Apple unveiled this week a totally redesigned iMac in a 24-inch version with a stunning new thin design. The new machine is powered by Apple’s own chip, the M1. Readers may be wondering if these machines are powerful enough for good performing CAD and 3D work. Below we provide some detailed answers.
Let’s put all other aspects of the new iMacs aside for a moment and simply concentrate on the performance of the M1 chip with regards to CPU and GPU (graphics) performance. Recently we published an in-depth feature here on Architosh. (see, Architosh: “The M1 Mac mini vs iMac Pro 2017 vs Everyone (Part 1),” 12 April 2021). That article dives deep but let’s summarize some key items below.
All About Single-Core
Most CAD and 3D modeling software are “single-threaded” and not optimized for the utilization of multiple cores on chips. This fundamentally has to do with the mathematical realities that make 2/3D CAD software work. We’ve had recent conversations in the last year with the folks at Siemens Parasolid, for example, talking about their market-leading modeling kernel, and how much of it can be optimized for multi-threaded processing taking advantage of more CPU cores. The short answer is some parts—but of a limited nature—can be optimized for parallel processing (multithreaded) performance improvements.
So whether one is talking about Revit models, SolidWorks models, or SketchUp models, the driver of performance in modeling activity workflows is primarily the single-core performance of the CPU in combination with the GPU’s performance to redraw the screen. And in this regard, we are talking about the M1’s high-performance Firestorm core(s).
When it comes to the Apple M1 chip, the Geekbench 5 scores we have achieved and those others reported are at the top of the industry. No Intel chip matches the M1 in single-core (SC) performance and only AMD’s 5000 series (Zen 3) chips are close. In our tests, we achieved a Geekbench 5 single-core test score of 1748 compared to the 1251 reference score for a 2020 27-in. iMac i7. In our scores on our own iMac Pro (2017 model) with a Xeon processor, the result was 1100, far off the M1’s performance.
And although we found excellent material online from Nuvia—the chip company started by Gerald Williams, Apple’s former chief CPU architect, about how well Geekbench 5 accurately simulates not just PC workloads but server CPU loads of a “comprehensive general nature”—even they state that an ideal benchmark is one “that is most representative of the customer’s workload.” Therefore, it is good to test against a range of most representative benchmarks. That is why we tested with GFXbench and Cinebench as well. In the latter, the M1 essentially tied a top reference score (Intel i7 11th Gen) 4-core machine. (see image here). When you get a moment read our two-part feature as it goes deep into the M1’s performance.
CAD programs whether 3D or 2D are not driven by CPU alone. The GPU plays a major role in any system. Apple’s M1 is a unified SoC (system on chip) including CPU, GPU, centralized memory, and many other features like the Neural Engine. Its GPU is strong but it is far from being able to rival the top GPUs out in the market. The good news is it is quite strong enough for many modern CAD and 3D workflows. The primary issue is one of tapping out on the memory limitation inherent with Apple’s unified chip approach.
Apple’s new 24-inch iMacs can be fashioned with up to 16GB of unified memory. Our M1-based Mac mini also had 16GB of unified memory. We highly recommend 16GB for anyone considering professional CAD or 3D work on the new M1-based iMacs.
Back to our GPU performance testing in our M1 Mac mini feature articles, the M1 in our tests showed performance marks better than the Radeon Pro Vega 56 in our 2017 iMac Pro, a machine I use every day for professional CAD and 3D tasks on applications like SketchUp and Twinmotion to name a few. In real-world tests—and these we had to tap the Rosetta 2 translation layer—I was impressed at how well large SketchUp models with loads of textures ran on the M1-based Mac mini. And the one thing that is clear by looking at the GFXbench GPU test benchmarks they share online is that OpenGL gets crushed when going up against Microsoft DirectX and Apple’s Metal APIs. That is generally the case. So applications written for the M1 will be extra speedy due to not just the M1 but Apple’s Metal API which marries ideally with the silicon architecture on the M1.
If you were to ask this author if he would buy a new 24-inch iMac for professional CAD or 3D work, I would say it depends. If your work needs to load massive amounts of data (like texture data) onto the GPU, then the new M1-based Macs are not ideally suited for you. For all those not impacted by that limit, then the answer is yes particularly if you find a 24-inch monitor your sweet spot or want to pair a second 24-inch monitor to the iMac.
As for me?
I prefer 27-inch format screens and honestly am too curious about the M1X or whatever Apple will call the “bigger M1” they are currently working on for larger pro models. Given that Apple put the M1 inside the smaller iMac—which is honestly something I didn’t think they would do—it is clear now that Apple intends to run lean on the total number of processors they intend to develop. The fact that they put the M1 inside the new iPad Pro furthers that point.
Future M chips
Apple said when they announced Apple Silicon they would take advantage of machine TDPs (thermals). This implied chips unique to each form factor’s thermal potentials. But it seems the new M1 iMac is thin because of the M1’s TDP rather than creating a chip for the true TDP of a newer iMac form-factor. In other words, “form follows chip” seems to be the design mantra for this new 24-inch iMac.
This suggests that Apple’s next chip may scale up TDP only to a point that allows the future Apple Silicon 27-inch iMac and future large MacBook Pro to hit design goal targets that incorporate a higher TDP (thermal design power) limits.
As for what happens with a future iMac Pro, the two new Mac Pro towers of different size is anybody’s guess. With the iPhone, the chips have led to ever smaller enclosures while chips still get faster. Same with iPad. While this now dictate what happens with Macs too? The new super-thin iMac seems to suggest so.