CAD Tech News (#102)

▶ Herrera on Hardware: A Compelling Example of AI in CAD — Autodesk's Take on Generative Design

Both evolutionary and revolutionary uses are emerging for artificial intelligence (AI) in CAD, which is making a splash from NVIDIA rendering applications to Autodesk Fusion 360 — and suggesting serious synergy with virtual workstations.

By Alex Herrera

Artificial intelligence (AI), machine learning, deep neural networks (DNNs) — these topics and buzzwords have captured the lion's share of technology press in the past few years. But for those who've seen more than a few hype-and-bust cycles in the past, the headlines beg the question: Is this stuff real and impactful, or just another round of marketing exuberance that will disappoint in the long run? The answer in a big-picture context is clear: In the long term, artificial and machine learning will fundamentally transform not only technology, but likely society as a whole.

The trickier (and more relevant) question for many is: How will it do so, when it will do so, and in which markets and applications will it have the most impact? Certainly, professional computing applications are among those most clearly in the crosshairs of machine learning. And of those professional spaces, CAD presents some of the most compelling uses I've seen for the technology. We're seeing both hardware and applications incorporate AI to speed and improve upon the things CAD professionals already rely on, and vendors such as Autodesk are planting new seeds — already starting to bear fruit — for transformational changes to traditional workflows, first and foremost in generative design.

Early — and Unexpected — AI Opportunities

Uses for machine learning (which you can pretty much equate to AI) that most of us never envisioned have already evolved to aid in an area that CAD workflows have long emphasized: 3D visualization. Promoted primarily by NVIDIA in conjunction with its deployment and promotion of AI-accelerating graphics processing units (GPUs) are two uses in particular: smart-sampled anti-aliasing and raytrace de-noising.

Those familiar with the most common, yet extremely compute-intensive technique to render photorealistic images — raytracing — know that the image does not appear in full fidelity in a single pass, but instead resolves over time as the engine fires rays into the scene and resolves the lighting contributions of that ray's path throughout the scene. To accelerate the process, NVIDIA (and others) have incorporated a DNN in the raytracer to accelerate image "convergence" by decreasing the computational load in the latter stages of rendering. Once the image congeals into something it can recognize, AI fills in remaining rays/pixels, de-noising the image and wrapping up the time-consuming rendering process far faster than requiring the full per-ray processing, and without any temporal artifacts.

NVIDIA has also found a way to leverage a trained DNN to speed the more common interactive 3D graphics we use for real-time modeling and viewing. An established, high-quality technique to reduce the visual artifacts of CGI aliasing, super-sampling is notoriously expensive in consumption of GPU processing cycles. Super-sampling essentially requires multiple passes through all or part of the 3D rasterization pipeline, with a different, shifted sample point for each pass.

Super-sampling would be much more appealing if the number of passes/frames could be reduced without adversely affecting quality, thereby reducing the performance hit. That's the goal of NVIDIA's Deep Learning Super Sampling (DLSS), which reduces the input sample count by using a GPU-accelerated DNN to analyze intermediate frames and gain some "knowledge" of the underlying geometry for intelligent placement of fewer sample points. The end result is either the same quality with higher performance, or better quality at the same performance. Read more »

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Alex Herrera is a consultant focusing on high-performance graphics and workstations.

▶ SOLIDWORKS World 2019 Exhibits Ground-Breaking 3D Printers and More

MakerBot, RIZE, BigRep, and other hardware and software developers shared new offerings the Dallas conference.

By Nancy Spurling Johnson

On the exhibition floor at SOLIDWORKS World 2019 in Dallas, Texas, last week, several new and often innovative software and hardware products vied for the attention of conference-goers. Following is our roundup, based on Cadalyst's in-person meetings with developers and updates shared at the event.

MakerBot Method 3D Printer

Cadalyst often doesn't report on newly announced products if they're not yet commercially available — but in the case of the MakerBot Method 3D printer, announced in December and shipping next month, we had to break our own rule to share the noteworthy news. Method combines MakerBot's roots in the hobbyist market with the industrial DNA of parent company Stratasys to deliver what the company calls a first-of-its-kind, professional-grade 3D printer that sits on an office desktop.

The MakerBot Method 3D printer is small, quiet, and safe enough to be integrated in a design environment. Image source: MakerBot

Method offers features that were previously only available on industrial 3D printers at significantly lower cost ($6,499 retail; save $350 via online preorder before February 28) — with a first-year cost of ownership that is one-third that of an entry-level industrial 3D printer, according to MakerBot.

The relatively affordable industrial-printer-for-the-desktop design aims to fill a gap in the existing market, particularly for small businesses being priced out of the competitive additive manufacturing (AM) market as well as large organizations that need a more agile, flexible AM option.

Method, which was modeled using SOLIDWORKS, reportedly prints up to two times faster than desktop 3D printers. It is designed to deliver industrial reliability and precision by carefully controlling every aspect of the 3D print environment, resulting in repeatable and consistent parts with ±0.2 mm dimensional accuracy as well as vertical layer uniformity. The dual extrusion system combined with water-soluble PVA provides a superior surface finish and enables unlimited design freedom and unrestricted geometries, such as complex overhangs without scarring.

"You can do much more complex geometry and obtain a level of accuracy you can't get with other desktop printers," Forrest Leighton, vice-president of marketing for MakerBot, told me during a product demonstration.

Precision materials include MakerBot Tough, MakerBot PLA, and MakerBot PVA. The first specialty material on the platform is PETG, with more to follow. Read more »

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Nancy Spurling Johnson is the content director for Longitude Media, publisher of Cadalyst.

▶ WHAT’S NEW FROM CADALYST

CAD Manager Column: Learn Your Boss's Priorities for Your Job
It's often difficult to determine how to organize your many tasks as a CAD manager. What does your boss want you to focus on first? There's only one way to know for certain — ask! Read more »

Cadalyst Publishes CAD Manager's Guide to Error Reduction
A collection of Robert Green's advice helps CAD managers catch more problems — and even stop some before they start. Read more »

AutoCAD Video Tips: Rid Your AutoCAD Drawings of Spelling Errors
Spelling errors can make you look very unprofessional — but they're easily prevented! Join AutoCAD tipster Lynn Allen as she shows you how to spell-check any drawing, and gives you customization tips to ensure SPELL gives you the best results possible (including working on external references). Watch the video »

'CAD Trends' Survey Covers More Technologies But Yields Few Surprises
3D printing adoption continues to grow significantly, as strong growth potential is found for emerging technologies such as generative design and artificial intelligence. Read more »