07:00 - 08:00 | top^ |
---|
Breakfast and Registration |
08:00 - 08:30 | top^ |
---|
HiPC 2014: Inauguration and Opening Remarks |
08:30 - 9:30 | top^ |
---|
Keynote 1: Die Stacking is Happening |
Bryan Black (Senior AMD Fellow, USA) |
Session Chair: |
09:30 - 10:00 | top^ |
---|
Break |
10:00 - 12:00 | top^ |
---|
Technical Session 1: Network and Computer Architectures |
Session Chair: Murali Annavaram |
- Optical Overlay NUCA: A High Speed Substrate for Shared L2 Caches
Eldhose Peter (Indian Institute of Technology Delhi, India); Anuj Arora (Indian Institute of Technology, Delhi, India); Akriti Bagaria (IIT Delhi, India); Smruti Sarangi (IIT Delhi, India);
- Trikon: A Hypervisor Aware Manycore Processor
Rohan Bhalla (Indian Institute of Technology, Delhi, India); Prathmesh Kallurkar (Indian Institute of Technology, Delhi, India); Nitin Gupta (Amazon India pvt ltd, India); Smruti Sarangi (IIT Delhi, India);
- Matrix-Matrix Multiplication on a Large Register File Architecture with Indirection
Dheeraj Sreedhar (IBM India Research Labs, India); Jeff H. Derby (IBM, USA); Robert Montoye (IBM Research Division, USA); Charles Johnson (IBM Research Division, USA);
- Scaling Graph Community Detection on the Tilera Many-core Architecture
Daniel Gerardo Chavarria (Pacific Northwest National Laboratory, USA); Mahantesh Halappanavar (Pacific Northwest National Laboratory, USA); Ananth Kalyanaraman (Washington State University, USA);
- Balancing Context Switch Penalty and Response Time with Elastic Time Slicing
Nagakishore Jammula (Georgia Institute of Technology, USA); Moinuddin Qureshi (Georgia Institute of Technology, USA); Ada Gavrilovska (Georgia Institute of Technology, USA); Jongman Kim (Georgia Institute of Technology, USA);
- Optimizing the performance of parallel applications on a 5D torus via task mapping
Abhinav Bhatele (Lawrence Livermore National Laboratory, USA); Nikhil Jain (UIUC, USA); Katherine Isaacs (University of California, Davis, USA); Ronak Buch (University of Illinois at Urbana-Champaign, USA); Todd Gamblin (Lawrence Livermore National Laboratory, USA); Steven Langer (Lawrence Livermore National Laboratory, USA); Laxmikant V. Kale (University of Illinois at Urbana-Champaign, USA);
|
IRUS 1: Computational Atmospheric and Climate Science in HPC: Methods being developed to tackle the performance issues |
Industry Demos & Exhibits |
12:00 - 13:30 | top^ |
---|
Lunch |
13:30 - 15:30 | top^ |
---|
Technical Session 2: MPI, I/O and Interconnects |
Session Chair: Vipin Chaudhary |
- DRIVE: Using Implicit Caching Hints to achieve Disk I/O Reduction in Virtualized Environments
Sujesha Sudevalayam (IIT Bombay, India); Purushottam Kulkarni (Indian Institute of Technology, Bombay, India); Rahul Balani (IBM Research India, India); Akshat Verma (IBM Research - India, India);
- High Performance MPI Library over SR-IOV Enabled InfiniBand Clusters
Jie Zhang (The Ohio State University, USA); Xiaoyi Lu (The Ohio State University, USA); Jithin Jose (The Ohio State University, USA); Mingzhe Li (The Ohio State University, USA); Rong Shi (The Ohio State University, USA); Dhabaleswar Panda (The Ohio State University, USA);
- A High Performance Broadcast Design with Hardware Multicast and GPUDirect RDMA for Streaming Applications on Infiniband Clusters
Akshay Venkatesh (Ohio State University, USA); Hari Subramoni (Senior Research Associate, USA); Khaled Hamidouche (The Ohio State University, USA); Dhabaleswar Panda (The Ohio State University, USA);
- Combining HoL-blocking Avoidance and Differentiated Services in High-Speed Interconnects
Pedro Yebenes (University of Castilla-La Mancha, Spain); Jesús Escudero-Sahuquillo (University of Castilla-La Mancha, Spain); Crispin Gomez (University of Castilla-La Mancha, Spain); Pedro Garcia (University of Castilla-La Mancha, Spain); Francisco Jose Alfaro (University of Castilla-La Mancha, Spain); Francisco J. Quiles (Universidad Castilla La Mancha, Spain); Jose Duato (Universidad Politecnica de Valencia, Spain);
- Designing Efficient Small Message Transfer Mechanism for Inter-node MPI Communication on InfiniBand GPU Clusters
Rong Shi (The Ohio State University, USA); Sreeram Potluri (The Ohio State University, USA); Khaled Hamidouche (The Ohio State University, USA); Mingzhe Li (The Ohio State University, USA); Davide Rossetti (NVIDIA Corporation, USA); Dhabaleswar Panda (The Ohio State University, USA);
- On the Suitability of MPI as a PGAS Runtime
Jeff Daily (Pacific Northwest National Laboratory, USA); Abhinav Vishnu (Pacific Northwest National Laboratory, USA); Bruce Palmer (Pacific Northwest National Laboratory, USA); Hubertus J. J. Van Dam (Pacific Northwest National Lab, USA); Darren J. Kerbyson (Pacific Northwest National Laboratory, USA);
|
Industry BOF 1-SHELL: Simulating and Visualizing Fluid Flow: HPC challenges |
Industry Demos & Exhibits |
15:30 - 16:00 | top^ |
---|
Break |
16:00 - 18:00 | top^ |
---|
Technical Session 3: Graph Partitioning and Numerical Algorithms |
Session Chair: Lionel Eyraud-Dubois |
- A Multilevel Compressed Sparse Row Format for Efficient Sparse Computations on Muticore Processors
Humayun Kabir (The Pennsylvania State University, USA); Joshua Booth (The Pennsylvania State University, USA); Padma Raghavan (The Pennsylvania State University, USA);
- Analysis and Tuning of Libtensor Framework on Multicore Architectures
Khaled Z Ibrahim (Lawrence Berkeley National Labratory, USA); Samuel W. Williams (Lawrence Berkeley National Laboratory, USA); Evgeny Epifanovsky (UC Berkeley, USA); Anna Krylov (University of Southern California, USA);
- Reducing elimination tree height for parallel LU factorization of sparse unsymmetric matrices
Enver Kayaaslan (INRIA, France); Bora Uçar (CNRS, France);
- Optimization of Scan Algorithms on Multi- and Many-core Processors
Qiao Sun (Institute of Software, Chinese Academy of Sciences, P.R. China); Chao Yang (Institute of Software, Chinese Academy of Sciences, P.R. China);
- Coupling-Aware Graph Partitioning Algorithms
Aurélien Esnard (University of Bordeaux, LaBRI, INRIA Bordeaux Sud-Ouest, HiePACS, France); Maria Predari (University of Bordeaux, INRIA Bordeaux Sud-Ouest, HiePACS, France);
- An improved recursive graph bipartitioning algorithm for well balanced domain decomposition
Astrid Casadei (Bordeaux University, France); Pierre Ramet (University of Bordeaux, France); Jean Roman (INRIA, France);
|
Industry BOF 2-NVIDIA: CUDA 7 and Beyond & Machine Learning with GPUs |
Industry Demos & Exhibits |
18:00 - 19:00 | top^ |
---|
Break |
19:00 - 21:00 | top^ |
---|
Industry BOF 3-MELLANOX: EDR - Step into the world of 100Gb/s |