Industry, Academia Meet on the Grid

By By Owen Appleton, CERN

April 25, 2005

** This is the first in a short series of articles commissioned by GRIDtoday and CERN on scientific and academic Grid projects, and how they might be relevant to commercial and Industrial uses of Grid computing. The series will be accompanied by a more formal overview of academic and scientific Grid projects that will be published at a later date.


Grid computing has been the buzzword in computing circles for some time now, and the Internet is awash with pronouncements on how it will change the future of networking. Both industry and academia have invested heavily in developing Grid technology, but the commercial sector has been struggling to identify end users for its new systems. This in part reflects the wide range of activities that can be clustered under the Grid umbrella, from cycle scavenging on the SETI@home model to processing petabytes of data on distributed but dedicated machines in a “data Grid.” But even without a clear customer base, commercial development of Grids might have been generated by purely commercial factors, with companies feeling that they must be seen to be involved in a new field, even if they have little immediate idea of how they will sell it.

Commercial uncertainty strikes a sharp contrast to academia's hunger for the Grid. While some computer scientists might carry out development for its own sake, the emergence of many large-scale Grid projects across the world has been in no small part driven by need. Perhaps the clearest example of this is the international effort to build a Grid for analyzing data from CERN's next-generation particle accelerator, the LHC (Large Hadron Collider). This Grid, called the LCG (LHC Computing Grid), is vital for analyzing the predicted 15 petabytes of data the accelerator will produce annually after it is turned on in 2007. In parallel, both the United States and Europe are building large-scale infrastructures for their scientific communities, both field-specific and general e-Science Grids.

While it can be argued that cooperation between industry and academia would benefit both parties, such ventures have not always gone well, and are burdened by differences of pace, regulation and work environment. Now, it seems that the Grid might provide a more appropriate meeting point for these traditionally antipathetic hemispheres of IT development.

EGEE (Enabling Grids for E-sciencE), is a large-scale e-infrastructure project designed to provide a 24/7 Grid service for scientists under the EU's Information Society Technologies program. Interconnected with LCG, this project's infrastructure comprises academic and research institutions spread across 31 countries. However, like all EU programs, it also has an obligation to support technology transfer to industry. As a result, it has made efforts in several areas to facilitate interaction with commercial IT companies, including an Industry Forum to garner feedback on their work. Perhaps more surprisingly, one of the project partners is a commercial company.

CGG, Compagnie General de Geophyisique, is a French company providing geophysical services and products, mostly for the oil and gas industry. It joined EGEE, but, rather than becoming a sponsor, chose to become an integral part of the project, with responsibility for European Grid support, operation and management. CGG was already interested in Grid computing prior to EGEE, as its business model requires it to process large amounts of seismic data.

“Typically, a survey is around 10TB, and the dataset becomes 10 times larger when processed,” said CGG software development manager Dominique Thomas. “We also carry out several surveys in parallel, so, typically, we have around 1.5 petabytes of disk storage at any one time and several petabytes near line.”

While still some way short of the data mass the LHC will produce, this is still a considerable amount for a single company to deal with and, as Thomas explained, it is still increasing. “We need to double our computing power every year, and we are already at the limit of our computing room. We've been pioneers in cluster computing since 2000. Now we are looking at what could be the next computing technology.”

While participation in a publicly funded project such as EGEE might have many side benefits for a commercial organization — by generating a positive PR image, for instance — CGG has taken its involvement somewhat deeper. After first becoming involved in EGEE, it experimented with Grid technology on the GILDA testbed, a Grid provided for dissemination activities by Italy's INFN (an EGEE partner). In the light of positive experiences, CGG formed a virtual organization, Expanding Geosciences on Demand (EGEODE), to support both its own research activities and those of the geosciences community in general.

“The goal was to share our experience with people doing geosciences, so we decided to give universities free access to geocluster, our seismic processing solution,” said Thomas.

While this particular collaboration between industry and academia seems harmonious, it still requires special considerations not seen in traditional academic collaboration. One of the most obvious is the issue of licensing. EGEE, like most academic Grid projects, releases its software under a broadly open source license, though one designed to be industry-friendly. In contrast, EGEE makes use of GEANT, the European high-speed network infrastructure for research and education, which runs under a license that explicitly forbids its use for profit-making calculations. As a result, CGG runs only R&D-related jobs on the EGEE production service, enabling it to gather the experience of a large-scale Grid without needing to build one itself.

Running commercial data on a public network also raises several other issues, especially those of security, since CGG is a contributor to EGEE as well as a user. “We give a node to the general EGEE infrastructure — not a large one, but not a small one either,” Thomas explained, “though typically it runs EGEODE jobs.”

In order to participate in this way, CGG had to look at two issues. “First is the security of the dataset and the software. The other is to avoid people using our resources who are not allowed to. We received a warning about this from our security manager, so our node is not linked to our internal computer network at all.”

Porting existing software to the Grid is also an important issue for uptake by businesses, especially those who use rather than develop high-performance computing. This did not prove difficult for CGG, as Thomas explained. “There are two parts to our computing, one is the traditional seismic processing. This was very easy to move as it already worked in a cluster environment, and so was well adapted for running on a Grid. The other part is for research and development, and here the seismic dataset is not large, so it is not difficult to move to the Grid either.”

Such positive experiences might bode well for future adoption of Grid technology in the commercial sector, particularly for users of cluster technology who need to increase their computing resources.

CGG's experience also bodes well for future academic-industrial collaborations. “For us, it is a very interesting experience,” said Thomas. “We discovered new people with a lot of expertise, but also new requirements. These requirements were very similar to ours, such as the use of big data sets.”

This easy interaction is perhaps surprising, but Thomas attributes it to the kind of academics CGG was working with. “EGEE is a production Grid and that makes a difference. We have always worked with academics, but this is the first time we've worked with computer scientists rather than geoscientists. Working with more theoretical researchers can be difficult, but working on research into a production Grid has been very easy.”

Given its unique experience, CGG is also in a good position to comment on the future of the Grid for similar companies. Thomas seems generally enthusiastic, at least about the future for CGG. “We will continue to experiment with the Grid, and we want to continue with EGEE. As we are a technical company, we need people around us with a very good level of technology. With EGEODE, we will continue to support the virtual organization. EGEODE is for research and education, and we will continue to support the geosciences that way. In parallel, we will continue to explore the Grid architecture from a commercial point of view. We are also a service company for our clients, and we will help them use Grid technology as well.”

On the other hand, Thomas also identifies a number of barriers to commercial use of the Grid. “There are technical and economic issues. Technically, there is the issue of network bandwidth, and there is no network for industry like GEANT is for academia. A network with good bandwidth is just not affordable. On the other side, there is no economics for the Grid, no usage model, so we don't know how much it costs; there is no business model around the Grid at all.”

Thomas also raised the thorny issue of Grid standards, remarking on the need for more middleware support, and the difficulty of getting such support for current open source software. While applauding GGF's efforts in that area, he didn't see them as a full solution.

“That is where standards start, but we need the large manufacturers, like IBM or HP, to really invest in this technology. We need standards, and we can't afford to change our software every two or three years as they change. I think these standards need to come from industry, so we need to wait for [large IT companies], to say 'we fully support this.'”

While Thomas and CGG clearly have some outstanding concerns, they remain enthusiastic, as demonstrated by their active and ongoing involvement with EGEE. Whatever issues must be dealt with in the future, Thomas's attitude to the Grid in general, and to the collaboration program, seems both simple and positive: “We feel that the best way to understand this new technology is to participate in its evolution.”

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