The HPC Cloud-Centric Guide to SC10

By Nicole Hemsoth

November 12, 2010

On Sunday we’ll be packing up and heading off to New Orleans for SC10 for a full week of live coverage, including details from select sessions and presentations, thoughts from some of the leaders in the HPC cloud space and video interviews with a number of interesting attendees from the academic and vendor communities.

Navigating the conference program requires pulling out all the stops in the “artful scheduling” department, but we’ve managed to take a look at the program and narrow in on some select sessions and other events that might be right up your alley if you’re regular reader and keep up to date with the news and ecosystem trends in the high-performance computing cloud space.

This year we were thrilled to learn that there would be a sub-set of special sections during the conference devoted to HPC in the cloud as a movement via the Birds of a Feather session series.

While there are a few of these that we want to call your attention to, there are also a few other highlights during the regular program that are worth mentioning.

This brief guide will give you a view of what to look for this year in New Orleans and might require you to make use of some virtual whiteout as you adjust your schedule accordingly.

If nothing else, the conference’s side focus on the growing role of cloud computing in HPC, in addition to other recent events, including ISC Cloud this year, shows that there is some momentum building—and that we could be witnessing a more pronounced move “cloudward” in the coming year.

For those who cannot attend SC10, we hope you’ll stay tuned to the site for an in-depth, on-spot view into what the HPC community is seeing in the clouds.

HPC Cloud Birds of Feather Sessions at SC10

Birds of a Feather (BOF) sessions have been an SC tradition and allow the conference organizers to designate a small handful of special topics to explore that are still in the HPC ecosystem, but lie just on the horizon for one reason or another.

BOFs will meet on Tuesday, Wednesday and Thursday at 12:15 p.m. and on Tuesday and Wednesday at 5:30 p.m. They will be open for all attendees, including exhibitors only badge types.

During this year’s event, the topics designated for BOFs will include HPC in Weather and Climate Modeling, Energy Efficiency in Supercomputing Center, Training and Education for High Performance Computing and, last but certainly not least, HPC in a Cloud Environment.

Low Latency, High Throughput, RDMA and the Cloud in Between

Whether in the context of traditional high-performance computing or HPC in the cloud, the issues of latency and throughput remain persistent concerns. Added to that list are matters of RDMA and offloading, which also have an impact on application performance.

Gilad Shainer from Mellanox and Jeff Layton of Dell will spend an hour on Tuesday talking about how, despite the promise of low latency Ethernet from any number of quarters, it is not the solution it needs to be to fulfill many requirements for HPC users. The presenters state that, “for enabling true low-latency Ethernet, new proposals now raise the idea of using different transport protocols on top of Ethernet, as such transports were proven to provide low latency and other important networking elements.”

While InfiniBand has already proven itself to be a viable solution for users of high-performance computing, the focus on Ethernet, especially for those who have already invested a great deal in existing networking infrastructures, is an important one.

One can expect this session on the latest progress points for RoCE will draw some spectators, as will the embedded promise of details about the InfiniBand FDR and EDR roadmap, which will be highlighted by use cases. 

The presenters also hope to hit on another topic in the wake of this more overarching discussion on low-latency Ethernet and InfiniBand by broaching, “the fourth mode of science—Science Discovery, in which HPC clouds will be required to handle the data flood generated by computation and science simulations.”

On a side note, Shainer discussed this as well as other matters in a recent interview with HPC in the Cloud that might serve as great background material for his presentation.

If this has piqued your interest, this discussion takes place on Tuesday from 12:15-1:15 p.m. in Room 397.

It sounds like a lot to pack into one short hour, but for those who are looking for a more thorough overview of RoCE in detail, you’re going to be forced to make a tough choice between Shainer and Layton’s presentation and Paul Grun’s related session entitled “RoCE: Next Generation RDMA Network” which will take place at the same bat time and channel, except in Room 280-281.

Decisions, decisions….When you get right down to it, this seems to be the toughest part of SC10. Unless you’re a journalist trying to take it all it and weave it together in no time. But enough about my struggles.
 
Building the World’s Largest HPC Cloud

William Lu from Platform Computing will be leading one of the juicer items on the HPC cloud plate during SC10 with his presentation on CERN’s cluster dedicated to crunching the massive datasets from the Large Hadron Collider (LHC) and its status as the world’s largest HPC cloud. While it is not what you’d call vendor neutral since Platform will be discussing how it built the research center’s platform, it will nonetheless be an exciting journey into the inner working of CERN’s ability to manage vastly complex virtual and physical workloads and requirements.

One aspect of this presentation that will be most interesting is that discussion participants who are facing challenges similar to those at CERN (those with massive datasets and intense throughput requirements) can consider the cloud. It will be interesting to see who attends and what experiences they share about their current infrastructure and budget challenges and what they’re considering in order to minimize these problems—and if cloud is really on the drawing board.

The CERN facility is one of a handful of large-scale HPC clouds that are wringing out some great news for the possibility of HPC in the cloud adoption. They have had to overcome some significant challenges and hopefully Platform’s Lu will talk in some detail about what these challenges were and how (and if) they can be mitigated enough to be acceptable solutions for other institutions.

William Lu’s presentation will take place on Wednesday, November 17th from 1:15 to 2:15 p.m. in Rooms 280-281.

For those interested, we have a recent article on CERN’s HPC cloud here for some background.
 
Enabling High Performance Cloud Computing Environments

On Thursday, November 18th from 1:15 to 2:15 Jurrie Van Den Breekel of Spirent will deliver a session on some overarching topics relevant to cloud environments for HPC users, including topics related to mult-core processors, virtualization and the current state of Ethernet—and how to build environments that maximize efficiency and performance capabilities.

The discussion will revolve around some case studies from Spirent, including their recent experiences with the European Advanced Networking Test Center (EANTC), which will reveal how actual cloud implementation on the large scale, both within the a private and bursting capacity model, works—and what challenges are present. The session also promises to provide “a close examination of how implementing a cloud approach within a datacenter affects the firewall, data center bridging, virtualization and WAN optimization.”

Again, this one sounds like it’s aiming to pack a lot into one hour but what it is providing, even if it is from a vendor’s view (why can’t there be more research team leaders presenting on their experiences with cloud on the large scale at more events?) but the pulling in implementation details to frame the discussion will make this session worthwhile.

More on the Cloud Front at SC10

Aside from the Birds of a Feather sessions, some of which touch on issues specific to HPC clouds, there are a number of presentations that are scattered around the regular conference program that will likely be of interest to some of you.

Below is a list of some items on the agenda worth paying attention to:

Disruptive Technologies: Cloud Era, Ltd.

A few weeks ago we posted a piece on an emerging company, which for now is a one-man show, that seeks to deliver the first cloud portal to the “R” language and far beyond.

While I could go on at length about this ambitious project (and what it could mean for the future of scientific and research collaboration via cloud computing) the best way to get a sense for the scope is to check out this detailed SC10 Disruptive Technologies preview article.

Karim Chine will be presenting on “Elastic-R: A Virtual Collaborative Environment for Scientific Computing and Data Analysis in the Cloud” via a tutorial/overview on Monday morning from 8:30 a.m.-12:00 p.m. in Room 389. Cloud Era, Ltd., which is the sole effort oChine, will also be featured during the Disruptive Technologies series during regular exhibition hours.

3rd Workshop on Many-Task Computing on Grids and Supercomputers (MTAGS)

Chances are, if you’re going to be at the conference on Monday and you plan on attending this workshop, you’ve already planned ahead by blocking off your entire day. From 9:00 to 5:30 in room 271, Ioan Raicu, Ian Foster and Yong Zhao will be leading a workshop to “provide the scientific community a dedicated forum for presenting new research, development and deployment efforts of large-scale, many-task computing (MTC) applications on large-scale cluster, grids, supercomputer and cloud computing infrastructure.”

This workshop has an ambitious range of topics that will explored, including what the organizers describe as “challenges that can hamper efficiency and utilization in running applications on large-scale systems…scalability, data management, I/O management, reliability at scale and application scalability” among others.

It would be interesting to take a quick census during this workshop and find out just how many of the world’s largest supercomputing center administrative folks are in attendance—and where they come from.

So, if you’ve got a national lab or university system to manage and you’re free on Monday…

Web Portals for Scientific Computing

On Monday from 1:30-5:00 p.m. in Room 287, Jano van Hemert and Jos Koetsier from the University of Edinburgh will hold court to discuss the growing trend of the use of web portals as interfaces to scientific research resources.

Far from being a general overview of the types of portals or some of their specific uses, this session will present a thorough description of actually making use of these resources. The presenters note that they will be discussing challenges to using these portals and via the tutorial they will “provide a basic hands-on tutorial on building portals and a more advanced hands-on session to deal with application and resource-specific requirements.”

Virtualization for HPC

Josh Simons, Stephan Scott, DK Panda, Bill Bryce and Scott Clark will be presenting this session in Rooms 385-386 on Tuesday, November 16 from 1:30-3:00 p.m. They plan to touch on reasons why, in the enterprise cloud adoption has remained significantly higher and how interest in virtualization for HPC has been growing.

The speakers will contend that “beyond cloud computing, virtualization offers additional potential benefits for HPC, among them support for multi-tenant environments, checkpoint-resistance capabilities, dynamic provisioning, low-overhead job migration, proactive fault tolerance, multi-OS support for heterogeneous HPC facilities, and system and application resilience.”

This panel session promises to be a contentious one since this argument tends to get heated words on both sides, so expect an interesting, debate if you have a couple of hours to set aside on Tuesday.

The Past, Present and Future of HPC

Jack Dongarra (University of Tennessee), Ian Foster (Argonne) and Dorian Arnold (University of New Mexico will be presenting this epic session for early birds on Sunday, November 14th from 3:30-5:00 p.m. in Rooms 290-291. While the details about what they will cover on the future spectrum can easily be guessed, one item that one can imagine will at least be mentioned is the impact on cloud computing on current HPC paradigms.

Even if some of the material is “old hat” to some, there’s nothing like kicking off a conference series by putting the ecosystem in historical perspective and having some leading voices in the arena voice their views on what will shape the coming new era of high-performance computing. Whether its multi-core, clouds, GPGPUs, innovations in networking, progressive application developments—this is a “must attend” for anyone arriving before the real fun begins on Monday.

Scattered Clouds at SC10

Aside from the sessions themselves, there are a number of other events going on, including poster reception events that are relating some information and ideas about HPC in the cloud. The following are a few that you might want to wander into.

A research poster reception entitled, HPCaaS: High Performance Computing as a Service, with Marcel Kunze and Viktor Mauch, both from the Karlsruhe Institute of Technology,will be held Tuesday in the main lobby from 5:15 to 7:00 p.m.  The focus of this poster reception will examine issues related to the problem that there is currently “no clear concept of how to provide HPC as a Service supporting InfiniBand with a dynamic configuration in a virtualized cloud computing environment” and how there are some different strategies that have been set forth to address this.

Another such reception that is right in our range, “High Performance Computing in the Cloud: Why Not?!” will be delivered by Tobias Lindinger, Nils Gentschen Felde and Dieter Franzmuller, a team from Ludwig-Maximillans University in Munich will provide “an analysis of the suitability of clouds for high-performance computing, thereby providing a qualitative evaluation of large-scale, virtualized infrastructures in contrast to specialized clusters or supercomputers.” In addition to offering a viability overview, the team will address issues of performance degradation and virtualization hurdles and will present some recommendations based on case studies.

Other notable receptions include:

Provisioning Virtual Clusters in the Cloud Using Wrangler – a research poster reception held on Tuesday from 5:15-7:00 p.m. in the main lobby, delivered by Gideon Juve and Ewa Deelman from the Information Sciences Institute.

Cumulus: Open Source Storage Cloud for Science – another research poster reception on Tuesday from 5:15 to 7:00 p.m. in the main lobby from a team comprised of Argonne National Laboratory’s John Bresnahan and Kate Keahey as well as Tim Freeman and David LaBissoniere from the University of Chicago.

Even More Events of Note…

TeraGrid Technology Auditing Services Tools — a session with Thomas R. Furlani, Matthew D. Jones, Steven M. Gallo on Tuesday, November 16, from 12:15-1:15 p.m.

Network Automation, the Power of Choice: Making the Cloud Work for You – an exhibitor forum led by Stephen Garrison from Force10 Networks, which will take place Thursday from 11:00-11:30 a.m. in Rooms 280-281.

Cloud Networking: Evolution of Data Center Traffic Patterns – another exhibitor forum with a networking focus, this time led by Anshul Sadana from Arista Networks. Taking place Thursday from 11:30 a.m. to noon on Thursday in the same room as Force10’s presentation, 280-281.

Enough Clouds for You?

Okay, so if you weren’t convinced there was a cloud movement in HPC up until this year, it has to be a little harder to make the same argument now. There are even more sessions, particularly on the networking end, that tie in nicely with clouds for HPC as well but I’ll leave this list as it is for now. After all, if you remember way back on page one of this guide I mentioned it was going to be “brief”…Well, so much for that.

If you’re not able to attend, please make sure you stay tuned to the site for special coverage and if you haven’t already, subscribe to our newsletter to get up-to-date coverage on this and other movements in HPC and cloud. This week we’ll be upping the normal dose with two special edition newsletters (instead of one)—the first is set to hit your inbox Wednesday morning, the second early Friday morning with some final wrap-up coverage and news items the next week.

If you are at the show, please do come say hello! Don’t know about any of you, but man–I’m excited for this one!
 

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!

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, code-named Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from its predecessors, including the red-hot H100 and A100 GPUs. 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. While Nvidia may not spring to mind when thinking of the quant Read more…

2024 Winter Classic: Meet the HPE Mentors

March 18, 2024

The latest installment of the 2024 Winter Classic Studio Update Show features our interview with the HPE mentor team who introduced our student teams to the joys (and potential sorrows) of the HPL (LINPACK) and accompany 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 field was normalized for boys in 1969 when the Apollo 11 missi Read more…

Apple Buys DarwinAI Deepening its AI Push According to Report

March 14, 2024

Apple has purchased Canadian AI startup DarwinAI according to a Bloomberg report today. Apparently the deal was done early this year but still hasn’t been publicly announced according to the report. Apple is preparing Read more…

Survey of Rapid Training Methods for Neural Networks

March 14, 2024

Artificial neural networks are computing systems with interconnected layers that process and learn from data. During training, neural networks utilize optimization algorithms to iteratively refine their parameters until Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, code-named 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…

Survey of Rapid Training Methods for Neural Networks

March 14, 2024

Artificial neural networks are computing systems with interconnected layers that process and learn from data. During training, neural networks utilize optimizat Read more…

PASQAL Issues Roadmap to 10,000 Qubits in 2026 and Fault Tolerance in 2028

March 13, 2024

Paris-based PASQAL, a developer of neutral atom-based quantum computers, yesterday issued a roadmap for delivering systems with 10,000 physical qubits in 2026 a Read more…

India Is an AI Powerhouse Waiting to Happen, but Challenges Await

March 12, 2024

The Indian government is pushing full speed ahead to make the country an attractive technology base, especially in the hot fields of AI and semiconductors, but Read more…

Charles Tahan Exits National Quantum Coordination Office

March 12, 2024

(March 1, 2024) My first official day at the White House Office of Science and Technology Policy (OSTP) was June 15, 2020, during the depths of the COVID-19 loc Read more…

AI Bias In the Spotlight On International Women’s Day

March 11, 2024

What impact does AI bias have on women and girls? What can people do to increase female participation in the AI field? These are some of the questions the tech 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…

Analyst Panel Says Take the Quantum Computing Plunge Now…

November 27, 2023

Should you start exploring quantum computing? Yes, said a panel of analysts convened at Tabor Communications HPC and AI on Wall Street conference earlier this y 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…

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

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…

Training of 1-Trillion Parameter Scientific AI Begins

November 13, 2023

A US national lab has started training a massive AI brain that could ultimately become the must-have computing resource for scientific researchers. Argonne N 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…

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…

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…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire