Gelato Brings ‘Linux on Itanium’ Message to GridAsia

By By Derrick Harris, Editor

May 2, 2005

GridAsia 2005 (which is hosting a handful of conferences, meetings, etc.) is taking place this week in Biopolis, Singapore, and one group that will have a fairly large presence throughout the event is the Gelato Federation. GRIDtoday editor Derrick Harris speaks with Gelato director Mark K. Smith about the organization in general, what Gelato and its members are up to at GridAsia, why Asia is such a hotbed for Grid, and why Linux on Itanium is the way to go.



GRIDtoday:
Can you give a little background on Gelato and, specifically, its Grid Focus Group?

MARK K. SMITH: The Gelato Federation is a world-wide Linux-Itanium user community. Gelato was co-founded by HP and seven of the world's leading research institutions in January 2002, and today has grown to 49 members and three sponsors. In addition to our 49 member institutions, we have a vibrant community of individuals who participate on Gelato-related projects and in general mailing list discussions. Our member institutions are leading supercomputer centers, government labs, research centers and universities worldwide, and are committed to the Linux-Itanium platform for production and research (details at www.gelato.org/participants/members.php).

Our mission as the organizing body of this community is to bring together those developing and using Linux on Itanium for the purpose of fostering Itanium-specific research, focus groups and collaborative discussions. An open exchange of ideas and solutions is nurtured through diverse lines of communication, including our portal (www.gelato.org), several interest-specific mailing lists and regular meetings. Finally, Gelato facilitates the development and dissemination of Linux Itanium open-source solutions, including a complete and robust tool chain.

One area of particular interest to many of our members is the Grid. Almost 60 percent of our members are contributing to the development of Grid-related software. Collectively, our members ranked developing Grid software and tools second in importance out of 18 areas. In addition, almost half have indicated a need for better Grid-related software and tools.

Since so many of our members have interest in, and are working on, Grid software and tools, we provide a forum for them to share their research and experiences in what we call the Gelato Grid Focus Group. Our vision for this group is not to re-invent what other groups (such as the Global Grid Forum) are doing, but to focus on maximizing the Itanium platform's contribution to Grid computing. We want to build on previous Grid work and focus on maximizing the performance of Itanium-specific applications.

As our members engage in more and more Grid-related work, they are sharing experiences with their Itanium systems in Grid environments. Issues such as configuration, scheduling, job classification, benchmark applications, authentication and data movement are key areas of discussion. The bottom line is the Gelato Grid Focus Group wants to see real-world applications running on a Grid which includes Itanium systems. Applications that are well-suited for Itanium include bioinformatics, computational fluid dynamics, climate modeling, gene modeling, drug design and a host of visualization applications.

This focus group is exploring setting up a mini Itanium test Grid to verify and optimize Itanium-specific Grid tools and software. The ultimate goal is to get those real-world applications benchmarked and running so the community at large can benefit from the computing power of Itanium systems world-wide.

Gt: Why the focus on Itanium on Linux?

SMITH: Itanium is offered in a refreshing, different way than other proprietary 64-bit processors on the market. HP, SGI, Dell, NEC, Fujitsu, Hitachi, Bull and Unisys all sell systems with Itanium processors. You don't see HP selling machines with MIPS chips or SGI selling machines with PA-RISC processors, but you do see HP and SGI selling systems with Itanium. It's a new day.

The academic, government and industrial research community is increasingly turning to commodity computing (i.e., commodity operating systems running on commodity hardware) to develop, execute and share work. While IA-32 Linux has been the commodity research platform of choice, Linux on Itanium is coming on very strong. The speed by which this transition occurs will greatly depend on the availability of software solutions that exploit the architectural advantages of Itanium and further advance the capabilities of Linux — from the node, to the cluster, to the Grid.

The combination of the open-source Linux operating system and the vendor-neutral offering of the Itanium processors is a powerful combination for encouraging cross company and community collaboration.

Gelato specifically takes advantage of an open-source operating system and a platform based on a non-proprietary processor to achieve its mission: to advance Linux on Itanium and create a community around the platform. From that community will flow collaboration and mutually beneficial projects that will further the infrastructure of the platform. As the infrastructure further matures, more migration to the platform will occur.

Gt: What kind of activities will Gelato be involved with at the upcoming GridAsia event?

SMITH: We're very thrilled to be exhibiting at this inaugural GridAsia event and having the opportunity to inform attendees about Gelato's mission to advance Linux on Itanium.

In addition, on the afternoon of Wednesday, May 4, we will host a Gelato Birds of a Feather (BoF) session to discuss Gelato's Grid efforts. We are expecting 50 Gelato member representatives to attend, and we'll have presentations from three noted Gelato member and sponsor Grid experts. Professor Hai Jin from the Huazhong University of Science & Technology in China will speak about the ChinaGrid Supporting Platform (CGSP); Chih-Chiang Chang from the Academia Sinica Computing Center in Taiwan will present his institution's LHC Computing Grid (LCG) and Enabling Grids for E-sciencE (EGEE) middleware and operations; and P. N. Anantharaman of HP India will talk about RSIP to enable MPICH-G2 applications over the Grid.

Gt: Can you speak a little about the work Gelato members are doing in the Grid field, specifically with Asian projects like ChinaGrid?

SMITH: I'd like to start off talking about the National Grid Office (NGO) in Singapore who is responsible for launching GridAsia 2005. This is a great opportunity for Grid computing researchers and users to come together, and NGO has done a fantastic job organizing everything. As part of their Gelato-related activities, NGO provides a digital media Grid testbed. They also participate in an operational Grid cyberinfrastructure connecting the National Grid Pilot Platform (NGPP) in Singapore and Gelato member CERN (the European Organization for Nuclear Research) in Switzerland.

As mentioned earlier, the Huazhong University of Science & Technology is working on CGSP middleware developed for the construction and evolution of the ChinaGrid. CGSP aims to integrate all sorts of heterogeneous resources distributed over the education and research network in China, and to provide transparent high performance, reliable, secure and convenient Grid services for scientific researchers and engineers. In addition to supplying the portal to ChinaGrid, CGSP offers a whole set of tools for developing and deploying various Grid applications.

CERN has created the Large Hadron Collider's Computing Grid (LCG). LCG is an operational Grid with 90 sites from Europe, the United States and Asia-Pacific participating. CERN is also part of the Enabling Grids for E-sciencE (EGEE) Project. The Academia Sinica Computing Center is collaborating with CERN on the development and deployment works of LCG/EGEE and is acting as the LCG Regional Center in Asia.

Zhejiang University in China is developing the Dart-InfoGrid Tool Suite, which focuses on building an IPF-based scalable information Grid enabling large-scale data sharing and massively parallel process coordination among loosely coupled clusters. They also have a project called MASSIVE, which is a visualization and simulation environment for multidisciplinary applications that supports local distributed computing and Grid computing across the Internet.

Also in China is Fudan University who is working on a Grid platform on an Itanium cluster and has several completed and ongoing projects on Grid algorithms, middleware, and tools. In Singapore, the Institute of High Performance Computing is working on Grid-based utilities for doing remote scientific visualization.

In other parts of the world, there is the University of Copenhagen Distributed Systems Lab, which is part of the Danish Center for Grid Computing. The SPACI Consortium plans to implement a computational Grid interconnecting research centers in southern Italy. And the Universidade Federal da Campina Grande is collaborating with HP and other Brazilian research institutions on the OurGrid Project to research and develop solutions of usage and management of computational Grids.

Gt: What does Gelato hope to gain from its presence at GridAsia?

SMITH: With any show or conference we attend, we hope to raise awareness about the Gelato community and make new contacts for membership and sponsorship of the organization. In addition, we are often introduced to other community groups with which we can partner.

GridAsia is unique because it is being hosted and organized by several Gelato Federation members: National Grid Office, Bioinformatics Institute, and Institute of High Performance Computing. In addition, many Gelato members in Southeast Asia and China will be attending the conference. Traveling to Singapore will give us a chance to visit and meet together with these member institutions at the Gelato BoF session and Gelato member dinner and specifically discuss Grid topics of interest.

Gt: Why is Asia such a big deal in the Grid community?

SMITH: Asia, and especially China, is taking a strong role in creating Grid tools and applications. It is becoming difficult to house in one location all the computational power and data storage necessary for complex problems. We see more Grid activity in Southeast Asia, China and South America out of necessity. They historically have not had massive single-site supercomputer installations to handle the increasing computational complexity of today's data sets. The day is quickly approaching when Europe and the U.S. will have to rely heavily on Grid computing to solve the next generation computational problems, as well.

Gt: The Gelato Coconut Project seems really interesting. Please explain it to our readers.

SMITH: The Gelato Coconut Project is a mini-Grid, which will allow Gelato members to remotely test upcoming Itanium processor releases via computing facilities housed at Gelato Central Operations headquartered at the University of Illinois. The Gelato Coconut Project is a software support system of Grid tools to setup these computing facilities and allow globally dispersed members access these resources.

The Coconut Project has many goals. One is offering a simple interface with easy access to these computing resources. Another is diminishing the registration footprint while providing a high level of security as Gelato Coconut administrators do not personally know every person involved with our 49 member institutions. Gelato hopes to gain Grid operational experience on this small secure Grid. It will also give us flexibility to provide our members with prerelease and virtual hardware for review and testing.

Gt: Is there anything else you'd like to add?

SMITH: We are very excited about the future of Itanium and the Linux-Itanium community. As you know, Itanium is making broad in-roads into the HPC market. On the last top 500 supercomputer list, there were 83 Itanium systems, up 160 percent from the year before. The No. 2 system on the list is the SGI Altix-based Columbia supercomputer at Gelato member NASA Ames.

There are new announcements every few weeks of Itanium installations in the enterprise space. From our vantage point, Itanium is extremely well-positioned to further penetrate both the HPC and enterprise space in 2005. Later this year, the dual-core Itanium chip, Montecito, will be released. Intel is also setting the stage for the release of their chipset that will support both Xeon and Itanium. At that point, Itanium will out perform Xeon by a factor of two for the same cost.

The Gelato community will continue to grow and expand offering a greater support network and will continue to build and further mature the infrastructure for the Linux-Itanium platform.

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