OCF Supersizes HPC Service

By Tiffany Trader

October 16, 2012

UK-based HPC systems integrator OCF plc just significantly expanded its pay-as-you-go supercomputing service, enCORE. The on-demand system first launched in late 2010 to bring additional computing capacity to the UK’s small-to-medium-sized business community. What started out as a small pilot project has developed into a full-fledged, 8,000-core HPC service.

Lola Cars

Using enCORE – racecar CFD simulation superimposed onto real Le Mans image: Picture courtesy of Lola Cars

Jerry Dixon, the HPC on Demand business development manager at OCF, joined the company just before the initial deployment. He recalls that at the time, the company was aware of the huge potential for a service of this kind, but did not have the capacity required to launch such an undertaking – at least not by themselves. However, via a partnership with the Science and Technology Facilities Council, a UK research council operation, the OCF came to an exclusive arrangement to sell the excess capacity of the Daresbury Laboratory’s IBM iDataplex cluster on essentially a revenue share basis.

The initial cluster was quite small, even by 2010 standards: a 2.5 teraflop System x iDataPlex server cluster. The OCF had a service-level agreement that allowed it to use half of the cycles. Since then, the OCF has been running essentially a pilot service, enabling them to fine-tune the service-level agreement and get a better understanding of what customers are looking for. While the focus has been on small-to-medium sized businesses in the UK, there are also a couple overseas customers.

This month, as part of a newly signed agreement between OCF and the Science and Technology Facilities Council’s Hartree Centre, the service is ramping up to 8,000 cores. It draws its power from a new IBM System x iDataPlex cluster named Blue Wonder, which was installed and configured by OCF in partnership with IBM. With 8,192 Intel Xeon E5 processor cores interconnected with FDR InfiniBand and plugged into a high-speed GPFS file system, the machine is capable of 206.3 teraflops (Linpack). Its 48 TB shared memory capacity makes it the largest shared memory cluster in the UK.

Each of the 512 nodes sports Intel SandyBridge 8-core CPUs with either 36Gb or 128Gb RAM. This is true HPC-as-a-Service; the compute nodes are not virtualized. Service users can also access 48 GPU nodes outfitted with NVIDIA Tesla 2090 GPUs.

The cluster operates with Platform HPC tools, so for customers using Platform LSF, it’s easy to switch their compute jobs to a remote cluster. Users who rely on Sun Grid Engine or other scheduling software need a separate account with OCF. Dixon says that job submissions have gone smoothly, but that OCF is still looking to develop different user interfaces to make it easier to use the enCORE service in a more automated way, over the Internet. Customers can use various open source applications available on enCORE, or load their own apps.

With this additional capacity, OCF and enCORE will be able to satisfy the type of requirements of larger organizations in addition to their current customer base of small and mid-size companies. Dixon recounts the meaningful business benefits enabled by the endeavor. Some customers have no HPC infrastructure available to them in-house and in order to run models and simulations successfully they need to access an HPC cluster. Other customers may own HPC resources but from time to time have peaks in demand or challenging project schedules or have workloads that require significantly more capacity than they have access to. Other clients who own systems outright are pushing up against capacity, datacenter and power limitations and use the service as way to minimize the gap.

One success story in particular stands out in Dixon’s mind: a customer that had the opportunity to bid for a contract to perform wind farm simulations, but did not have the necessary computing power necessary to carry out the work. By working with OCF and using the enCORE service, they were able to put in a successful bid and delivered the work on time and on budget.

While enCORE is officially a public-private partnership – the first one of its kind in the UK – from the customer perspective, this is a commercial service. The entire customer engagement, from sales and marketing right through to service delivery is with OCF. So the customer does not have any exposure whatsoever to the partner institutions – all technical support, requirements or requests come in to the OCF service desk.

But this is still a collaboration, and the cluster operates based on service agreements. Dixon characterized the arrangement as a flexible arrangement, with OCF having access to 8,000 of the 8,192 available cores. The distribution of resources toward commercial endeavors is intentional.

The Hartree Center – where the cluster resides – is a collaboration between the STFC, IBM and other partners, including OCF. The center, launched in 2011 with a £37.5 government investment, has a mandate to help UK businesses harness the power of high-performance computing in order to better compete on the global playing field. Dixon explains that historically the Germans and the French have invested significantly more federal dollars into HPC than Britain has and that’s one reason this project is so important.

“The objective of the Hartree Center,” says Dixon, “is to help customers adopt high-performance computing, optimize codes and build applications in a collaborative framework to help them become more innovative.” By using the latest modeling and simulation technologies, vendors can optimize their research and development process and get products to market more quickly.

Running codes on HPC systems is rarely a simple task, and as part of their services, OCF provides access to HPC experts. They help users resolve issues of compiling code and installing modules. “I think that’s an important distinction from users that try to run HPC simulations on public clouds, like Amazon EC2,” says Dixon, “where you wouldn’t get that level or any level of support of that type. We’ve got a number of notes of thanks from our customers for the support we’ve provided which has allowed them to get up and running very quickly.”

In talking with Dixon, one gets the sense that there is quite the ecosystem of users and potential users who have a need for this kind of HPC capacity. “The range of industries that we’ll be supporting is going to expand quite significantly along with the growth of the cluster,” he says.

Current and would-be customers tend to have a mix of engineering and geoscience codes. The list of possible use cases is quite varied and includes semiconductor design, hydrodynamics, modeling high-speed trains (two trains passing in a tunnel), insurance risk modeling based on natural disasters, financial modeling, and more. BHR, Engys, Actiflow, HR Wallingford, Lola Cars and Renuda are just some of their customers.

Dr. David Kelsall, senior consultant at fluid engineering consultancy, BHR Group, shared his thoughts on using the service as a way to increase user confidence in digital tools. BHR group has operated mostly with physical models and under new leadership is increasing its use of computer modeling and simulation technologies. Kelsall points to a customer who, through an outside agency, has done computer modeling for a massive pumping system and now wants to ensure the validity of the results, so they turned to BHR to create a physical model and to help them get a feel for the pros and cons of each approach.

Kelsall sees other companies straddling the physical/digital divide and views the cloud service as a way to obtain the necessary compute capacity without making a huge capital investment. Kelsall admits that it’s often more difficult for SMEs to access HPC technology, but he says “organizations like ours can provide a bridge between what they want and what’s available.”

Keeping data in the UK was also a sticking point for BHR. Kelsall says that a UK-based service provider is helping them meet data privacy mandates.

OCF, a small company of about 26 employees, has established a significant customer base and a solid reputation over the ten yeas its been in business. While based in the UK, OCF is well-known throughout the HPC community. They are an IBM Premier partner, and an accredited IBM Cloud Service provider. Customers find out about OCF via the IBM organization and community networking as well as through more traditional channels like marketing, trade press, and direct sales activities.

The service is charged on a per-core hour basis, and the website lists “a small annual fee of £350.” Users pay for storage above a half a TB. Dixon says the nice thing about the simple charging model is that it makes it easy to budget and control spend. The per-core charge varies depending on the level of usage, so a heavy user will get a discounted price as per economies of scale.

The revamped service is going through some final configuration and testing, but should be up and running within next week or two.

“We expect to see all sorts of workloads,” says Dixon. “Some customers will use it very regularly because they don’t have their own infrastructure and others will go to the other extreme, and use it only sparingly, and everything in between. One user was a heavy user at first and since then, they’ve only used it several times. But this uneven usage is actually good because it opens up the system for other users and the overall demand levels out.”

This brief (under 5 minute) video shares further details about the Science and Technology Facilities Council at Sci-Tech Daresbury, home of Blue Wonder, the workhorse behind the enCORE service.

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!

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…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a 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…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi 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