Profile driven dataflow optimisation of mean shift visual tracking

BHOWMIK, Deepayan, WALLACE, Andrew, STEWART, Robert, QIAN, Xinyuan and MICHAELSON, Greg (2015). Profile driven dataflow optimisation of mean shift visual tracking. In: Signal and Information Processing (GlobalSIP), 2014 IEEE Global Conference on. IEEE, 1-5.

[img]
Preview
PDF
Bhowmik - profile driven dataflow optimisation (AM).pdf - Accepted Version
All rights reserved.

Download (793kB) | Preview
Official URL: http://ieeexplore.ieee.org/document/7032066/
Link to published version:: https://doi.org/10.1109/GlobalSIP.2014.7032066

Abstract

Profile guided optimisation is a common technique used by compilers and runtime systems to shorten execution runtimes and to optimise locality aware scheduling and memory access on heterogeneous hardware platforms. Some profiling tools trace the execution of low level code, whilst others are designed for abstract models of computation to provide rich domain-specific context in profiling reports. We have implemented mean shift, a computer vision tracking algorithm, in the RVC-CAL dataflow language and use both dynamic runtime and static dataflow profiling mechanisms to identify and eliminate bottlenecks in our naive initial version. We use these profiling reports to tune the CPU scheduler reducing runtime by 88%, and to optimise our dataflow implementation that reduces runtime by a further 43% - an overall runtime reduction of 93%. We also assess the portability of our mean shift optimisations by trading off CPU runtime against resource utilisation on FPGAs. Applying all dataflow optimisations reduces FPGA design space significantly, requiring fewer slice LUTs and less block memory.

Item Type: Book Section
Additional Information: IEEE Global Conference on Signal and Information Processing (GlobalSIP) held 3-5 December 2014. INSPEC Accession Number: 14916605
Identification Number: https://doi.org/10.1109/GlobalSIP.2014.7032066
Page Range: 1-5
Depositing User: Deepayan Bhowmik
Date Deposited: 05 Jan 2017 12:51
Last Modified: 18 Mar 2021 16:04
URI: https://shura.shu.ac.uk/id/eprint/13808

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics