Table of Contents
Autodesk ReMake (formerly Memento) is a photogrammetry application, similar to Agisoft PhotoScan. It takes a set of photos as input and uses them to create a textured 3D model of the object(s) in the photos. Autodesk publishes a basic system requirements page, but there is not much information available there regarding what hardware actually performs best in this program.
In this article we are going to look at several NVIDIA GeForce GPU (video card) options that you might consider in a workstation to see how they compare in ReMake. Some of the steps in ReMake are GPU accelerated, and specifically use NVIDIA's CUDA technology – so it cannot run on Intel or AMD graphics chips. We also tested a selection of Quadro cards, and the results from those are available on another article.
To see how each of the GeForce cards perform in Revit, we used the following workstation hardware and software:
|Asus PRIME Z270-A
|Intel Core i7 7700K 4.2GHz (4.5GHz Max Turbo) 4 Core
|4x Crucial DDR4-2400 16GB (64GB total)
|Samsung 960 Pro 2TB M.2 SSD
|Windows 10 Pro 64-bit
|Autodesk ReMake v220.127.116.11
This hardware is based on one of the top-performing CPU platforms for ReMake, as determined by our CPU comparison testing.
The GeForce cards we are testing are the latest Pascal based models, with the GTX 1050 through 1080 Ti as well as the top-end Titan Xp. These cards tend to have lower video memory than the “professional” Quadro line, but they also cost much less. Please note that if you use other Autodesk software, in addition to ReMake, it may be prudent to stick with a Quadro in order to have better support from Autodesk.
|Test Video Cards
|NVIDIA GeForce GTX 1050 2GB
|NVIDIA GeForce GTX 1060 6GB
|NVIDIA GeForce GTX 1070 8GB
|NVIDIA GeForce GTX 1080 8GB
|NVIDIA GeForce GTX 1080 Ti 11GB
|NVIDIA GeForce Titan Xp 12GB
We performed our testing using two image sets I took: a set of 78 images of a chessboard and 300 images of a playground climbing toy. The smaller image set was used for most tests, with the larger set reserved for a comparison of GPU memory usage. Both the number of photos you use and the resolution of those images will increase memory demands and processing time, and we targetted an image set that would take long enough to run that we could see measurable differences between hardware but not so long that it would take weeks to perform the testing.
At the completion of each run, ReMake creates a log file that records the total time as well as several individual steps. Unfortunately, those steps are not labeled or described – so we will present only the total time here, not the various parts that make up the total.
Benchmark Results – Performance
Here are the processing times (in seconds) for ReMake with the full set of GeForce cards:
As could be expected, the faster GeForce cards performed better in ReMake. The jumps from the GTX 1050 through the GTX 1080 are especially noticable, but the 1080 Ti and Titan Xp ended up within a few seconds of each other.
Benchmark Results – GPU Memory
Using larger image sets can utilize more video memory, which is why we also ran a test with 300 photos. We ran this test on a different platform (Core i7 7820X on an X299 motherboard) and, in order to try and isolate the video memory rather than GPU performance, we used a Quadro P6000 24GB along with the GeForce Titan Xp 12GB. These cards perform very similarly with smaller image sets, as shown in the graph below, but the difference in video memory impacts performance with higher numbers of photos.
With our larger image set, the Titan Xp's lower amount of memory caused it to fall behind the P6000 by about 10%, despite a slight lead when processing the smaller image set. To see why this is the case, the graph below shows peak GPU memory usage when ReMake is processing both 78 and 300 photos (20 megapixels each):
It turns out that even the smaller image set we used comes close to filling the Titan Xp's 12GB of video memory. With the larger image set the Titan cannot keep everything on the card, and shuffling data in and out of the card's memory is the likely culprit behind its drop in performance. If you are going to work with either large numbers of photos or higher resolution images in ReMake please keep this factor in mind, and perhaps consider a Quadro video card with higher memory capacity.
Benchmark Results – Dual GPUs
Some GPU accelerated applications can utilize multiple video cards to increase performance, so we tried using two of the GeForce GTX 1070 cards to see what impact that had. These are the only GeForce cards we had two of handy at the time, though additional dual GPU testing was done on Quadro cards as well.
There is a slight increase in performance with a second GTX 1070, but it is less than a 2% improvement. That is similar to what we found with dual Quadro cards. Because of the minimal impact that a second GPU has, along with concerns about stability we encountered with dual Quadro cards on some image sets, we advise against purchasing multiple video cards in a ReMake workstation.
Given the results of our testing, there are three factors to consider when selecting a GeForce video card for ReMake:
1) Raw performance
2) Memory capacity
The GTX 1050 has very little onboard memory, and does not perform well either, so it is not good candidate in any situation. The GTX 1060 through 1080 are okay, but if you work with even moderate-size image sets the 6 to 8GB of memory on those models may not really be enough. Of all the GeForce cards, the 1080 Ti and Titan Xp offer both the best performance and the most onboard memory, but if you work with large image sets then even they may not be ideal from a memory usage standpoint. NVIDIA's Quadro series are currently available with 16 and 24GB cards which are much better equipped for processing large numbers of photos in ReMake. It is also worth noting that if you use other Autodesk applications (like Inventor, Revit, or Maya) then only Quadro cards are going to be officially certified for use in those programs. For pure ReMake usage, though, GeForce cards can do well with small to mid-size image sets.