An experiment specification language for goal-driven, automated performance evaluations

Authors:
Dennis Westermann;Jens Happe;Roozbeh Farahbod
Affiliations:
SAP Research, Karlsruhe, Germany;SAP Research, Karlsruhe, Germany;SAP Research, Karlsruhe, Germany
Venue:
Proceedings of the 28th Annual ACM Symposium on Applied Computing
Year:
2013

Citing 11
Cited 0

Experiment management support for performance tuning

SC '97 Proceedings of the 1997 ACM/IEEE conference on Supercomputing
The Paradyn Parallel Performance Measurement Tool

Computer
ZOO: A Desktop Experiment Management Environment

VLDB '96 Proceedings of the 22th International Conference on Very Large Data Bases
Nimrod: a tool for performing parametrised simulations using distributed workstations

HPDC '95 Proceedings of the 4th IEEE International Symposium on High Performance Distributed Computing
High Performance Parametric Modeling with Nimrod/G: Killer Application for the Global Grid?

IPDPS '00 Proceedings of the 14th International Symposium on Parallel and Distributed Processing
ZENTURIO: a grid middleware-based tool for experiment management of parallel and distributed applications

Journal of Parallel and Distributed Computing - Special issue on middleware
SAP Performance Optimization Guide: Analyzing and Tuning SAP Systems

SAP Performance Optimization Guide: Analyzing and Tuning SAP Systems
ZEN: a directive based experiment specification language for performance and parameter studies of parallel scientific applications

International Journal of High Performance Computing and Networking
The Performance Cockpit Approach: A Framework For Systematic Performance Evaluations

SEAA '10 Proceedings of the 2010 36th EUROMICRO Conference on Software Engineering and Advanced Applications
An industrial case study on quality impact prediction for evolving service-oriented software

Proceedings of the 33rd International Conference on Software Engineering
Automated inference of goal-oriented performance prediction functions

Proceedings of the 27th IEEE/ACM International Conference on Automated Software Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

In performance engineering, experimentation is used to compare design alternatives, identify bottlenecks, or infer prediction functions. In many cases, performance analysts apply individual, unstructured approaches for the definition of experiments which hampers reusability, collaboration, and automation. In this paper, we introduce an experiment specification language that supports performance analysts in capturing all information required to implement a systematic performance evaluation process. The language design specifically aims at facilitating reusability, collaboration, and automation. The presented approach is applied in different scenarios at SAP development departments.