HeteroPar'2020 Program

Opening session
09:00 - 09:15 Welcome from Steering Committee and Program Chair
Roman Wyrzykowski
Session 1: Algorithms and languages for heterogeneous computing
Chair: Alexey Lastovetsky
09:15 - 10:00 Scientific keynote 1: Prof. Enrique S. Quintana-Orti, Technical University of Valencia
Opportunities for Approximate vs Transprecision Computing in Sparse Linear Solvers for GPUs (abstract)
10:00 - 10:30 Samer Alhaddad, Jens Förstner, Stefan Groth, Daniel Grünewald, Yevgen Grynko, Frank Hannig, Tobias Kenter, Franz-Josef Pfreundt, Christian Plessl, Merlind Schotte, Thomas Steinke, Jürgen Teich
HighPerMeshes - A Domain-Specific Language for Numerical Algorithms on Unstructured Grids
10:30 - 11:00 Coffee break
Session 2: Software engineering for heterogeneous parallel systems
Chair: Tal El-Nun
11:00 - 11:30 Niklas Eiling, Stefan Lankes and Antonello Monti
An Open-Source Virtualization Layer for CUDA Applications
11:30 - 12:00 Lena Oden.
Implementation and evaluation of CUDA-Unified memory in Numba
12:00 - 12:30 Yuhsiang M. Tsai, Terry Cojean, Tobias Ribizel and Hartwig Anzt
Preparing Ginkgo for AMD GPUs - A Testimonial on Porting CUDA Code to HIP
12:30 - 13:15 Lunch
Session 3: Heterogeneous computing and machine learning/AI algorithms
Chair: Enrique S. Quintana-Orti
13:15 - 14:00 Scientific keynote 2: Tal El-Nun, ETHZ Zurich
Stateful Dataflow Multigraphs: A Data-Centric Approach for Performance Portability on Heterogeneous Architectures (abstract)
14:00 - 14:30 Paweł Koperek, Wlodzimierz Funika and Jacek Kitowski
Management of heterogeneous cloud resources with use of the Proximal Policy Optimization
14:30 - 15:00 Tokio Kibata, Mineto Tsukada and Hiroki Matsutani
An Edge Attribute-wise Partitioning and Distributed Processing of R-GCN using GPUs
15:00 - 15:30 Coffee break
Session 4: Heterogeneous parallel computing
Chair: Leonel Sousa
15:30 - 16:00 Yaniv Rubinpur and Sivan Toledo
High-Performance GPU and CPU Signal Processing for a Reverse-GPS Wildlife Tracking System
16:00 - 16:30 Guanlin He, Stephane Vialle and Marc Baboulin
Parallelization of the k-means algorithm in a spectral clustering chain on CPU-GPU platforms
16:30 - 17:00 Beata Dmitruk and Przemyslaw Stpiczynski
High Performance Portable Solver for Tridiagonal Toeplitz Systems of Linear Equations