AE CS6 11.0.1 CUDA BENCHMARK PROJECT – test your graphics cards!

[Teddy Gage]

This is very interesting. Been very curious about the Titan’s performance in AE

So basically, the titan seems to brute-force its way through to times that can compete (although not outlass) a speedy 580 setup, despite having less than optimal CUDA performance like the rest of the 6xx kepler series.

However it seems it may be software-limited performance, given that it’s basically just a consumer version of the k20 used in the tesla.

What I’m curious about is viewport performance in maya, and whether it can outperform the radeon 7970…

[Teddy Gage]

I find that render time extremely hard to believe from a 6xx series card, unless it is watercooled. Make sure your cache was cleared (if the frame are already on disc it will be 10x faster)

If confirmed, I will add it to the spreadsheet thanks

[Teddy Gage]

Guys, I have posted a spreadsheet of these results for everyone in .pdf and .ods format in the benchmark folder.

https://www.teddygage.com/AEBENCHCS6/

Hope these results are informative and thanks to everyone who has posted their info so far. If I didn’t include your results I only used one system per GPU unless the results were radically different (ie amd vs intel).

I would love to get more quadro and tesla results if possible to add to the list. Thanks!

[Cesar Siena]

Hi, I wonder how did make your Ae CS6 recognize the GTX 675MX card. Could you explain your steps, please? I work on PC’s win8 and latest versions of Ae 11.0.2 and NVIDIA driver, but nothing’s happening. Ae isn’t able to recognize it as a compatible video board. Could you give me some hint? Thank you!

[Teddy Gage]

I just got a GTX Titan and wanted to post my numbers

intel 3930K @ 4.6 ghz, with Titan @ stock speed = 3:57
intel 3930K @ 4.6 ghz, with Titan OC @ 1110 mhz base clock = 3:40

I will be testing this against a 2x GTX 580 in SLI, but still waiting on my second card

right now

GTX 580 3GB I am getting 5 min 5 sec with GPU clock at 925 mhz, or 5:45 at stock speed. testbed is intel 3770k @ 4.7 ghz

[Teddy Gage]

Just because I was curious, with double-precision on, the benchmark renders slower. Just tried it. not by much, maybe 5-10%? Honestly I have no idea what double-precision is useful for. Anyone can fill me in?

I was also wondering whether it was possible to edit a preferences file allowing AE to use more available VRAM. I understand limiting cards with less memory, but I’m only getting 4.5 GB of usable VRAM with the titan in AE. Granted, that is a lot but it would be great to get another GB and I doubt the OS needs more than 500 mb of overhead.

[Tijmen Kuipers]

Processor Intel(R) Core(TM) i7 CPU 860 @ 2.80GHz
Memory (RAM) 32,0 GB
EVGA Nvidia GeForce GTX680 4GB DDR5 Classified (PCI-e)

Render time: 7min 16sec

[Alex Barrios]

Components:
All stock no OC
Motherboard: ASUS Rampage 4
PS: Corsair 1200
CPU: intel 3960x
Ram: Corsair Dominator GT 32GB
HD: Corsair GT solid state 240GB
Graphic card: 2 EVGA GTX 590- with old driver 301.42WHQL
i will try and post results with new Nvidia 320.18 driver

Render time: 3min 57sec.

[Alex Barrios]

with new Nvidia 320.18 driver

render time- 3min 40sec

[Adrian Thompson]

Mac 4,1
8-core 2.26Ghz
32GB Ram
7200rpm hard drive

Latest version of Mountain Lion and Nvidia Drivers.

Nvidia GTX 570, 2.5GB (flashed by MacVidCards)

6 Min, 51 Sec