Research summary

I got my Ph.D. for my research on programming models for future HPC systems. My research has always been centered around easing parallel programming mostly with a focus on programming models and high performance computing. I am working on existing programming models like OpenMP, Chapel and OpenCL, as well as on designing new programming models/libraries. I currently maintain the Autopin+ tool.

Publications

  • Inclusive Cost Attribution for Cache Use Profiling

    Josef Weidendorfer and Jens Breitbart • 2016

    Procedia Computer Science
    Volume 80 pp. 1439 - 1449
    International Conference on Computational Science 2016, ICCS 2016, 6-8 June 2016, San Diego, California, USA
    DOI: 10.1016/j.procs.2016.05.464
    BibTeX

  • Binary Rewriting at Runtime for Efficient Dynamic Domain Map Implementations

    Josef Weidendorfer and Jens Breitbart • 2016

    CHIUW: Chapel Implementers and Users Workshop 2016
    Extended Abstract
    Download
    BibTeX

  • Detailed Characterization of HPC Applications for Co-Scheduling

    Josef Weidendorfer and Jens Breitbart • 2016

    Proceedings of the 1st COSH Workshop on Co-Scheduling of HPC Applications pp. 19
    DOI: 10.14459/2016md1286951
    BibTeX

  • Implications of Process-Migration in Virtualized Environments

    Simon Pickartz and Jens Breitbart and Stefan Lankes • 2016

    Proceedings of the 1st COSH Workshop on Co-Scheduling of HPC Applications pp. 6
    DOI: 10.14459/2016md1320971
    BibTeX

  • Data flow programming – a high performance and highly complicated programming concept?

    Jens Breitbart • 2015

    CHIUW: Chapel Implementers and Users Workshop 2015
    Extended Abstract
    Link
    BibTeX

  • Case Study on Co-Scheduling for HPC Applications

    Jens Breitbart and Josef Weidendorfer and Carsten Trinitis • 2015

    44th International Conference on Parallel Processing Workshops (ICPPW) pp. 277-285
    DOI: 10.1109/ICPPW.2015.38
    BibTeX

  • Evaluation of the Global Address Space Programming Interface (GASPI)

    Jens Breitbart and Mareike Schmidtobreick and Vincent Heuveline • 2014

    Proceedings of the 2014 IEEE International Parallel & Distributed Processing Symposium Workshops IPDPSW ’14 pp. 717–726
    DOI: 10.1109/IPDPSW.2014.83
    BibTeX

  • Experiences with Implementing Task Pools in Chapel and X10

    Claudia Fohry and Jens Breitbart • 2014

    Parallel Processing and Applied Mathematics
    Volume 8385 of the series Lecture Notes in Computer Science Lecture Notes in Computer Science pp. 75-85
    DOI: 10.1007/978-3-642-55195-6_7
    BibTeX

  • User Experiences with a Chapel Implementation of UTS

    Claudia Fohry and Jens Breitbart • 2014

    CHIUW: Chapel Implementers and Users Workshop 2014
    Extended Abstract
    Download
    BibTeX

  • A dataflow-like programming model for future hybrid clusters

    Jens Breitbart • 2013

    International Journal of Networking and Computing
    Volume 3 pp. 15–36
    Link
    BibTeX

  • Programming Models for Next Generation HPC Systems

    Jens Breitbart • 2013

    Ph.D. thesis, Universität Kassel
    BibTeX

  • Dataflow-like Synchronization in a PGAS Programming Model

    Jens Breitbart • 2012

    Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum IPDPSW ’12 pp. 762–769
    DOI: 10.1109/IPDPSW.2012.94
    BibTeX

  • An Approach for Semiautomatic Locality Optimizations Using OpenMP

    Jens Breitbart • 2012

    Applied Parallel and Scientific Computing
    Volume 7134 of the series Lecture Notes in Computer Science Lecture Notes in Computer Science pp. 291-301
    DOI: 10.1007/978-3-642-28145-7_29
    BibTeX

  • An Exploration of CUDA and CBEA for a Gravitational Wave Data- Analysis Application (Einstein@Home)

    Jens Breitbart and Gaurav Khanna • 2011

    The Open Astronomy Journal
    Volume 4 pp. 154–161
    DOI: 10.2174/1874381101004010154
    BibTeX

  • Programming hybrid systems with implicit memory based synchronization

    Jens Breitbart • 2011

    Workshop on Hybrid Multicore Computing held in conjunction with HiPC 2011
    Download
    BibTeX

  • Analysis of a Memory Bandwidth Limited Scenario for NUMA and GPU Systems

    Jens Breitbart • 2011

    Proceedings of the 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PhD Forum IPDPSW ’11 pp. 693–699
    DOI: 10.1109/IPDPS.2011.193
    BibTeX

  • Analyzing Use of OpenCL on the Cell Broadband Engine and a Proposal for OpenCL Extensions

    Jens Breitbart and Claudia Fohry • 2011

    International Journal of Networking and Computing
    Volume 1 pp. 114–130
    Link
    BibTeX

  • Static GPU Threads and an Improved Scan Algorithm

    Jens Breitbart • 2011

    Euro-Par 2010 Parallel Processing Workshops
    Volume 6586 of the series Lecture Notes in Computer Science Lecture Notes in Computer Science pp. 373-380
    DOI: 10.1007/978-3-642-21878-1_46
    BibTeX

  • OpenMP for next generation heterogeneous clusters

    Jens Breitbart • 2010

    2nd USENIX Workshop on Hot Topics in Parallelism
    Download
    BibTeX

  • An Exploration of CUDA and CBEA for Einstein@Home

    Jens Breitbart and Gaurav Khanna • 2010

    Parallel Processing and Applied Mathematics
    Volume 6067 of the series Lecture Notes in Computer Science Lecture Notes in Computer Science pp. 486-495
    DOI: 10.1007/978-3-642-14390-8_51
    BibTeX

  • OpenCL-an effective programming model for data parallel computations at the cell broadband engine

    Jens Breitbart and Claudia Fohry • 2010

    24th IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2010, Atlanta, Georgia, USA, 19-23 April 2010 - Workshop Proceedings pp. 1–8
    DOI: 10.1109/IPDPSW.2010.5470823
    BibTeX

  • Data structure design for GPU based heterogeneous systems

    Jens Breitbart • 2009

    International Conference on High Performance Computing Simulation pp. 44-51
    DOI: 10.1109/HPCSIM.2009.5192780
    BibTeX

  • An Exploration of CUDA and CBEA for Gravitational Wave Data‐Analysis

    Jens Breitbart and Gaurav Khanna • 2009

    AIP Conference Proceedings
    Volume 1168 pp. 1065-1067
    DOI: 10.1063/1.3241237
    BibTeX

  • CuPP - A Framework for Easy CUDA Integration

    Jens Breitbart • 2009

    Proceedings of the 2009 IEEE International Symposium on Parallel&Distributed Processing IPDPS ’09 pp. 1–8
    DOI: 10.1109/IPDPS.2009.5160937
    BibTeX

  • A framework for easy CUDA integration in C++ applications

    Jens Breitbart • 2008

    Diploma thesis, Universität Kassel, Kassel, Germany
    Download
    BibTeX

  • Case studies on GPU usage and data structure design

    Jens Breitbart • 2008

    Master’s thesis, Universität Kassel
    Download
    BibTeX

  • Programming for malleability with hybrid MPI-2 and OpenMP: Experiences with a simulation program for global water prognosis

    Claudia Leopold and Michael Süß and Jens Breitbart • 2006

    Proceedings of the European Conference on Modelling and Simulation pp. 665–670
    Download
    BibTeX

Projects

HermitCore

Research interest • 2015 — Present

HermitCore is a novel unikernel operating system targeting a scalable and predictable runtime behavior for HPC and cloud environments. It extends the multi-kernel approach and combines it with unikernel features.

PSAM: Partitioned Single Assignment Memory

Research interest • 2011 — Present

PSAM is an experimental PGAS implementation designed to provide allow fine-grained synchronization and efficient remote memory caching mechanism.

FaST: Find a Suitable Topology for Exascale Applications

ICT 2020 - Research for Innovation project project • 2014 — 2016

FaST deals with the temporal and spatial placement of processes on high performance computers of the future. We develop autopin+, a tool to optimize the local placement within a node.

GASPI: Global Address Space Programming Interface

ICT 2020 - Research for Innovation project • 2013 — 2015

GASPI is a Partitioned Global Address Space (PGAS) API for C, C++ and Fortran. Its communication mechanism is based on one-sided RDMA transfers with a notification mechanism.

Teaching

Here is a brief list of classes, seminars and theses I was involved with in the last years.

Education

Dr. rer. nat. in parallel computing

University of Kassel • 2008 — 2012

Programming Models for Next Generation HPC Systems.

Master of Science (in Computer Science)

University of Kassel • 2008

Case Studies on GPU Usage and Data Structure Design.

Diplom Informatiker

University of Kassel • 2003 — 2008

A Framework for Easy CUDA Integration in C++ Applications.

Additional Links