The electronic proceedings of the workshop are available from the ACM Digital Library. Click on the image above or on the ACM page links below.

We also include below the links to the slides for each presentation from the workshop.

Workshop Workshop
Workshop audience. We came close to breaking our attendance record, with over 50 participants in the room at one point.


Wednesday, June 1, 2016, Special Conference Room (2nd floor)



Kenjiro Taura A Quest for Unified, Global View Parallel Programming Models for Our Future
Kenjiro Taura
Abstract, Bio, ACM page, Slides (728 KB)
Coffee Break

Session I: Operating Systems (chair: Christian Engelmann)

Carsten Weinhold Decoupled: Low-Effort Noise-Free Execution on Commodity Systems
Adam Lackorzynski, Carsten Weinhold, Hermann Härtig
ACM page, Slides (4.9 MB)
Noah Evans A Cross-Enclave Composition Mechanism for Exascale System Software
Noah Evans, Kevin Pedretti, Brian Kocoloski, John Lange, Michael Lang, Patrick G. Bridges
ACM page, Slides (2.8 MB)
Stefan Lankes HermitCore—A Unikernel for Extreme Scale Computing
Stefan Lankes, Simon Pickartz, Jens Breitbart
ACM page, Slides (456 KB)
Yutaka Ishikawa A Multi-Kernel Survey for High-Performance Computing
Balazs Gerofi, Yutaka Ishikawa, Rolf Riesen, Robert W. Wisniewski, Yoonho Park, Bryan Rosenburg
ACM page, Slides (823 KB)

Session II: Runtime Systems and Accelerators (chair: John Lange)

Feras Daoud GPUrdma: GPU-side Library for High Performance Networking from GPU Kernels
Feras Daoud, Amir Watad, Mark Silberstein
ACM page, Slides (1.8 MB)
Paul Harvey A Scalable Runtime for the ECOSCALE Heterogeneous Exascale Hardware Platform
Paul Harvey, Konstantin Bakanov, Ivor Spence, Dimitrios S. Nikolopoulos
ACM page, Slides (2.0 MB)
Jeffrey Vetter Using Application-Specific Performance Models to Inform Dynamic Scheduling (invited talk)
Jeffrey S. Vetter
Abstract, Bio, Slides (7.1 MB)
Kyle Hale Accelerating Asynchronous Events for Hybrid Parallel Runtimes (invited talk)
Kyle Hale
Abstract, Bio, Slides (3.7 MB)
Coffee Break


The Role of System Software in the HPC Accelerator Space
Moderator: Torsten Hoefler, ETH Zurich, Opening slides (2.3 MB)
Satoshi Matsuoka, Tokyo Institute of Technology
Taisuke Boku, University of Tsukuba
Naoya Maruyama, RIKEN
Paul Harvey, Queen’s University Belfast
Feras Daoud, Technion
Panel Panel Panel
In the pictures: Torsten Hoefler (standing in the first picture), Satoshi Matsuoka, Taisuke Boku, Naoya Maruyama, Paul Harvey, Feras Daoud (sitting left-to-right).
Closing Remarks
Best Paper Award went to Feras Daoud et al. for the paper GPUrdma: GPU-side Library for High Performance Networking from GPU Kernels.
Best Paper Award
In the picture: paper author Feras Daoud (center); workshop chairs Kamil Iskra (left) and Torsten Hoefler (right).