My research over the last years has been centered around easing parallel programming mostly with a focus on programming models and high performance computing. I have been working on existing programming models like OpenMP and OpenCL, as well as on designing new programming models/libraries.

My work on existing programming models mostly concentrated on OpenMP and OpenCL. Whereas with future hardware, memory accesses and data transfers seem to become more important than on current hardware, yet OpenMP does not take care of data locality. I have been working on adding the concept of tiling to OpenMP, to allow both better control over data locality and the possibility to effectively utilize tile based many-core chips. OpenCL already incorporates tiling has mechanisms for effective memory transfers, yet it does not effective data sharing between tasks. I have been working on proving ways to share data among task to eliminate off-chip memory accesses. My own programming model called Partitioned Single Assignment Memory (PSAM) is designed to deal with hybrid CPUs, missing cache coherency, and purely relies on RDMA memory accesses. Synchronization follows the dataflow semantic on a single assignment memory space. CuPP is one of my first research project and a library designed to allow easy integration of CUDA into C++ programs.

Parallel Computing

The classes covered OpenMP, CUDA and MPI. They have been targeted at both undergraduate and master students. Some of the classes have been co-taught by Claudia Fohry.

Cloud (that is scalable web projects)

I supervised several student projects trying to create scalable web projects.

Other hot topics

I commonly offered seminars/projects on other hot topics including e.g. GPUs shortly after CUDA was released or PGAS.

[Bre13a]

J. Breitbart: A dataflow-like programming model for future hybrid clusters, Int. Journal of Networking and Computing. To appear.

[Bre12a]

J. Breitbart: Dataflow-like synchronization in a PGAS programming model, Parallel and Distributed Processing Symposium Workshops (IPDPSW), Shanghai, China, 2012.

[Bre11c]

J. Breitbart: Programming hybrid systems with implicit memory based synchronization, Proceedings of the IEEE International Conference on High Performance Computing (HiPC), Bangalore, India, 2011.

[BK11]

J. Breitbart, G. Khanna: An Exploration of CUDA and CBEA for a Gravitational Wave Data- Analysis Application (Einstein@)Home, The Open Astronomy Journal, 2011.

[Bre11b]

J. Breitbart: Analysis of a memory bandwidth limited scenario for NUMA and GPU systems, Parallel and Distributed Processing Symposium (IPDPS), Anchorage, USA, 2011.

[BF11]

J. Breitbart, C. Fohry: Analyzing Use of OpenCL on the Cell Broadband Engine and a Proposal for OpenCL Extensions, Int. Journal of Networking and Computing, Vol. 1, No. 1 (2011).

[Bre11a]

J. Breitbart: Semiautomatic cache optimizations using OpenMP, Proceedings of the 10th Para: State of the Art in Scientific and Parallel Computing Conference (Para 2010) Reykjavík, Iceland, 2011.

[Bre10b]

J. Breitbart: Static GPU threads and an improved scan algorithm, Workshop Proceedings of 2010 Euro-Par, Ischia, Italy, 2010.

[Bre10a]

J. Breitbart: OpenMP for next generation heterogeneous clusters, Proceedings of the 2nd USENIX Workshop on Hot Topics in Parallelism (HOTPAR 2010) Berkley, USA, 2010.

[BF10]

J. Breitbart, C. Fohry: OpenCL – An effective programming model for data parallel computations at the Cell Broadband Engine, Parallel and Distributed Processing Symposium (IPDPS), Atlanta, USA, 2010.

[BK09b]

J. Breitbart, G. Khanna: An exploration of CUDA and CBEA for gravitational wave data-analysis, Proceedings of the 7th International Conference of Numerical Analysis and Applied Mathematics (ICNAAM 2009) Creta, Greece, 2009.

[BK09a]

J. Breitbart, G. Khanna: An Exploration of CUDA and CBEA for Einstein@Home, Proceedings of the Eighth International Conference on Parallel Processing and applied Mathematics (PPAM 2009) Wroclaw, Poland, September 2009.

[Bre09b]

J. Breitbart: Data structure design for GPU based heterogeneous systems, Proceedings of the 2009 International Conference on High Performance Computing & Simulation (HPCS 2009) Leipzig, Germany, 2009.

[Bre09a]

J. Breitbart: CuPP -- A framework for easy CUDA integration, Parallel and Distributed Processing Symposium (IPDPS), Rome, Italy, 2009.

[Bre08b]

J. Breitbart: Case studies on GPU usage and data structure design, Master Thesis, University of Kassel, 2008.

[Bre08a]

J. Breitbart: A framework for easy CUDA integration in C++ applications, Diploma Thesis, University of Kassel, 2008.

[LSB06]

C. Leopold, M. Süß, J. Breitbart: Programming for Malleability with Hybrid MPI-2 and OpenMP: Experiences with a Simulation Program for Global Water Prognosis, European Conference on Modelling and Simulation, Bonn, Germany, 2006.

Aug. 08 - Jul. 12

Research Associate University of Kassel, Research Group Programming Languages / Methodologies
Teaching bachelor and master courses (see above). Ph.D. studies in parallel computing with focus on high productive parallel programming.

Apr. 06 -- Jul. 07

Student worker University of Kassel, Research Group Programming Languages / Methodologies
Modifying the open source C++ steering library OpenSteer to enable different parallelization techniques. Paused from August 06 - October 06, see next item.

Aug. 06 - Oct. 06

Internship IBM Germany Research & Development GmbH
Developing a C++ library for the Cell Broadband Engine Architecture allowing automatic parallelization and SPU local store management for simple data parallel tasks.

Dec. 04 - Dec. 05

Student worker University of Kassel, Research Group Programming Languages / Methodologies
Parallelization of WaterGAP, an application that simulates current and future water availability worldwide based on input data for climate, vegetation, water usage etc., with MPI and OpenMP.

approx. Jan. 13

Dr. rer. nat. (in Parallel Programming), University of Kassel, under review

Aug. 08

Master of Science (in Computer Science), University of Kassel, Grade 1.2

Feb. 08

Diplom Informatiker (comparable to bachelor degree in Computer Science), University of Kassel, Grade 1.2