Industrial HPC Solutions: Visualisation

HPC Scientific Research

When you imagine what visualisation is in the world of HPC, most people think of astronomy, such as images of galaxies or black holes, or they think of weather, like analyses of tornadoes or hurricanes. Astronomical and atmospheric data is huge, requires HPC to analyse, and can make for amazing, sophisticated visualisations.

In industrial HPC, visualisations are different. There have been industrial (applied) visualisations for years for engine modelling, drug discovery, and other areas. Those visualisations now, in hindsight, look almost crude but were advanced in past years and eras. The data explosion combined with advancing computing power now create deeper, more meaningful visualisations serving a wide range of applications.

This article will detail what makes industry visualisations different and will provide only a few of what are many current examples of HPC-driven visualisations that impact industry. Architecture that helps to compute and display today’s visualisations will also be provided. Let’s get started.

The Industry Differentiator

Industrial visualisations, while having evolved to provide greater depth with more elegance and sophistication in presentation, clearly differ because companies need information quickly. They need to make important decisions in little time. Visualisations can be a tool to do just that, to make informed decisions rapidly.

The earliest days of information visualisation (a.k.a., infovis) focused on presenting textual and numerical data efficiently. Today, where the most sophisticated, many times animated visualisations are the high end to those initial, rudimentary visualisations, visualisations are stillabout the users’ experience and ability to disseminate information, however complex, effectively and, especially in industry, efficiently.

In "Lessons on Visualization from the Industrial Environment" (UX matters, 6 May 2019), the industrial differentiation is detailed. The article gets into the mind of industrial consumers of visualisations, stating that “users do not view a data visualisation for the sake of admiring its aesthetics, but to get answers to their top-of-mind questions. Viewing an effective visualisation should be like receiving a report from a trusted confidant that clearly answers the users’ questions in a way that does not further burden them.”

In short, industrial visualisations need to provide insights and answers quickly, despite the huge growth in data being analysed — hence the need for HPC — when building the visualisation. Many times in industry, decisions are made by a team or committee, with not all decision-makers possessing a technical or statistical background. Visualisations help businesses to be quick, nimble, yet effective in reaching certain decisions crucial to business success.

Examples of Applied/Industrial Visualisations

One example of leveraging visualisations as a solution set to grand challenges in healthcare involves Mayo Clinic. In "Molecular and Genomic Approaches for Improving Risk in Breast Cancer", Mayo’s collaborative approach focused on “applying analytical approaches to discover relevant genes that are predictors of cancer development. DNA from thousands of tissue samples from biopsies performed at Mayo over the last 40 years. These biopsies were benign, yet some develop into cancer in later years.” The article continues that their work focused on “two categories that sometimes develop into cancers (Sclerosing Adenosis, Atypical Hyperplasias).”

What does this mean and what were the results? “Success in this project results in a better predictive marker of breast cancer development that can be used in the clinical lab and informs clinical care, resulting in lives saved and targeted treatments.”

Now that matters.

Another area of HPC-influenced visualisation is detailed in "Exploring the Three Models of Remote Visualization" (HPCwire, 22 May 2017): “Remote visualisation is an HPC technology that is rapidly changing the face of today’s energy, oil and gas (EO&G) industry. Remote visualisation allows a centralised HPC resource to host high-end compute and visualisation processing, while delivering a local copy to remote users so they can access, manipulate and share business-critical information regardless of their location. Specifically in the EO&G sector, remote visualisation technologies are helping companies more quickly discover untapped reserves, appraise new sites with less exploratory drilling, and enhance collaboration and productivity along remote teams.”

What Drives Today’s Visualisations

The true answer to the title of this section is “many,” in that visualisations are driven by many different types of processors, storage, and compute hardware as well as custom-to-enterprise software solutions for creation and development.

In "Accelerating the Shift to Software Defined Visualization" (TheNextPlatform, 9 October 2018), the author details how Software-defined visualisation (SDVis) have become prominent. “SDVis offers a scalable, highly performant approach to visualizing massive data sets without GPU hardware. By enabling simulation and visualisation to run on the same platform hardware, SDVis not only produces high fidelity visualisation but also reduces costs and complexity while increasing flexibility for scientists and system managers alike.”

The SDVIs are combined with an Intel offering: “Four Intel Parallel Computing Centers (IPCCs) are working to expand the power of SDVis, driving higher performance, fidelity, usability, and scalability.” Combined, SDVIs and IPCCs together “are incorporated into updated versions of SDVis libraries such as OSPRay, Embree, and OpenSWR, and delivered to the HPC community through open-source and third-party software solutions.”

While just one example of a framework to drive HPC visualisations, many others, be it from CPU or GPU processors, have had success as well.


HPC drives sophisticated visualisations that help to make business decisions with greater accuracy and in less time than ever before. They are a crucial yet under-realised solution set in business operations that can impact time-to-market and ROI substantially.

The next five years will continue to see visualisations created using more data on faster machines with more memory and storage. That’s the easy part to predict. The hard part is considering when companies will truly maximise the power of visualisations more extensively and intelligently in their business operations to help deliver more, better, faster.

Written by Brendan McGinty (Guest)

See Brendan McGinty (Guest)'s blog

Brendan McGinty is Director of Industry for the National Center for Supercomputing Applications (NCSA), University of Illinois at Urbana-Champaign.

Related blogs

TrueHPC at Industrial Scale

As we prepare to descend upon Frankfurt this week for ISC18, science will take its appropriate place at center stage. Throughout the week, the gathering will hear how through science we are challenging the world’s toughest problems, dissecting those problems down to their foundations and then building them back up by methodically moving every minute detail that has been learned into the powerful realm of the supercomputer. Science shows us that the best innovations are created by literally starting from scratch and building from there.

Read more

Opportunities in Applied Research and HPC

Data-intensive research and the use of advanced digital resources are key to addressing research grand challenges of our age, for the benefit of science, society, and industry. This article focuses on industrial opportunities, including potentially neglected applied research topics, and how access to high-performance computing (HPC) can provide companies with a competitive advantage.

Read more

HPCs role in seismological study and advanced earthquake analysis

Researchers have typically taken an empirical approach to earthquake study, but as high performance computing (HPC) becomes more prevalent, traditional methods of seismological study are making way for a new paradigm of earthquake analysis based on high-granularity models.

Read more

We use cookies to ensure we give you the best experience on our website, to analyse our website traffic, and to understand where our visitors are coming from. By browsing our website, you consent to our use of cookies and other tracking technologies. Read our Privacy Policy for more information.