Community Research and Development Information Service - CORDIS

  • European Commission
  • CORDIS
  • Projects and Results
  • Periodic Reporting for period 1 - OPERA (lOw Power heterogeneous architecture for nExt generation of smaRt infrastructure and platforms in industrial and societal Applications)
H2020

OPERA Report Summary

Project ID: 688386
Funded under: H2020-EU.2.1.1.

Periodic Reporting for period 1 - OPERA (lOw Power heterogeneous architecture for nExt generation of smaRt infrastructure and platforms in industrial and societal Applications)

Reporting period: 2015-12-01 to 2017-05-31

Summary of the context and overall objectives of the project

The aim of OPERA is to create a cooperative, secure, reliable, customized, and low power computing platform that is able to address the challenges imposed by the future convergence of datacentre computing, embedded devices and sensors. To this end OPERA will develop a new generation of high-density servers, that will be the basic “bricks” for implementing a scalable Low Power datacentre. At the base of these modules there are heterogeneous architectures, based on different architectures, to enable energy efficient server-class processors, and FPGA accelerators for optimized functions and computation offloading. These devices form a mix of processing elements and accelerators designed for achieving significantly better energy efficiency at the cost of flexibility. Moreover, the integration of the CAPI (Coherent Accelerator Processor Interface) technology allows these accelerators appearing to external high-performance systems as if they were cores integrated on the same chip. The OPERA project aims also at exploiting high-speed optical links to provide interconnections between the accelerators and the external system with no performance limitations.
These technologies forms the substrate used by OPERA to implement an efficient workload decomposition system that automatically and dynamically executes tasks on the most suitable processing element. The result of the integration of this workload decomposition system is to make optimal use of computing resources and application in a heterogeneous architecture so that it is possible to guarantee high performance computing capabilities in a scalable (cloud) energy efficient infrastructure perspective.
In order to exploit at all levels the improvements, the project will develop a highly parallel embedded system based on an ultra-low power System-on-Chip (SoC) which can be deployed on various application domains. The strong integration of sensors, radio communication interfaces, and computing resources allow spreading such a small intelligent devices in several contexts. The availability of reconfigurable communication interfaces (e.g., wireless vs. wired) guarantees that these devices can be flexibly adapted to different contexts (e.g., smart cameras can dynamically switch between Wi-Fi and 3G connections depending on the quality of the signal with the aim of saving energy every time it is necessary). Highly parallel on-board processing elements provide enough computing power for pre-processing raw data that can be later sent to a remote facility (scalable Low Power datacentre) for subsequent analysis. OPERA leverages these capabilities to deliver real-world applications where to test the proposed platform and that can easily be extended to other application scenarios.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The OPERA project started the activities with two main goals. The first was the study and the updated on the state of the art description, in order to define a baseline for improvement.
The second step was to define the requirements of the OPERA system, with a focus on the level of performances, power consumption and overall improvement to be targeted. These requirements have been adapted to the three use cases selected for the project that have been detailed as well in the first part of the project.
This preliminary study has been the base for the development and the integration of the various ULP and LP technologies involved, both in terms of hardware components (FPGA, R&D ULP embedded processing unit, New Moonshot chassis) and in terms of software components for the deployment of heterogeneous platforms, with a distribution of the workload, with the two goals of improvement of the efficiency and reduction of the power consumption.
After the definition of the baseline and the requirements, the development stage has been started. The main activities has been focused on the development of the ULP platform for traffic monitoring applications and the implementation of the mini server, for applications like the Virtual Desktop and the installation of a mini server on a truck used for support in areas where the usual network infrastructure is not available, after for instance earthquakes or floods.
The First prototype of the ULP computing node has been integrated, with the implementation of the traffic congestion detection. In this context the first prototype of communication module has been achieved, with the reconfigurable antenna, for a peer to peer communication.
All the components have been integrated in a first prototype, capable to be installed in a real-life environment.
On the mini server side the hardware has been designed and the first prototype built.
The software frameworks used for the implementation of the VDI and the truck use cases have been selected, implemented on a SOTA reference platform, and finally on the OPERA prototype, in order to have comparable results of the efficiency of the frameworks for the evaluation of the OPERA progress.
The frameworks have been adapted in order to include power meter and performance meter elements, and to support the cross-ISA process migration.
The main resource manager and a new memory allocator have been implemented.
In terms of energy efficiency measures and improvement methods, a specific research has been conducted.
Research shows that metrics in use in the industry are not directly usable for the OPERA project, however the methods used in determining these metrics are. Along similar lines, OPERA partners defined the model, the method and use case specific metrics for determining Energy Efficiency.
At the current state of development in the use cases, the “component view” is proving useful in determining progress and research direction.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

The first results of the implementation of OPERA architecture show encouraging results, with an effective reduction of the power consumption and a significant increase of the efficiency.
The impact of this results is relatively low at the time this report is written, because the analysis on the performances in the use cases is not completed. Anyhow the impact foreseen in the specific use cases is still valid and the results are leading in this direction. For the traffic monitoring use case the possibility to install autonomous and automatic detectors could improve the efficiency of the road managers, and create new use cases with the possibility to reach remote areas where the power grid and the wireless network are not easily available. The estimated low cost of the devices will allow also the deployment of many nodes, with a significant extension of the monitoring capabilities of the road managers. This improvements will lead to a better management of the roads traffic, notification and overall management, for the benefit of the users.
In the truck context, the impact will be determined by the adoption of high performant servers locally where needed. The truck used in the OPERA project is a real truck developed by Protezione Civile in Italy to support the actions of this organization in the areas where a catastrophic event occurred. The adoption of this approach will improve the quality of the support of these organizations all over Europe.
The impact on the VDI use case can be found in the reduction of installation costs for large systems accessible by many users, in private and public contexts. It will lead to an increased number of services available in the private and public sectors.

Related information

Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top