O
Oliver Perks
Researcher at University of Warwick
Publications - 13
Citations - 91
Oliver Perks is an academic researcher from University of Warwick. The author has contributed to research in topics: Memory management & Uniform memory access. The author has an hindex of 6, co-authored 13 publications receiving 79 citations.
Papers
More filters
Proceedings ArticleDOI
Achieving portability and performance through OpenACC
TL;DR: This paper experimentally evaluates the currently available compilers by assessing two approaches to the OpenACC programming model: the "parallel" and "kernels" constructs, showing performance differences of up to 84%.
Journal ArticleDOI
Patterns for High Performance Multiscale Computing
Saad Alowayyed,Saad Alowayyed,Tomasz Piontek,James L. Suter,O. Hoenen,Derek Groen,Derek Groen,O. O. Luk,Bartosz Bosak,Piotr Kopta,Krzysztof Kurowski,Oliver Perks,Keeran Brabazon,Vytautas Jancauskas,D. P. Coster,Peter V. Coveney,Alfons G. Hoekstra,Alfons G. Hoekstra +17 more
TL;DR: The main purpose of the Multiscale Computing Patterns software is to simplify and automate the execution of complex multiscale simulations on high performance computers, and to provide both application-specific and pattern-specific performance optimisation.
Optimising Hydrodynamics applications for the Cray XC30 with the application tool suite
Wayne Gaudin,A. C. Mallinson,Oliver Perks,J. A. Herdman,David Beckingsale,J. M. Levesque,M. Boulton,Simon McIntosh-Smith,Stephen A. Jarvis +8 more
TL;DR: This work examines different strategies for improving the strong-scaling performance of explicit Hydrodynamics applications and evaluates Cray Reveal as a tool for automatically hybridising HPC applications and Cray’s MPI rank to network topology-mapping tools for improving application performance.
WMTrace - A Lightweight Memory Allocation Tracker and Analysis Framework
TL;DR: WMTrace, a lightweight tool to trace and analyse memory allocation events in parallel applications able to dynamically link to pre-existing application binaries requiring no source code modification or recompilation is presented.
Journal ArticleDOI
Towards Automated Memory Model Generation Via Event Tracing
Oliver Perks,David Beckingsale,Simon D. Hammond,I. Miller,J. A. Herdman,A. Vadgama,Abhir Bhalerao,Ligang He,Stephen A. Jarvis +8 more
TL;DR: WMTools is presented, a lightweight memory tracing tool and analysis framework for parallel codes, which is able to identify peak memory usage and also analyse per-function memory use over time and is ableto predict memory consumption with under 7% error.