The Second International Workshop on
Accelerators and Hybrid Exascale Systems (AsHES)
Accelerators and Hybrid Exascale Systems (AsHES)
Join us on May 25th, 2012 in Shanghai, China
to be held in conjunction
with
IPDPS 2012: IEEE International Parallel and Distributed Processing Symposium
IPDPS 2012: IEEE International Parallel and Distributed Processing Symposium
Opening Session
8:00am - 9:30am
- Opening Remarks Pavan Balaji, Jiayuan Meng, Yunquan Zhang and Satoshi Matsuoka
- Keynote: An Ecosystem for the New HPC: Heterogeneous Parallel Computing Prof. Wu-chun Feng, Virginia Tech Slides Abstract: With processor core counts doubling every 18-24 months and penetrating all markets from high-end servers in supercomputers to desktops and laptops down to even mobile phones, we sit at the dawn of a world of ubiquitous parallelism, one where extracting performance via parallelism is paramount. That is, the "free lunch" to better performance, where programmers could rely on substantial increases in single-threaded performance to improve software, is over. The burden falls on developers to exploit parallel hardware for performance gains. But how do we lower the cost of extracting such parallelism, particularly in the face of the increasing heterogeneity of processing cores? To address this issue, this talk will present a vision for an ecosystem for delivering accessible and personalized supercomputing to the masses, one with a heterogeneity of (hardware) processing cores on a die or in a package, coupled with enabling software that tunes the parameters of the processing cores with respect to performance, power, and portability via a benchmark suite of computational dwarfs and applications.
Break
10:00am-10:30am
Session 1: Modeling and Optimization
10:30am - 12:00pm
Session Chair: Prof. Wenguang Cheng, Tsinghua Universty, China- Modeling and Predicting Performance of High Performance Computing Applications on Hardware Accelerators. Mitesh Meswani, Laura Carrington, Didem Unat, Allan Snavely, Scott Baden and Stephen Poole Slides
- Efficient Intranode Communication in GPU-Accelerated Systems. Feng Ji, Ashwin Aji, James Dinan, Darius Buntinas, Pavan Balaji, Wu-Chun Feng and Xiaosong Ma Slides
- Optimizing MPI Communication on Multi-GPU Systems using CUDA Inter-Process Communication. Sreeram Potluri, Hao Wang, Devendar Bureddy, Ashish Singh, Carlos Rosales and Dhabaleswar Panda Slides
Lunch
12:00pm - 1:30pm
Session 2: Programming Models
1:30pm - 3:00pm
Session Chair: Dr. Vinod Tipparaju, AMD, USA- Towards High-Level Programming of Multi-GPU Systems Using the SkelCL Library. Michel Steuwer, Philipp Kegel and Sergei Gorlatch Slides
- Scaling Data-Intensive Applications on Heterogeneous Platforms with Accelerators. Ana Balevic and Bart Kienhuis Slides
- An Analysis of Multicore Specific Optimization in MPI Implementations. Pengqi Cheng and Yan Gu Slides
Break
3:00pm-3:30pm
Session 3: Accelerated Applications
3:30pm - 4:30pm
Session Chair: Prof. Toshio ENDO, Tokyo Institute of Technology, Japan- Parallelizing the Hamiltonian Computation in DQMC Simulations: Checkerboard Method for Sparse Matrix Exponentials on Multicore and GPU. Che-Rung Lee, Zhi-Hung Chen and Quey-Liang Kao Slides
- Parallel Multi-Temporal Remote Sensing Image Change Detection on GPU. Huming Zhu, Yu Cao, Zhiqiang Zhou and Maoguo Gong Slides
- Implementing High-performance Intensity Model with Blur Effect on GPUs for Large-scale Star Image Simulation. Chao Li and Yunquan Zhang. Presented by Liang Yuan Slides
Web Chair: Gregory Diamos, NVIDIA