News

Workshop Program online

Call for Papers

Download CFP as TXT file

Important Dates

Papers due: 22 May 2015
5 June 2015 AOE
Notification: 30 June 2015
Workshop Date: 25 Aug 2015

Links

Euro-Par 2015
REPPAR 2014

Workshop Program

Workshop Date: 25 August 2015
Place: Lecture Room EI 5 (1040 Wien, Gußhausstraße 25) (area map)

Time Talk
9:00 - 9:15 Workshop Introduction and Survey Announcement
Session chair: Sascha Hunold
9:15 - 10:30 Keynote 1: Walid Dabbous
Title: Realistic and Reproducible Wireless Networking Experiments
10:30 - 11:00 Coffee break
11:00 - 12:30 Paper session
Session chair: Mark Stillwell
  1. Reproducible and User-Controlled Software Environments in HPC with Guix
    Ludovic Courtès and Ricardo Wurmus
  2. Reproducibility in Practice: Lessons learned from Research and Teaching Experiments
    Antonio Maffia, Helmar Burkhart and Danilo Guerrera
  3. Towards Complete Tracking of Provenance in Experimental Distributed Systems Research
    Tomasz Buchert, Lucas Nussbaum and Jens Gustedt
12:30 - 14:00 Lunch Break
14:00 - 14:45 Keynote 2: Gerhard Wellein
Title: Some Obstacles on the Way to Reproducibility of Performance Measurements - Tales from the Trenches
14:45 - 16:00 Mini-Tutorials on Tools and Methods to Support Reproducible Research
Session chair: Arnaud Legrand
  • Arnaud Legrand: Effective Data Visualization/Presentation with R/ggplot2
  • Lucas Nussbaum: Testbeds for Reproducible Research
  • Mark Stillwell: Data Analysis with Jupyter
  • Sascha Hunold: Measurement Bias introduced by MPI_Barrier
16:00 - 16:30 Coffee Break
16:30 - 18:00 Survey Evaluation and Open Discussion on the State of Reproducibility in Parallel Computing and the Future of REPPAR
Session chair: Lucas Nussbaum

Walid Dabbous

Title: Realistic and Reproducible Wireless Networking Experiments

Abstract

Scientific evaluation of network protocols requires that experiment results must be reproducible before they can be considered as valid. This is particularly difficult to obtain in the wireless networking domain, where characteristics of wireless channels are known to be variable, unpredictable and hardly controllable. Indeed, anechoic chambers with RF absorbers preventing radio waves reflections and with Faraday cage blocking external interferences represent a ideal environment for experiments reproducibility. However, even if noise and interferences represent unwanted signals, they are unavoidable in real testbeds. It is therefore important to augment the realism of anechoic chamber settings by injecting noise and interfering signals in a controllable way. In this talk we will analyse the difficulties to run reproducible wireless networking experiments in indoor/outdoor environments and describe FIT-R2LAB (Reproducible Research Lab), an anechoic chamber to run realistic and reproducible wireless experiments located at Inria Sophia Antipolis.

Gerhard Wellein

Title: Some Obstacles on the Way to Reproducibility of Performance Measurements - Tales from the Trenches

Abstract

Reproducing external performance results or own performance measurements over time is often a big challenge. Even if using the same application code small changes in the deep system software stack (including OS, compiler, BIOS etc) and the dynamic behaviour of modern hardware with its increasing complexity can introduce large measurement changes. This talk will discuss some of these obstacles on modern HPC systems. It will further demonstrate that performance modelling can substantially foster performance reproducibility by providing a clear understanding of the interaction between the application code and the hardware.