Bull Unveils Exascale Program

November 25, 2014

PARIS, France, Nov. 25 — Bull, an Atos company, has unveiled its exascale program. The main ambition of this program is to design and develop in Europe the next generation of supercomputers that will contribute to producing world-class solutions for both research and industrial purposes. With one of the largest teams dedicated to High-Performance Computing (HPC) – now able to leverage the international strength of Atos, with its 86,000 employees worldwide – Bull is experiencing a paradigm shift that will give it the critical mass to address vertical market sectors across the entire world.

Exascale will increase the competitiveness and innovation capabilities of industries and address the industrial, scientific and societal challenges of the 2020s, from nanoscience and genomics to climatology, aeronautics and energy.

As such, the Bull exascale program is a key contributor to Europe’s leadership in science and innovation, as well to its position in the HPC field. It is aligned with the Strategic Research Agenda proposed by ETP4HPC (the European Technology Platform for High Performance Computing). This new generation of supercomputers will be capable of achieving a performance of more than one exaflops, i.e. one billion billion operations a second, a thousand times more powerful than current systems. Exascale computing power is believed to be the order of processing power that matches the human brain.

Most of the complex problems scientists and engineers will address in the future are at the crossroads where Big Data meets HPC. For instance, domains like genomic therapy and drug discovery, full-scale simulations of aircraft or modelling of entire weather systems – that involve huge volumes of data and demand massive computing power – require exascale supercomputers and beyond.

The Bull exascale program therefore relies on tight integration between high levels of computing power and the capacity to process huge amount of data. It combines faster processors, more data capacity, ultra-fast interconnections, greater energy efficiency, enhanced cooling, a scalable packaging, fundamentally redesigned software and a full set of services to optimize user applications.

The Bull exascale program initially involves the development of five main elements:

  • An open exascale supercomputer, code-named SEQUANA
  • The matching software stack, known as bullx supercomputer suite
  • A new generation of fast interconnect, code-named BXI
  • A range of servers with ultra-high memory capacity, known as the bullx S6000 series
  • A complete set of services to optimize customer applications and make the most of exascale.

The Bull exascale program derives synergies from Bull’s global mission to deliver Big Data, HPC and security solutions. It is the result of major investments in R&D, close cooperation with European labs such as the CEA (the French Alternative Energies and Atomic Energy Authority) and other partners, and the long-standing experience built up by Bull’s HPC teams in designing, implementing and running large-scale HPC systems. It relies upon the Bull Center for Excellence in Parallel Programming (CEPP) for the application expertise needed to reengineer existing applications so as to make the most of exascale systems.

“To fulfill its missions, the French Alternative Energies and Atomic Energy Commission (CEA) set up a R&D program in partnership with industry which aims at developing the key technologies needed to design and build competitive supercomputers by 2020. Within this framework, CEA and Bull have renewed their long-time partnership that led in 2010 to the first petaflops supercomputer designed and manufactured in Europe,” said Pierre Leca, Head of Simulation and Software Engineering at the CEA

“With the unveiling of its exascale program, Bull has reaffirmed its capacity for innovation and its ability to design the world’s most powerful supercomputers. Bull meets the needs of performance and reliability that our customers require to handle the massive amounts of data generated in the digital world and to help solve major societal and environmental challenges that are arising in our societies,” said Philippe Vannier, Bull’s CEO.

The exascale program is a new step forward in Bull’s strategy to deliver exascale supercomputers capable of addressing the new challenges of science, industry and society.

The Bull exascale program aims to address technologies and processes to meet the requirements of High-Performance Computing (HPC) and Big Data: i.e. the rapid computation and analysis of massive data sets. In a first step, it involves developing five main elements:

  • An open exascale supercomputer, code-named SEQUANA
  • The matching software stack, known as bullx supercomputer suite
  • A new generation of fast interconnect, code-named BXI
  • A range of servers with ultra-high memory capacity, known as the bullx S6000 series
  • A complete set of services to optimize customer applications and make the most of exascale.

A Never-Ending Need for More Performance

The Bull exascale program ensures that HPC performance will continue to increase in the foreseeable future, with the objective to reach exascale performance levels. That means a complete change in scale compared to today’s petascale systems, with more constraints on size and power footprints, while improving system resiliency and usability for current and new categories of users.

SEQUANA: The foundation for exascale

SEQUANA is an open exascale supercomputer. It is designed to easily integrate with and make the most of current and future technologies. It is deliberately designed to be compatible with successive generations of different technologies (CPUs and accelerators). It supports fast state-of-the-art interconnects.

SEQUANA is highly modular, cost-effective and scales to tens of thousands of nodes. The computing resources are grouped into cells to facilitate large-scale implementations.

All SEQUANA components are hot-swappable and can be serviced without interrupting production. The SEQUANA components are cooled using the enhanced Bull Direct Liquid Cooling (DLC) technology currently used in the bullx DLC B700 racks. DLC minimizes the global energy consumption of a system by using warm water up to 40°C.¿

Getting rid of the communications overhead

Exascale computing entails an explosion in performance, data volumes, power consumption and data movement. So it will be increasingly critical to ensure that CPUs are fully dedicated to computation. Today, with current interconnects, CPUs are also responsible for communications, at the expense of performance. Getting rid of this overhead would immediately and significantly free up CPU performance. Bull is therefore developing a new-generation of fast interconnect, code-named BXI.

The Bull exascale interconnect (BXI) unleashes CPU performance

For compute-intensive HPC workloads, the BXI interconnect is the foundation that will enable the next generation of application scalability. Its core feature is completely hardware-encoded communication management, which enables CPUs to be dedicated to computational tasks while communications are independently managed by BXI. Thanks to this hardware acceleration, BXI will deliver the highest level of communication performance for HPC applications, at full scale, characterized by high bandwidth, low latency and high message rates.

Where HPC Meets Big Data

Thanks to its data-oriented conception, SEQUANA implements a tight coupling of data and simulation, and makes it possible to compute, explore and analyze massive multi-disciplinary datasets. It will unlock a new generation of complex simulations and analyses.

SEQUANA is the foundation for High-Performance Data Analytics and will leverage the upcoming Bull Hadoop-based search and analytics appliances and discovery appliances.

In-memory data processing

Some applications – such as some genomics applications – require in-memory data processing. Bull addresses this challenge with a new range of ultra-high memory capacity servers, known as the bullx S6000 series. They will support massive in-memory databases, pre-processing, post-processing and visualization operations. The bullx S6000 series relies on two major Bull innovations: the Bull BCS (Bull Coherence Switch) to inter-connect up to 16 CPUs, and the connecting box to easily assemble modules together.

The bullx S6130, the first available model of the bullx 6000 series, is fully scalable up to 16 CPUs/24 TB. It supports full memory protection and features hot-swappable memory and I/O capabilities. The bullx S6130 is the HPC version of the bullion S16 enterprise server, currently recognized as the fastest x86 server on the market (SPECint_rate2006 for the 16 socket configuration).

Applications Challenges

The shift to multicore exascale systems will require applications to exploit million way parallelism. Today, the main limitation lies within the code itself: programmers are struggling to extract greater parallelism from their codes, handle increasingly hybrid configurations and support a higher degree of heterogeneity. The Bull Center for Excellence in Parallel Programming (CEPP) is available to help HPC users make the most of the latest and future hardware evolutions, by modifying and optimizing their source codes.

About Bull

Bull is the trusted partner for enterprise data. The Group, which is firmly established in the Cloud and in Big Data, integrates and manages high-performance systems and end-to-end security solutions. Bull’s offerings enable its customers to process all the data at their disposal, creating new types of demand. Bull converts data into value for organisations in a completely secure manner.

Bull currently employs around 9,200 people across more than 50 countries, with over 700 staff totally focused on R&D. In 2013, Bull recorded revenues of €1.3 billion.

Source: Bull

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…

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…

Leading Solution Providers

Contributors

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…

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