
The gameplay impact from this is trivial to none; the issue never exceeds a 6 pixel slice, only occurs at the top of the frame (which is generally skybox territory), and is periodic to the point where it occurs at most a few times per minute. And based on our experience this primarily occurs when a buffer swap should be occurring during or right after the start of a new refresh cycle, which is why it’s so periodic.
However the larger issue is that FCAT detects this as a frame drop, believing that over a dozen frames have been dropped. This isn’t actually possible of course – the context queue isn’t large enough to hold that many frames – and analysis shows that it’s actually part of the old frame as we’ve explained earlier. As such we’ve had to modify FCAT to ignore this issue so that it doesn’t find these slices and count them as dropped frames. The issue is real enough (this isn’t a capture error) and AMD will be fixing it, but it’s not evidence of a dropped frame as the stock implementation of FCAT would assume.
Ultimately our best guess here is that AMD is somehow mistiming their buffer swaps, as the 2 frame old aspect of this correlates nicely to the fact that the dark blue and light blue frames would both be generated by the same GPU in a two-GPU setup.
|CPU:||Intel Core i7-3960X @ 4.3GHz|
|Motherboard:||EVGA X79 SLI|
|Power Supply:||Antec True Power Quattro 1200|
|Hard Disk:||Samsung 470 (256GB)|
|Memory:||G.Skill Ripjaws DDR3-1867 4 x 4GB (8-10-9-26)|
|Case:||Thermaltake Spedo Advance|
AMD Radeon HD 6990
AMD Radeon HD 7970GE
AMD Radeon HD 7990
NVIDIA GeForce GTX 590
NVIDIA GeForce GTX 680
NVIDIA GeForce GTX 690
NVIDIA ForceWare 326.19
AMD Catalyst 13.5 Beta 2
AMD Catalyst 13.6 Beta 2
AMD Catalyst 13.8 Beta 1
|OS:||Windows 8 Pro|
Post Your CommentPlease log in or sign up to comment.
View All Comments
chizow - Friday, August 2, 2013 - linkAgree for the most part, but I wouldn't go as far to say boycott AMD, I'd say it's a good learning experience for AMD fans. In order to better their own products, they need to be forthcoming and honest about their experiences. If something's broken, demand a fix, don't sit there and dismiss or minimize the problem, or worst, deflect the issue toward the competition in denial. In the end, they just end up hurting themselves by gimping the products they enjoy.
Will Robinson - Tuesday, August 13, 2013 - linkPlease go back to spamming the comments section at Tech Report with your NVDA shill buddy Wreckage.
Its beyond boring having to read it here too.
chizow - Friday, August 2, 2013 - linkTom Petersen, Technical Marketing Director for Nvidia, has stated Nvidia has had built-in frame metering provisions since at least G80. Nvidia invented modern day AFR and they have clearly put a lot of thought behind it with the science to back it up. Every time you see them talk about AFR/microstutter/runtframes you see a lot of detailed technical slides and backup. Not so much from AMD. It should be obvious why Nvidia has had less of an issue with microstutter, they actually knew what they were looking to fix.
"Nvidia's Tom Petersen threw us for a loop by asserting that Nvidia's GPUs have had, since "at least" the G80, a built-in provision called frame metering that attempts to counteract the problem."
Sabresiberian - Thursday, August 1, 2013 - linkTech Reports is a competing company to AMD?
While it is very good to see AMD making progress here, it is far from over for both AMD and Nvidia. Both companies have work to do to get frame rates to be consistent and high.
BryanDobbins - Saturday, August 17, 2013 - linkmy neighbor's mom makes $72/hour on the internet. She has been unemployed for 7 months but last month her pay check was $19114 just working on the internet for a few hours. Read more on this web site... http://goo.gl/qHdAQ4
Mondozai - Thursday, August 1, 2013 - linkAlways liked Ryan's articles but I hope he gets to write more for this site in the future. For example, he should write more about mobile GPU's now that that area is gaining importance(this year we get to see PowerVR's newest generation, Rogue and next year we get to see Kepler in Tegra 5). Yet he didn't write anything on Tegra 5's Kepler story on this site even if he is the expert on GPU's.
Doing a story on AMD drivers is all well and good but honestly, would like to see moar.
Ryan Smith - Thursday, August 1, 2013 - linkWe have some in-depth mobile coverage scheduled for later this year, though I can't go into any more detail on it at this moment.
mwildtech - Thursday, August 1, 2013 - linkGreat write up! Thanks Ryan!
SeeManRun - Thursday, August 1, 2013 - linkIt wasn't totally clear from reading, but is there any point in upgrading to this driver if you have a single graphics card? It doesn't appear so.
DanNeely - Thursday, August 1, 2013 - linkRelease notes aren't out yet; but the 3rd page mentions that it adds full OpenGL ES 3.0 support as well as other not yes specified improvements. Most likely they include the obligatory few games to get a performance boost; but it's not purely a crossfire update.