Periodic Reporting for period 2 - LEGaTO (Low Energy Toolset for Heterogeneous Computing)
Reporting period: 2019-06-01 to 2020-11-30
Why the emphasis on energy? Information and Communications Technology (ICT) has made great strides in recent decades, impacting the quality of life of every European citizen. However, this transformation comes with a cost, currently ICT sector accounts for 10% of the European electricity consumption. Furthermore, this percentage is expected to increase as the industry is hitting fundamental physics limits to decrease the size of computational building blocks, thus making them less energy efficient. This situation clearly requires a fundamental energy-savings approach at all layers of the computational stack. While attaining these energy-savings, care must be taken not to compromise the system from security attacks, and the system should continue to function correctly in spite of occasional faults. Finally, the energy-efficient software stack must be easy to program and to maintain.
The overall objective of the LEGaTO project is to produce a mature software stack to optimize the energy-efficiency of heterogeneous computing leading to an order of magnitude increase in energy-efficiency. The project strived to achieve this objective through employing a task-based programming model, coupled to a dataflow runtime while simultaneously ensuring security, resilience and programmability. The LEGaTO project applied this energy-efficient software stack for heterogeneous hardware to the use cases of health care, smart home, smart city, machine learning (ML) and secure IoT gateway.
LEGaTO has developed several software packages and tools in the first phase of the project and ten of these packages have been made available for the public through the project Software Components portal at https://legato-project.eu/software/components and at the LEGaTO project github at https://github.com/legato-project
The project has already demonstrated substantial decrease in energy consumption in the five use cases, based on the energy-efficient hardware platform and the task-based programming environment:
• The use of FPGAs resulted in a phenomenal 822x speedup in the healthcare use case, enabling a new world of biomarker analysis.
• The use of shared-memory programming style on distributed GPUs led to 10x energy savings in the smart home use case, the SmartMirror.
• The smart city use case on operational urban pollutant dispersion modelling had a 7x gain in energy efficiency thanks to the use of FPGAs and the OmpSs@FPGA programming environment.
• Up to 16x gain in energy efficiency and performance was achieved in the ML use case using the LEGaTO optimizer.
• The Secure IoT Gateway was vital to simplify the complexity of communication of local devices to a network, and it supported the above mentioned use cases to achieve their goals by reducing the complexity of security.
On the research side, partner BSC has decreased FPGA memory energy consumption by one order of magnitude through a technique termed undervolting; the results of this work appeared in the 51st Annual Symposium on Microarchitecture and were awarded a Tetramax technology transfer project to partners BSC and MIS.
The various elements of the software toolset have been integrated together to facilitate the porting of future use cases to the energy-efficient LEGaTO hardware/software platform. With regard to the work on hardware, a Cloud to Edge Microserver Platform was developed, which covers most of the domains from cloud, edge and embedded computing by using a microserver architecture and a scalable system. It includes the LEGaTO Edge Server, which was completely designed and built in the project and focuses on edge and embedded applications.
The results of the project were disseminated in many scientific papers, training courses, and events, and a final event was organised to present the project’s results. In addition, press releases were launched and technical news pieces were published regularly on the website, resulting in 27 press clippings and over 37,500 page views respectively. Two videos were produced to display the SmartMirror use case and the hardware developed in the project.
The LEGaTO consortium is highly committed with the involvement of SMEs, in fact, 3 of the 5 partners are SMEs or mid-caps. The role of SMEs in LEGaTO is critical: MIS not only developed the ML use-case, they also provided know-how to other partners who applied ML schemes. Christmann worked on increasing the value of LEGaTO hardware through the integration of a high-performance interconnect fabric. Maxeler, the third SME, provided the other LEGaTO initial platform.
With respect to facilitating SMEs competitiveness, the consortium is fully aware of the barriers that SMEs occasionally encounter in funding their technology platforms. To correct this direction, the LEGaTO ecosystem enabled the use of cost-effective low-energy distributed computing solutions that provide a substantial percent reduction in the Total Cost of Ownership (TCO), i.e. the cost to buy, own, operate, and manage; when compared to the systems currently on the market. The SMEs highly benefited from the reduction of such costs. In addition, open source software provides a low cost entry point for SMEs and startups, allowing them to lower the risk and increase the speed of European business innovations.
Most of the LEGaTO components raised their Technology Readiness Levels (TRL) from concept to demonstrator moving closer to market, and some of them even became improved products or services offered commercially by LEGaTO's industrial partners.
The work carried out in LEGaTO has influenced a large number of European research projects, relevant standardization bodies and diverse academic programmes. Three upcoming European projects will continue the development of the results achieved in LEGaTO:
• LV-EmbeDL will implement and demonstrate the FPGA undervolting techniques developed in LEGaTO.
• eProcessor will deliver the first completely open source European full stack ecosystem based on RISC-V technology.
• VEDLIoT will develop an IoT platform that uses deep learning algorithms distributed throughout the IoT continuum to achieve higher performance and energy efficiency.