Omnia vincit amor
Home -> Publications
Home
  Publications
    
all years
    2020
    2019
    2018
    2017
    2016
    2015
    2014
    2013
    2012
    2011
    2010
    2009
    2008
    2007
    2006
    2005
    2004
    theses
    techreports
    presentations
    conferences
    edited volumes
  Awards
  Research
  Teaching
  BLOG
  Miscellaneous
  Full CV [pdf]






  Events








  Past Events





Publications of Torsten Hoefler
Copyright Notice:

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Citation Listings: DBLP   CSB   Google Scholar   ACM Digital Library   Semantic Scholar

Research overview                  Using Advanced MPI                 Edited volumes
      

Invited Talks and Presentations

MLHPC
[1] Torsten Hoefler:
 HPC for ML and ML for HPC - Scalability, Communication, and Programming (Presentation) presented in Denver, CO, USA, Nov. 2019, Keynote talk at the International Machine Learning in High-Performance Computing (MLHPC'19 in conjunction with ACM/IEEE Supercomputing, SC19)
PARCO
[2] Torsten Hoefler:
 Data-Centric Parallel Programming (Presentation) presented in Prague, Czech Republic, Sep. 2019, Keynote talk at the The 18th International Parallel Computing conference (ParCo'19)
PPAM
[3] Torsten Hoefler:
 High-Performance Communication in Machine Learning (Presentation) presented in Bialystok, Poland, Sep. 2019, Keynote talk at the 13th International Conference on Parallel Processing and Applied Mathematics (PPAM'19)
ISC'19
[4] Torsten Hoefler, Alexandros Nikolaos Ziogas, Tal Ben-Nun, Guillermo Indalecio Fernández, Timo Schneider, Mathieu Luisier and Johannes de Fine Licht:
 Data-Centric Parallel Programming (Presentation) presented in Frankfurt, Germany, Jun. 2019, invited talk at the International Conference on Supercomputing (ISC'19)
GG500
[5] Torsten Hoefler:
 The Green Graph500 List (June 2019) (Presentation) presented in Frankfurt, Germany, Jun. 2019, Presented at the Green Graph 500 BoF at the International Conference on Supercomputing (ISC'19)
ISC'19 ML
[6] Torsten Hoefler, Tal Ben-Nun:
 Optimizing and Benchmarking Large-Scale Deep Learning (Presentation) presented in Frankfurt, Germany, Jun. 2019, Invited talk at the Machine Learning day at the International Conference on Supercomputing (ISC'19)
NRE'19
[7] Torsten Hoefler:
 Performance Reproducibility in HPC and Deep Learning (Presentation) presented in Frankfurt, Germany, Jun. 2019, Keynote talk at the Numerical Reproducibility at Exascale Workshop (NRE2019), ISC’19
AsHES
[8] Torsten Hoefler:
 Performance Portability with Data-Centric Parallel Programming (Presentation) presented in Rio de Janeiro, Brasil, May 2019, Keynote talk at the The Ninth International Workshop on Accelerators and Hybrid Exascale Systems (AsHES) (delayed online)
HPCAC
[9] Torsten Hoefler:
 RDMA, Scalable MPI-3 RMA, and Next-Generation Post-RDMA Interconnects (Presentation) Apr. 2019, Best talk award winner at Swiss HPC Advisory Council Conference 2019
EMiT
[10] Torsten Hoefler:
 High-Performance Communication for Machine Learning (Presentation) presented in Huddersfield, UK, Apr. 2019, Keynote talk at the 5th Conference on Emerging Technologies – EMiT2019
SCFE'19
[11] Torsten Hoefler:
 Extreme-Scale Graphs (Presentation) presented in Warsaw, Poland, Mar. 2019, Invited talk at Supercomputing Frontiers Europe 2019
AHPC'19
[12] Torsten Hoefler:
 High-Performance Communication in Machine Learning (Presentation) presented in Grundlsee, Austria, Feb. 2019, Keynote at the Austrian HPC meeting 2019
ICL
[13] Torsten Hoefler:
 High-Performance Communication in Machine Learning (Presentation) presented in Knowville, TN, Feb. 2019,
RWTH Aachen
[14] Torsten Hoefler:
 High-Performance Communication for Machine Learning (Presentation) presented in Aachen, Germany, Jan. 2019,
RWTH Aachen
[15] Torsten Hoefler:
 MPI Remote Memory Access Programming and Scientific Benchmarking of Parallel Codes (Presentation) presented in Aachen, Germany, Jan. 2019,
TU Darmstadt
[16] Torsten Hoefler:
 An HPC Systems Guy’s View of Quantum Computing (Presentation) presented in Darstadt, Germany, Jan. 2019,
IPAM UCLA
[17] Torsten Hoefler:
 Twelve ways to fool the masses when reporting performance of deep learning workloads (Presentation) presented in Los Angeles, CA, Nov. 2018, Workshop III: HPC for Computationally and Data-Intensive Problems
IPAM UCLA
[18] Torsten Hoefler:
 High-Performance Communication for Machine Learning (Presentation) presented in Los Angeles, CA, Nov. 2018, Workshop III: HPC for Computationally and Data-Intensive Problems
SC18
[19] Torsten Hoefler:
 High Level Programming Languages for Quantum Computation (Presentation) presented in Dallas, TX, USA, Nov. 2018,
SC18
[20] Torsten Hoefler:
 RDMA, Scalable MPI-3 RMA, and Next-Generation Post-RDMA Interconnects (Presentation) presented in Dallas, TX, USA, Nov. 2018, Keynote at ExaMPI 2018 Workshop (in conjunction with SC18)
SC18
[21] Torsten Hoefler:
 Will FPGAs make it this time? (Presentation) presented in Dallas, TX, USA, Nov. 2018,
SC18
[22] Torsten Hoefler:
 Deep500: An HPC Deep Learning Benchmark and Competition (Presentation) presented in Dallas, TX, USA, Nov. 2018,
FacSum
[23] Torsten Hoefler:
 An HPC System's guy's view of Quantum Computing (Presentation) presented in Redmond, WA, Aug. 2018, Presentation at the Microsoft Faculty Summit 2018
Tsinghua
[24] Torsten Hoefler:
 Performance Modeling for Future Computing Technologies (Presentation) Jun. 2018, Invited talk at 60 years of CS @ Tsinghua celebration
HPCAC
[25] Torsten Hoefler:
 Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis (Presentation) Apr. 2018, Keynote at Swiss HPC Advisory Council Conference 2018
SOS'18
[26] Torsten Hoefler:
 Performance Portability - An Oxymoron? (Presentation) presented in Kona, HI, USA, Mar. 2018, Invited talk at SOS'18 Workshop
Multicore @ Siemens
[27] Torsten Hoefler:
 Developing high-performance software, from modeling to programming (Presentation) presented in Nuremberg, Germany, Feb. 2018, Invited opening presentation at the Multicore@Siemens conference
HiPINEB @ HPCA'18
[28] Torsten Hoefler:
 The three L's in modern high-performance networking: low latency, low cost, low processing load (Presentation) presented in Vienna, Austria, Feb. 2018, Keynote at the HiPINEB workshop at HPCA'18
HPCDC
[29] Torsten Hoefler, Sabela Ramos, Carlos Osuna, Felix Thaler, S. Moosbrugger, Oliver Fuhrer:
 Capability Models for Manycore Memory Systems: A Case-Study with Xeon Phi KNL and the COSMO Weather Code (Presentation) presented in Denver, CO, Nov. 2017, Presentation at the Intel HPC Developer's Conference 2017
Co-Design
[30] Torsten Hoefler, Sabela Ramos, Tal Ben-Nun:
 HPC Performance Optimization Advances at Extreme Scale (Presentation) presented in Hefei, China, Oct. 2017, Invited talk at the Co-Design workshop (HPC China 2017)
25 Years MPI
[31] Torsten Hoefler:
 A View on MPI's Recent Past, Present, and Future (Presentation) presented in Chicago, IL, Sep. 2017, Invited talk at 25 Years of MPI Symposium
EMBRACE
[32] Torsten Hoefler:
 Scientific Benchmarking of Parallel Computing Systems (Presentation) presented in Orlando, FL, Jun. 2017, Keynote talk at EMBRACE Workshop (IPDPS'17)
IPDRM
[33] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Orlando, FL, Jun. 2017, Invited talk at IPDRM Workshop (IPDPS'17)
Uni Saarland
[34] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Orlando, FL, Jun. 2017, Invited talk at IPDRM Workshop (IPDPS'17)
HPCAC
[35] Torsten Hoefler:
 dCUDA: Hardware Supported Overlap of Computation and Communication (Presentation) Apr. 2017,
HiPINEB
[36] Torsten Hoefler:
 HiPINEB Panel (highly exaggerated) (Presentation) presented in Austin, TX, USA, Feb. 2017,
ARM
[37] Torsten Hoefler:
 High-Performance Distributed RMA Locks (Presentation) presented in Austin, TX, Feb. 2017, Seminar at ARM Research
UT Austin
[38] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Austin, TX, Feb. 2017, Seminar at University of texas Austin
FAU
[39] Torsten Hoefler:
 Accelerating weather and climate simulations on heterogeneous architectures (Presentation) presented in Erlangen, Germany, Feb. 2017, Colloquium at the Friedrich-Alexander-Universitaet Erlangen-Nuernberg
UIUC
[40] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Champaign, IL, Jan. 2017, Seminar at University of Illinois at Urbana-Champaign/NCSA
ANL
[41] Torsten Hoefler:
 High-Performance Distributed RMA Locks (Presentation) presented in Champaign, IL, Jan. 2017, Seminar at University of Illinois at Urbana-Champaign/NCSA
Tsinghua
[42] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Beijing, China, Jan. 2017, Seminar at Tsinghua University, Beijing, China
ICT/CAS
[43] Torsten Hoefler:
 Accelerating weather and climate simulations on heterogeneous architectures (Presentation) presented in Beijing, China, Jan. 2017, Distinguished colloquium at the Institute of Computing Technology at the Chinese Academy of Sciences, Beijing, China Distinguished colloquium
LLVM-HPC'16
[44] Torsten Hoefler:
 Polly-ACC: Transparent Compilation to Heterogeneous Hardware. (Presentation) presented in Salt Lake City, UT, Nov. 2016, Invited talk at the LLVM-HPC workshop and TiTech Booth at SC16
CCDSC'16
[45] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Lyon, France, Oct. 2016, Invited talk at the CCDSC meeting
CoDesign'16
[46] Torsten Hoefler:
 Accelerating weather and climate simulations on heterogeneous architectures (Presentation) presented in Xi'an, China, Oct. 2016, Invited talk at the CoDesign Meeting at HPC China 2016
HPC China'16
[47] Torsten Hoefler:
 Theory and Practice in HPC: Modeling, Programming, and Networking (Presentation) presented in Xi'an, China, Oct. 2016, Keynote talk at HPC China 2016
Cluster'16
[48] Torsten Hoefler:
 Theory and Practice in HPC: Modeling, Programming, and Networking (Presentation) presented in Taipei, Taiwan, Sep. 2016, Opening keynote talk at IEEE Cluster 2016
Wuxi'16
[49] Torsten Hoefler:
 High-Performance Distributed RMA Locks (Presentation) presented in Wuxi, China, Sep. 2016, Seminar talk at Intl. Workshop on High-Performance Systems
Guangzhou'16
[50] Torsten Hoefler:
 MODESTO: Data-centric Analytic Optimization of Complex Stencil Programs on Heterogeneous Architectures (Presentation) presented in Guangzhou, China, Sep. 2016, Seminar talk at Intl. Workshop on High-Performance Systems
HotI'16
[51] Torsten Hoefler:
 Network topologies for large-scale compute centers: It's the diameter, stupid! (Presentation) presented in San Jose, CA, USA, Aug. 2016, Invited talk at the IEEE Hot Interconnects 2016
HP
[52] Torsten Hoefler:
 Towards scalable RDMA locking on a NIC (Presentation) presented in Palo Alto, CA, USA, Aug. 2016,
UTK
[53] Torsten Hoefler:
 Scientific Benchmarking of Parallel Computing Systems (Presentation) presented in Knoxville, TN, USA, Aug. 2016,
ISC'16
[54] Torsten Hoefler:
 An Overview of Static & Dynamic Techniques for Automatic Performance Modeling (Presentation) presented in Frankfurt, Germany, Jun. 2016, Invited talk at International Supercomputing Conference
ISC'16
[55] Torsten Hoefler:
 The Eigth Green Graph500 (Presentation) presented in Frankfurt, Germany, Jun. 2016,
Cetraro'16
[56] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Cetraro, Italy, Jun. 2016, Invited talk at the Cetraro HPC conference
Technion'16
[57] Torsten Hoefler:
 Progress in automatic GPU compilation and why you want to run MPI on your GPU. (Presentation) presented in Haifa, Israel, Jun. 2016, Seminar talk at Israel Institute of Technology (Technion)
HLRS
[58] Torsten Hoefler:
 Scientific Benchmarking of Parallel Computing Systems (Presentation) presented in Stuttgart, Germany, Apr. 2016,
Salishan
[59] Torsten Hoefler:
 Active RDMA - new tricks for an old dog (Presentation) presented in Gleneden Beach, OR, USA, Apr. 2016, Invited talk at Salishan Meeting
SC15
[60] Torsten Hoefler:
 The Seventh Green Graph500 (Presentation) presented in Austin, TX, USA, Nov. 2015,
SC15
[61] Torsten Hoefler:
 Performance Reproducibility Birds of a Feather (Presentation) presented in Austin, TX, USA, Nov. 2015,
Tsinghua
[62] Torsten Hoefler:
 Remote Memory Access Programming: Faster Parallel Computing Without Messages (Presentation) presented in Tsinghua University, Beijing, China, Nov. 2015,
CoDesign
[63] Torsten Hoefler:
 Automatic Performance Models for the Masses: Static and dynamic techniques for application performance modeling (Presentation) presented in CoDesign Workshop, Wuxi, China, Nov. 2015,
IUB
[64] Torsten Hoefler:
 How fast will your application go? Static and dynamic techniques for application performance modeling (Presentation) presented in Bloomington, IN, USA, Jul. 2015,
UChicago
[65] Torsten Hoefler:
 Towards Remote Memory Access Programming for Data Analytics (Presentation) presented in Chicago, IL, USA, Jul. 2015,
ISC'15
[66] Torsten Hoefler:
 The Sixth Green Graph500 List (Presentation) presented in Frankfurt, Germany, Jul. 2015,
UCSD
[67] Torsten Hoefler:
 Remote Memory Access Programming: Faster Parallel Computing Without Messages (Presentation) presented in San Diego, CA, USA, Jun. 2015,
HP
[68] Torsten Hoefler:
 Efficient networking and programming of large-scale computing systems (Presentation) presented in Palo Alto, CA, USA, Jun. 2015,
LBNL
[69] Torsten Hoefler:
 Towards Remote Memory Access Programming for Data Analytics (Presentation) presented in Berkeley, CA, USA, Jun. 2015,
GATech
[70] Torsten Hoefler:
 Remote Memory Access Programming: Faster Parallel Computing Without Messages (Presentation) presented in Atlanta, GA, USA, Jun. 2015,
ORNL
[71] Torsten Hoefler:
 How fast will your application go? Static and dynamic techniques for application performance modeling (Presentation) presented in Oak Ridge, TN, USA, Jun. 2015,
Simula
[72] Torsten Hoefler, Jens Domke:
 Fail-in-Place Network Design presented in Oslo, Norway, May 2015,
HIPS/LSPP
[73] Torsten Hoefler:
 How fast will your application go? Static and dynamic techniques for application performance modeling. (Presentation) presented in Hyderabad, India, May 2015, Keynote talk at HIPS'15/LSPP'15 in conjuntion with IPDPS'15
PLC
[74] Torsten Hoefler:
 MODESTO: Data-centric Analytic Optimization of Complex Stencil Programs on Heterogeneous Architectures (Presentation) presented in Hyderabad, India, May 2015,
FFMK
[75] Torsten Hoefler:
 Resilience Overheads at Scale and Scalability (Presentation) presented in Dresden, Germany, Dec. 2014,
SC14
[76] Torsten Hoefler:
 The Fourth Green Graph500 List (Presentation) presented in New Orleans, Louisiana, USA, Nov. 2014,
SC14
[77] Torsten Hoefler:
 IA3 Panel: HPC vs. Irregular Applications (Presentation) presented in New Orleans, Louisiana, USA, Nov. 2014,
SC14
[78] Torsten Hoefler:
 A case for runtime recompilation in HPC (Presentation) presented in New Orleans, Louisiana, USA, Nov. 2014, The LLVM Compiler Infrastructure in HPC, Keynote Presentation
SC14
[79] Torsten Hoefler:
 What about MPI + LLVM? (Presentation) presented in New Orleans, Louisiana, USA, Nov. 2014,
SC14
[80] Torsten Hoefler:
 LogGOPSim - Simple and Fast Large-Scale Simulations (Presentation) presented in New Orleans, Louisiana, USA, Nov. 2014,
MSU
[81] Torsten Hoefler:
 Remote Memory Access Programming - Tools and Fault Tolerance (Presentation) presented in Moscow, Russia, Jul. 2014,
ISC'14
[82] Torsten Hoefler:
 The Green Graph500 List (Presentation) presented in Leipzig, Germany, Jun. 2014,
ISC'14
[83] Torsten Hoefler:
 Using Simulation to Evaluate the Performance of Resilience Strategies at Scale (Presentation) In ISC workshop on International Cooperation, presented in Leipzig, Germany, Jun. 2014,
ExaMPI'13
[84] Torsten Hoefler:
 MPI Beyond 3.0 and Towards Larger-Scale Computing (Presentation) presented in Denver, CO, USA, Nov. 2013, Keynote at ExaMPI 2013 Workshop (in conjunction with SC13)
SC13
[85] Torsten Hoefler:
 The Green Graph500 List (Presentation) presented in Denver, Colorado, Nov. 2013,
ISC'13
[86] Torsten Hoefler:
 The Green Graph500 List (Presentation) presented in Leipzig, Germany, Jun. 2013,
EASC'13
[87] Torsten Hoefler:
 Application-Centric Benchmarking and Modeling for Co-Design (Presentation) presented in Edinburgh, Great Britain, Apr. 2013, Presented at the Exascale Applications and Software Conference (EASC'13)
MCC'12
[88] Torsten Hoefler:
 MPI-3.0: A Response to New Challenges in Hardware and Software (Presentation) presented in Stuttgart, Germany, Sep. 2012, Keynote at Multicore Challenge 2012
ISC'12
[89] Torsten Hoefler:
 The Green Graph500 (Presentation) presented in Hamburg, Germany, Jul. 2012,
TiTech'12
[90] Torsten Hoefler:
 Optimized routing and process mapping for arbitrary network topologies (Presentation) presented in Tokyo, Japan, Jun. 2012, Tokyo Institute of Technology
CUG 2012
[91] G. Bauer, Torsten Hoefler, W. Kramer and B. Fiedler:
 Analyses and Modeling of Applications Used to Demonstrate Sustained Petascale Performance on Blue Waters (Presentation) presented in Stuttgart, Germany, May 2012, Cray User Group
TUM'12
[92] Torsten Hoefler:
 New and old Features in MPI-3.0: The Past, the Standard, and the Future (Presentation) University of Illinois at Urbana-Champaign. presented in Munich, Germany, Apr. 2012,
RWTH'12
[93] Torsten Hoefler:
 Performance Modeling for Systematic Performance Tuning (Presentation) presented in Aachen, Germany, Mar. 2012,
SIAM award
[94] Torsten Hoefler:
 Performance-oriented Parallel Programming Integrating Hardware, Middleware, and Applications (Presentation) presented in Savannah, GA, USA, Feb. 2012, SIAM SIAG/SC Junior Scientist Award Lecture
Utah'12
[95] Torsten Hoefler:
 Energy-aware Software Development for Massive-Scale Systems (Presentation) presented in Salt Lake City, Utah, USA, Jan. 2012,
SC11 panel
[96] Torsten Hoefler:
 Performance Modeling for the Masses (Presentation) presented in Seattle, WA, USA, Nov. 2011,
EnA-HPC'11
[97] Torsten Hoefler:
 Energy-aware Software Development for Massive-Scale Systems (Presentation) presented in Hamburg, Germany, Sep. 2011, Keynote at the International Conference on Energy-Aware High Performance Computing (EnA-HPC'11) EnA-HPC'11 Keynote Presentation
EuroMPI'11
[98] Torsten Hoefler:
 Writing Parallel Libraries with MPI - The Good, the Bad, and the Ugly presented in Santorini, Greece, Sep. 2011, Keynote talk at 18th European PVM/MPI User's Group Meeting Keynote talk at EuroMPI 2011.
Juelich
[99] Torsten Hoefler:
 Model-Driven, Performance-Centric HPC Software and System Design and Optimization (Presentation) presented in Juelich, Germany, Apr. 2011, Talk at Juelich Supercomputing Center (JSC)
Aachen
[100] Torsten Hoefler:
 Characterizing the Influence of System Noise on Large-Scale Parallel Applications (Presentation) presented in Aachen, Germany, Apr. 2011, Talk at RWTH Aachen University
CSE'11
[101] William Gropp, Torsten Hoefler and Marc Snir:
 Performance Modeling for Systematic Performance Tuning (Presentation) In SIAM Conference on Computational Science and Engineering 2011 (Abstracts), presented in Reno, NV, SIAM, Feb. 2011,
NCSA
[102] Torsten Hoefler:
 Optimizing Communication on Blue Waters (Presentation) In Talk at the Blue Waters PRAC Workshop, presented in Urbana, IL, USA, Oct. 2010,
PROPER'10
[103] Torsten Hoefler:
 Analytical Performance Modeling and Simulation for Blue Waters (Presentation) In Keynote at Workshop on Productivity and Performance (PROPER 2010), presented in Ischia, Italy, Aug. 2010, PROPER'10 Keynote Presentation
ANL
[104] Torsten Hoefler:
 Nonblocking and Sparse Collective Operations on Petascale Computers (Presentation) presented in Argonne National Laboratory, Jun. 2010,
NCSA
[105] Torsten Hoefler:
 2010 Blue Waters Performance Modeling Workshop -- Opening and Introduction (Presentation) In Opening Slides for the Blue Waters Modeling Workshop, presented in Urbana, IL, USA, Mar. 2010,
MPICH BoF
[106] Torsten Hoefler:
 Selected MPI-2.2 and MPI-3 Features (Presentation) presented in Portland, OR, USA, Nov. 2009, MPICH Birds of a Feather Supercomputing 2009 (SC09), host: Darius Buntinas
TUM
[107] Torsten Hoefler:
 Improving Parallel Computing Platforms (Presentation) presented in Munich, Germany, Oct. 2009, Presentation at the Technical University of Munich, Host: Prof. M. Gerndt
MPI Forum
[108] Torsten Hoefler:
 MPI-3 Collective Working Group - December'08 Meeting (Presentation) Indiana University. presented in Menlo Park, CA, USA, Dec. 2008, Activity Report to the MPI Forum
MPI Forum
[109] Torsten Hoefler:
 MPI-3 Collective Working Group - October'08 Meeting (Presentation) Indiana University. presented in Chicago, IL, USA, Oct. 2008, Activity Report to the MPI Forum
MPI Forum
[110] Torsten Hoefler:
 MPI-3 Collective Working Group - September'08 Meeting (Presentation) Indiana University. presented in Dublin, Ireland, Sep. 2008, Activity Report to the MPI Forum
Cisco
[111] Torsten Hoefler:
 The effects of common communication patterns in large-scale networks with switch-based static routing (Presentation) Nerd Lunch at Cisco Systems. presented in San Jose, CA, USA, Aug. 2008,
LBNL
[112] Torsten Hoefler:
 Multistage Interconnection Networks are not Crossbars (Presentation) Lawrence Berkeley National Lab. presented in Berkeley, CA, USA, Aug. 2008,
LLNL
[113] Torsten Hoefler:
 Non-blocking Collective Operations for MPI (Presentation) Lawrence Livermore National Lab. presented in Livermore, CA, USA, Aug. 2008,
TUM'08
[114] Torsten Hoefler:
 Towards coordinated optimization of computation and communication in parallel applications (Presentation) Fakultaet fuer Informatik, Universität Münster. presented in Muenster, Germany, Jun. 2008,
MPI Forum
[115] Torsten Hoefler, Jesper Larsson Träff, Christian Siebert and Andrew Lumsdaine:
 MPI-3 Collective Working Group - June'08 Meeting (Presentation) Indiana University. presented in Menlo Park, CA, USA, Jun. 2008, Activity Report to the MPI Forum
IWR-TUD
[116] Torsten Hoefler:
 Non-Blocking Collectives for MPI (Presentation) Institut fuer Wissenschaftliches Rechnen, Technische Universitaet Dresden. presented in Dresden, Germany, May 2008,
MPI Forum
[117] Torsten Hoefler and Andrew Lumsdaine:
 MPI-3 Collective Working Group - April'08 Meeting (Presentation) Indiana University. presented in Chicago, IL, USA, Apr. 2008, Slides with proposals to the MPI-3 collective WG, all preliminary, published on request
MPI Forum
[118] Torsten Hoefler and Andrew Lumsdaine:
 MPI-3 Collective Working Group - January'08 Meeting (Presentation) Indiana University. presented in Chicago, IL, USA, Mar. 2008, Slides with proposals to the MPI-3 collective WG, all preliminary, published on request
HLRS
[119] Torsten Hoefler:
 Non-blocking Collectives for MPI-2 (Presentation) High Performance Computing Center Stuttgart (HLRS). presented in Stuttgart, Germany, Dec. 2007,
NEC'07
[120] Torsten Hoefler:
 Accurately Measuring Collective Operations at Massive Scale (Presentation) C&C Research Laboratories, NEC Europe Ltd.. presented in Sankt Augustin, Germany, Dec. 2007,
ZiH-TUD
[121] Torsten Hoefler:
 Non-blocking Collectives for MPI-2 (Presentation) Dresden University of Technology, Center for Information Services and High Performance Computing (ZIH). presented in Dresden, Germany, Oct. 2007,
Talk
[122] Frank Mietke, Torsten Hoefler, Torsten Mehlan and Wolfgang Rehm:
 Diskless Cluster und Lustre - Erfahrungsbericht zum CHiC (Presentation) TU Chemnitz. presented in Chemnitz, Germany, Apr. 2007,
ZKI'07
[123] Frank Mietke, Torsten Mehlan, Torsten Hoefler and Wolfgang Rehm:
 Stand HPC Cluster CHiC (Presentation) TU Chemnitz. presented in Chemnitz, Germany, Apr. 2007,
CEA'06
[124] Torsten Hoefler:
 Application Optimization with non-blocking Collectives (Presentation) Commissariat a l'Energie Atomique - Direction des applications militaires (CEA-DAM). presented in Bruyeres-le-chatel, France, Jan. 2007,
CEA'07
[125] Torsten Hoefler:
 Non-Blocking Collectives for MPI-2 (Presentation) Commissariat a l'Energie Atomique - Direction des applications militaires (CEA-DAM). presented in Bruyeres-le-chatel, France, Jan. 2007,
ABINIT'07
[126] Torsten Hoefler and G. Zerah:
 Optimization of a parallel 3d-FFT with non-blocking collective operations (Presentation) Invited to the 3rd International ABINIT Developer Workshop. presented in Liege, Belgium, Jan. 2007,
NEC'06
[127] Torsten Hoefler:
 Non-blocking Collectives for MPI-2 (Presentation) C&C Research Laboratories, NEC Europe Ltd.. presented in Sankt Augustin, Germany, Nov. 2006,
OMPI'06
[128] Torsten Hoefler:
 Open MPI - Collv2 Design (Presentation) Cisco Systems. presented in San Jose, CA, USA, Apr. 2006,
ABINIT'06
[129] Torsten Hoefler:
 Parallelization Options for the Band-by-Band Minimization of Teter et. al. (Presentation) Universite catholique de Louvain. presented in Louvain-la-Neuve, Belgium, Feb. 2006,
SFB'05
[130] Torsten Hoefler and Wolfgang Rehm:
 Communication/Computation Overlap in MPI (Presentation) Technical University of Chemnitz. presented in Chemnitz, Germany, Nov. 2005,
TUM'05
[131] Torsten Hoefler:
 Fast Barrier Synchronization for InfiniBand (Presentation) Technical University of Chemnitz. presented in Munich, Germany, Sep. 2005,
URZ-WS'04
[132] Torsten Hoefler:
 Remote network analysis (Presentation) Technical University of Chemnitz, URZ Workshop. presented in Loebsal, Germany, May 2004,
Unix-ST'04
[133] Torsten Hoefler:
 Remote network analysis (Presentation) Technical University of Chemnitz, Unix Stammtisch. presented in Chemnitz, Germany, May 2004,

serving: 18.205.60.226:42302© Torsten Hoefler