Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A Generalized Software System for Accurate and Efficient Management of Application Performance Goals

Hoffmann, Henry ; Maggio, Martina LU ; Santambrogio, Marco Domenico ; Leva, Alberto and Agarwal, Anant (2013) International Conference on Embedded Software (EMSOFT 2013)
Abstract
A number of techniques have been proposed to provide run- time performance guarantees while minimizing power consumption. One drawback of existing approaches is that they work only on a fixed set of components (or actuators) that must be specified at design time. If new components become available, these management systems must be redesigned and reimplemented. In this paper, we propose PTRADE, a novel performance management framework that is general with respect to the components it manages. PTRADE can be deployed to work on a new system with different components without redesign and reimplementation. PTRADE’s generality is demonstrated through the management of performance goals for a variety of benchmarks on two different Linux/x86... (More)
A number of techniques have been proposed to provide run- time performance guarantees while minimizing power consumption. One drawback of existing approaches is that they work only on a fixed set of components (or actuators) that must be specified at design time. If new components become available, these management systems must be redesigned and reimplemented. In this paper, we propose PTRADE, a novel performance management framework that is general with respect to the components it manages. PTRADE can be deployed to work on a new system with different components without redesign and reimplementation. PTRADE’s generality is demonstrated through the management of performance goals for a variety of benchmarks on two different Linux/x86 systems and a simulated 128-core system, each with different components governing power and performance tradeoffs. Our experimental results show that PTRADE provides generality while meeting performance goals and ap- proaching optimal power consumption. PTRADE consumes only 7% more power than optimal on the Linux/x86 systems and 3% more power than optimal on the simulated many-core. (Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to conference
publication status
in press
subject
conference name
International Conference on Embedded Software (EMSOFT 2013)
conference location
Montréal, Canada
conference dates
2013-09-29 - 2013-10-04
language
English
LU publication?
yes
id
449bc910-7212-483d-9d6a-6a3923084c59 (old id 4019328)
date added to LUP
2016-04-04 13:57:31
date last changed
2019-04-30 20:36:04
@misc{449bc910-7212-483d-9d6a-6a3923084c59,
  abstract     = {{A number of techniques have been proposed to provide run- time performance guarantees while minimizing power consumption. One drawback of existing approaches is that they work only on a fixed set of components (or actuators) that must be specified at design time. If new components become available, these management systems must be redesigned and reimplemented. In this paper, we propose PTRADE, a novel performance management framework that is general with respect to the components it manages. PTRADE can be deployed to work on a new system with different components without redesign and reimplementation. PTRADE’s generality is demonstrated through the management of performance goals for a variety of benchmarks on two different Linux/x86 systems and a simulated 128-core system, each with different components governing power and performance tradeoffs. Our experimental results show that PTRADE provides generality while meeting performance goals and ap- proaching optimal power consumption. PTRADE consumes only 7% more power than optimal on the Linux/x86 systems and 3% more power than optimal on the simulated many-core.}},
  author       = {{Hoffmann, Henry and Maggio, Martina and Santambrogio, Marco Domenico and Leva, Alberto and Agarwal, Anant}},
  language     = {{eng}},
  title        = {{A Generalized Software System for Accurate and Efficient Management of Application Performance Goals}},
  year         = {{2013}},
}