Distributed Heterogeneous Vertically Integrated Energy Efficient Data Centres
Lead Research Organisation:
Queen's University 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


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

Hong C
(2017)
GPU Virtualization and Scheduling Methods A Comprehensive Survey
in ACM Computing Surveys

Hong C
(2017)
FairGV: Fair and Fast GPU Virtualization
in IEEE Transactions on Parallel and Distributed Systems



Karakonstantis G
(2017)
Error-Resilient Server Ecosystems for Edge and Cloud Datacenters
in Computer

Kostas Tovletoglou
(2017)
An Energy-Efficient and Error-Resilient Server Ecosystem Exceeding Conservative Scaling Limits

Marcu M
(2016)
Architecture of Computing Systems - ARCS 2016

Minhas U
(2018)
NanoStreams: A Microserver Architecture for Real-Time Analytics on Fast Data Streams
in IEEE Transactions on Multi-Scale Computing Systems
Description | In the DIVIDEND project, we explored new approaches to model and apportion power consumption between co-executing VMs (Virtual Machines). Our approach collects in runtime utilisation parameters for each VM, such as CPU time, memory and IO usage, and estimates contribution of a VM to the total system power consumption on the basis of these parameters. The experimental study shows that our model precisely predicts VM power consumption with the mean absolute percentage error 3.5%. This approach allows data centre service operators to account consumed energy for each customer in a straightforward way, while the available alternative models are cpu-time utilisation based which is not enough to infer about contribution of each VM to the total power consumption. In turn, we expect that applying of the new energy accounting/pricing model will inadvertently make data centre users to become aware of and improve power efficiency of running applications. As follow, in a long-term perspective, we assume that the new energy accounting policy will help operators to reduce peak power consumption of data centre. The second part of this project involves energy and power profiling of software running on a heterogeneous architecture. The AMD A-series processor (AMD A10-7870K) has been chosen as the base platform for experimental study in the DIVIDEND project. This processor belongs to the generation of accelerated processing units (APUs) which implements the HSA (Heterogeneous System Architecture ) by combining multiple-core CPUs and discrete GPUs. Profiling of an application running on the heterogeneous architecture gives insights into energy distribution between CPU and GPU parts of the processor. Particularly, it enables understanding of how much energy is spent on execution of a program kernel and how much energy is required to start this kernel and transfer data to GPU. The results of energy profiling for an application running on the heterogeneous platform can help software engineers to improve energy efficiency of this application by balancing load between CPU and GPU. Integration of the developed profiling technologies with hardware and software solutions, including Distributed HSA, Scale-Out NUMA, HSA for FPGA, provided by other partners in the DIVIDEND project will result in an experimental heterogeneous distributed substrate and background knowledge highly demanded by companies to build commodity energy efficient heterogeneous data centre. |
Exploitation Route | The findings of the DIVIDEND project have been used to explore the energy-efficiency of datacenter architectures that integrate multiple forms of computational accelerators (FPGAs, GPUs, and Dataflow Engines) within the context of the VINEYARD H2020 project and in collaboration with Maxeler. The findings of DIVIDEND are also underpinning two ongoing PhD projects at Queen's University Belfast. The first project explores software methods for deploying applications in Edge Computing environments where computational accelerators are enabled in both edge devices (such as mobile user devices, routers and switches) and Cloud servers. The second project explores virtual machine migration between Cloud providers based on cost, performance and energy-efficiency criteria. |
Sectors | Digital/Communication/Information Technologies (including Software) Electronics Energy |
Description | The findings of this project have led to the proposal and award of a Knowledge Transfer Partnership project with Vox Financial Services. The partnership explores the use of blockchain technology for managing regulatory change. |
First Year Of Impact | 2018 |
Sector | Digital/Communication/Information Technologies (including Software) |
Impact Types | Economic |
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 | 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 | Royal Society Wolfson Research Merit Award: Principles and Practice of Near-Data Computing |
Amount | £50,000 (GBP) |
Funding ID | WM150009 |
Organisation | The Royal Society |
Sector | Charity/Non Profit |
Country | United Kingdom |
Start | 08/2015 |
End | 08/2020 |
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 | Collaboration with Maxeler on integrating dataflow accelerators in Big Data software stacks |
Organisation | Maxeler Technologies Inc |
Department | Maxeler Technologies |
Country | United Kingdom |
Sector | Private |
PI Contribution | Integration of Maxeler's dataflow engines into the Spark, Storm and other Big Data software stacks, in collaboration with Maxeler Technologies and STFC Hartree. |
Collaborator Contribution | Programming APIs for Maxeler dataflow accelerators. |
Impact | No outputs yet, extensions of Spark and Storm with streaming APIs using Maxeler dataflow engines are currently under design. |
Start Year | 2016 |
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 |