Proceedings of the 2018 ACM/SPEC International Conference

It is our great pleasure to welcome you to the 9th ACM/SPEC International Conference on Performance Engineering (ICPE 2018), being held in Berlin, Germany from April 9 to 13, 2018. The goal of the ACM/SPEC International Conference on Performance Engineering (ICPE) 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.

The call for contributions solicited submissions for several tracks, namely for research papers, industry/experience papers, work-in-progress/vision papers, artifacts (for accepted full papers), posters and demonstrations, tutorials, and workshops.

In the research track, 14 out of 59 papers were accepted as full papers. Hence, the full paper acceptance rate is 24 %. Two full papers received an ACM artifact badge after the subsequent review process in the newly introduced artifact evaluation track. Seven submissions were accepted as short research papers. In the industry/experience track, four out of 16 papers were accepted as full papers. Six submissions were accepted as short papers. The awards chairs selected three papers from the research track and two papers from the industry/experience track as candidates for the best paper award. The winner for both tracks will be announced during the banquet, after the candidates have presented their work during the conference. In the work-in-progress/vision track, ten out of 23 papers were accepted.

The technical program features the following three invited keynotes:

  • Peter Braam: Performance Engineering for the SKA Telescope
  • Michael R. Lyu: AI Techniques in Software Engineering Paradigm
  • Aad van Moorsel: Benchmarks and Models for Blockchain

In addition, the technical program includes three tutorials, the presentation of the SPEC Distinguished Dissertation Award, a poster and demonstration session, as well as six workshops on Performance Analysis of Big data Systems (PABS), Hot Topics in Cloud Computing Performance (HotCloudPerf), Challenges in Performance Methods for Software Development (WOSP-C), Load Testing and Benchmarking of Software Systems (LTB), Energy-aware Simulation and Modelling (ENERGY-SIM), and Quality-Aware DevOps (QUDOS).

The program covers traditional ICPE topics such as performance modeling, prediction, optimization, monitoring, profiling, load testing, benchmarking, and runtime adaptation for fields such as cloud and high performance computing, big data, energy, and enterprise applications.

General Chairs’ Welcome

Katinka Wolter, Freie Universität zu Berlin, Germany
William Knottenbelt, Imperial College London, UK

ICPE 2019 Program Chairs’ Welcome

André van Hoorn, Univ. of Stuttgart, Germany
Manoj Nambiar, Tata Consultancy Services, India
Heiko Koziolek, ABB, Germany

ICPE 2018 Conference Organization

ICPE 2018 Sponsors & Supporters

Table of contents

Keynote and Invited Talks

Performance Engineering for the SKA Telescope

Authors
Peter J. Braam
DOI
10.1145/3184407.3184439
Pages
1 – 1

AI Techniques in Software Engineering Paradigm

Authors
Michael R. Lyu
DOI
10.1145/3184407.3184440
Pages
2 – 2

Benchmarks and Models for Blockchain

Authors
Aad van Moorsel
DOI
10.1145/3184407.3184441
Pages
3 – 3

Runtime Adaptation

FOX: Cost-Awareness for Autonomic Resource Management in Public Clouds

Authors
Veronika Lesch
André Bauer
Nikolas Herbst
Samuel Kounev
DOI
10.1145/3184407.3184415
Pages
4 – 15

Adaptive Performance Optimization under Power Constraint in Multi-thread Applications with Diverse Scalability

Authors
Stefano Conoci
Pierangelo Di Sanzo
Bruno Ciciani
Francesco Quaglia
DOI
10.1145/3184407.3184419
Pages
16 – 27

Optimising Dynamic Binary Modification Across ARM Microarchitectures

Authors
Cosmin Gorgovan
Amanieu d’Antras
Mikel Luján
DOI
10.1145/3184407.3184425
Pages
28 – 39

TESS: Automated Performance Evaluation of Self-Healing and Self-Adaptive Distributed Software Systems

Authors
Jason Porter
Daniel A. Menascé
Hassan Gomaa
Emad Albassam
DOI
10.1145/3184407.3184408
Pages
40 – 47

To Adapt or Not to Adapt?: Technical Debt and Learning Driven Self-Adaptation for Managing Runtime Performance

Authors
Tao Chen
Rami Bahsoon
Shuo Wang
Xin Yao
DOI
10.1145/3184407.3184413
Pages
48 – 55

High Performance Computing

Involving CPUs into Multi-GPU Deep Learning

Authors
Tung D. Le
Taro Sekiyama
Yasushi Negishi
Haruki Imai
Kiyokuni Kawachiya
DOI
10.1145/3184407.3184424
Pages
56 – 67

Measuring Network Latency Variation Impacts to High Performance Computing Application Performance

Authors
Robert Underwood
Jason Anderson
Amy Apon
DOI
10.1145/3184407.3184427
Pages
68 – 79

Pattern-based Modeling of Multiresilience Solutions for High-Performance Computing

Authors
Rizwan A. Ashraf
Saurabh Hukerikar
Christian Engelmann
DOI
10.1145/3184407.3184421
Pages
80 – 87

Energy and Performance Analysis of Parallel Particle Solvers from the ScaFaCoS Library

Authors
Michael Hofmann
Robert Kiesel
Gudula Rünger
DOI
10.1145/3184407.3184409
Pages
88 – 95

Characterizing the Microarchitectural Implications of a Convolutional Neural Network (CNN) Execution on GPUs

Authors
Shi Dong
Xiang Gong
Yifan Sun
Trinayan Baruah
David Kaeli
DOI
10.1145/3184407.3184423
Pages
96 – 106

Monitoring and Profiling

Round-Trip Time Anomaly Detection

Authors
Daniel Brahneborg
Wasif Afzal
Adnan Čaušević
Daniel Sundmark
Mats Björkman
DOI
10.1145/3184407.3184436
Pages
107 – 114

User-defined Classification and Multi-level Grouping of Objects in Memory Monitoring

Authors
Markus Weninger
Hanspeter Mössenböck
DOI
10.1145/3184407.3184412
Pages
115 – 126

Log4Perf: Suggesting Logging Locations for Web-based Systems’ Performance Monitoring

Authors
Kundi Yao
Guilherme B. de Pádua
Weiyi Shang
Steve Sporea
Andrei Toma
Sarah Sajedi
DOI
10.1145/3184407.3184416
Pages
127 – 138

ODP: An Infrastructure for On-Demand Service Profiling

Authors
John Nicol
Chen Li
Peinan Chen
Tao Feng
Haricharan Ramachandra
DOI
10.1145/3184407.3184433
Pages
139 – 144

Cloud Computing

Virtualization Techniques Compared: Performance, Resource, and Power Usage Overheads in Clouds

Authors
Selome Kostentinos Tesfatsion
Cristian Klein
Johan Tordsson
DOI
10.1145/3184407.3184414
Pages
145 – 156

Investigating Performance Metrics for Scaling Microservices in CloudIoT-Environments

Authors
Manuel Gotin
Felix Lösch
Robert Heinrich
Ralf Reussner
DOI
10.1145/3184407.3184430
Pages
157 – 167

Evaluating Scalability and Performance of a Security Management Solution in Large Virtualized Environments

Authors
Lishan Yang
Ludmila Cherkasova
Rajeev Badgujar
Jack Blancaflor
Rahul Konde
Jason Mills
Evgenia Smirni
DOI
10.1145/3184407.3184435
Pages
168 – 175

Runtime Performance Management for Cloud Applications with Adaptive Controllers

Authors
Cornel Barna
Marin Litoiu
Marios Fokaefs
Mark Shtern
Joe Wigglesworth
DOI
10.1145/3184407.3184438
Pages
176 – 183

Rapid Testing of IaaS Resource Management Algorithms via Cloud Middleware Simulation

Authors
Christian Stier
Jörg Domaschka
Anne Koziolek
Sebastian Krach
Jakub Krzywda
Ralf Reussner
DOI
10.1145/3184407.3184428
Pages
184 – 191

Performance Prediction of Cloud-Based Big Data Applications

Authors
Danilo Ardagna
Enrico Barbierato
Athanasia Evangelinou
Eugenio Gianniti
Marco Gribaudo
Túlio B. M. Pinto
Anna Guimarães
Ana Paula Couto da Silva
Jussara M. Almeida
DOI
10.1145/3184407.3184420
Pages
192 – 199

Enterprise Applications

Generating Workload for ERP Applications through End-User Organization Categorization using High Level Business Operation Data

Authors
Gururaj Maddodi
Slinger Jansen
Rolf de Jong
DOI
10.1145/3184407.3184432
Pages
200 – 210

One Size Does Not Fit All: In-Test Workload Adaptation for Performance Testing of Enterprise Applications

Authors
Vanessa Ayala-Rivera
Maciej Kaczmarski
John Murphy
Amarendra Darisa
A. Omar Portillo-Dominguez
DOI
10.1145/3184407.3184418
Pages
211 – 222

Performance Improvement Barriers for SAP Enterprise Applications: An Analysis of Expert Interviews

Authors
Adrian Streitz
Maximilian Barnert
Harald Kienegger
Helmut Krcmar
DOI
10.1145/3184407.3184434
Pages
223 – 228

Modeling, Prediction, and Optimization

Joint Data Compression and Caching: Approaching Optimality with Guarantees

Authors
Jian Li
Faheem Zafari
Don Towsley
Kin K. Leung
Ananthram Swami
DOI
10.1145/3184407.3184410
Pages
229 – 240

Choice of Aggregation Groups for Layered Performance Model Simplification

Authors
Farhana Islam
Dorina Petriu
Murray Woodside
DOI
10.1145/3184407.3184411
Pages
241 – 252

Optimizing Energy-Performance Trade-Offs in Solar-Powered Edge Devices

Authors
Peter G. Harrison
Naresh M. Patel
DOI
10.1145/3184407.3184426
Pages
253 – 260

Load Testing and Benchmarking

A Declarative Approach for Performance Tests Execution in Continuous Software Development Environments

Authors
Vincenzo Ferme
Cesare Pautasso
DOI
10.1145/3184407.3184417
Pages
261 – 272

quiho: Automated Performance Regression Testing Using Inferred Resource Utilization Profiles

Authors
Ivo Jimenez
Noah Watkins
Michael Sevilla
Jay Lofstead
Carlos Maltzahn
DOI
10.1145/3184407.3184422
Pages
273 – 284

Characterizing the Performance of Concurrent Virtualized Network Functions with OVS-DPDK, FD.IO VPP and SR-IOV

Authors
Nikolai Pitaev
Matthias Falkner
Aris Leivadeas
Ioannis Lambadaris
DOI
10.1145/3184407.3184437
Pages
285 – 292

Methods for Quantifying Energy Consumption in TPC-H

Authors
Meikel Poess
Da Qi Ren
Tilmann Rabl
Hans-Arno Jacobsen
DOI
10.1145/3184407.3184429
Pages
293 – 304

Using the Raspberry Pi and Docker for Replicable Performance Experiments: Experience Paper

Authors
Holger Knoche
Holger Eichelberger
DOI
10.1145/3184407.3184431
Pages
305 – 316