ESL Black Box Power Estimation: Automatic Calibration for IEEE UPF 3.0 Power Models

Authors:
Gereon Onnebrink, Rainer Leupers, and Gerd Ascheid
Book Title:
Proceedings of the 2018 Workshop on Rapid Simulation and Performance Evaluation: Methods and Tools
Address:
Manchester, England
Date:
Jan. 2018
Language:
English

BibTeX

@inproceedings{onnebrink-rapido-2018,
author = {Gereon Onnebrink, Rainer Leupers, and Gerd Ascheid},
booktitle = {Proceedings of the 2018 Workshop on Rapid Simulation and Performance Evaluation: Methods and Tools},
title = {ESL Black Box Power Estimation: Automatic Calibration for IEEE UPF 3.0 Power Models},
year = {2018},
month = {jan},
address = {Manchester, England},
}

Abstract

Power-aware design space exploration at early electronic system level (ESL) is highly facilitated by virtual platforms. In order to define and exchange power models, the IEEE standard 1801-2015 UPF has been defined to allow developers, vendors and customers seamless usage of the same power models. However, one obstacle is still not covered by the standard: it is not specified and solved how to construct the model in the first place. This paper offers a solution to close this gap. A well proven semi-automatic black box ESL power estimation methodology, which allows to have power estimates with approximately 5 % error, is combined with UPF. Although the standard is based on power state machines and requires another tracing method, a procedure is presented to overcome these differences. Representative case studies show that similar estimation accuracy can be achieved.

Download

No download found.

News >> News >> News

ICE spin-off Silexica raises $18m in Series B funding

Investment will fund the further development of a Simulation Platform for software developers in

Best Paper Award at RAPIDO’18

The Paper titled "ESL Black Box Power Estimation: Automatic Calibration for IEEE UPF 3.0 Power

Miguel Angel Aguilar wins the ICT Young Researcher Award 2017

The profile area "Information and Communication Technology (ICT)" at RWTH Aachen

User login

Login

Forgot your password?