Beyond pure performance, supercomputers must not just leverage the latest technologies, but also perfectly meet the needs of applications and users. Atos’s HPC R&D has designed the BullSequana X series of servers to provide maximum flexibility in terms of interconnect, power, and cooling, and cover the widest possible spectrum of applications. BullSequana X supercomputers offer an infinitely adaptable response, with a large choice of compute nodes, accelerated nodes and specialized nodes. And this multitude of components can be combined, in a completely customized way, into a single system and managed as a single system using the Bull supercomputer suite.
With BullSequana XH2000, Atos brings to the market a no compromise, highly flexible, Exascale-ready and lowest TCO on the market, Hybrid Computing solution for today’s and tomorrow’s real-life problem solving.
Thanks to the flexibility and energy efficiency of the BullSequana XH2000, our customers are able to control their energy consumption and reduce costs, at the same time as benefitting from processors with the very highest power requirements.
Organizations of all sizes can manage peak computing demand using either private or public cloud solutions while consuming less energy, enjoying higher elasticity and benefiting from new opportunities for scale, all for a lower Total Cost of Ownership (TCO).
The BullSequana XH2000 flexible packaging
BullSequana XH2000’s self-contained and modular architecture makes it scalable and open to future technologies.
- Energy efficient
- Application efficient
- Cost efficient
- Modular and scalable
- A futureproof solution
BullSequana X1000 open supercomputers
Designed by Atos’s R&D in close cooperation with major customers, the BullSequana X1000 supercomputer leverages the latest technological advances, so as to guarantee maximum performance for a minimized operation cost. BullSequana takes up the exascale technological challenges:
► Open for future technologies
► Limit energy consumption
► Handle the data deluge
► Accelerate application performance
► Deliver a resilient system
BullSequana X1000 cell
In BullSequana X1000, the computing resources are grouped into cells. Each cell tightly integrates:
► compute nodes,
► interconnect switches,
► redundant power supply units,
► redundant liquid cooling heat exchangers,
► a dual node for distributed management and diskless support.
This packaging consisting of large building blocks facilitates high-scale deployment – up to 64.000 nodes, and optimizes density, scalability and cost- effectiveness.
MORE INFORMATION ON THIS PRODUCT
The BullSequana X1000 cell is organized across three cabinets.
► the two side cabinets contain compute nodes,
► the central cabinet houses the interconnect switches.
Limiting energy consumption
Controlling energy consumption is the main roadblock on the path to exascale. BullSequana X1000 is ultra energy-efficient: it targets a PUE very close to 1.
100% of the components of BullSequana X1000 – both compute nodes and switches – are cooled using an enhanced version of the Bull patented Direct Liquid Cooling (DLC) solution. DLC is a proven cooling technology that minimizes the global energy consumption of a system by using warm water up to 40°C.
The cooling system of BullSequana X1000 is sized to evacuate the heat generated even by the most extreme configurations – with very powerful and energy-hungry nodes.MORE INFORMATION ON THIS PRODUCT
For easy maintenance, all Bull Sequana X1000 components (compute nodes, interconnect switches, PSUs, heat exchangers…) are hot-swappable and can be serviced without interrupting system production. In the compute blades, the processors and DIMMs can be replaced without removing the cold plate. In a BullSequana X1000 cell, all maintenance operations are just as easy as in a standard air-cooled system.MORE INFORMATION ON THIS PRODUCT
Related resources BullSequana X1000
The jury, which is made up of independent industry figures from the French scientific and industrial sectors, rewarded 5 revolutionary projects in numerical simulation, Artificial Intelligence (AI) and quantum computing.
Discover the range of supercomputers developed by Atos’s R&D, the systems needed to meet the major challenges of the 21st century.
The BullSequana X1000 named JUWELS (short for Jülich Wizard for European Leadership Science) is operational at the Jülich Supercomputing Centre (JSC). The supercomputer has a peak performance of 12 petaflop/s, making it Germany’s fastest supercomputer.
BullSequana X800: at the confluence of HPC and Big Data
Featuring an architecture that supports an impressive number of processing cores and an exceptional memory capacity, the BullSequana X800 servers are engineered for high performance and in-memory computing. They are ideally suited to support massive in-memory data bases, pre-processing, post-processing, and visualization. They are among the most scalable and modular ultra-high memory servers on the market, starting with 2 CPUs and 24 memory DIMMs, and going up to 32 CPUs with 384 memory DIMMs in 16 interconnected boxes – with a linear performance scaling.
A powerful and modular range
The BullSequana X800 series consists of five complementary models, assembling 1 to 16 2-socket compute boxes thanks to two types of interconnects:
- A glueless interconnect is used for 1, 2 or 4 compute boxes, allowing to form a glue-less configuration with up to 8 sockets.
- For larger configurations, a UNC (UPI Node Controller) stacks 8 to 16 boxes.
This distinctive Atos technology makes it possible to form 16- or 32-socket servers.
A Connecting Box assembles compute boxes with no apparent cabling, and makes it possible to easily add compute and memory resources. This helps adjust memory and compute resources to application needs, and facilitates the scaling of Big Data applications. For more agility in configuring, BullSequana X800 servers feature hot plug I/O blades, disks, fans and PSUs.
Key innovative components
Each compute box is a 2U 2-socket rack server and contains:
- up to 24 memory DIMMs, i.e. a total of up to 3 TB per compute module when using 128GB DIMMs – and ready for higher capacities with future memory technology;
- hot plug I/O blades that offer up to 5x PCIe Gen3 slots, with capability for a disk controller in charge of the front-end disks;
- a number of options to customize the system to match application requirements: internal disks, NVMe drives or GPUs.
The performance of leading-edge Intel® Xeon® Scalable processors
The BullSequana X800 embarks Intel® Xeon® processors Scalable family, with a large choice of models for the best fit with your applications in terms of:
- number of cores, or
- power consumption.
Designed for operational efficiency and maintainability
The BullSequana X800 focuses on serviceability and operational efficiency. It has all required features for reliability, availability and quality of service:
- redundancy of critical components;
- hot-pluggable critical components – the innovative blade form-factor of I/O modules enables hot-plugging;
- patented mechanics for easy replacement of components: the disks, fans and PSUs can be extracted without rack decabling and without stopping running applications;
- server partitioning;
- internal regulation and alert systems;
- dedicated maintenance processor;
- power-conscious design: with the Gen2 Active/Passive Power supply, energy consumption is reduced by 40%.
The BullSequana X550 series is a modular air-cooled blade system, designed specifically for Extreme Computing. Our aim? To offer you made-to-measure solutions based on industry standards so you can go even further, to demand more from your systems, to innovate even faster, and to turn the corner into the future at the head of the pack. Delivering anything from a few teraflops to several petaflops, depending on your needs, the BullSequana X550 blade system helps you push back the frontiers of innovation.
The BullSequana X550 blade system was designed with the following guidelines in mind:
► optimization and simplification of the compute node for HPC usage,
► integration of several compute nodes and first-level InfiniBand EDR or OPA interconnect,
► flexible structure for communication and I/O networks, for the closest fit with customer requirements,
► large memory footprint: for structured data management, structured and unstructured data analytics.
BullSequana X550 air-cooled
The BullSequana X550 series initially proposes one blade model with two sockets per node. In the near future, the series will be extended with new blade models: four sockets per node, storage. They will be fully compatible with the existing enclosure, to maximize the longevity of your system.
Leading edge technologies
The BullSequana X550 series leverages the latest technological advances such as:
► Intel® Xeon® processors Scalable family and matching Intel chipset;
► InfiniBand EDR or OPA interconnect switch integrated in chassis;
► different options available for Ethernet network connection with 1GbE or 10GbE switches;
► storage: 2.5” SSDs or HDDs and NVMe drives available.
Thanks to these innovations, the BullSequana X550 blade system delivers:
► improved performance (enhanced compute node efficiency, reduced latency, higher communication and I/O throughput);
► reduced cost of ownership compared to rack-mount servers with equivalent features;
► enhanced reliability (less cabling).
The BullSequana X400 series is a comprehensive family of rack-mounted servers designed for High Performance Computing and offering an optimum balance between cost and efficiency.Download BullSequana X400 series factsheet
BullSequana X440 E5 – Compute servers
The BullSequana X440 E5 compute/service nodes integrate 4 2-way nodes within a rackmounted 2U chassis. Equipped with new generation Intel® Xeon® Processors Scalable Family , they offer even more performance and improved energy efficiency.
These cost-effective and ultra-dense servers are ideally suited for two uses:
► as compute nodes within a cluster, in combination with BullSequana X430 E5 service
nodes (standard or cost-effective) and/or
► as light service nodes in small clusters.
BullSequana X410 E5 – dense GPU-accelerated compute node
The 1U BullSequana X410 E5 servers are optimized for compute density, performance and power efficiency:
► They support up to four NVIDIA® Tesla® P100 GPUs, interconnected either via PCI-E direct connect or via NVIDIA® NVLink™.
► They also feature two Intel® Xeon® Scalable processors.
► They are powered by ultra-high efficiency redundant Titanium Level power supplies.
The integration of up to four GPUs within 1U places this system at the forefront of today’s accelerated computing solutions, both in terms of performance and cost-optimization.
BullSequana X430 E5 1U – cost-efficient I/O node
The BullSequana X430 E5 cost-efficient I/O node is a rack-mounted 1U mono socket server optimized specifically to serve as an I/O node within a small to medium High Performance Computing cluster.
This model offers the full breadth of features needed in an efficient I/O server – with no unnecessary add-ons that may weigh on your licensing costs. It offers the perfect trade-off between cost-efficiency and performance.
BullSequana X430 E5 2U – HPC service node
The BullSequana X430 E5 is a 2U rackmounted 2-socket server. It is ideally suited as a service node, since its advanced connectivity features, its extended storage options and its redundancy features guarantee efficient and reliable cluster administration services.
BullSequana X450 E5 – graphics node
The BullSequana X450 E5 is a versatile rack- mounted 2-socket server designed specifically to satisfy the visualization needs involved in Extreme Computing.
The BullSequana X450 E5 can handle the most demanding HPC, data visualization and rendering workloads. It is optimized to support the latest graphics, coprocessor and accelerator cards.
BullSequana X Supercomputer Suite version 5 – SCS 5 – introduces a new approach to eXtreme computing software solutions. SCS 5 is a scalable, open, and robust software suite that meets the requirements of the most challenging high-performance computing (HPC) environments, with high security standards.
Suited for small to very large configurations
SCS 5 is the result of Atos’s long experience in deploying large-scale supercomputers, combined to continued efforts in Research & Development.
Bull supercomputer suite version 5 is designed for every HPC need, from small supercomputers with just a few hundred cores to supercomputers with tens of thousands of nodes. It is cut out to reach performance targets of the order of up to 100 PFlops, based on new-generation CPUs and GPUs. The main goal of Bull SCS 5 is to provide a global high performance supercomputing environment. It includes:
- a standardized and scalable installation process with an enhanced update solution; mechanisms to ease integration of new hardware,
- default security with on-time fixes,
- and support for several user development and execution environments with top performance.
This new generation HPC software suite is a further step towards Exascale computing.Download SCS 5 factsheet
A software suite for your supercomputer and your applications
SCS 5 is a software solution that globally manages supercomputer environments, including data and applications. It is based on a recent Linux distribution (RHEL 7™).
SCS 5 provides a robust, scalable, modular and flexible solution that easily adapts to customer needs. It is closely integrated with the Bull Sequana X1000 series based on the latest available technologies. It supports EDR InfiniBand with the MOFED stack and MPI accelerators MXM/FCA (both from Mellanox®), a complete development suite and Lustre (based on the Intel® solution). All critical services are configured to ensure High Availability.
SCS 5 is based on best-of-breed open source and ISV software. The selected open source components are enhanced with Atos’s added-value features. ISV components can be added or can fully replace default components, depending on user needs.
By design, SCS 5 is modular, allowing any ISV, open source or home grown software and tools to run seamlessly.
Atos services to take full advantage of supercomputer suite
As a leading provider of end-to-end Extreme Computing solutions, Atos provides consultancy services to help its customers to take full advantage of the benefits of Bull supercomputer suite throughout their projects: design, deployment and operations.
SCS 5 users can benefit from Atos’s worldwide and highly professional support offer, comprising traditional maintenance and upgrade services as well as dedicated, personalized and pro-active services.