The New Frontier: HPC in Enterprise Applications

By Ed Turkel

July 21, 2006

To the once-rarified list of human activities to which HPC has been frequently applied — predicting the weather, simulating chemical reactions, sequencing genomes and so on — one can now add business applications. This is particularly true in industries like aerospace and finance, which are heavily dependent on science, math and engineering, but HPC is turning up in less-expected places, like retail and insurance. As time goes on and HPC hardware gets less expensive, more powerful and easier to implement, the list of commercial uses for cluster-based supercomputing will expand as fast as business decision makers can find ways to translate it into a business advantage.

While off-the-shelf HPC has been widely available for several years, pundits have energetically debated the merits of the various technologies for just as long. Now it appears that just as monolithic, custom-built supercomputing towers have been largely outpaced by parallel cluster systems in universities and government labs, Itanium 2-based servers are an increasingly competitive choice for many of today’s enterprise HPC needs.

Some of the reasons for Itanium 2-based systems’ growing share of the enterprise HPC market include scalability, flexibility, low TCO and greater flexibility in terms of operating systems and software providers compared to RISC-based systems. As Itanium 2-based microprocessors continue to make inroads into uncharted business territories, the very definition of what constitutes HPC will shift.

On the Ground

Companies with a basis in engineering are the first places one might think to look for cutting-edge uses of 64-bit HPC to meet enterprise challenges, as these industries represent a bridge between “traditional” realms of supercomputing and more contemporary commercial applications. One such area where Itanium 2-based solutions are leading the pack is in auto manufacturing, where the ability to accurately simulate real-world conditions saves time and money and can result in a palpable competitive advantage.

Computer-aided engineering (CAE) has revolutionized the auto industry. Historically, the manufacture of a new car model could require as many as 60 or more physical prototypes for design, development and crash tests, and each prototype can cost up to $500,000 — adding up to tens of millions of dollars in manufacturing costs before a single car is sold.

In the past decade, the increasing sophistication of mathematical simulations made possible by HPC has rapidly reduced the number of prototypes required before rolling out a new model to almost zero, resulting in substantially shortened production cycles for those manufacturers able to implement the technology most effectively.

Simulations are by their very nature memory intensive; the more data points that can be included, the more accurately the simulation maps to the physical world and the more precise the result will be. This is why 64-bit systems are ideal for CAE. With vastly superior on-board memory caching and I/O systems designed to deal with larger data volumes, servers based on the Intel Itanium 2 processor can provide faster, more accurate calculations at a lower price point than comparable RISC-based systems.

HPC also enables a greater ability to deliver innovation, particularly important in the luxury auto sector. For high-end car buyers, the smallest feature gains can make the difference between one brand and another. More accurate simulations result in improved functioning in the final product: less vibration, better performance in diverse conditions, more safety — even improvements in climate control and the ability to de-ice windows are made possible by HPC.

In addition to the performance successes of Itanium 2-based systems for CAE, the approach computing vendors are taking to the overall HPC marketplace makes a big difference for these customers. Instead of trying to maintain a monopoly on its HPC solutions, Intel has partnered with as many different vendors as possible to provide the widest range of solutions to the users of Itanium 2-based systems, ensuring that the most sophisticated simulation tools will always be available to users of Itanium 2-based servers and clusters. The Itanium Solutions Alliance is one resource available for users and developers of Itanium-based systems, and offers programs, tools, workshops and directories that inform users of the variety of options available with Itanium 2-based solutions and also enables implementation.

Users of Itanium 2-based solutions also have greater freedom in choosing operating systems, including Microsoft Windows, HP-UX, Unix and Linux and can run multiple operating systems simultaneously. This makes is it easy for carmakers to upgrade underperforming legacy systems with less downtime. In fact, eight of the top 10 car manufacturers have deployed Itanium 2-based systems, demonstrating that cost-effective HPC is critical for success.

In the Air

In the field of aeronautics, the absolute need for physical testing puts the dream of zero-prototype production much further from reality than in auto manufacturing. On the whole, however, the power of HPC to run accurate simulations may be even more critical to success for aerospace companies, as the cost of building multiple prototypes has always been prohibitively high.

They also have particular needs that have not always been fully met by past HPC solutions. Because a given aircraft can remain in use for decades, the ability to duplicate analyses with absolute precision years removed from the initial design process is required for maintenance over the life of the product. The need to reproduce mathematical results and use hardware and software systems that will continue to be supported is key not only to meeting FAA and JAA standards but to keep customers happy over the long term.

While RISC-based systems can be effectively tuned to meet the computing challenges of a given aerospace company, on a RISC-based platform the need for longevity could, in theory, bind such a company to one HPC solution provider for decades regardless of the cost or quality of the relationship.

Itanium 2-based servers are an appealing choice in this regard because they are based on industry standards, meaning they are supported by a wider community of users and developers, each with a stake in the continued viability of the architecture as well as a commitment to expanding its capabilities. For example, along with Intel, the other founders of the Itanium Solutions Alliance — Bull, Fujitsu, Fujitsu Siemens Computers, Hitachi, HP, NEC, SGI and Unisys — all provide Itanium-based solutions. This advantage is enhanced by the fact that Itanium 2-based systems support a wider variety of operating systems than any other HPC solution, providing the ability to keep legacy applications running intact for the long term without necessarily having to re-port at every turn.

These facts beget yet another reason for aerospace companies to make use of Itanium 2-based HPC clusters: as the industry is highly concentrated in a few key players, yet has a high need for specialized software, makers of aircraft tend to write an extraordinary number of applications in-house.

While it would seem that customized or RISC-based hardware would offer the greatest opportunity for such customization, in many cases the opposite is true. With Itanium 2-based servers, standards-based hardware and true open-source OS options, IT staff are able to write, deploy, optimize and modify custom software solutions more easily than in cases where systems are designed and controlled by RISC-based computing vendors with a stake in controlling access to their technology.

Under the Earth

Petroleum geology is yet another industry benefiting from advances in cluster computing, as it relies on the analysis of large seismic datasets to image underground reserves and calculate drilling locations for maximum output. It is also another business in which supercomputers have been in use for decades but which is now being transformed by cluster-based HPC.

For one thing, the outsourcing of seismic data processing to specialized geophysical service companies is becoming a thing of the past. Energy companies are reaping the cost benefits and efficiencies of bringing data processing in-house with massively-scaled cluster computing solutions. In fact, 44 of the top 500 most powerful supercomputers now belong to energy companies.

With the massive onboard memory and easy scalability of Itanium 2-based systems, geological analyses that used to take months are now performed in weeks or days, allowing petroleum companies to be more nimble and efficient in their drilling practices.

In the past, less powerful processors and the necessity of utilizing tape storage required the data to be sliced into manageable chunks. The efficiency gained from employing Itanium 2-based server clusters lies in the ability of Intel Itanium processors to handle thousands of GB of data as a single job, obviating the need to cut the work up into smaller segments and shuffle those segments back and forth between hard disks and CPUs. The decreasing cost of hard disk memory has also played a strong role in enabling rapid, high-precision earth imaging by reducing reliance on tape-based storage systems.

In addition to overall efficiency and price/performance gains, Itanium 2-based clusters are setting new HPC benchmarks for earth imaging. It is in the nature of seismic petroleum exploration that the more data one can process, the further one can “see” underground. Geophysical images may contain ten billion or more data points. Due to the complex interactions of seismic waves, each of these data points must be calculated based on iterative calculations involving the entire dataset.

The ability of highly scalable, parallel Itanium 2-based servers to process seismic signals reaching out 20 kilometers underground allows petroleum geologists to see massive “earth volumes,” enabling ever-more-precise placement of wells — critically important when drilling and maintenance can cost tens of millions of dollars.

Such vast pictures of subsurface matter were not even possible a decade ago; now they can be executed in a matter of weeks. The competitive advantage — the very necessity — of HPC in the energy sector is clear.

Everywhere Else

EPIC-based 64-bit architectures have also found a natural place in other industries with compute-intensive requirements. In the financial sector, HPC is being applied to economic forecasting and portfolio strategy. Cable operators are using it to deliver rich video-on-demand systems to consumers while media companies utilize the fast memory access and reliability of Itanium 2-based systems to realize the potential of virtualizing their content libraries.

Perhaps the most exciting trend, however, is the application of HPC to industries that lie outside the traditional inner circle of supercomputing. Of course, it is number-crunching that distinguishes HPC from standard memory-intensive business applications. With the ability to store and access vast data stores now a given, businesses have to look elsewhere for a sustainable competitive advantage, and many are blazing the trail with new applications of cluster-based supercomputing to analyze customer behavior, identify business trends and manage global supply chains.

Sophisticated data mining solutions such as neural networks employ statistical calculations more similar to iterative physical modeling techniques than traditional database programming and make excellent use of the features unique to Itanium 2-based systems.

The number of sophisticated analytical tools available to businesses grows in number every year: enterprise resource planning, complex business intelligence systems that need to be seamless and accessible to ordinary users, and the increased ability to forecast changing market conditions are all applications of HPC for the enterprise that will become more prominent in coming years.

HPC itself is being redefined as more and more enterprise users find ways to use hyper-powered computational resources in the marketplace. While government and institutional users continue push the envelope of HPC performance, the list of the world’s most powerful supercomputers may one day be dominated by users such as global retailers, marketing companies and manufacturers of consumer packaged goods. Raw power alone will no longer provide a competitive edge when it is so widely available. The leaders will be those who choose the right technology for their industry and apply it in ways their rivals cannot imagine.

—–

The Itanium Solutions Alliance was formed by leading enterprise and technical solutions providers to work together towards a common objective of transitioning the world of RISC-based computing platforms to open, industry standard solutions based on Intel Itanium 2 architecture. Together with leading enterprise software and hardware providers, the Alliance is dedicated to accelerating the adoption and ongoing development of Itanium 2-based solutions. Its membership comprises some of the most influential companies in the computing industry. Visit www.itaniumsolutionsalliance.org for more information.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire