extreme computing services
Accelerate your HPC production with Atos services
Our HPC service teams offer a complete portfolio of professional services, with the required competence and experience to support the design, installation, operation, management, and continuous improvement of HPC infrastructures.
|Data management||Application performance||Application workflow|
|Data center & energy efficiency||I/O optimization||HPC-as-a-Service|
Managing massive data sets
Extreme data is a set of skills, experience and technologies offered by Atos to manage the complete lifecycle of your data in an optimized way. Extreme data addresses in particular data workflow analysis, HSM configuration, I/O optimization, as well as data storage, restore and movement.
Some references for Data Management
Application Performance Optimization
Reap immediate benefit from the latest HPC technologies
Atos experts can help you ensure your applications make the most of the latest HPC technologies and the bullx parallel computing capabilities.
Our expert services include:
- Recommendations to application developers so that they can make the most efficient use of new parallel technologies (accelerators, co-processors, hybrid systems, many-core processors…)
- Optimization of commercial and open-source applications
- Proof-of-concept to introduce end-users to the benefits of parallelism at the start of the project
- I/O and network optimization
- Ensuring applications make the most of your Bull supercomputers from day one, with the Fast Start program that addresses the porting, optimizing and configuring of your applications well ahead of system delivery.
Some references for Application Performance Optimization
Increase the reliability of your applications
Atos experts can help you manage your application workflow. Atos’s best practices rely on the ITIL recommendations.
Optimizing the application workflow starts with the strategy defining the user need analysis, and spans to the design phase with the definition of SLAs, and to the transition and the operation phases.
The transition phase includes the integration, acceptance and pre-production tests. The operation phase includes the incident and problem management and an on-going optimization.
Data Center and Energy Efficiency
Bring the PUE (Power Usage Effectiveness) of your data center as low as 1.1 – or even lower
There are many ways to optimize energy consumption, from the design of a green hardware architecture, with Direct Liquid Cooling technologies for example, to the optimization of the cooling system, and including also the scheduler configuration, and the setting of energy KPIs to make your applications energy-aware.
Atos has a long-standing experience of delivering and supporting the largest data centers, and has thus acquired unique experience in all aspects of energy efficiency. Atos’s range of expertise around data center efficiency includes customer site analysis, logistics requirements, standard compliance, data center integration, and maintenance and support.
For example, to optimize data center design, Atos can simulate an entire computing room, including air flows for optimum cooling, and modeled cable routes and rack locations.
Some references for Data Center and Energy Efficiency
Boost application performance by 30%
Optimizing the I/O to boost data flow and application performance can bring a gain in performance of up to 30%. To help you achieve this, Atos experts can run a performance audit, evaluate the workflow balance, tune the write operations, the data traffic on the controllers, optimize the data transfer, tune the file system, ensure all meta data are located on high-speed disks, and define the storage architecture.
Optimize production and operation costs
As a matter of efficiency and operation costs, Atos experts ensure you remain compliant with your SLAs.
Atos teams can run your operations until the skills transfer and handover to your team. Our service operation consists in a remote monitoring coupled with event management, trouble ticketing coupled with incident management and user request management, change management with impact analysis and on-going optimization service including problem management, knowledge management and documentation.
Some references for Service Operation
As a standard part of the installation process, Atos provides on-site, tailored, workshop training for the system administration team. Atos can also deliver on request a range of advanced training programs for HPC users and HPC developers, which will help your teams make the most of their Bull supercomputer and run the operations in an optimal way.
Proposed training courses include application development and optimization, how to port applications and what compilation options to select, how to improve performance, for example how to improve job submissions, or how to choose message queues. Some training course are dedicated to operations and system administration, OS management and tools (batch manager, file system management, network management, monitoring…). A specific data management course focuses on data assessment.