Energy-efficient mapping of biomedical applications on domain-specific accelerator under process variation

Abstract:

The variability of deep-submicron technologies creates systems 
with asymmetric cores from a frequency and leakage power viewpoint, 
which makes an opportunity for performance-power optimization. In particular, 
process variation can transform a homogeneous many-core platform into a 
heterogeneous system where the task mapping is NP-hard problem. In this paper, we 
propose a mapping algorithm that selects the appropriate task mapping along with 
voltage and frequency assignment for a cluster of cores. The mapping algorithm, 
which is based on simulated annealing, determines cluster voltages and core 
frequencies to minimize energy consumption and EDP under process variation. We 
examine the effectiveness of our proposed algorithm on a fully placed and routed 
128-core biomedical accelerator in 45 nm when running various applications including 
compressive sensing, seizure detection and ultrasound spectral Doppler and linear 
regression. The results indicate that exposing frequency and power variation to the 
mapping algorithm results in up to 22% (on average 11%) energy saving and 31% (on 
average19%) EDP improvement.

Paper

• ACM DIgital Library Link,  

Reference

Mohammad Khavari Tavana, Amey Kulkarni, Abbas Rahimi, Tinoosh Mohsenin, and Houman Homayoun. 2014. Energy-efficient mapping of biomedical applications on domain-specific accelerator under process variation. In Proceedings of the 2014 international symposium on Low power electronics and design (ISLPED '14). ACM, New York, NY, USA, 275-278.

BibTeX Entry

@inproceedings{KhavariTavana:2014:EMB:2627369.2627654,
 author = {Khavari Tavana, Mohammad and Kulkarni, Amey and Rahimi, Abbas and Mohsenin, Tinoosh and Homayoun, Houman},
 title = {Energy-efficient Mapping of Biomedical Applications on Domain-specific Accelerator Under Process Variation},
 booktitle = {Proceedings of the 2014 International Symposium on Low Power Electronics and Design},
 series = {ISLPED '14},
 year = {2014},
 isbn = {978-1-4503-2975-0},
 location = {La Jolla, California, USA},
 pages = {275--278},
 numpages = {4},
 url = {http://doi.acm.org/10.1145/2627369.2627654},
 doi = {10.1145/2627369.2627654},
 acmid = {2627654},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {accelerator, energy efficiency, many-core systems, mapping, process variation},
}