Grid Pioneer Ian Foster Discusses the Future of Science in the Cloud

By Rich Wellner

February 24, 2011

In this interview, Rich Wellner checks in with computer science pioneer, Ian Foster. Often called “the father of the grid” Foster serves as Director of the Computation Institute, a joint institute of the University of Chicago and Argonne National Laboratory, a professor of Computer Science at the University of Chicago and also a key member of the Open Grid Forum and the Globus Alliance, the community guiding Globus toolkit development.

Wellner and Foster discuss the next logical steps beyond grid now that resources once available only for “big science” projects are available to a far larger user base. Foster also details new developments among the Globus team’s efforts, particularly with projects like Globus Online, and describes how it is being used to open further avenues for scientists and researchers.

RW: What’s new with you, Ian?

IF: I’m still at Argonne’s and University of Chicago’s Computation Institute, and my research continues to focus on accelerating discovery in a networked world. So you might say not much! But in fact a lot is new. Indeed, I believe we face unprecedented opportunities for transformational change in how research is done in the coming years. I’m working hard to seize these opportunities.

RW: “Transformational” sounds intriguing! Tell me more.

IF: The driving forces are the new capabilities with which we’re all familiar: massive data, exponentially faster computers, and deep interdisciplinary collaboration. The opportunity—and challenge—is to make these capabilities accessible not just to a few “big science” projects but to every researcher everywhere. It’s amazing but true that an entrepreneur today can run a business from a coffee shop, outsourcing many of the complexities of operating that business to third parties. My dream is that one day soon, we’ll see researchers running ambitious research programs from that same coffee shop.

RW: So this is a step beyond grid and into something with important differences.

IF: I would say it is the next logical step beyond grid. It’s been over a decade since Carl Kesselman and I posited a world in which computing is delivered on demand as a service, and virtual organizations link scientists and resources worldwide. These ideas are now a reality. For example, the Large Hadron Collider (LHC) Computing Grid distributes hundreds of terabytes to hundreds of analysis sites worldwide for the High Energy Physics community. The Earth System Grid serves global climate change data to 25,000 users. Commercial cloud providers deliver on-demand cycles and storage at scales unachievable in academic settings. The US InCommon trust federation enables more than five million people to use local credentials to access remote resources. It’s been astonishing to see these developments occur so quickly, and at this scale.

However, while big science projects can afford to create and operate dedicated grid infrastructures, smaller teams can’t. Their IT staff is maybe a grad student or a technician. Yet to be competitive, they somehow need to collect, manage, analyze, etc., tens of terabytes of data—just like the big guys.

The answer is not to give them more software because they don’t have the time and expertise to install and operate it. We need to take the IT required for research and deliver that IT in a convenient and cost-effective manner, just as Google delivers email and Salesforce.com delivers customer relationship management. In many cases, commercial clouds may offer a cost-effective source of computing and storage. But we still need to provide what we might call the “business logic” or “workflow” of science.

RW: Where does Globus fit in this new world?

IF: The Globus team is jumping in with both feet. We’ve started by focusing on the task of moving large quantities of data from one place to another, packaging this capability as a service called Globus Online (http://www.globusonline.org). Using Web browser, command line, or REST interfaces, you can ask Globus Online to move or synchronize files and directories—much as you might ask Amazon to ship a book. Globus Online then handles the numerous tedious details of making that transfer happen reliably and efficiently. NERSC has already listed Globus Online as one of their top preferred file transfer systems, and users are rapidly adopting it.

Globus Online is our first foray into what you might call a computational science cloud: hosted services that let you “use the grid” without installing software. Meanwhile, we continue to enhance the Globus Toolkit used by so many people worldwide to “build the grid”—deploying and operating infrastructures and applications to support data-intensive, computation-intensive, and collaboration-intensive science. Use of Globus Toolkit continues to grow, so that work is important too.

RW: Where are you seeing the quickest uptake?

IF: I joke that its target audience is anyone whose data is in the wrong place. But we’re particularly targeting users of high-performance computing facilities, who routinely need to move data between centers and their local machines, and between different centers. For example, an Indiana University physics researcher recently used it to move 730 GB data from Kraken (at Oak Ridge) to Longhorn (at TACC), in just 1.5 hours. Just last week, we moved 100,000 files totaling 98 TB from Argonne to NERSC and Oak Ridge in a couple of days. This scale of data movement is routine in say high energy physics, but for ordinary users to do it easily without installing any software is unprecedented.

We’re also starting to see people use Globus Online in different modes. Most early users have been ad hoc: they sign on to the service whenever they want to move some data and basically treat each use as a one-off “transaction.” As they get more comfortable with it, we see them integrating Globus Online commands into their scripts so that file transfer is handled automatically as part of other scientific workflows. And we have a REST API available that’s useful to folks building and operating science gateways, because they can easily integrate a robust file transfer mechanism into the standard set of functions they offer their end-users.

RW: GridFTP solved a good chunk of the ‘bits on the wire’ problem a while back.  Tell us more about why this new approach is more than just a retreading of a mundane task.

IF: Data movement is indeed a mundane task. But that makes it perfect for delivery via SaaS. Many people have data to move, but who wants to become a data movement specialist? Yet moving Terabytes reliably and efficiently can be surprisingly complicated. One needs to discover endpoints, determine available protocols, negotiate firewalls, configure software, manage space, negotiate authentication, configure protocols, detect and respond to failures, determine expected and actual performance, identify, diagnose and correct network misconfigurations, integrate with file systems, and a host of other things. We have a lot of experience with these issues.  Automating them makes researchers’ lives much, much easier.

As an example of how Globus Online can improve computing processes, one early user used Globus Online to move data from a single source to 11 destinations across the US. All completed successfully, but our monitoring showed that three sites had high retry rates. (Retrying failed transfers is one way that Globus Online achieves reliability.) Further investigation revealed a misconfigured firewall at one site, and old GridFTP servers at two others. These were problems that had gone unnoticed for months. We got them fixed within days.

RW: Why would someone need Globus Online? Why not just use commercial cloud offerings such as Google, Amazon Web Services, Dropbox, etc.?

IF: I use Dropbox and Yousendit frequently, but neither helps me move terabytes at gigabit/sec speeds. I love Amazon Web Services, and indeed we host Globus Online on Amazon. But again, I still need services that can manage data movement for me. These different elements are complementary, not competing.

RW: I gather that you’re planning to do a lot more than just move data

IF: Indeed! We’re looking carefully at what people find most tedious in science. For example, almost every researcher we work with has a need to share data and results with collaborators, so an obvious next step is to give those researchers a straightforward way to do that. Believe it or not, sharing today often means copying thousands of files on a hard disk and shipping it via FedEx. Making this type of exchange more direct, intuitive and manageable will be of value to a lot of people.

RW: You have the GlobusWORLD conference coming in April. What can you tell us about it?

IF: GlobusWORLD (http://www.globusworld.org) will be held on April 11-12, with tutorials on the 13th, at Argonne National Laboratory near Chicago. It is co-located with the Cloud Computing and Applications (CCA) conference (http://cca11.org) on April 13.

GlobusWORLD is an excellent opportunity to learn about the latest Globus technologies and applications, meet other Globus users and developers, and exchange notes about data-intensive, computational, and collaborative science.

We expect to see the usual cross-section of the Globus community, including researchers using Globus-based systems in their work, developers using Globus software to create their research systems, infrastructure providers operating Globus-based systems, and Globus developers.

GlobusWORLD provides presentations from community members, ample time to interact (including a fun social event on the evening of the 11th), and tutorials on Globus Toolkit and Globus Online.

RW: What new capabilities will you be demonstrating at GlobusWORLD?

IF: We will demonstrate Globus Toolkit version 5.2, which introduces oft-requested native packaging for components such as GridFTP and GRAM. Linux users will get RPMs and dpkg that they can easily install from repositories using yum and apt.

We will also introduce a new Globus Online feature called Globus Connect. Globus Connect solves the “last mile” problem in file transfer. While Globus GridFTP is available at most major research computing facilities, your files often need to get to or from other places: a laptop, lab server, department cluster, or scientific instrument.

These computers probably do not have GridFTP installed, may be behind a firewall or NAT, and may not provide administrative privileges. Globus Connect, available for Mac, Windows, and many Linux flavors, solves this problem. It only requires outbound connections so that it works behind most firewalls and NATs, can be run either temporarily or on a long-term basis, and does not require administrative privileges or knowledge. In fact, I have started using it to back up my laptop!

We will also be discussing and demonstrating prototypes of future Globus Online capabilities we expect to introduce in the coming year, and soliciting feedback to help guide our future work.

RW: Earlier you mentioned that Globus Toolkit continues to grow.  What are some examples of that?

IF: The Globus community has always been highly international. Globus Toolkit security, file transfer, and job submission are used in many national and international cyberinfrastructures, including TeraGrid and Open Science Grid in the US; PRACE, D-Grid, the UK National Grid Service, and others in Europe; GARUDA in India; BestGrid in New Zealand; and many more. It’s also used in campus and regional infrastructures, such as TIGRE in Texas and the UCLA grid. We’re also seeing growing use within the biomedical community, within such infrastructures as the Biomedical Informatics Research Network (BIRN), cancer Biomedical Informatics Grid (caBIG), and Cardiovascular Research Grid (CVRG).

As I mentioned earlier, a common use case for Globus Toolkit is that scientific communities use its security, file transfer and job submission capabilities to build custom distributed data management and analysis solutions. That is what the LHC Computing Grid, Earth System Grid, and LIGO Scientific Collaboratory have done, for example. Another common use case involved the development of Web-based portals, such as the various TeraGrid gateways, that allow a many users to access HPC and data facilities provided by these cyberinfrastructure providers.

One recent exciting development is the funding by the European Union of the Initiative for Globus in Europe (IGE: www.ige-project.eu).

RW: What is your current role within all this?

IF: I’ve been Director of the Computation Institute for four years now. The Computation Institute is a joint unit of the University of Chicago and Argonne National Laboratory, with a mandate to pursue challenging problems that require the use of advanced computation. I must say that it’s tremendous fun due to the incredibly smart and talented people that I get to work with. My position as Director involves broader responsibilities and has led to new projects, such as the Center for Robust Decision making on Climate and Energy Policy. Of course, the Computation Institute is also a wonderful place to drive the new ideas that we’ve been discussing here. I’ve been fortunate to attract some very talented people to help me run the Institute, such as Steve Tuecke and Julie Wulf-Knoezer, so I am still able to spend time on research.

***

About the Author

Richard Wellner, Jr. is an independent consultant and President of Object Environments, a firm specializing in cloud computing and distributed applications. He has worked in and led professional services organizations for 20+ years with customers in the defense, finance, telecommunications, government research, manufacturing, semiconductor, pharmaceutical and automotive sectors.

Until 2010 Wellner was the Chief Scientist at Univa and responsible for the architecture and design of their industry leading product focused on enabling managed service providers in efforts to establish cloud computing offerings.

Prior to Univa Wellner co-founded, with partner Pawel Plaszczak, Gridwise Technologies, a company based in Krakow, Poland that specializes in grid technology implementations.

His earlier work has spanned guiding customers from the emerging client/server technology landscape in the late 80’s, through object oriented technology and project management into distributed computing and grid computing with Globus.

Wellner is the co-author of Grid Computing: A Savvy Manager’s Guide, published by Elsevier, founding editor of the popular Grid Guru’s blog and a contributing editor for GridToday.

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!

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that have occurred about once a decade. With this in mind, the ISC Read more…

2024 Winter Classic: Texas Two Step

April 18, 2024

Texas Tech University. Their middle name is ‘tech’, so it’s no surprise that they’ve been fielding not one, but two teams in the last three Winter Classic cluster competitions. Their teams, dubbed Matador and Red Read more…

2024 Winter Classic: The Return of Team Fayetteville

April 18, 2024

Hailing from Fayetteville, NC, Fayetteville State University stayed under the radar in their first Winter Classic competition in 2022. Solid students for sure, but not a lot of HPC experience. All good. They didn’t Read more…

Software Specialist Horizon Quantum to Build First-of-a-Kind Hardware Testbed

April 18, 2024

Horizon Quantum Computing, a Singapore-based quantum software start-up, announced today it would build its own testbed of quantum computers, starting with use of Rigetti’s Novera 9-qubit QPU. The approach by a quantum Read more…

2024 Winter Classic: Meet Team Morehouse

April 17, 2024

Morehouse College? The university is well-known for their long list of illustrious graduates, the rigor of their academics, and the quality of the instruction. They were one of the first schools to sign up for the Winter Read more…

MLCommons Launches New AI Safety Benchmark Initiative

April 16, 2024

MLCommons, organizer of the popular MLPerf benchmarking exercises (training and inference), is starting a new effort to benchmark AI Safety, one of the most pressing needs and hurdles to widespread AI adoption. The sudde Read more…

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that ha Read more…

Software Specialist Horizon Quantum to Build First-of-a-Kind Hardware Testbed

April 18, 2024

Horizon Quantum Computing, a Singapore-based quantum software start-up, announced today it would build its own testbed of quantum computers, starting with use o Read more…

MLCommons Launches New AI Safety Benchmark Initiative

April 16, 2024

MLCommons, organizer of the popular MLPerf benchmarking exercises (training and inference), is starting a new effort to benchmark AI Safety, one of the most pre Read more…

Exciting Updates From Stanford HAI’s Seventh Annual AI Index Report

April 15, 2024

As the AI revolution marches on, it is vital to continually reassess how this technology is reshaping our world. To that end, researchers at Stanford’s Instit Read more…

Intel’s Vision Advantage: Chips Are Available Off-the-Shelf

April 11, 2024

The chip market is facing a crisis: chip development is now concentrated in the hands of the few. A confluence of events this week reminded us how few chips Read more…

The VC View: Quantonation’s Deep Dive into Funding Quantum Start-ups

April 11, 2024

Yesterday Quantonation — which promotes itself as a one-of-a-kind venture capital (VC) company specializing in quantum science and deep physics  — announce Read more…

Nvidia’s GTC Is the New Intel IDF

April 9, 2024

After many years, Nvidia's GPU Technology Conference (GTC) was back in person and has become the conference for those who care about semiconductors and AI. I Read more…

Google Announces Homegrown ARM-based CPUs 

April 9, 2024

Google sprang a surprise at the ongoing Google Next Cloud conference by introducing its own ARM-based CPU called Axion, which will be offered to customers in it 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…

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…

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…

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…

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…

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…

Leading Solution Providers

Contributors

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…

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…

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…

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…

Eyes on the Quantum Prize – D-Wave Says its Time is Now

January 30, 2024

Early quantum computing pioneer D-Wave again asserted – that at least for D-Wave – the commercial quantum era has begun. Speaking at its first in-person Ana Read more…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to Read more…

The GenAI Datacenter Squeeze Is Here

February 1, 2024

The immediate effect of the GenAI GPU Squeeze was to reduce availability, either direct purchase or cloud access, increase cost, and push demand through the roof. A secondary issue has been developing over the last several years. Even though your organization secured several racks... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire