BIGGER BETTER FASTER: HERE COMES INTERNET2

September 1, 2000

SCIENCE & ENGINEERING NEWS

San Diego, CA — Remember 8-track? Richard M. Stapleton reports that in a few years, that’s how we’ll recall today’s Internet. Internet2, bigger, better, faster – and for now, very exclusive – is just over the virtual horizon, transmitting prodigious packages of data in real-time with little or no degradation. And while researchers are putting Internet2 to the test, theorists are already visualizing Internet3.

It seems that history is repeating itself. The Internet we use today was originally created so government defense agencies and their research university partners could readily share information. But with the advent of commercial and individual use, the Internet has doubled in size and traffic has increased fourfold annually since 1988. Like any aging super-highway, traffic slowed, and the Web’s utility to the research community was compromised. It was time to reinvent the Net.

The challenge was twofold: Build a better Web, and design applications that could fully exploit it. The university-led Internet2 consortium, which now includes nearly 180 campuses, and the federally led Next Generation Internet Initiative, joined by key commercial partners, began work in 1998. In a sense, the old team has come back together. “We are recreating the same kind of partnerships and environment that gave us the Web we use today,” says Internet2 President and Chief Executive Douglas Van Houweling.

Capacity. Capacity. Capacity. It all starts with capacity. NGI’s goal was to create network test-beds that would be 100 to 1,000 times faster than today’s Internet. What does that mean? Well, the Encyclopaedia Britannica DVD 2000 Edition contains 4.5 gigabytes of data. If you connect from home at 56 kilobits per second, it would take you nearly eight days to download EB. If you’re at a research university, tied to today’s Internet, your download time could be just under 14 minutes. On NGI’s 100X test-bed, you’re looking at about 1 minute download time, and on a 1000X Web, the full EB can be yours in just 15 seconds.

From vision to reality took less than two years. Through a cooperative agreement with the National Science Foundation, WorldCom linked several dozen universities to a 100X test-bed in 1998 and by the end of 1999, vBNS, its very high-performance backbone network service, was in full operation, linking nearly 200 campuses. Meanwhile, Defense’s Advanced Research Project Agency has successfully fielded an all-optical 1000X test-bed linking 20 sites on the two coasts.

What’s being transmitted? The applications being tested are as mind-popping as the Web that’s carrying them: Fourteen thousand feet above the beaches of Hawaii, 11 international astronomical observatories atop Mauna Kea are tied to the Net. Via the new Web, an astronomer in Amsterdam can remotely manipulate a telescope, study a distant nebula, and then participate in an international videoconference to discuss his or her findings.

“This advances the level of scientific inquiry beyond what is possible on-site alone,” says David Lassner, director of information technology at the University of Hawaii. And benefits go far beyond convenience; astronomers no longer must work in the oxygen-poor atmosphere at the observatories’ high altitude. Future plans call for Webcasting the deep-sky pictures so anyone can have a real-time look.

Put on a pair of special glasses and enter “The Cave” at the University of Illinois at Chicago’s Electronic Visualization Laboratory. 3-D images of a table pop out at you. A computer tracks your movement, letting you walk around the table, viewing it from all sides. You can even get on your knees and peer under it. Auto designers already use caves to study new car designs. Unlike the old clay model, design changes can be as simple as a few mouse clicks. The next Internet will tie caves together, letting designers in Germany, for instance, critique a sports car being displayed in Detroit.

3-D imaging is being used at the San Diego Supercomputer Center to “molecule scenes,” where 3-D images can be manipulated, made interactive and shared on the Web via a collaboration server.

The University of Pennsylvania is exploring virtual microscopy, linking high-power electron microscopes to the Web, allowing a doctor to seek a second opinion from experts anywhere in the world. A second project is creating an electronic archive of digital mammograms, available for transmittal and study anywhere in the world. “The effect of this,” says Michael Palladino, associate vice president of networking and telecommunications at Penn, “will be to spread high-tech medical specialization far beyond the urban or university center.”

Indiana University music students can now hear the performances associated with their course work on computer. IU, which has the largest music school in the nation, has digitized its entire music library. Jon Dunn, manager of digital library operations and development, says the new Net can make such libraries available to students worldwide.

Students, in general, stand to benefit. Northwestern University students will be able to send and receive video from their dorm rooms by this fall. Marteza A. Rahimi, vice president of information technology, says this will let engineering students continue work on design projects from their rooms, while marketing students can view archived TV commercials being studied in class. The next step could easily be to make course materials available to the vast world of distance learning.

The universities, aware that Worldcom would likely take vBNS commercial once federal funding expired, quickly began building a parallel Web, called Abilene, after the 19th-century railhead that opened the West for settlement. Built by a partnership with Cisco Systems, Nortel Networks, Qwest Communications International and the University of Indiana, Abilene today links nearly 180 research facilities with a 2.4-gigabit-per-second fiber-optic cable. Abilene’s structure looks like an airline service map; the universities are linked in regional networks that connect to the main Web at gigabit portals (called gigaPoPs), much like feeder airlines connecting at hub-city airports.

Internet2 spokesman Greg Wood is quick to point out that there’s much more to the new Web than just capacity. “Bandwidth within a network is easy,” he says. “The difficulty is getting consistent performance across multiple networks. That’s what I-2 is working on.” Data does not flow in an unbroken stream on the Internet; it is sent in packets that are reassembled at the user’s end. Like the 8-track of old that split songs mid-tune, the current Internet can leave some annoying holes when reassembling streamed data.

I-2 is researching what it calls “quality of service,” some way to guarantee seamless delivery of priority transmissions. A collaborative medical procedure, for instance, should not be interrupted by e-mail traffic. One thought is to create a premium service, where critical data would be tagged so that routers would pass it through first, much the way railroads clear the tracks for express trains. I-2’s goal is to guarantee 30-frame-per-second synchronized video across multiple networks without delays, jerkiness or dropped frames.

The creation of Abilene allows, for the first time, large-scale implementation of the next generation of Internet Protocol. It’s no small deal. IPv6 – we’re using IPv4 now – blows through the ceiling on Internet expansion. Every device that’s connected to the Internet has a unique numerical address. Problem is, we’re running out of numbers. When phone companies faced a similar problem, they added area codes and people found themselves dialing 10 digits to call their neighbor. The IPv6 solution is the same; add more digits to the address. The new scheme expands exponentially the number of devices that can be connected, anticipating the day when air conditioners, heating systems, even lights and the microwave are all connected.

Of more immediate concern, IPv6 allows mobile devices – your cell phone, a GPS receiver in your car, perhaps even your wristwatch – to retain its unique identity while connecting to the Web from anywhere in the world. Think of it as being able to take your telephone number with you wherever you might move.

IPv6 also opens the door to multicasting, the capability for one-to-many communication, much like cable television. The present Internet “unicasts”: Person A sends information to Person B, who then sends it to Person C. Each communication is a separate transaction. It’s like working the pay phone outside the delivery room, calling each family member with the good news. Multicasting, far more efficient, is like setting up a conference call and telling everyone, “It’s a girl!”

Multicasting is what will let astronomers around the world peek through the Mauna Kea telescopes.

The work of I-2 and NGI is not so much parallel as it is interwoven. “We’ve been working hand-in-hand since the beginning,” says Heather Boyles, I-2’s director of government and international relations. A joint engineering team meets monthly to ensure coordination between projects, and federal agency representatives sit on I-2’s many specialized workgroups. Many, perhaps most, of the key research universities are affiliated with both I-2 and NGI. Federal funding, in the form of National Science Foundation grants, supports a big chunk of their research and development, and dozens of universities are developing joint NGI/I-2 applications using federal grant money.

“The federal role is to look far into the future,” says Sally Howe, associate director at the National Coordination Office for Computing, Information and Communications, “and then support development of the technologies needed to fill those needs.”

Both Abilene and vBNS are domestic Webs, but that’s not to say the rest of the world is standing still. “We have formal relationships with over 30 organizations in other countries,” says I-2’s Boyles. “These are agreements to promote applications collaboration as well as to get [an international] backbone in place.” Abilene and vBNS are already interconnected with nearly a dozen second-generation networks in Europe and Asia.

100X, 1000X, gigaPoPs: What does all this mean for the rest of us? “Convergence of services, for one,” says I-2’s Wood. “Television, radio, telephone; these and more will all be coming to us over the Net.” I-2’s Van Houweling predicts that within three years, people will be routinely watching TV on the Internet. And the Web will quickly become a collaborative tool. Experiments with 3-D virtual worlds and virtual laboratories foretell scenarios ranging from collaboration on medical procedures to virtual family reunions. “Today’s Web is used primarily to reach out for information,” Van Houweling says. “Tomorrow’s Internet will be used to reach out to people and work with them.”

But no one really knows what’s next. “As was the case with e-mail and the Web in the first cycle of Internet development,” he says, “we fully expect that we’ll soon see capabilities we haven’t yet imagined.”

============================================================

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