SOLIDWORKS Visualize 2017 GeForce GPU Performance ComparisonWritten on February 3, 2017 by Matt Bach
SOLIDWORKS Visualize (formerly known as bunkspeed) is a relatively new addition to the wide range of product offered by Dassault Systemes. Based on the NVIDIA Iray rendering engine, Visualize is able to utilize the power of both the CPU and the GPU to complete renders extremely quickly. However, in the Iray-specific CPU testing we have performed in the past, we have found that your choice of GPU (and the use of multiple cards) is much more important than your choice of CPU when it comes to raw render times.
Dassault Systemes does not yet have a formal hardware requirements list or an official stance of whether they recommend you use a workstation or consumer card, but in this article we will be focusing on the NVIDIA GeForce line of cards. These cards should give you much more performance for your dollar than a Quadro card (which makes them very popular with those looking to maximize performance), but it is worth keeping in mind that there is a high likelihood that Dassault Systemes will eventually decide to only certify workstation cards for Visualize. In addition, if you plan on using the same workstation for SOLIDWORKS as well as Visualize be aware that SOLIDWORKS really works best with a Quadro card. They may be more expensive than their GeForce counterparts, but we found in our testing that even a low-end Quadro card will outperform the fastest GeForce card in key situations.
If you are interested in how Quadro cards perform or how Visualize scales with multiple GPUs, we recommend reading our other Visualize articles:
To see how the different Quadro cards perform, we used the following hardware and software:
|Motherboard:||Asus X99-M WS|
|CPU:||Intel Core i7 6950X 3.0GHz (3.4-4GHz Turbo) 10 Core|
|RAM:||4x Samsung DDR4-2133 32GB ECC Reg. RDIMM (128GB total)|
|Hard Drive:||Samsung 850 Pro 1TB SATA 6Gb/s SSD|
|OS:||Windows 10 Pro 64-bit|
|PSU:||EVGA SuperNOVA 850W P2|
Our test platform is based on the Dual GPU Workstation from our SOLIDWORKS Visualize Recommended Systems. We will be testing in GPU only mode, but to ensure that we do not have any CPU or RAM bottlenecks we are using the fastest Core i7 CPU currently available and have many times more RAM in the system than we need. We will be testing a range of GeForce cards ranging from the GTX 1060 to the Titan X.
We will be using two of the samples files provided by Dassault Systemes to see how quickly each card is able to complete a render:
The render settings used were:
- 1000 passes
- GPU only mode
GeForce Rendering Performance
The two projects used in our testing certainly rendered at very different speeds, but the relative performance between the different video cards was actually very consistent across both of them. Putting these results into relative numbers, the GTX 1070 was about 40% faster than the GTX 1060 and the GTX 1080 was just under 15% faster. Going up to the Titan X, there is actually a very decent 43% increase in performance.
These performance gains are not as significant as what we saw in our Quadro testing but it is worth pointing out that the GeForce cards don't have nearly the same price scaling as the Quadro cards and the Titan X actually performs almost exactly the same as the P6000 for about 1/4 the cost. So while the performance gains are smaller for each model, these cards will definitely still give you much faster render times for the same dollar amount.
Overall, the only "disappointing" card for Visualize is the GTX 1080. Where the GTX 1070 and Titan X were both about 40% faster than the next model down, the GTX 1080 was only about 14% faster than the GTX 1070. If your budget allows for a bit more than a GTX 1070, but not quite enough for a Titan X then the GTX 1080 might still fit, but for most users we would recommend sticking to either the GTX 1070 or Titan X if possible.
Even though this article is more about the relative performance between GeForce cards, it is worth pointing out that because Visualize scales almost perfectly with multiple GPUs it brings up some interesting considerations. The Titan X is almost exactly twice the cost of the GTX 1070, but from a performance standpoint it is only about 60% faster. So if you are looking to get the maximum performance for your dollar, you might be considering using two or four GTX 1070 cards instead of one or two Titan X cards. While this is technically more performance for your dollar, we do want to point out that while more GTX 1070s might be slightly faster, it is a much more complex configuration. Not only will you need a physically larger workstation to house the extra cards, but you will also need a motherboard that supports that many cards and a larger power supply. This will largely offset the cost savings you would get by using more GTX 1070s - not to mention that you will need be able to add as many cards in the future if you choose to.
If you are trying to decide which GeForce card(s) to use for Visualize, our testing in both this article and our scaling article actually make the decision fairly easy. Once you have decided workstation requirements (size, power draw, etc), simply choose whichever number of GTX 1070 or Titan X cards fall within your budget. By sticking with these two models, you should almost always be getting the fastest possible render times for your dollar.