Ethernet BTL eth
Torsten Hoefler's Home Page|
I recently started a new position as Assistant Professor for Computer
Science at ETH Zürich. I am leading the Scalable Parallel Computing Laboratory
(SPCL) at ETH.
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]
|SC12|| 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) |
|PACT'12|| T. Hoefler, T. Schneider:|
| ||Runtime Detection and Optimization of Collective Communication Patterns In Proceedings of the 21st international conference on Parallel Architectures and Compilation Techniques (PACT), presented in Minneapolis, MN, USA, pages 263--272, ACM, ISBN: 978-1-4503-1182-3, Sep. 2012, (acceptance rate: 18.9%, 39/207) |
|SC07|| T. Hoefler, A. Lumsdaine and W. Rehm:|
| ||Implementation and Performance Analysis of Non-Blocking Collective Operations for MPI In Proceedings of the 2007 International Conference on High Performance Computing, Networking, Storage and Analysis, SC07, presented in Reno, USA, IEEE Computer Society/ACM, Nov. 2007, (acceptance rate 20%, 54/268) |