Q&A with Atos’ Eric Eppe, an HPCwire Person to Watch in 2022

By HPCwire Editorial Team

May 26, 2022

HPCwire presents our interview with Eric Eppe, head of portfolio & solutions, HPC & Quantum at Atos, and an HPCwire 2022 Person to Watch. In this exclusive Q&A, Eppe recounts Atos’ major milestones from the past year and previews what’s in store for the year ahead. Exascale computing, quantum hybridization and decarbonization are focus areas for the company — and having won five out of the seven EuroHPC system contracts, Atos is playing a big role in Europe’s sovereign technology plans. Eppe also shares his views on HPC trends — what’s going well and what needs to change — and offers advice for the next-generation of HPC professionals.

Eric, congratulations on your selection as a 2022 HPCwire Person to Watch. Summarize the major milestones achieved last year for Atos in your division and briefly outline your HPC/AI/quantum agenda for 2022.

2021 was a strong year for Atos’ Big Data and Security teams, despite the pandemic. Atos’ BullSequana XH2000 was in its third year and was already exceeding all sales expectations. More than 100,000 top bin AMD CPUs were sold on this platform, and it made one of the first entries for AMD Epyc in the Top500.

We have not only won five out of seven EuroHPC petascale projects, but also delivered some of the most significant HPC systems. For example, we delivered one of largest climate studies and weather forecast systems in the world to the European Centre for Medium-Range Weather Forecasts (ECMWF). In addition, Atos delivered a full BullSequana XH2000 cluster to the German climate research center (DKRZ). 2021 was also the launch of Atos’ ThinkAI and the delivery of a number of very large AI systems such as WASP in Sweden.

2022 is the year in which we are preparing the future with our next-gen Atos BullSequana XH3000 supercomputer, a hybrid computing platform bringing together flexibility, performance and energy-efficiency. Announced recently in Paris, this goes along with the work that has started on hybrid computing frameworks to integrate AI and quantum accelerations with supercomputing workflows.

Sovereignty and sustainability were key themes at Atos’ launch of its exascale supercomputing architecture, the BullSequana XH3000. Please address in a couple paragraphs how Atos views these areas and why they are important.

This was a key point I mentioned during the supercomputer’s reveal. For Europe, the real question is should we indefinitely rely on foreign technologies to find new vaccines, develop autonomous electric vehicles, and find strategies to face climate changes?

The paradox is that Europe leads the semiconductor substrate and manufacturing markets (with Soitec and ASML) but has no European foundry in the <10nm class yet. It is participating in the European Processor Initiative (EPI) and will implement SiPearl technologies in the BullSequana XH3000, but it will take time to mature enough and replace other technologies.

Atos has built a full HPC business in less than 15 years, becoming number one in Europe and in the top four worldwide in the supercomputer segment, with its entire production localized in its French factory. We are heavily involved in all projects that are improving European sovereignty.

EU authorities are today standing a bit behind compared to how the USA and China regulations are managing large petascale or exascale procurements, as well as the difference between how funding flows to local companies developing HPC technologies. This is a major topic.

Atos has developed a significant amount of IP, ranging from supercomputing platforms, low latency networks, cooling technologies, software and AI, security and large manufacturing capabilities in France with sustainability and sovereignty as a guideline. We are partnering with a number of European companies, such as SiPearl, IQM, Pasqal, AQT, Graphcore, ARM, OVH and many labs, to continue building this European Sovereignty.

Atos has announced its intention to develop and support quantum accelerators. What is Atos’ quantum computing strategy?

Atos has taken a hardware-agnostic approach in crafting quantum-powered supercomputers and enabling end-user applications. Atos’ ambition is to be a major player in multiple domains amongst which are quantum programming and simulation, the next-generation quantum-powered supercomputers, consulting services, and of course, quantum-safe cybersecurity.
Atos launched the Atos Quantum Learning Machine (QLM) in 2017, a quantum appliance emulating almost all target quantum processing units with abstractions to connect to real quantum computing hardware when available. We have been very successful with the QLM in large academics or research centers on all continents. In 2021, there was a shift of many commercial companies starting to work on real use cases, and the QLM is the best platform to start these projects without waiting for hardware to be available at scale.

Atos plays a central role in European-funded quantum computing projects. We are cooperating with NISC QPU makers to develop new technologies and increase their effectiveness in a hybrid computing scenario. This includes, but is not limited to, hybrid frameworks, containerization, parallelization, VQE, GPU usage and more.

Where do you see HPC headed? What trends – and in particular emerging trends – do you find most notable? Any areas you are concerned about, or identify as in need of more attention/investment?

As for upcoming trends in the world of supercomputing, I see a few low-noise trends. Some technological barriers that may trigger drastic changes, and some arising technologies that may have large impacts on how we do HPC in the future. Most players, and Atos more specifically, are looking into quantum hybridization and decarbonization which will open many doors in the near future.

Up to this point, HPC environment has been quite conservative. I believe that administrators are starting to see the benefits of orchestration and micro service-based cluster management. There are some obstacles, but I do see more merits than issues in containerizing and orchestrating HPC workloads. There are some rising technological barriers that may push our industry in a corner, while at the same time giving us opportunities to change the way we architect our systems.

High performance low latency networks are making massive use of copper cables. With higher data rates (400Gb/s in 2022 and 800Gb/s in 2025) the workable copper cable length will be divided by 4x, replaced by active or fiber cables with cabling costs certainly increasing by 5 or 6x. This is clearly an obstacle to systems that are going to range in the 25,000 endpoints, with a cabling budget in tens of millions.

This very simple problem may impose a paradigm shift in the way devices, from a general standpoint, are connected and communicate together. This triggers deeper architectural design points changes from racks to nodes and down to elements that are deeply integrated today such as compute cores, buses, memory and associated controllers, and switches. I won’t say the 800Gb/s step alone will change everything, but the maturity of some technologies, such as silicon photonics and the emerging standardization on very powerful protocols like CXL, will enable a lot more flexibility while continuing to push the limits. Also, note that CXL is just in its infancy, but already shows promise for a memory coherent space between heterogenous devices, centralized or distributed, mono or multi-tenant memory pools.

Silicon photonic integrated circuits (PICs), because they offer theoretically Tb/s bandwidth through native fiber connection, should allow a real disaggregation between devices that are today very tightly connected together on more complex and more expensive than ever PCBs.

What will be possible inside a node will be possible outside of it, blurring the traditional frontier between a node, a blade, a rack and a supercomputer, offering a world of possibilities and new architectures.

The market is probably not fully interested in finding an alternative to the ultra-dominance of the Linpack or its impact on how we imagine, engineer, size and deliver our supercomputers. Ultimately, how relevant is its associated ranking to real life problems? I wish we could initiate a trend that ranks global system efficiency versus available peak power. This would help HPC players to consider working on all optimization paths rather than piling more and more compute power.

Lastly, I am concerned by the fact that almost nothing has changed in the last 30 years in how applications are interacting with data. Well, HPC certainly uses faster devices. We now have clustered shared file systems like Lustre. Also, we have invented object-oriented key and value abstractions, but in reality storage subsystems are most of the time centralized. They are connected on the high-speed fabric. They are also oversized to absorb checkpoints from an ever-growing node count, while in nominal regime they only use a portion of the available bandwidth. Ultimately with workloads, by nature spread across all fabric, most of the power consumption comes from IOs.

However, it’s time to change this situation. There are some possible avenues, and they will improve as a side effect, the global efficiency of HPC workloads, hence the sustainability and the value of HPC solutions.

More generally, what excites you about working in high-performance computing?

I’ve always loved to learn and be intellectually stimulated, especially in my career environment. High performance computing, along with AI and now quantum, are giving me constant food for thoughts and options to solve big problems than I will ever been able to absorb.

I appreciate pushing the limits every day, driving the Atos portfolio and setting the directions, ultimately helping our customers to solve their toughest problems. This is really rewarding for me and our Atos team. I’m never satisfied, but I’m very proud of what we have achieved together, bringing Atos into the top four ranking worldwide in supercomputers.

What led you to pursue a career in the computing field and what are your suggestions for engaging the next generation of IT professionals?

I’ve always been interested by technology, initially attracted by everything that either flew or sailed. Really, I’m summarizing this into everything that plays with wind. In my teenage years, after experiencing sailboards and gliders, I was fortunate enough to have access to my first computer in late 1979 when I was 16. My field of vision prevented me from being a commercial pilot, thus I started pursuing a software engineering master degree that led me into the information technology world.

When I began my career in IT, I was not planning any specific path to a specific domain. I simply took all opportunities to learn a new domain, work hard to succeed, and jump to something new that excited me. In my first position, I was lucky enough to work on an IBM mainframe doing CAD with some software development, as well as embracing a fully unknown system engineering role that I had to learn from scratch. Very educational! I jumped from developing in Fortran and doing system engineering on VM/SP and Unix. Then I learned Oracle RDMBS and Internet at Intergraph, HPC servers and storage at SGI. I pursued my own startups, and now I’m leading the HPC, AI and quantum portfolio at Atos.

What I would tell the next generation of IT professional for their career is to:

First, only take roles in which you will learn new things. It could be managerial, financial, technical – it doesn’t matter. To evolve in your future career, the more diverse experience you have, the better you will be able to react and be effective. Move to another role when you are not learning anymore or if you are far too long in your comfort zone.

Second, look at problems to solve, think out of the box and with a 360-degree vision. Break the barriers, and change the angle of view to give new perspectives and solutions to your management and customers.

Also, compensation is important, but it’s not all. What you will do, how it will make you happy in your life, and what you will achieve professionally is more important. Ultimately, compare your salary with the free time that remains to spend it with your family and friends. Lastly, compensation is not always an indicator of success, but rather changing the world for the better and making our planet a better place to live is the most important benefit you will find in high performance computing.

Outside of the professional sphere, what can you tell us about yourself – family stories, unique hobbies, favorite places, etc.? Is there anything about you your colleagues might be surprised to learn?

Together with my wife, we are the proud parents of two beautiful adult daughters. Also we have our three-year-old, bombshell Jack Russell named Pepsy, who brings a lot of energy to our house.

We live Northwest of Paris in a small city on the Seine river. I’m still a private pilot and still cruising sail boats with family and friends. I recently participated in the ARC 2021 transatlantic race with three friends on a trimaran boat – a real challenge and a great experience. Soon, we’re off to visiting Scotland for a family vacation!

Eppe is one of 12 HPCwire People to Watch for 2022. You can read the interviews with the other honorees at this link.

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!

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 Quinn in a presentation delivered to the 79th HPC User Forum 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…

Q&A with Intel’s Jeff McVeigh, an HPCwire Person to Watch in 2022

June 17, 2022

HPCwire presents our interview with Jeff McVeigh, vice president and general manager, Super Compute Group, Intel Corporation, and an HPCwire 2022 Person to Watch. McVeigh shares Intel's plans for the year ahead, his pers Read more…

AWS Solution Channel

Shutterstock 152995403

Bayesian ML Models at Scale with AWS Batch

This post was contributed by Ampersand’s Jeffrey Enos, Senior Machine Learning Engineer, Daniel Gerlanc, Senior Director for Data Science, and Brandon Willard, Data Science Lead. Read more…

Microsoft/NVIDIA Solution Channel

Shutterstock 261863138

Using Cloud-Based, GPU-Accelerated AI for Financial Risk Management

There are strict rules governing financial institutions with a number of global regulatory groups publishing financial compliance requirements. Financial institutions face many challenges and legal responsibilities for risk management, compliance violations, and failure to catch financial fraud. 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 Intel CPUs and GPUs across multiple partitions. The newly reimag 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…

Q&A with Intel’s Jeff McVeigh, an HPCwire Person to Watch in 2022

June 17, 2022

HPCwire presents our interview with Jeff McVeigh, vice president and general manager, Super Compute Group, Intel Corporation, and an HPCwire 2022 Person to Watc 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…

D-Wave Debuts Advantage2 Prototype; Seeks User Exploration and Feedback

June 16, 2022

Starting today, D-Wave Systems is providing access to a 500-plus-qubit prototype of its forthcoming 7000-qubit Advantage2 quantum annealing computer, which is d Read more…

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…

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

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 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…

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 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…

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…

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…

Industry Consortium Forms to Drive UCIe Chiplet Interconnect Standard

March 2, 2022

A new industry consortium aims to establish a die-to-die interconnect standard – Universal Chiplet Interconnect Express (UCIe) – in support of an open chipl 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…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire