Non quia difficilia sunt non audemus, sed quia non audemus difficilia sunt
Home -> Research
NB Collectives
    MPI Topologies
    MPI Datatypes
    Network Topologies
    Ethernet BTL eth
    Older Projects
  CV [in pdf format]


  Recent Events

Torsten Hoefler's Home Page

Watertower (Bautzen, Germany) [2011]
 Assistant Professor
 Scalable Parallel Computing Lab
 Computer Science Department
 ETH Zürich
 Universitaetsstrasse 6
 CAB E 64.1
 8092 Zürich, Switzerland
 Office phone: +41 44 632 63 44

I am Assistant Professor for Computer Science at ETH Zürich where I lead the Scalable Parallel Computing Laboratory (SPCL).

Before I left the USA, I was working in the Blue Waters Directorate at the University of Illinois at Urbana-Champaign. I was responsible for performance modeling and simulation of the Blue Waters Petascale computer and applications running on it. In this effort, I worked with William Kramer, Marc Snir, and Bill Gropp and external partners.

I am co-chair of the collective operations working group in the MPI Forum. I am interested in Collective Communications, Process Topologies, One Sided Operations, and Hybrid Programming in MPI. I am also a member of ACM SIGHPC, ACM, and IEEE.

My research interests revolve around the central topic of "Performance-centric Software Development". In the context of High-Performance Computing (HPC), one can identify three sub-branches that I am actively working on: (1) performance modeling, simulation, and optimization of large-scale parallel applications, (2) topologies, routing, and host interfaces of large-scale networks, and (3) advanced parallel programming techniques and runtime environments. An overview graph of my past and current research activities (relative to my publication list) shows their connections: Research Overview.

My Erdős number is three (via Marc Snir and Shlomo Moran) and I am an academic descendant of Hermann von Helmholtz.

Selected Recent Service

Selected Recent Publications

[click here for full list]
[1] R. Gerstenberger, M. Besta, T. Hoefler:
 Enabling Highly-Scalable Remote Memory Access Programming with MPI-3 One Sided presented in Denver, Colorado, USA, Nov. 2013, IEEE/ACM International Conference on High Performance Computing, Networking, Storage and Analysis (SC13) (acceptance rate: 20%, 92/457) SC13 Best Paper (1/92) and Best Student Paper Finalist (8/92)
[2] S. Ramos and T. Hoefler:
 Modeling Communication in Cache-Coherent SMP Systems - A Case-Study with Xeon Phi In Proceedings of the 22nd international symposium on High-performance parallel and distributed computing, presented in New York City, NY, USA, pages 97--108, ACM, ISBN: 978-1-4503-1910-2, Jun. 2013, (acceptance rate: 15%, 20/131)
[3] A. Friedley, T. Hoefler, G. Bronevetsky, A. Lumsdaine:
 Ownership Passing: Efficient Distributed Memory Programming on Multi-core Systems In Proceedings of the 18th ACM SIGPLAN symposium on Principles and practice of parallel programming, presented in Shenzen, China, pages 177--186, ACM, ISBN: 978-1-4503-1922-5, Feb. 2013, (acceptance rate: 18%, 26/146)
[4] T. Hoefler, T. Schneider:
 Optimization Principles for Collective Neighborhood Communications In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, presented in Salt Lake City, Utah, USA, pages 98:1--98:10, IEEE Computer Society Press, ISBN: 978-1-4673-0804-5, Nov. 2012, (acceptance rate: 21%, 100/472)
[5] T. Hoefler and M. Snir:
 Generic Topology Mapping Strategies for Large-scale Parallel Architectures In Proceedings of the 2011 ACM International Conference on Supercomputing (ICS'11), presented in Tucson, AZ, pages 75--85, ACM, ISBN: 978-1-4503-0102-2, Jun. 2011, (acceptance rate 21.7%, 35/161)
[6] T. Hoefler, T. Schneider and A. Lumsdaine:
 Characterizing the Influence of System Noise on Large-Scale Applications by Simulation In International Conference for High Performance Computing, Networking, Storage and Analysis (SC'10), Nov. 2010, (acceptance rate 19.8%, 50/253) SC10 Best Paper Award
[7] T. Hoefler, C. Siebert and A. Lumsdaine:
 Scalable Communication Protocols for Dynamic Sparse Data Exchange In Proceedings of the 2010 ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP'10), presented in Bangalore, India, pages 159--168, ACM, ISBN: 978-1-60558-708-0, Jan. 2010, (acceptance rate 16.8%, 29/173)


serving:© Torsten Hoefler