CAD Tech News (#117)

Herrera on Hardware: Hardware Benchmarks for CAD, Part 1 — Value, Limitations, and a Strategy for Use

Benchmarks remain the best performance evaluation tools, but not all benchmarks are created equal.

By Alex Herrera

For those whose daily productivity depends on how fast their workstation can model, simulate, visualize, and render, searching out the most capable hardware to handle those tasks can be a rewarding pursuit. But what's the best way to assess and compare the performance of GPUs and workstations for CAD workflows?

There is no one precise way. Rather, it becomes an exercise in triangulating among several datapoints, while always keeping in mind the context and characteristics of your specific application, workflow, and compute loads, as well as other criteria that might matter, like price and future-focused features. Though not perfect, benchmarks remain the best performance evaluation tools ... but not all benchmarks are created equal, nor can they validate the same conclusions.

Are Spec Sheets and Performance Numbers Enough?

Datasheets supplied by GPU and workstation vendors aren't usually the easiest to navigate or exploit. Consider a GPU's ratings for FLOPS or graphics memory bandwidth, or a CPU's specs of core counts and GHz ratings. Unfortunately, there's a fundamental problem with virtually all of these metrics: they tend to reflect theoretical hardware limits, indicating performance levels that can be reached in very specific circumstances, most of which are not realistic when running real-world applications.

Each of these numbers taken alone means nothing, unless all of the other salient architectural metrics can deliver to similarly capable levels. For example, consider a couple of hypothetical CPUs: model A from Intel that offers 8 cores running at (nominal) 4.3 GHz, and one from AMD that offers 12 cores running at (nominal) 4.0 GHz. There are no valid conclusions to draw from those numbers by themselves, without knowing answers to a few questions: How comparable are the respective core microarchitectures? How threaded are your critical workloads? How much time do you spend running that workload versus, say, modeling?

Comparing raw GPU metrics is no more concise. Where GPU A's array of internal computing engines might promise X TFLOPS (trillion floating-point operations per second) of peak computing throughput, in may only utilize a small fraction of those FLOPS if the instruction stream and the rest of the architecture (e.g., GPU's input/output, instruction pipeline, and memory subsystems) can't supply those floating-point engines with data fast enough. Read more »

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

Matterport Adds Interactive 3D Measuring Functionality to Its Spatial Data Platform

New Measurement Mode enables users to make and share measurements from Matterport digital twins of built environments.

By Cadalyst Staff

Matterport is a spatial data company that helps professionals in AEC, real estate, insurance, and other fields create 3D digital twins of the built environment, using tools including its structured-light reality-capture cameras and Cloud 3.0 software platform. Today, Matterport announced new functionality that gives users the ability to take measurements in a Matterport 3D digital twin and share them with others. The new Measurement Mode in Showcase (the company's web-based client for exploring its 3D spaces) enables users to "accurately measure rooms, windows, doors, or furniture with a simple click or tap on a PC or mobile device," according to the company.

AEC professionals can share Matterport digital twins with stakeholders so they can review property measurements from any location with Internet access. This enables firms to bid for projects virtually, can reduce the number of change orders in a project, and reduce the time spent verifying measurements in person, Matterport reports.

"Measurement Mode is an important step in our strategy to turn buildings into data and actionable insights," said Matterport CEO R.J. Pittman in a press release. "This new capability gives customers an invaluable tool for sharing vital information of spaces or objects within a Matterport digital twin. The potential for smarter space planning, utilization, and collaboration for the built world is enormous."

While digitally navigating the 3D environment, users can click to create point-to-point measurements anywhere.

Read more »

WHAT’S NEW FROM CADALYST

CAD Manager Column: The State of CAD Management at the Start of a New Decade
Conferring with hundreds of CAD managers and vendors at Autodesk University provides perspective on which issues are most pressing for the profession as we enter 2020. Read more »

Graebert Unveils CAD SaaS Road Map, New BIM Features
According to the Berlin-based CAD developer, the software-as-a-service transformation will likely take more than a decade, but the time to start investing in cloud solutions is now. Read more »

Viewpoint: Why BIM Models Serve Designers Better Than Contractors
With BIM, the design stage is privileged over the execution stage — and tools that require specialized knowledge of BIM technology and operating skills are limiting the use of BIM in construction. Read more »

Autodesk Creates Construction Cloud to Connect Scattered Teams
New solution promises to help team members collaborate effectively — whether they're in an office or the field — and to enable data to flow from design to fabrication to the job site. Read more »

In nTop Platform 2.0, New Toolkits Aim to Make Advanced Capabilities More Accessible
Prepackaged workflows are intended to help users quickly grasp and apply the most advanced aspects of the computational modeling software, nTopology reports. Read more »