Edinburgh Research Explorer

MaxPair: Enhance OpenCL Concurrent Kernel Execution by Weighted Maximum Matching

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

https://dl.acm.org/citation.cfm?id=3180272
Original languageEnglish
Title of host publicationProceedings of the 11th Workshop on General Purpose GPUs
Place of PublicationNew York, NY, USA
PublisherACM
Pages40-49
Number of pages10
ISBN (Print)978-1-4503-5647-3
DOIs
Publication statusPublished - 24 Feb 2018
Event11th Workshop on General Purpose GPUs - Vienna, Austria
Duration: 24 Feb 201828 Feb 2018
https://ppopp18.sigplan.org/track/GPGPU-2018-papers

Publication series

NameGPGPU-11
PublisherACM

Workshop

Workshop11th Workshop on General Purpose GPUs
Abbreviated titleGPGPU-11
CountryAustria
CityVienna
Period24/02/1828/02/18
Internet address

Abstract

Executing multiple OpenCL kernels on the same GPU concurrently
is a promising method for improving hardware utilisation and
system performance. Schemes of scheduling impact the resulting
performance significantly by selecting different kernels to run together on the same GPU. Existing approaches use either execution time or relative speedup of kernels as a guide to group and map them to the device. However, these simple methods work on the cost of providing suboptimal performance.
In this paper, we propose a graph-based algorithm to schedule
co-run kernel in pairs to optimise the system performance. Target
workloads are represented by a graph, in which vertices stand for distinct kernels while edges between two vertices represent the corresponding two kernels co-execution can deliver a better
performance than run them one after another. Edges are weighted
to provide information of performance gain from co-execution. Our algorithm works in the way of finding out the maximum weighted matching of the graph. By maximising the accumulated weights, our algorithm improves performance significantly
comparing to other approaches.

    Research areas

  • Concurrent Kernels, GPGPU, Scheduling

Event

11th Workshop on General Purpose GPUs

24/02/1828/02/18

Vienna, Austria

Event: Workshop

Download statistics

No data available

ID: 57092603