2nd International Workshop on

Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS11)

held as part of SC11, Seattle, WA, USA, November 13th 2011, in association with ACM SIGMETRICS


09:00 - Welcome by the PMBS Workshop Chair - Professor Stephen Jarvis, University of Warwick, UK

09:00 - 09:30 - Evaluating Interconnect and Virtualization Performance for High Performance Computing, L. Ramakrishnan, R.S. Canon, K. Muriki, I. Sakrejda, N. Wright, LBNL (USA) [Research Note]

09:30 - 10:00 - Predictive Modeling and Analysis of OP2 on Distributed Memory GPU Clusters, G. Mudalige, M. Giles, C. Bertolli, P. Kelly, University of Oxford (UK), Imperial College London (UK) [Research Note]

10:00 - 10:30 - Optimizing Matrix Transposes Using a POWER7 Cache Model and Explicit Prefetching, G. Mateescu, G. Bauer, R. Fiedler, EPFL (Switzerland), NCSA (USA) [Research Note]

10:30 - 11:00 - Morning Coffee

11:00 - 11:30 - BlackjackBench: Portable Hardware Characterization, A. Danalis, P. Luszczek, G. Marin, J. Vetter, J. Dongarra, University of Tennessee (USA), ORNL (USA) [Research Note]

11:30 - 12:00 - Towards Autotuning by Alternating Communication Methods, A. Tineo, S. Alam, T. Schulthess, CSCS (Switzerland) [Research Note]

12:00 - 12:30 - Modeling Performance through Memory-Stalls, R. Iakymchuk, P. Bientinesi, RWTH Aachen (Germany) [Research Note]

12:30 - 14:00 - Lunch

14:00 - 14:30 - A Preliminary Evaluation of the Hardware Acceleration of the Cray Gemini Interconnect for PGAS Languages and Comparison with MPI, H. Shan, N. Wright, J. Shalf, K. Yelick, M. Wagner, N. Wichmann, LBNL (USA), NERSC (USA), Cray (USA) [Research Note]

14:30 - 15:00 - Auto-Generation of Communication Benchmark Traces, V. Deshpande, X. Wu, F. Mueller, North Carolina State University (USA) [Research Note]

15:00 - 15:30 - A Method for Automatically Generating Analogue Benchmark Suites using Low-Level Hardware Metrics, S. McIntosh-Smith, O. Thomas, University of Bristol (UK), Red Oak Consulting (UK) [Research Note]

15:30 - 16:00 - Afternoon Coffee

16:00 - 16:30 - Critical Path-Based Thread Placement for NUMA Systems, C. Su, D. Li, D, Nikolopoulos, M. Grove, K. Cameron, B. de Supinski, Virginia Tech (USA), ORNL (USA), LLNL (USA), University of Crete (Greece) [Research Note]

16:30 - 17:00 - Benchmarking Disk-based Archival Storage Tiers using Appropriate Archival Workloads, D. Lee, M. O'Sullivan, C. Walker, University of Auckland (New Zealand) [Research Note]

17:00 - 17:30 - Towards Efficient GPU Sharing on Multicore Processors, L. Wang, M. Huang, T. El-Ghazawi, George Washington University (USA), University of Arkansas (USA) [Research Note]

17:30 - 18:00 - Memory Access Cycle and the Measurement of Memory Systems, X.-H. Sun, D. Wang, Illinois Institute of Technology (USA) [Research Note]

18:00 - Workshop Close