"This site requires JavaScript to work correctly"
minimize Header

Prof. Dr. Peter Faber

  • High Performance Computing (HPC)
  • (Parallel) programming
  • General-purpose graphics programming GPGPU
  • Elearning
  • Software engineering

Faculty of Computer Science

Professors

Professor

  • Study program counsel: Master HPC/QC, Master Applied Computer Science
  • Study program coordination: Master Applied Computer Science
  • Examination board (head): PK I/II/III of the Faculty of Computer Science
  • Elearning mentor

DEGG's 2.18

0991/3615-509

consulting time

See http://officehours.peterfaber.net

Sortierung:
Contribution
  • Peter Faber
  • M. Griebl
  • C. Lengauer

A Closer Look at Loop-Carried Code Replacement.

In: Proc. GI/ITG PARS’01. (PARS-Mitteilungen Nr.18) pg. 109-118

Gesellschaft für Informatik e.V

  • (2001)
Contribution
  • Peter Faber
  • M. Griebl
  • C. Lengauer

Loop-Carried Code Placement.

In: Euro-Par 2001. (LNCS 2150) pg. 340-348

  • Eds.:
  • L. Freeman
  • J. Gurd
  • J. Keane
  • R. Sakellariou

SV

  • (2001)
Contribution
  • Peter Faber
  • M. Griebl
  • C. Lengauer

Replicated Placements in the Polyhedron Model.

In: Euro-Par 2003: Parallel Processing. (Lecture Notes in Computer Science 2790) pg. 303-308

  • Eds.:
  • H. Kosch
  • H. Hellwagner
  • L. Böszörményi

Springer-Verlag

  • (2003)
Contribution
  • Peter Faber
  • M. Griebl
  • C. Lengauer

Polyhedral Loop Parallelization: The Fine Grain.

In: Proceedings of the 11th Workshop on Compilers for Parallel Computers (CPC 2004). (Research Report Series) pg. 25-36

  • Eds.:
  • E. Kereku
  • M. Gerndt

LRR-TUM, Technische Universität München

  • (2004)
Journal article
  • M. Griebl
  • Peter Faber
  • C. Lengauer

Space-time mapping and tiling: a helpful combination.

In: Concurrency and Computation: Practice and Experience vol. 16 pg. 221-246

  • (2004)

DOI: 10.1002/cpe.772

show abstract

Tiling is a well‐known technique for sequential compiler optimization, as well as for automatic program parallelization. However, in the context of parallelization, tiling should not be considered as a stand‐alone technique, but should be applied after a dedicated parallelization phase, in our case after space–time mapping. We show how tiling can benefit from space–time mapping, and we derive an algorithm for computing tiles which can minimize the number of communication startups, taking the number of physically available processors into account. We also present how the use of a simple cost model reduces real execution time.
Thesis
  • Peter Faber

Code Optimization in the Polyhedron Model ‐ Improving the Efficiency of Parallel Loop Nests.

Universität Passau

  • 2007 (2007)

Journal article
  • Peter Faber
  • Sebastian Och
  • M. Schlott

Virtuelles Guckloch.

In: c’t Magazin für Computer Technik vol. 24 pg. 212-216

Heise

  • (2013)
Journal article
  • Peter Faber
  • T. Maier
  • Sebastian Och
  • M. Schlott

Parallelwelten.

In: c’t Magazin für Computer Technik vol. 26 pg. 160-165

Heise

  • (2014)
Journal article
  • Peter Faber
  • Sebastian Och
  • M. Schlott

Panoramabilder auf Android-Handys anzeigen.

In: c’t Programmieren pg. 212-216

Heise

  • (2014)
Journal article
  • Peter Faber
  • A. Größlinger

A Comparison of GPGPU Computing Frameworks on Embedded Systems.

In: IFAC-PapersOnLine/13th IFAC and IEEE Conference on Programmable Devices and Embedded Systems — PDES 2015 vol. 48 pg. 240-245

  • (2015)

DOI: 10.1016/j.ifacol.2015.07.040

show abstract

Graphics processing units have found their way onto the die of embedded CPUs. Embedded devices have thus gained access to on-die parallel co-processors that can be put to good use with the help of the low-level OpenCL standard API, but also using programming frameworks that help making use of this additional compute power. This paper compares several programming frameworks with different coding styles. We report on the coding effort needed and the performance achieved on a Congatec conga-QG embedded computer on a module using two representative codes taken from the SHOC benchmark suite as comparison.
Journal article
  • Peter Faber
  • Tanja Maier
  • Stefan Schuster

Using Code Metrics for Android Programming.

In: Bavarian Journal of Applied Sciences pg. 162-175

  • (2016)

DOI: 10.25929/y4b9-e908

show abstract

Today, maintainability is of great importance for software projects. In this regard, software metrics play a crucial role in software development: these metrics may be used to objectively assess certain aspects of the software project at hand. We give an overview of available software metrics and evaluate their availability in software development tools. To that end, we explore their usage for the improvement of an Android app project – the E-WALD InCarApp. We provide evidence about their usefulness in a case study by measuring and comparing different aspects of the software project, leading to a derived software metric. We focus especially on measuring and improving code quality and compare these results to statements obtained from developer interviews which indicate that our derived metric may well be used to identify hot-spots for optimization. Wartbarkeit ist heutzutage von größter Wichtigkeit für Software-Projekte. Hierzu spielen Software-Metriken eine zentrale Rolle in der Software-Entwicklung: Diese Metriken können genutzt werden, um gewisse Aspekte des betrachteten Software-Projekts objektiv einzuordnen. Wir geben eine Übersicht über zur Verfügung stehende Software-Metriken und evaluieren ihre Verfügbarkeit in Software-Entwicklungs-Tools. Dazu betrachten wir ihre Anwendung bei der Verbesserung eines Android-App-Projekts – der E-WALD InCarApp. Wir weisen ihre Nutzbarkeit in einer Fallstudie nach, in der wir unterschiedliche Aspekte des Software-Projekts messen und vergleichen, was uns zu einer abgeleiteten Software-Metrik führt. Wir konzentrieren uns hier vor allem auf die Messung und Verbesserung der Code-Qualität insbesondere der Wartbarkeit und vergleichen die Resultate mit Aussagen aus Interviews mit den Software-Entwicklern. Die einfache abgeleitete Metrik erscheint dabei durchaus schon geeignet, um Hot-Spots für Optimierungspotenziale zu identifizieren.
Lecture
  • Peter Faber

Contactless Inductive Flow Tomography (CIFT). Posterpräsentation.

In: 6. Tag der Forschung der THD 2019

Technische Hochschule Deggendorf Deggendorf

  • 10.04.2019 (2019)
Contribution
  • Peter Faber
  • Helena Liebelt

High-Performance and Quantum Computing for Students.

In: Informatik 2022 - Informatik in den Naturwissenschaften. vol. P-326 pg. 1085-1091

  • Eds.:
  • D. Demmler
  • H. Federrath
  • D. Krupka

Gesellschaft für Informatik Bonn

  • (2022)
Lecture
  • Markus Eider
  • Peter Faber
  • F. Haselbeck
  • Cordula Krinner

Travel Mate Matching – Strengthening Shared Mobility through the Formation of Interest Groups.

In: Abschlusskonferenz des AI-Clash „Clashing Approaches to Artificial Intelligence“

Technische Hochschule Deggendorf Deggendorf; Online

  • 13.05.2022

labs

DGS206 (HPC I / computer graphics)

Vita

  • 2009 – now: Professor (THD)
  • 2005 – 2009: Software engineer (science+computing ag)
  • 1999 – 2004: Researcher (Uni Passau)
  • 1998 – 1999: Researcher (GMD – Forschungszentrum Informationstechnik GmbH)