Proceedings of the 3rd ACM/SPEC International Conference

It is our great pleasure to welcome you to the Third ACM/SPEC International Conference on Performance Engineering (ICPE 2012). The primary goal of the conference is to integrate theory and practice in the field of performance engineering by providing a forum for sharing ideas and experiences between industry and academia. This year's conference brings together researchers and industry practitioners to share and present their experiences, discuss challenges, and report on both state-of-the-art research and work-in-progress on performance engineering of software and systems, including performance measurement, modeling, benchmark design, and run-time performance management. ICPE gives researchers and practitioners a unique opportunity to share their perspectives with others interested in the various aspects of computer systems performance engineering.

The calls for papers attracted 66 paper submissions across three different tracks namely, research, industry, and work-in-progress/vision. Papers were submitted from Asia, Australia, Europe, North America and South America. Each paper went through a rigorous peer review process involving at least 3 and in most cases 4 program committee members. The program committee accepted 19 full research papers, 2 short research papers, 2 industrial papers, and 10 work-in-progress/vision papers. These papers cover a variety of topics, including performance modeling, performance and software development processes, benchmarking, energy efficiency, and performance evaluation of cloud and adaptive systems. The program is further enriched with 3 tutorials, 2 presentations from SPEC Distinguished Dissertation Award Winners, and 9 poster/demo exhibitions.

In addition to the paper presentations, the conference offers two keynote speakers of international prestige:

  • William H. Sanders, Professor, University of Illinois at Urbana-Champaign (USA), presenting "Assuring the Trustworthiness of the Smarter Electric Grid"
  • Amnon Naamad, Senior Director of Innovation, EMC (USA), presenting "New Challenges in Performance Engineering"

Altogether there are 33 peer-reviewed papers that have been selected from high quality submissions for presentation at this year's conference in Boston. We are confident that you will find the program stimulating and that it will provide you with many new ideas and insights.

General Chairs' Welcome

David Kaeli, Northeastern University, USA
Jerry Rolia, HP Labs, USA

ICPE 2012 Program Chairs' Welcome

Lizy Kurian John, UT Austin, USA
Diwakar Krishnamurthy, University of Calgary, Canada

ICPE 2012 Conference Organization

ICPE 2012 Sponsors & Supporters

Table of contents

Tutorial 1

Best practices for writing and managing performance requirements: a tutorial

Authors
André B. Bondi
DOI
10.1145/2188286.2188288
Pages
1 -- 8

Tutorial 2

Introduction to queueing petri nets: modeling formalism, tool support and case studies

Authors
Samuel Kounev
Simon Spinner
Philipp Meier
DOI
10.1145/2188286.2188290
Pages
9 -- 18

Keynote address 1

Session details: Keynote address 1

Authors
Jerry Rolia
DOI
10.1145/3248141
Pages
19 --

Assuring the trustworthiness of the smarter electric grid

Authors
William H. Sanders
DOI
10.1145/2188286.2188292
Pages
19 -- 20

Performance prediction techniques for software and systems

On the accuracy of cache sharing models

Authors
Vlastimil Babka
Peter Libič
Tomáš Martinec
Petr Tůma
DOI
10.1145/2188286.2188294
Pages
21 -- 32

Systematic adoption of genetic programming for deriving software performance curves

Authors
Michael Faber
Jens Happe
DOI
10.1145/2188286.2188295
Pages
33 -- 44

Fluid limits of queueing networks with batches

Authors
Luca Bortolussi
Mirco Tribastone
DOI
10.1145/2188286.2188296
Pages
45 -- 56

An approximate solution for Ph/Ph/1 and Ph/Ph/1/N queues

Authors
Alexandre Brandwajn
Thomas Begin
DOI
10.1145/2188286.2188297
Pages
57 -- 62

Performance modeling and evaluation of adaptive

A class of tractable models for run-time performance evaluation

Authors
Giuliano Casale
Peter Harrison
DOI
10.1145/2188286.2188299
Pages
63 -- 74

Analysis of bursty workload-aware self-adaptive systems

Authors
Diego Perez-Palacin
José Merseguer
Raffaela Mirandola
DOI
10.1145/2188286.2188300
Pages
75 -- 84

How a consumer can measure elasticity for cloud platforms

Authors
Sadeka Islam
Kevin Lee
Alan Fekete
Anna Liu
DOI
10.1145/2188286.2188301
Pages
85 -- 96

Statistical detection of QoS violations based on CUSUM control charts

Authors
Ayman Amin
Alan Colman
Lars Grunske
DOI
10.1145/2188286.2188302
Pages
97 -- 108

Performance and software development processes

User-friendly approach for handling performance parameters during predictive software performance engineering

Authors
Rasha Tawhid
Dorina Petriu
DOI
10.1145/2188286.2188304
Pages
109 -- 120

Architecture-level reliability prediction of concurrent systems

Authors
Leslie Cheung
Ivo Krka
Leana Golubchik
Nenad Medvidovic
DOI
10.1145/2188286.2188305
Pages
121 -- 132

Performance and energy efficiency

The implementation of the server efficiency rating tool

Authors
Klaus-Dieter Lange
Mike G. Tricker
Jeremy A. Arnold
Hansfried Block
Christian Koopmann
DOI
10.1145/2188286.2188307
Pages
133 -- 144

Busy bee: how to use traffic information for better scheduling of background tasks

Authors
Feng Yan
Alma Riska
Evgenia Smirni
DOI
10.1145/2188286.2188308
Pages
145 -- 156

Towards efficient supercomputing: searching for the right efficiency metric

Authors
Chung-Hsing Hsu
Jeffery A. Kuehn
Stephen W. Poole
DOI
10.1145/2188286.2188309
Pages
157 -- 162

Keynote address 2

Session details: Keynote address 2

Authors
David Kaeli
DOI
10.1145/3248142
Pages
163 --

New challenges in performance engineering

Authors
Amnon Naamad
DOI
10.1145/2188286.2188311
Pages
163 -- 164

Benchmarking

Workload generation for microprocessor performance evaluation: SPEC PhD award (invited abstract)

Authors
Luk Van Ertvelde
Lieven Eeckhout
DOI
10.1145/2188286.2188313
Pages
165 -- 166

Performance evaluation and benchmarking of event-based systems: SPEC distinguished dissertation award 2011 (invited abstract)

Authors
Kai Sachs
DOI
10.1145/2188286.2188314
Pages
167 -- 168

Efficient update data generation for DBMS benchmarks

Authors
Michael Frank
Meikel Poess
Tilmann Rabl
DOI
10.1145/2188286.2188315
Pages
169 -- 180

Studying hardware and software trade-offs for a real-life web 2.0 workload

Authors
Stijn Polfliet
Frederick Ryckbosch
Lieven Eeckhout
DOI
10.1145/2188286.2188316
Pages
181 -- 192

Benchmarking decentralized monitoring mechanisms in peer-to-peer systems

Authors
Dominik Stingl
Christian Gross
Karsten Saller
Sebastian Kaune
Ralf Steinmetz
DOI
10.1145/2188286.2188317
Pages
193 -- 204

Performance modeling of software and systems

An industrial case study of performance and cost design space exploration

Authors
Thijmen de Gooijer
Anton Jansen
Heiko Koziolek
Anne Koziolek
DOI
10.1145/2188286.2188319
Pages
205 -- 216

Using computer simulation to predict the performance of multithreaded programs

Authors
Alexander Tarvo
Steven P. Reiss
DOI
10.1145/2188286.2188320
Pages
217 -- 228

Parallel file system measurement and modeling using colored petri nets

Authors
Hai Quang Nguyen
Amy Apon
DOI
10.1145/2188286.2188321
Pages
229 -- 240

Poster preview presentations

Apache hadoop performance-tuning methodologies and best practices

Authors
Shrinivas B. Joshi
DOI
10.1145/2188286.2188323
Pages
241 -- 242

Find your best match: predicting performance of consolidated workloads

Authors
Danilo Ansaloni
Lydia Y. Chen
Evgenia Smirni
Akira Yokokawa
Walter Binder
DOI
10.1145/2188286.2188324
Pages
243 -- 244

Importing PMIF models into PIPE2 using M2M transformation

Authors
Pere Bonet
Catalina M. Lladó
DOI
10.1145/2188286.2188325
Pages
245 -- 246

Kieker: a framework for application performance monitoring and dynamic software analysis

Authors
André van Hoorn
Jan Waller
Wilhelm Hasselbring
DOI
10.1145/2188286.2188326
Pages
247 -- 248

SPEC: driving better benchmarks

Authors
Walter Bays
Klaus-Dieter Lange
DOI
10.1145/2188286.2188327
Pages
249 -- 250

SPECvirt_sc2010 - driving virtualization innovation

Authors
Klaus-Dieter Lange
David Schmidt
Andrew Bond
Lisa Roderick
DOI
10.1145/2188286.2188328
Pages
251 -- 252

SPECpower_ssj2008: driving server energy efficiency

Authors
Klaus-Dieter Lange
Mike G. Tricker
Jeremy A. Arnold
Hansfried Block
Sanjay Sharma
DOI
10.1145/2188286.2188329
Pages
253 -- 254

Server efficiency rating tool (SERT)

Authors
Klaus-Dieter Lange
Mike G. Tricker
Jeremy A. Arnold
Hansfried Block
Sanjay Sharma
DOI
10.1145/2188286.2188330
Pages
255 -- 256

SPEC: enabling efficiency measurement

Authors
Karl Huppler
Klaus-Dieter Lange
John Beckett
DOI
10.1145/2188286.2188331
Pages
257 -- 258

Work-in-progress/vision track

Understanding performance modeling for modular mobile-cloud applications

Authors
Ioana Giurgiu
DOI
10.1145/2188286.2188333
Pages
259 -- 262

Is your cloud elastic enough?: performance modelling the elasticity of infrastructure as a service (IaaS) cloud applications

Authors
Paul C. Brebner
DOI
10.1145/2188286.2188334
Pages
263 -- 266

Clock driven programming: a programming paradigm which enables machine-independent performance design

Authors
Kenjiro Yamanaka
DOI
10.1145/2188286.2188335
Pages
267 -- 270

A performance modeling "blending" approach for early life-cycle risk mitigation

Authors
Paul C. Brebner
DOI
10.1145/2188286.2188336
Pages
271 -- 274

Compositional performance abstractions of software connectors

Authors
Misha Strittmatter
Lucia Kapova Happe
DOI
10.1145/2188286.2188337
Pages
275 -- 278

Efficiency improvements for solving layered queueing networks

Authors
Greg Franks
Lianhua Li
DOI
10.1145/2188286.2188338
Pages
279 -- 282

Integrating software performance curves with the palladio component model

Authors
Alexander Wert
Jens Happe
Dennis Westermann
DOI
10.1145/2188286.2188339
Pages
283 -- 286

SPECjbb2012: updated metrics for a business benchmark

Authors
Aleksey Shipilev
David Keenan
DOI
10.1145/2188286.2188340
Pages
287 -- 290

OpenCL and the 13 dwarfs: a work in progress

Authors
Wu-chun Feng
Heshan Lin
Thomas Scogland
Jing Zhang
DOI
10.1145/2188286.2188341
Pages
291 -- 294

Automatic NUMA characterization using Cbench

Authors
Ryan K. Braithwaite
Wu-chun Feng
Patrick S. McCormick
DOI
10.1145/2188286.2188342
Pages
295 -- 298

Performance measurement and experimental analysis

Automated detection of performance regressions using statistical process control techniques

Authors
Thanh H.D. Nguyen
Bram Adams
Zhen Ming Jiang
Ahmed E. Hassan
Mohamed Nasser
Parminder Flora
DOI
10.1145/2188286.2188344
Pages
299 -- 310

Capturing performance assumptions using stochastic performance logic

Authors
Lubomír Bulej
Tomáš Bureš
Jaroslav Keznikl
Alena Koubková
Andrej Podzimek
Petr Tůma
DOI
10.1145/2188286.2188345
Pages
311 -- 322

Refactoring access control policies for performance improvement

Authors
Donia El Kateb
Tejeddine Mouelhi
Yves Le Traon
JeeHyun Hwang
Tao Xie
DOI
10.1145/2188286.2188346
Pages
323 -- 334

Hirundo: a mechanism for automated production of optimized data stream graphs

Authors
Miyuru Dayarathna
Toyotaro Suzumura
DOI
10.1145/2188286.2188347
Pages
335 -- 346