Pix4D 4.5.6 - NVIDIA GeForce RTX 3070, 3080 & 3090 PerformanceWritten on October 29, 2020 by William George
TL;DR: NVIDIA GeForce RTX 30 Series Performance in Pix4D
There isn't much of a difference between the cards we tested for this review, with all of them performing within 5% or less of each other. That indicates that either Pix4D is CPU bound at this point or else the video card's utilization in this application is somewhat limited.
The RTX 3080 and 3090 offer fine performance in Pix4D, but the much cheaper GeForce RTX 3070 is just as fast in this application - so it is going to be the best choice for most users. If you already have a high-end GeForce 10 or 20 Series card, however, there is no reason to upgrade.
NVIDIA has launched their new GeForce RTX 30 Series video cards in a set of rolling releases during the fall of 2020, and has touted major advancements in performance and efficiency with this "Ampere" architecture. While gaming is almost always the media's focus during these kinds of launches, professional applications like Pix4D should see some improvements as well. Now that all three of the initial cards - the GeForce RTX 3070, 3080, and 3090 - are available, we can test them against each other and a wide range of previous-gen models to see how they perform.
If you want to see the full specs for the new GeForce RTX 3070, 3080, and 3090 cards, we recommend checking out NVIDIA's page for the new RTX 30 Series. But at a glance, here are what we consider to be the most important specs:
|VRAM||CUDA Cores||Boost Clock||Power||MSRP|
|RTX 2070 Super||8GB||2,560||1.77 GHz||215W||$499|
|RTX 3070||8GB||5,888||1.70 GHz||220W||$499|
|RTX 2080 Super||8GB||3,072||1.65 GHz||250W||$699|
|RTX 3080||10GB||8,704||1.71 GHz||320W||$699|
|RTX 2080 Ti||11GB||4,352||1.55 GHz||250W||$1,199|
|RTX 3090||24GB||10,496||1.73 GHz||350W||$1,499|
|Titan RTX||24GB||4,608||1.77 GHz||280W||$2,499|
While specs don't always line up with real-world performance, it is a great sign that NVIDIA has roughly doubled the number of CUDA cores compared to the GeForce RTX 20 Series cards at similar price points. At the top-end of the new line, NVIDIA appears to have also combined the roles of the previous-gen RTX 2080 Ti and Titan RTX into the new RTX 3090. It has as much VRAM as the Titan did, but for $1,000 less - putting it in the same ballpark as the 2080 Ti, but with more than double the memory and CUDA cores.
Puget Systems offers a range of powerful and reliable systems that are tailor-made for your unique workflow.
Listed below are the specifications of the system we used for our Pix4D testing:
|CPU||AMD TR 3970X 32 Core|
|CPU Cooler||Noctua NH-U14S TR4-SP3|
|Motherboard||Gigabyte TRX40 AORUS PRO WIFI|
|RAM||4x DDR4-2933 16GB (64GB total)|
|Video Card||NVIDIA GeForce RTX 3090 24GB
NVIDIA GeForce RTX 3080 10GB
NVIDIA GeForce RTX 3070 8GB
NVIDIA Titan RTX 24GB
NVIDIA GeForce RTX 2080 Ti 11GB
NVIDIA GeForce RTX 2080 SUPER 8GB
NVIDIA GeForce RTX 2070 SUPER 8GB
NVIDIA GeForce RTX 2060 SUPER 8GB
NVIDIA GeForce GTX 1080 Ti 11GB
|Hard Drive||Samsung 960 Pro 1TB|
|Software||Windows 10 Pro 64-bit (Ver. 2004)
To test each video card, we used our in-house Pix4D benchmark - both the standard and extended versions. Each was run twice per GPU, and the best results were included in the charts below. Here is some basic info about the image sets in these projects:
- Rock Model - 82 photos at 20 megapixels each
- School Map - 51 photos at 18 megapixels each
- School Model - 278 photos at 18 megapixels each
- Park Map - 810 photos at 18 megapixels each
We make these benchmarks publicly available under the Creative Commons BY-ND license, so if you have a copy of Pix4D you can download them from our website and compare your system's performance with the results shown here.
Here are charts showing the performance of the new GeForce RTX 30 Series (in dark green) compared to the other cards we tested:
There isn't much of a difference between the cards we tested for this review, with all of them performing within 5% or less of each other. That indicates to me that either Pix4D is mostly CPU bound or else the video card's utilization in this application is somewhat limited. In the past we have looked into the individual processing steps within Pix4D, and we saw that only Step 1's time is substantially impacted by which GPU is installed. Since Step 1 is also the shortest part of the overall Pix4D workflow, the selection of video card ends up having minimal impact on the overall processing time.
Are the NVIDIA GeForce RTX 3070, 3080 & 3090 Good for Pix4D?
The RTX 3070, 3080, and 3090 are all solid video cards for Pix4D, but if you already have a high-end GeForce 10 or 20 Series card then there is no reason to upgrade. There is also no need to spend more on the RTX 3090 or 3080 over the more affordable RTX 3070 if you are buying a new workstation - unless you use other applications which depend more heavily on the GPU.
As always, please keep in mind that these results are strictly for photogrammetry in Pix4D. If you have performance concerns for other applications in your workflow, we highly recommend checking out our Hardware Articles (you can filter by "Video Card") for the latest information on how a wide range of programs perform with various GPUs, CPUs, and other hardware.
Puget Systems offers a range of poweful and reliable systems that are tailor-made for your unique workflow.