NCSA Gives Update on FABRIC Research Infrastructure Project

May 16, 2022

May 16, 2022 — When the internet launched in the last century it was an amazing feat of science and technology. But it was not designed for the massive data sets, machine-learning tools, advanced sensors and Internet of Things devices that have become central to many research and business endeavors and our homes.

Funded with a $20 million grant from the National Science FoundationFABRIC (Adaptive Programmable Research Infrastructure for Computer Science and Science Applications) is exploring ways to replace an internet infrastructure that’s been showing its age for the last 20 years.

NCSA is one of 13 collaborating institutions helping create a platform for testing novel internet architectures that could enable a faster, more secure internet better suited for today’s users and future needs. One that’s also able to do things not possible now. The FABRIC project is led by the Network Research and Infrastructure Group at RENCI at the University of North Carolina at Chapel Hill.

NCSA: First with the Gigs

Last fall, NCSA installed a 100-gigabit network connection that’s dedicated solely to the FABRIC project, the first FABRIC collaborator to do so.

NCSA already had six 100-gigabit internet connections, says David Wheeler, leader of NCSA’s ICI Data Management and Delivery Division and the principal investigator for NCSA’s FABRIC node. The FABRIC connection, however, is used solely for research on the FABRIC objectives and is connected to FABRIC’s 400-gigabit backbone.

Wheeler says the NCSA networking team is supporting the FABRIC design in the NCSA environments, hosting a FABRIC hank (network node) and an experimenter-facing storage system.

NCSA network engineer Corey Eichelberger installed the rack, coordinated the connections and ensured the FABRIC equipment is isolated from NCSA’s other network nodes. The isolation is partly for security but mostly to allow full accessibility of the testbed. Matt Kollross, network engineering team lead, and network engineers Eric Boyer and Michael Douglas are also contributing expertise.

“People don’t often think much about a network. Networking is a given from a lot of people’s perspectives. But I think it is the fascinating underpinnings of what we do. Science relies on the internet more and more. That need will just continue to grow. And the internet we have now won’t be able to keep up, said David Wheeler, NCSA ICI Data Management and Delivery Division Lead.

He notes it’s the work of network engineers that makes it possible for people to have and use the internet, whether for personal or business use or scientific research.

Phase 2 of the current FABRIC topology.

Research Ramping Up

This is year three of the four-year FABRIC project and is the point “where it’s really getting exciting,” says Wheeler and NCSA faculty affiliate Anita Nikolich, a research scientist and director of research innovation at the iSchool at the University of Illinois Urbana Champaign and a co-PI on the FABRIC project.

This is the phase where collaborators can experiment and test. It’s a networking laboratory. Although NCSA’s grant funding and investment in the project is small, about $170,000, being able to offer networking insight, expertise and a safe environment for researchers to be creative and try new things is invaluable.

“FABRIC’s intent,” says Nikolich, “is a place that people can [try new things] and experiment to build the new internet, one that’s secure, censorship-resistant and supportive of big science. More than just a big network, one that really supports science.”

What NCSA is Researching

While FABRIC focuses on the United States, science is conducted globally. So, Nikolich is the principal investigator on a supplemental grant to focus internationally called FABRIC Across Borders. FAB is an extension of the FABRIC testbed connecting the core North America infrastructure to four nodes in Asia, Europe, and eventually South America, creating the networks needed for science to move vast amounts of data across oceans and time zones seamlessly and securely.

Current FABRIC Across Borders topography.

A key FAB collaborator, says Nikolich, is the NCSA team working on Rubin Observatory’s Legacy Survey of Space and Time.

“Basically, FABRIC is going to serve as a testbed to try out how to get the data streams in the hands of scientists more quickly. And once it’s proven out on FABRIC, LSST ideally will include it in their science workflow,” says Nikolich.

NCSA’s LSST team is experimenting with tweaks to the software used to transmit data to the data brokers. The focus is on optimizing the alert streams so when the telescope becomes operational in Chile later this year, scientists will receive alerts faster than they do now.

As FAB currently has no nodes in South America, the team emulates what a network connection would be. They begin by taking a long-lasting slice of Docker and emulating the processing to get the test alert streams running.  (Docker is a type of container, an app that packages code and dependencies together so software will always run the same, regardless of the infrastructure.) The next step will be to emulate going from Chile to the FABRIC node here.

“We want to make sure that they’re testing how to do this particular networking angle,” explains  Nikolich, “so that when real-life networking is installed during the next two years, they already have the optimized software. FABRIC is helping prepare this workflow.”

An AI Internet That’s Also Secure

Some other research areas on which various FABRIC collaborators are focusing, says Nikolich, are cybersecurity, censorship evasion and artificial intelligence, commonly known as AI.

Censorship Evasion

For example, she says, an experimenter at Clemson is exploring how to make sure that the future internet is censorship resistant so there is free and open communication. It’s an important societal issue, she notes, as we’ve recently seen entire countries disconnected from the internet. Networking is crucial to providing barriers to censorship.

AI Innovations

The advanced chip features in the FABRIC nodes have led to some AI experimentation and more experiments are anticipated in the next few months. These include in-network processing and adversarial AI.

In-network processing, explains Nikolich, is just what it sounds like. In traditional networking, the packets – small amounts of data sent over a network – are reassembled into a single file or another contiguous block of data at the receiving end.

With in-network processing, the software processes the data as it’s being transmitted across the network, stripping things out or doing things to add value or do analysis or do machine learning. Nikolich says physicists at CERN are experimenting with in-networking processing, transmitting data from CERN to Chicago and to NCSA. “It’s just more efficient,” she notes.

“For scientists, it’s huge,” says Nikolich. “They don’t have to ship a ton of data and wait. They can do it along the path.”

With two AI institutes at Illinois, Nikolich hopes to do more AI-focused experiments to show the power of in-network processing for AI.

Adversarial AI

Encouraging people to secure the next internet by thinking ahead is also part of the FABRIC process, say, Nikolich and Wheeler. Even though it’s open science, how do you protect it? What can an adversary do? How do we protect against that?

This is how to make the future internet more secure, they say. By thinking like an adversary now, not in 30 years.

The Fabric Testbed

FABRIC consists of storage, computational and network hardware nodes connected by dedicated high-speed optical links. All major aspects of the infrastructure are programmable so researchers can create new configurations or tailor the platform for specific research purposes, such as cybersecurity.

The core nodes are deeply programmable, meaning they are controlled by the network owners and can be programmed to suit their needs. This flexibility and control over the network functionality at all points in the network allows experimenters to test new architectures not possible today.

The FABRIC network is also extensible, meaning it’s designed to allow the addition of new capabilities, facilities and functionality like cloud, networking, other testbeds, computing facilities and scientific instruments.

Sounds like the internet of the future.


Source: Barbara Jewett, NCSA

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!

The Mainstreaming of MLPerf? Nvidia Dominates Training v2.0 but Challengers Are Rising

June 29, 2022

MLCommons’ latest MLPerf Training results (v2.0) issued today are broadly similar to v1.1 released last December. Nvidia still dominates, but less so (no grand sweep of wins). Relative newcomers to the exercise – AI Read more…

NOAA Launches Twin Supercomputers, Tripling Operational Forecasting Capacity

June 29, 2022

In February 2020, the United States’ National Oceanic and Atmospheric Administration (NOAA) announced that it would be procuring two HPE Cray systems, allowing the organization to triple its operational supercomputing Read more…

US Pursues Next-gen Exascale Systems with 5-10x the Performance of Frontier

June 28, 2022

With the Linpack exaflops milestone achieved by the Frontier supercomputer at Oak Ridge National Laboratory, the United States is turning its attention to the next crop of exascale machines, some 5-10x more performant than Frontier. At least one such system is being planned for the 2025-2030 timeline, and the DOE is soliciting input from the vendor community... Read more…

HPE’s New Arm Server Signals Shift in x86 Mindset

June 28, 2022

HPE's early stab at ARM servers close to a decade ago didn't pan out, but the company is hoping the second time is a charm. The company introduced the ProLiant RL300 Gen11 server, which has Ampere's ARM server processor. The one-socket server is designed for cloud-based applications, with the ability to scale up applications in a power efficient... Read more…

What’s New in HPC Research: EXA2PRO, DQRA, and HiCMA-PaRSE Frameworks & More

June 28, 2022

In this regular feature, HPCwire highlights newly published research in the high-performance computing community and related domains. From parallel programming to exascale to quantum computing, the details are here. Read more…

AWS Solution Channel

Shutterstock 1413860048

Indivumed Boosts Cancer Research With Powerful Analytics Built on AWS

Hamburg-based Indivumed specializes in using the highest quality biospecimen and comprehensive clinical data to advance research and development in precision oncology. Its IndivuType discovery solution uses AWS to store data and support analysis to decipher the complexity of cancer. Read more…

Microsoft/NVIDIA Solution Channel

Shutterstock 1179306271

Using Cloud-Based, GPU-Accelerated AI to Track Identity Fraud

Consumers use many accounts for financial transactions, ordering products, and social media—a customer’s identity can be stolen using any of these accounts. Identity fraud can happen when setting up or using financial accounts, but it can also occur with communications such as audio, images, and chats. Read more…

Is Time Running Out for Compromise on America COMPETES/USICA Act?

June 22, 2022

You may recall that efforts proposed in 2020 to remake the National Science Foundation (Endless Frontier Act) have since expanded and morphed into two gigantic bills, the America COMPETES Act in the U.S. House of Representatives and the U.S. Innovation and Competition Act in the U.S. Senate. So far, efforts to reconcile the two pieces of legislation have snagged and recent reports... Read more…

Shutterstock 1874021860

The Mainstreaming of MLPerf? Nvidia Dominates Training v2.0 but Challengers Are Rising

June 29, 2022

MLCommons’ latest MLPerf Training results (v2.0) issued today are broadly similar to v1.1 released last December. Nvidia still dominates, but less so (no gran Read more…

NOAA Launches Twin Supercomputers, Tripling Operational Forecasting Capacity

June 29, 2022

In February 2020, the United States’ National Oceanic and Atmospheric Administration (NOAA) announced that it would be procuring two HPE Cray systems, allowin Read more…

US Pursues Next-gen Exascale Systems with 5-10x the Performance of Frontier

June 28, 2022

With the Linpack exaflops milestone achieved by the Frontier supercomputer at Oak Ridge National Laboratory, the United States is turning its attention to the next crop of exascale machines, some 5-10x more performant than Frontier. At least one such system is being planned for the 2025-2030 timeline, and the DOE is soliciting input from the vendor community... Read more…

HPE’s New Arm Server Signals Shift in x86 Mindset

June 28, 2022

HPE's early stab at ARM servers close to a decade ago didn't pan out, but the company is hoping the second time is a charm. The company introduced the ProLiant RL300 Gen11 server, which has Ampere's ARM server processor. The one-socket server is designed for cloud-based applications, with the ability to scale up applications in a power efficient... Read more…

Is Time Running Out for Compromise on America COMPETES/USICA Act?

June 22, 2022

You may recall that efforts proposed in 2020 to remake the National Science Foundation (Endless Frontier Act) have since expanded and morphed into two gigantic bills, the America COMPETES Act in the U.S. House of Representatives and the U.S. Innovation and Competition Act in the U.S. Senate. So far, efforts to reconcile the two pieces of legislation have snagged and recent reports... Read more…

Cerebras Systems Thinks Forward on AI Chips as it Claims Performance Win

June 22, 2022

Cerebras Systems makes the largest chip in the world, but is already thinking about its upcoming AI chips as learning models continue to grow at breakneck speed. The company’s latest Wafer Scale Engine chip is indeed the size of a wafer, and is made using TSMC’s 7nm process. The next chip will pack in more cores to handle the fast-growing compute needs of AI, said Andrew Feldman, CEO of Cerebras Systems. Read more…

AMD’s MI300 APUs to Power Exascale El Capitan Supercomputer

June 21, 2022

Additional details of the architecture of the exascale El Capitan supercomputer were disclosed today by Lawrence Livermore National Laboratory’s (LLNL) Terri Read more…

IDC Perspective on Integration of Quantum Computing and HPC

June 20, 2022

The insatiable need to compress time to insights from massive and complex datasets is fueling the demand for quantum computing integration into high performance computing (HPC) environments. Such an integration would allow enterprises to accelerate and optimize current HPC applications and processes by simulating and emulating them on today’s noisy... Read more…

Nvidia R&D Chief on How AI is Improving Chip Design

April 18, 2022

Getting a glimpse into Nvidia’s R&D has become a regular feature of the spring GTC conference with Bill Dally, chief scientist and senior vice president of research, providing an overview of Nvidia’s R&D organization and a few details on current priorities. This year, Dally focused mostly on AI tools that Nvidia is both developing and using in-house to improve... Read more…

Royalty-free stock illustration ID: 1919750255

Intel Says UCIe to Outpace PCIe in Speed Race

May 11, 2022

Intel has shared more details on a new interconnect that is the foundation of the company’s long-term plan for x86, Arm and RISC-V architectures to co-exist in a single chip package. The semiconductor company is taking a modular approach to chip design with the option for customers to cram computing blocks such as CPUs, GPUs and AI accelerators inside a single chip package. Read more…

The Final Frontier: US Has Its First Exascale Supercomputer

May 30, 2022

In April 2018, the U.S. Department of Energy announced plans to procure a trio of exascale supercomputers at a total cost of up to $1.8 billion dollars. Over the ensuing four years, many announcements were made, many deadlines were missed, and a pandemic threw the world into disarray. Now, at long last, HPE and Oak Ridge National Laboratory (ORNL) have announced that the first of those... Read more…

AMD/Xilinx Takes Aim at Nvidia with Improved VCK5000 Inferencing Card

March 8, 2022

AMD/Xilinx has released an improved version of its VCK5000 AI inferencing card along with a series of competitive benchmarks aimed directly at Nvidia’s GPU line. AMD says the new VCK5000 has 3x better performance than earlier versions and delivers 2x TCO over Nvidia T4. AMD also showed favorable benchmarks against several Nvidia GPUs, claiming its VCK5000 achieved... Read more…

Top500: Exascale Is Officially Here with Debut of Frontier

May 30, 2022

The 59th installment of the Top500 list, issued today from ISC 2022 in Hamburg, Germany, officially marks a new era in supercomputing with the debut of the first-ever exascale system on the list. Frontier, deployed at the Department of Energy’s Oak Ridge National Laboratory, achieved 1.102 exaflops in its fastest High Performance Linpack run, which was completed... Read more…

Newly-Observed Higgs Mode Holds Promise in Quantum Computing

June 8, 2022

The first-ever appearance of a previously undetectable quantum excitation known as the axial Higgs mode – exciting in its own right – also holds promise for developing and manipulating higher temperature quantum materials... Read more…

Nvidia Launches Hopper H100 GPU, New DGXs and Grace Superchips

March 22, 2022

The battle for datacenter dominance keeps getting hotter. Today, Nvidia kicked off its spring GTC event with new silicon, new software and a new supercomputer. Speaking from a virtual environment in the Nvidia Omniverse 3D collaboration and simulation platform, CEO Jensen Huang introduced the new Hopper GPU architecture and the H100 GPU... Read more…

PsiQuantum’s Path to 1 Million Qubits

April 21, 2022

PsiQuantum, founded in 2016 by four researchers with roots at Bristol University, Stanford University, and York University, is one of a few quantum computing startups that’s kept a moderately low PR profile. (That’s if you disregard the roughly $700 million in funding it has attracted.) The main reason is PsiQuantum has eschewed the clamorous public chase for... Read more…

Leading Solution Providers

Contributors

ISC 2022 Booth Video Tours

AMD
AWS
DDN
Dell
Intel
Lenovo
Microsoft
PENGUIN SOLUTIONS

AMD Opens Up Chip Design to the Outside for Custom Future

June 15, 2022

AMD is getting personal with chips as it sets sail to make products more to the liking of its customers. The chipmaker detailed a modular chip future in which customers can mix and match non-AMD processors in a custom chip package. "We are focused on making it easier to implement chips with more flexibility," said Mark Papermaster, chief technology officer at AMD during the analyst day meeting late last week. Read more…

Intel Reiterates Plans to Merge CPU, GPU High-performance Chip Roadmaps

May 31, 2022

Intel reiterated it is well on its way to merging its roadmap of high-performance CPUs and GPUs as it shifts over to newer manufacturing processes and packaging technologies in the coming years. The company is merging the CPU and GPU lineups into a chip (codenamed Falcon Shores) which Intel has dubbed an XPU. Falcon Shores... Read more…

AMD’s MI300 APUs to Power Exascale El Capitan Supercomputer

June 21, 2022

Additional details of the architecture of the exascale El Capitan supercomputer were disclosed today by Lawrence Livermore National Laboratory’s (LLNL) Terri Read more…

India Launches Petascale ‘PARAM Ganga’ Supercomputer

March 8, 2022

Just a couple of weeks ago, the Indian government promised that it had five HPC systems in the final stages of installation and would launch nine new supercomputers this year. Now, it appears to be making good on that promise: the country’s National Supercomputing Mission (NSM) has announced the deployment of “PARAM Ganga” petascale supercomputer at Indian Institute of Technology (IIT)... Read more…

Nvidia, Intel to Power Atos-Built MareNostrum 5 Supercomputer

June 16, 2022

The long-troubled, hotly anticipated MareNostrum 5 supercomputer finally has a vendor: Atos, which will be supplying a system that includes both Nvidia and Inte Read more…

Nvidia Dominates MLPerf Inference, Qualcomm also Shines, Where’s Everybody Else?

April 6, 2022

MLCommons today released its latest MLPerf inferencing results, with another strong showing by Nvidia accelerators inside a diverse array of systems. Roughly fo Read more…

Covid Policies at HPC Conferences Should Reflect HPC Research

June 6, 2022

Supercomputing has been indispensable throughout the Covid-19 pandemic, from modeling the virus and its spread to designing vaccines and therapeutics. But, desp Read more…

AMD Lines Up Alternate Chips as It Eyes a ‘Post-exaflops’ Future

June 10, 2022

Close to a decade ago, AMD was in turmoil. The company was playing second fiddle to Intel in PCs and datacenters, and its road to profitability hinged mostly on Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire