Authors: Preeti N. Jain; Dinesh Kumar Gautam; Sunil K. Surve
Addresses: Department of Electronics Engineering, Fr. Conceicao Rodrigues College of Engineering, Bandra, Mumbai, India ' Department of Chemical Engineering, Indian Institute of Technology, Guwahati, Assam, India ' Department of Computer Engineering, Fr. Conceicao Rodrigues College of Engineering, Bandra, Mumbai, India
Abstract: The need to meet the high computing demands under constraints of power, low latency, inter-process interference, etc. has led to a shift in the paradigm from uniprocessor systems to multicore systems. The challenge in these multicore systems arises from the fact that these cores are not independent in functioning, rather they share few on-chip and off-chip resources. This resource sharing also affects performance due to cross-core interference. Different workloads running on these cores demand different resources for their growth in performance. In this work we examine the contention due to resource sharing amongst co-runners using the adapted multi-species Tilman model. Thereafter, alternative solutions like application scheduling and resource partitioning are simulated using the built model. Based on the simulation results a comparison between solo and co-running systems for different applications under both the solution regimes is conducted at various resource levels. The observed phenomenon can be used for prior study or prediction of performance of applications when co-run to mitigate contention due to shared resources.
Keywords: multi-core; constrained resources; Tilman model; competition; LLC; bandwidth utilisation; scheduling; resource segregation.
International Journal of High Performance Computing and Networking, 2019 Vol.15 No.3/4, pp.210 - 222
Received: 06 Apr 2019
Accepted: 29 Aug 2019
Published online: 18 Mar 2020 *