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 industy updates delivered to you every week!

TACC Helps ROSIE Bioscience Gateway Expand its Impact

April 26, 2017

Biomolecule structure prediction has long been challenging not least because the relevant software and workflows often require high-end HPC systems that many bioscience researchers lack easy access to. Read more…

By John Russell

Messina Update: The US Path to Exascale in 16 Slides

April 26, 2017

Paul Messina, director of the U.S. Exascale Computing Project, provided a wide-ranging review of ECP’s evolving plans last week at the HPC User Forum. Read more…

By John Russell

IBM, Nvidia, Stone Ridge Claim Gas & Oil Simulation Record

April 25, 2017

IBM, Nvidia, and Stone Ridge Technology today reported setting the performance record for a “billion cell” oil and gas reservoir simulation. Read more…

By John Russell

ASC17 Makes Splash at Wuxi Supercomputing Center

April 24, 2017

A record-breaking twenty student teams plus scores of company representatives, media professionals, staff and student volunteers transformed a formerly empty hall inside the Wuxi Supercomputing Center into a bustling hub of HPC activity, kicking off day one of 2017 Asia Student Supercomputer Challenge (ASC17). Read more…

By Tiffany Trader

HPE Extreme Performance Solutions

Remote Visualization Optimizing Life Sciences Operations and Care Delivery

As patients continually demand a better quality of care and increasingly complex workloads challenge healthcare organizations to innovate, investing in the right technologies is key to ensuring growth and success. Read more…

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

April 24, 2017

CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp of a new generation of chips designed specifically for deep learning workloads. Read more…

By Alex Woodie

Musk’s Latest Startup Eyes Brain-Computer Links

April 21, 2017

Elon Musk, the auto and space entrepreneur and severe critic of artificial intelligence, is forming a new venture that reportedly will seek to develop an interface between the human brain and computers. Read more…

By George Leopold

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Engine (GCE) job. Sutherland ran the massive mathematics workload on 220,000 GCE cores using preemptible virtual machine instances. Read more…

By Tiffany Trader

NERSC Cori Shows the World How Many-Cores for the Masses Works

April 21, 2017

As its mission, the high performance computing center for the U.S. Department of Energy Office of Science, NERSC (the National Energy Research Supercomputer Center), supports a broad spectrum of forefront scientific research across diverse areas that includes climate, material science, chemistry, fusion energy, high-energy physics and many others. Read more…

By Rob Farber

Messina Update: The US Path to Exascale in 16 Slides

April 26, 2017

Paul Messina, director of the U.S. Exascale Computing Project, provided a wide-ranging review of ECP’s evolving plans last week at the HPC User Forum. Read more…

By John Russell

ASC17 Makes Splash at Wuxi Supercomputing Center

April 24, 2017

A record-breaking twenty student teams plus scores of company representatives, media professionals, staff and student volunteers transformed a formerly empty hall inside the Wuxi Supercomputing Center into a bustling hub of HPC activity, kicking off day one of 2017 Asia Student Supercomputer Challenge (ASC17). Read more…

By Tiffany Trader

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

April 24, 2017

CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp of a new generation of chips designed specifically for deep learning workloads. Read more…

By Alex Woodie

NERSC Cori Shows the World How Many-Cores for the Masses Works

April 21, 2017

As its mission, the high performance computing center for the U.S. Department of Energy Office of Science, NERSC (the National Energy Research Supercomputer Center), supports a broad spectrum of forefront scientific research across diverse areas that includes climate, material science, chemistry, fusion energy, high-energy physics and many others. Read more…

By Rob Farber

Hyperion (IDC) Paints a Bullish Picture of HPC Future

April 20, 2017

Hyperion Research – formerly IDC’s HPC group – yesterday painted a fascinating and complicated portrait of the HPC community’s health and prospects at the HPC User Forum held in Albuquerque, NM. HPC sales are up and growing ($22 billion, all HPC segments, 2016). Read more…

By John Russell

Knights Landing Processor with Omni-Path Makes Cloud Debut

April 18, 2017

HPC cloud specialist Rescale is partnering with Intel and HPC resource provider R Systems to offer first-ever cloud access to Xeon Phi "Knights Landing" processors. The infrastructure is based on the 68-core Intel Knights Landing processor with integrated Omni-Path fabric (the 7250F Xeon Phi). Read more…

By Tiffany Trader

CERN openlab Explores New CPU/FPGA Processing Solutions

April 14, 2017

Through a CERN openlab project known as the ‘High-Throughput Computing Collaboration,’ researchers are investigating the use of various Intel technologies in data filtering and data acquisition systems. Read more…

By Linda Barney

DOE Supercomputer Achieves Record 45-Qubit Quantum Simulation

April 13, 2017

In order to simulate larger and larger quantum systems and usher in an age of “quantum supremacy,” researchers are stretching the limits of today’s most advanced supercomputers. Read more…

By Tiffany Trader

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference phase of neural networks (NN). Read more…

By Tiffany Trader

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Read more…

By John Russell

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the campaign. Read more…

By John Russell

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its assets. Read more…

By Tiffany Trader

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

For IBM/OpenPOWER: Success in 2017 = (Volume) Sales

January 11, 2017

To a large degree IBM and the OpenPOWER Foundation have done what they said they would – assembling a substantial and growing ecosystem and bringing Power-based products to market, all in about three years. Read more…

By John Russell

TSUBAME3.0 Points to Future HPE Pascal-NVLink-OPA Server

February 17, 2017

Since our initial coverage of the TSUBAME3.0 supercomputer yesterday, more details have come to light on this innovative project. Of particular interest is a new board design for NVLink-equipped Pascal P100 GPUs that will create another entrant to the space currently occupied by Nvidia's DGX-1 system, IBM's "Minsky" platform and the Supermicro SuperServer (1028GQ-TXR). Read more…

By Tiffany Trader

Leading Solution Providers

Tokyo Tech’s TSUBAME3.0 Will Be First HPE-SGI Super

February 16, 2017

In a press event Friday afternoon local time in Japan, Tokyo Institute of Technology (Tokyo Tech) announced its plans for the TSUBAME3.0 supercomputer, which will be Japan’s “fastest AI supercomputer,” Read more…

By Tiffany Trader

Is Liquid Cooling Ready to Go Mainstream?

February 13, 2017

Lost in the frenzy of SC16 was a substantial rise in the number of vendors showing server oriented liquid cooling technologies. Three decades ago liquid cooling was pretty much the exclusive realm of the Cray-2 and IBM mainframe class products. That’s changing. We are now seeing an emergence of x86 class server products with exotic plumbing technology ranging from Direct-to-Chip to servers and storage completely immersed in a dielectric fluid. Read more…

By Steve Campbell

IBM Wants to be “Red Hat” of Deep Learning

January 26, 2017

IBM today announced the addition of TensorFlow and Chainer deep learning frameworks to its PowerAI suite of deep learning tools, which already includes popular offerings such as Caffe, Theano, and Torch. Read more…

By John Russell

Facebook Open Sources Caffe2; Nvidia, Intel Rush to Optimize

April 18, 2017

From its F8 developer conference in San Jose, Calif., today, Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. Caffe2 is the successor to Caffe, the deep learning framework developed by Berkeley AI Research and community contributors. Read more…

By Tiffany Trader

BioTeam’s Berman Charts 2017 HPC Trends in Life Sciences

January 4, 2017

Twenty years ago high performance computing was nearly absent from life sciences. Today it’s used throughout life sciences and biomedical research. Genomics and the data deluge from modern lab instruments are the main drivers, but so is the longer-term desire to perform predictive simulation in support of Precision Medicine (PM). There’s even a specialized life sciences supercomputer, ‘Anton’ from D.E. Shaw Research, and the Pittsburgh Supercomputing Center is standing up its second Anton 2 and actively soliciting project proposals. There’s a lot going on. Read more…

By John Russell

HPC Startup Advances Auto-Parallelization’s Promise

January 23, 2017

The shift from single core to multicore hardware has made finding parallelism in codes more important than ever, but that hasn’t made the task of parallel programming any easier. Read more…

By Tiffany Trader

HPC Technique Propels Deep Learning at Scale

February 21, 2017

Researchers from Baidu’s Silicon Valley AI Lab (SVAIL) have adapted a well-known HPC communication technique to boost the speed and scale of their neural network training and now they are sharing their implementation with the larger deep learning community. Read more…

By Tiffany Trader

IDG to Be Bought by Chinese Investors; IDC to Spin Out HPC Group

January 19, 2017

US-based publishing and investment firm International Data Group, Inc. (IDG) will be acquired by a pair of Chinese investors, China Oceanwide Holdings Group Co., Ltd. Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This