ENPOWER
Lead Research Organisation:
Queen's University of Belfast
Department Name: Sch of Electronics, Elec Eng & Comp Sci
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Publications


Barbhuiya S
(2018)
RADS: Real-time Anomaly Detection System for Cloud Data Centres

Chalios C
(2015)
Evaluating Asymmetric Multicore Systems-on-Chip using Iso-Metrics

Chalios C
(2016)
Evaluating fault tolerance on asymmetric multicore systems-on-chip using iso-metrics
in IET Computers & Digital Techniques

Georgakoudis G
(2017)
SCALO Scalability-Aware Parallelism Orchestration for Multi-Threaded Workloads
in ACM Transactions on Architecture and Code Optimization

Georgakoudis G
(2016)
NanoStreams: Codesigned microservers for edge analytics in real time


Georgakoudis G
(2015)
Iso-Quality of Service: Fairly Ranking Servers for Real-Time Data Analytics
in Parallel Processing Letters

Georgakoudis G
(2015)
Methods and metrics for fair server assessment under real-time financial workloads
in Concurrency and Computation: Practice and Experience

Gillan C
(2014)
On the Viability of Microservers for Financial Analytics
Description | The ENPOWER project is the first to explore power-proportional heterogeneous many-core platforms with reconfigurable fabric. The term power-proportional refers to the ability of the platform to execute a given workload with power consumption that is linearly proportional with the utilisation of the platform's hardware components. ENPOWER is also the first research activity to implement reconfigurable fabrics with power proportionality via voltage and frequency scaling, and the first to implement performance optimisation under power caps on these fabrics. ENPOWER contributes novel power-capped performance optimisation methods via fine-grain power modelling in conjunction with intelligent workload allocation between software and hardware. ENPOWER is finally the first project to construct and validate detailed models of the energy consumption of data transfers through memories and system-level interconnects. Energy proportionality is crucial for modern computing systems. Despite significant advances in building more power-efficient computing systems by leveraging heterogeneity, effective and proportional power scaling of hardware resources is not well established yet. This is particularly true in embedded Systems-On-Chip with both general purpose processors (GPP) and field programmable gate array (FPGA) devices, an emerging class of processors with significant potential across embedded and high-performance computing. To enable energy proportionality on such heterogeneous systems, it is essential to understand how different computation patterns affect energy consumption. In ENPOWER, we accomplish this task by associating compute kernels running in the system and the programming constructs used to express these kernels, with energy. We specifically use the OpenCL programming model and extend it to achieve energy aware kernel mapping to heterogeneous devices. We propose new power capping methods for adapting task kernel to the overall energy budget of heterogeneous systems. Our methods aim at achieving the highest performance under capped power consumption. We develop new power models for entire heterogeneous platforms with multi-thread and vector processing capabilities on GPPs and FPGAs. We demonstrate the effectiveness of these models in applications ranging from image processing to financial analytics and evaluate these models on commercial platforms, such as the ZYNQ7000 ZC702. Our research outcome shows that we have achieved lower than 8% error in estimating the power consumption of highly complex heterogeneous platforms and sustained optimal power-capped performance on these platforms in 97.5% of all tested application scenarios. We have also improved power-capped performance by over 30% compared to state of the art approaches. By adopting a dominant heterogeneous programming model, namely OpenCL, we have also achieved productive and seamless power-aware programming model across GPPs and FPGAs. |
Exploitation Route | In 2017, the findings of the ENPOWER project were used for the implementation and optimisation of several algorithms on micro-servers, including credit risk analytics algorithms, and algorithms used in gaming environments where the gaming service is distributed between mobile devices and the Cloud, and graph algorithms. The ENPOWER findings were also used in a number of comparative studies of virtualisation technologies for accelerators based on GPUs and FPGAs. Last, the ENPOWER findings were used to understand the energy-efficiency implications of error mitigation and resilience management solutions on heterogeneous SoCs. In a broader context, the findings of the ENPOWER project provide pathways to cap, both statically and dynamically, the energy consumption of computing systems designed for both the embedded systems market and the server market. Importantly, ENPOWER will enable on-demand energy capping with performance guarantees set by the platform user or operator, in response to the application's computational and data access requirements. We are actively deploying the ENPOWER models and optimisers in four tiers of computing devices which underpin IoT applications, namely intelligent sensing devices, data acquisition devices, data pre-processing micro-servers at network edges, and high-end data analytics servers within datacentres. |
Sectors | Digital/Communication/Information Technologies (including Software) Energy |
Description | The findings of this award led to the proposal and funding of a Knowledge Transfer Partnership project with Crevinn Teoranta, an Irish company specialising in FPGA acceleration, silicon design and verification for various sectors including the healthcare, automotive and financial sectors. The project transferred knowledge of using OpenCL for productive deployment of algorithms on FPGAs. |
First Year Of Impact | 2017 |
Sector | Digital/Communication/Information Technologies (including Software),Financial Services, and Management Consultancy |
Impact Types | Economic |
Description | Distributed Heterogeneous Vertically IntegrateD ENergy Efficient Data centres |
Amount | £140,710 (GBP) |
Funding ID | EP/M015742/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 01/2015 |
End | 12/2017 |
Description | EU Horizon2020 Programme: AllScale: An Exascale Programming, Multi-objective Optimisation and Resilience Management Environment Based on Nested Recursive Parallelism. |
Amount | € 438,578 (EUR) |
Funding ID | 671603 |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 09/2015 |
End | 09/2018 |
Description | EU Horizon2020 Programme: ECOSCALE: Energy-Efficient Heterogeneous Computing at Scale |
Amount | € 696,750 (EUR) |
Funding ID | 671632 |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 09/2015 |
End | 09/2018 |
Description | EU Horizon2020 Programme: RAPID Heterogeneous Secure Multi-level Remote Acceleration Service for Low-Power Integrated Systems and Devices |
Amount | € 326,925 (EUR) |
Funding ID | 644312 |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 01/2015 |
End | 12/2017 |
Description | EU Horizon2020 Programme: UniServer Project |
Amount | € 663,625 (EUR) |
Funding ID | 687628 |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 02/2016 |
End | 01/2019 |
Description | EU Horizon2020 Programme: Vineyard Project |
Amount | € 4,815,810 (EUR) |
Funding ID | 688540 |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 02/2016 |
End | 01/2019 |
Description | Heterogeneous parallel and distributed computing with Java |
Amount | £221,592 (GBP) |
Funding ID | EP/M015750/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 01/2015 |
End | 12/2017 |
Description | Horizon2020 Programme |
Amount | € 5,999,510 (EUR) |
Funding ID | H2020-732631 |
Organisation | European Commission |
Sector | Public |
Country | European Union (EU) |
Start | 01/2017 |
End | 12/2020 |
Description | Collaboration with ARM and Applied Micro on micro-servers operating with extended voltage/frequency margins |
Organisation | Arm Limited |
Country | United Kingdom |
Sector | Private |
PI Contribution | New resource management methods at the operating system & hypervisor levels for leveraging extended operating margins of 64-bit ARM processors to improve system-wide energy-efficiency in micro-servers. |
Collaborator Contribution | Donation of experimental boards from Applied Micro (XGene) and ARM (Juno). |
Impact | Ongoing development of variation-aware hypervisors with enhanced resilience, power management and performance management capabilities. |
Start Year | 2016 |
Description | Collaboration with ARM on fine-grain energy accounting tools |
Organisation | Arm Limited |
Country | United Kingdom |
Sector | Private |
PI Contribution | Partnership with ARM on developing energy-efficient system software and methods for accurate and fine-grain energy accounting in the Linux operating system. Our research team has contributed new probabilistic models for energy accounting at time scales which are finer than the power sensing or sampling periods of on-chip or off-chip power sensing instruments. |
Collaborator Contribution | ARM has scoped this collaboration and contributed in an advisory role via a series of online and face-to-face meetings with the ALEA, ENPOWER and GEMSCLAIM project consortia. |
Impact | Thread-level energy accounting tools for ARM Big.Little platforms (e.g. Exynos) and their use in energy-aware scheduling and resource allocation on mobile devices are currently in implementation and preliminary evaluation stages. |
Start Year | 2016 |
Description | Collaboration with IBM on disaggregated memory technologies and near-data computing |
Organisation | IBM |
Country | United States |
Sector | Private |
PI Contribution | Our research team has contributed methods to manage data caching and placement on disaggregated memory architectures with near-data processing elements. |
Collaborator Contribution | IBM has contributed novel remote memory server infrastructures and near-data acceleration technologies. |
Impact | Materialised through an industrial placement of QUB research staff, this partnership is exploring designs to substantially improve the energy-efficiency of large memory systems, via the use of disaggregation of memory, RDMA-based networking to remote memory devices and near-data accelerators for in-situ, in-memory analytics. |
Start Year | 2015 |
Description | Credit Suisse |
Organisation | Credit Suisse Group |
Country | Switzerland |
Sector | Private |
PI Contribution | Partnership with Credit Suisse explores design methods and tools to reduce the carbon and space footprint of datacentres that serve real-time financial analytics applications in London. |
Collaborator Contribution | The partner contributed time equivalent to 0.1FTE over a year to engage in meetings and a joint experimental campaign to evaluate tools developed in the context of the ALEA (EP/L000055/1,) ENPOWER (EP/L004232/1) and GEMSCLAIM (EP/K017594/1) projects. |
Impact | The collaboration has resulted in dissemination of datacentre energy measurement, energy accounting, and energy optimisation methods explored within the ALEA (EP/L000055/1), ENPOWER (EP/L004232/1) and GEMSCLAIM (EP/L017594/1) projects among stakeholders in the capital markets, as well as a preliminary evaluation of energy-efficient micro-servers based on heterogeneous many-core architectures and the ARM ecosystem, as an alternative to heavily overprovisioned servers in financial datacentres. |
Start Year | 2014 |
Title | ALEA Energy Accounting Tool |
Description | The ALEA profiler is a cross-platform statistical profiling tool for Linux, which provides time and energy profiling at the basic block level on Intel and ARM architectures (32 and 64 bit). Energy profiling is available for platforms with energy or power meters. Currently, ALEA supports all Intel platforms with enabled RAPL interface and ARM-based Odoroid-XU/Odroid-XU3 platforms. The tool can be used for profiling both sequential and multi-threaded applications. Energy and execution time accounting to source code is also supported for applications compiled with debugging information (DWARF). |
Type Of Technology | Software |
Year Produced | 2017 |
Open Source License? | Yes |
Impact | ALEA is actively used by a number of groups in the UK and the US (e.g. Edinburgh, Lancaster, Virginia Tech, Old Dominion University) to perform targeted, energy-aware code optimisation on high-end computing systems. |
URL | https://hpdc-gitlab.eeecs.qub.ac.uk/lmukhanov/alea-release.git |
Description | NVTV Interview on Superocmputing |
Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Media (as a channel to the public) |
Results and Impact | Interview in NVTV's Behind the Science program on Supercomputing as a technology with impact on our everyday lives. |
Year(s) Of Engagement Activity | 2015 |
URL | http://www.nvtv.co.uk/shows/behind-the-science-dimitrios-nikolopoulos/ |