publications

2019

1. Evaluating the Arm Ecosystem for High Performance Computing

   William Jackson, Andrew Turner, Michele Weiland, and 3 more authors

   In Proceedings of the Platform for Advanced Scientific Computing Conference, Jun 2019

   6th Platform for Advanced Scientific Computing (PASC) Conference, PASC19 ; Conference date: 12-06-2019 Through 14-06-2019

   Abs DOI

   In recent years, Arm-based processors have arrived on the HPC scene, offering an alternative the existing status quo, which was largely dominated by x86 processors. In this paper, we evaluate the Arm ecosystem, both the hardware offering and the software stack that is available to users, by benchmarking a production HPC platform that uses Marvell’s ThunderX2 processors. We investigate the performance of complex scientific applications across multiple nodes, and we also assess the maturity of the software stack and the ease of use from a users’ perspective. This papers finds that the performance across our benchmarking applications is generally as good as, or better, than that of well-established platforms, and we can conclude from our experience that there are no major hurdles that might hinder wider adoption of this ecosystem within the HPC community.

2. An Early Evaluation of Intel’s Optane DC Persistent Memory Module and its Impact on High-Performance Scientific Applications

   Michele Weiland, Holger Brunst, Tiago Quintino, and 7 more authors

   In SC’19 Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, Nov 2019

   International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2019) : SC 2019 ; Conference date: 19-11-2019 Through 21-11-2019

   Abs DOI

   Memory and I/O performance bottlenecks in supercomputing simulations are two key challenges that need to be addressed on the road to Exascale. The recently released byte-addressable persistent non-volatile memory technology from Intel, DCPMM, promises to be an exciting opportunity to break with the status quo, with unprecedented levels of capacity at near-DRAM speeds. In this paper, we explore the potential of DCPMM in the context of high-performance scientific computing using two distinct applications in terms of outright performance, efficiency and usability for both its Memory and App Direct modes. In Memory mode, we show that it is possible to achieve equivalent performance and better efficiency for a CASTEP simulation that struggles with memory capacity limitations on conventional DRAM-only systems without needing to introduce any changes to the application. For IFS, we demonstrate that using a distributed object-store over the NVRAM devices reduces the data contention created in weather forecasting data producer-consumer workflows. In addition to presenting the impact on two applications, we also present results for achievable memory bandwidth performance using STREAM.

2017

1. CityFlow, enabling quality of service in the Internet: Opportunities, challenges, and experimentation

   Sachin Sharma, David Palma, Joao Goncalves, and 10 more authors

   In Proceedings of the IM 2017 - 2017 IFIP/IEEE International Symposium on Integrated Network and Service Management, Jul 2017

   15th IFIP/IEEE International Symposium on Integrated Network and Service Management, IM 2017 ; Conference date: 08-05-2017 Through 12-05-2017

   Abs DOI

   In this paper, we propose an OpenFlow enabled Internet infrastructure, using virtual path slicing in an end-to-end path, so that any user connected to an OpenFlow network is dynamically allocated a corresponding right of way. This approach allows an interference-free path, from other traffic, between any two endpoints, on multiple autonomous systems, for a given application flow (e.g., WebHD Video Streaming). Additionally, we propose and implement an end-to-end quality of service framework for the Future Internet and extend the virtual path slice engine to support future Internet technologies such as OpenFlow. The proposed framework is evaluated in distinct multiple autonomous scenarios for a city with a population of 1 million inhabitants, emulating xDSL (Digital Subscriber Line), LTE (Long-Term Evolution) and Fibre networking scenarios. The obtained results confirm the suitability of the proposed architecture between multiple autonomous systems, considering both data and control traffic scalability, as well as resilience and failure recovery. Furthermore, challenges and solutions for experimentation in a large-scale testbed are described.

2016

1. On the Trade-offs between Energy to Solution and Runtime for Real-World CFD Test-Cases

   Michael Bareford, Nicholas Johnson, and Michele Weiland

   In Exascale Applications and Software Conference 2016 Proceedings, May 2016

   Abs DOI

   This paper provides an insight into the optimisation of runtime and energy performance for two widely-used CFD codes. Energy efficiency is a hot-topic in HPC and methods to reduce the energy consumption of large machines are an active area of research. In this paper, we examine the energy efficiency and runtime performance of the SBLI and Nektar++ codes, using small but real-world test cases. The codes are instrumented in sufficient detail to reveal significant variability in energy usage during the course of the simulations. In addition, the test cases are run at different CPU frequencies and the consequences of changing this parameter, for both runtime performance (time to solution) and power performance (energy to solution) are presented.

2014

1. CityFlow: OpenFlow city experiment - Linking infrastructure and applications

   Adam Carter, Donal Morris, Sachin Sharma, and 6 more authors

   In Proceedings - 2014 3rd European Workshop on Software-Defined Networks, EWSDN 2014, Dec 2014

   3rd European Workshop on Software-Defined Networks, EWSDN 2014 ; Conference date: 01-09-2014 Through 03-09-2014

   Abs DOI

   CityFlow is an EU FP7 project, aiming to create a set of multi-autonomous-system OpenFlow experiments on the OFELIA infrastructure to emulate a city of one million inhabitants. In this demo, we demonstrate all of the key components of the CityFlow experimentation stack working together.

2013

1. Input-aware auto-tuning for directive-based GPU programming

   Alberto Magni, Dominik Grewe, and Nicholas Johnson

   In ACM International Conference Proceeding Series, Dec 2013

   6th Workshop on General Purpose Processor Using Graphics Processing Units, GPGPU 2013 ; Conference date: 16-03-2013 Through 16-03-2013

   Abs DOI

   The difficulties posed by GPGPU programming and the need to increase productivity have guided research towards directive-based high-level programs for accelerators. This effort has led to the definition of the OpenACC industry standard. It significantly simplifies writing code for graph- ics engines leaving the programmer the opportunity to tune the application for the target hardware and input. In this paper we address the problem of choosing the best mapping of sequential OpenACC loops to the parallel thread- space for a given program and input size. We show that auto-tuning on mapping parameters can improve performance by up to 4.8x over the default chosen by a state-of-the- art compiler. To reduce the overhead of auto-tuning we introduce a search technique that exploits similarities in be- haviour across inputs using a nearest neighbour approach. This dramatically reduces the search for a good mapping (by 97% compared to random search). Finally we propose a heuristic for stopping the focused search which, averaged across 12 benchmarks and 30 input sizes each, achieves a speedup over the default of 1.26x with only 8 sampling runs.

2009

1. A Comparison of Some Bottleneck-link Detection Methods for Network Tomography

   Nicholas Johnson, John Thompson, and F. Garcia

   In Proceedings Eurasip EUSIPCO Conference, Aug 2009

2008

1. Delay Estimation, Network Tomography amp; Bottleneck-link Detection

   Nicholas Johnson, J. S. Thompson, S. McLaughlin, and 1 more author

   In 1st IAPR Workshop on Cognitive Pattern Recognition, Aug 2008

2006

1. Towards control algorithms for distributed wireless networks

   Nicholas Johnson, S. McLaughlin, and J. S. Thompson

   In Proceedings of the 7th Annual Postgraduate Symposium (PGNET), Aug 2006