@inproceedings{7d3b44f55ed44cabb661bd330b2dfbfc,
title = "Low-power heterogeneous computing via adaptive execution of dataflow actors",
abstract = "Dataflow models of computation have been shown to provide an excellent basis for describing signal processing applications and mapping them to heterogeneous computing platforms that consist of multicore CPUs and graphics processing units (GPUs). Recently several efficient dataflow-based programming frameworks have been introduced for such needs. Most of contemporary signal processing applications can be described using static dataflow models of computation (e.g. synchronous dataflow) that have desirable features such as compile-time analyzability. Unfortunately, static dataflow models of computation turn out to be restrictive when applications need to adapt their behavior to varying conditions at run-time, such as power saving through adaptive processing. This paper analyzes three dataflow approaches for implementing adaptive application behavior in terms of expressiveness and efficiency. The focus of the paper is on heterogeneous computing platforms and particularly on adapting application processing for achieving power saving. Experiments are conducted with deep neural network and dynamic predistortion applications on two platforms: a mobile multicore SoC and a GPU-equipped workstation.",
keywords = "data flow computing, graphics processing units, multiprocessing systems, neural nets, power aware computing, program compilers, system-on-chip, GPU-equipped workstation, adaptive application behavior, adaptive execution, adaptive processing, application processing, compile-time analyzability, contemporary signal processing applications, dataflow actors, dataflow-based programming frameworks, dynamic predistortion applications, heterogeneous computing platforms, low-power heterogeneous computing, mobile multicore SoC, power saving, static dataflow models, Adaptation models, Computational modeling, Graphics processing units, Motion detection, Ports (Computers), Programming, Surveillance, Dataflow computing, deep neural networks, parallel processing, signal processing",
author = "Jani Boutellier and Bhattacharyya, {Shuvra S.}",
note = "jufoid=70581 ; IEEE International Workshop on Signal Processing Systems ; Conference date: 01-01-1900",
year = "2017",
month = nov,
day = "16",
doi = "10.1109/SiPS.2017.8110002",
language = "English",
publisher = "IEEE",
booktitle = "2017 IEEE International Workshop on Signal Processing Systems (SiPS)",
address = "United States",
}