Monday Sep 24th
8:00 Registration opens
9:00 Welcome Message - Joint presentation with EuroMPI
9:30 Keynote Presentation - Joint with EuroMPI
Jesus Labarta, BSC
10:30 Coffee break
11:00 1st Paper Session
Jose Manuel Monsalve Diaz, Gabriele Jost, Sunita Chandrasekaran and Sergio Pino
"Is OpenMP 4.5 Target Off-load Ready for Real Life? -- A Case Study of Three Benchmarks Kernels"
Jaume Bosch, Xubin Tan, Carlos Álvarez, Daniel Jiménez, Xavier Martorell and Eduard Ayguadé
"Asynchronous Task Creation for Task-Based Parallel Programming Runtimes"
2:00pm 2nd Paper Session
Oscar Hernandez, Helen He and Barbara Chapman
"Using MPI+OpenMP for current and future architectures"
Vicenç Beltran, Xavier Teruel, Kevin Sala, Josep M. Perez and Jesus Labarta
"Extending the Task-Aware MPI (TAMPI) library to support asynchronous MPI primitives"
Jim Cownie and Jonathan Peyton
"Small, Easy to Use, OpenMP* Features You May Have Missed"
"OpenMP API 5.0 - Update on new Features"
8:00pm Social Dinner -- El Xalet de Montjuïc
Bus service will be provided
Tuesday Sep 25th
9:30 Keynote Presentation -- Joint with EuroMPI
Bronis R. de Supinski, Lawrence Livermore National Laboratory
10:30 Coffee break
11:00 3rd Paper Session
Jannek Squar, Michael Blesel, Michael Kuhn and Thomas Ludwig
"Compiler assisted source-to-source transformation of OpenMP kernels to utilise distributed memory"
Xubin Tan, Jaume Bosch, Carlos Álvarez, Daniel Jiménez-González and Eduard Ayguadé
"Hardware Hetergeneous Task Scheduling for Task-based Programming Models"
Vivek Kale and Martin Kong
"Enhancing Support in OpenMP to Improve DataLocality in Application Programs Using Task Scheduling"
2:00pm Keynote Presentation
3:00pm 4th Paper Session
"OpenMP usage on ARCHER"
Jim Cownie, Dmitry Prohorov and Alejandro Duran
"Tuning OpenMP* Codes with Intel® Vtune™ Performance Analyzer"
Idan Mosseri, Re'Em Harel, Harel Levin, Matan Rusanovsky and Gal Oren
"Automatic Parallelization for Shared Memory Scientific Multiprocessing"
Wednesday, Sep. 26th
Thursday Sep. 27th
8:30 Registration opens
9:30 Welcome to IWOMP 2018
9:40 Keynote -- Alejandro Duran (Intel Corporation)
"10 years of task parallelism in OpenMP: a success story?"
Abstract: OpenMP 3.0 introduced the concept of task parallelism. Over the past ten years, OpenMP has continued to expand its tasking model to allow more expressiveness and performance. In this talk, we will explore the design principles that guided the introduction of task parallelism, the new features that have been added over the years, and its outlook for the upcoming OpenMP 5.0 specification and beyond.
Bio: Alex obtained his PhD degree in Computer Architecture by the Universitat Politècnica de Catalunya in 2008. He currently is an Application Engineer at Intel Corporation. He was previously a Senior Researcher at the Barcelona Supercomputing Center. He joined the OpenMP Language Committee in 2006 and has helped to develop the areas of tasking, SIMD, scheduling and memory management among others. His areas of interest are parallel programming models, runtime optimizations and performance analysis.
10:30 Best Paper
Joseph Schuchart, Keisuke Tsugane, Jose Gracia and Mitsuhisa Sato
"The Impact of Taskyield on the Design of Tasks Communicating through MPI"
11:00 Coffee break
11:30 1st Paper Session: Loops and OpenMP
Florina M. Ciorba, Christian Iwainsky and Patrick Buder
"OpenMP Loop Scheduling Revisited: Making a Case for More Schedules"
Michael Kruse and Hal Finkel
"A Proposal for Loop-Transformation Pragmas"
Ian Bertolacci, Michelle Strout, Bronis de Supinski, Tom Scogland,Eddie Davis and Catherine Olschanowsky
"Extending OpenMP to Facilitate Loop Optimization"
2:30pm 2nd Paper Session: OpenMP in Heterogeneous Systems
Lingda Li, Hal Finkel, Martin Kong and Barbara Chapman
"Manage OpenMP GPU Data Environment under Unified Address Space"
Swaroop Pophale, Jose Manuel Monsalve Diaz, Oscar Hernandez, David E. Bernholdt and Sunita Chandrasekaran
"OpenMP 4.5 Validation and Verification Suite for Device Offload"
Yutaka Watanabe, Jinpil Lee, Taisuke Boku and Mitsuhisa Sato
"Trade-off of offloading to FPGA in OpenMP Task-based programming"
4:00pm Coffee break
4:30pm 3rd Paper Session: OpenMP Improvements and Innovations
Johannes Doerfert and Hal Finkel
"Compiler Optimizations For OpenMP"
John Pennycook, Jason Sewall and Alejandro Duran
"Supporting Function Variants in OpenMP"
Maria A. Serrano, Sara Royuela and Eduardo Quiñones
"Towards an OpenMP Specification for Critical Real-time Systems"
6:00pm End of the day
8:00pm Social Dinner -- El Asador de Aranda
Friday, Sep. 28th
10:00 Keynote - Simon Mcintosh-Smith (Univ. of Bristol)
"OpenMP on future architectures"
Abstract: OpenMP has proven its ability to scale well on today’s CPUs and GPUs, but how will it fare in the future? In this talk we will describe some recent results which explore OpenMP’s abilities to scale to high core counts on next-generation CPUs, as well as new results from the latest GPUs.
Bio: Simon McIntosh-Smith is a full Professor of High Performance Computing at the
University of Bristol in the UK. He began his career as a microprocessor
architect at Inmos and STMicroelectronics in the early 1990s, before
co-designing the world's first fully programmable GPU at Pixelfusion in 1999. In
2002 he co-founded ClearSpeed Technology where, as Director of Architecture and
Applications, he co-developed the first modern many-core HPC accelerators. He
now leads the High Performance Computing Research Group at the University of
Bristol, where his research focuses on performance portability and application
based fault tolerance. He plays a key role in designing and procuring HPC
services at the local, regional and national level, including the UK’s national
HPC server, Archer. In 2016 he led the successful bid by the GW4 Alliance along
with the UK’s Met Office and Cray, to design and build ‘Isambard’, the world’s
first production, ARMv8-based supercomputer.
11:00 Coffee break
11:30 4th Paper Session: OpenMP User Experiences: Applications and Tools
Tianmu Xin, Zhengji Zhao, Yue Hao, Binping Xiao, Qiong Wu, Kevin Smith, Alexander Zaltsman and Xinmin Tian
"Performance Tuning to Close Ninja Gap for Accelerator Physics Emulation System (APES) on Intel Xeon Phi Processors"
Vishakha Agrawal, Michael J. Voss, Pablo Reble, Vasanth Tovinkere, Jeff Hammond and Michael Klemm
"Visualization of OpenMP Task Dependencies using Intel Advisor Flow Graph Analyzer"
Chunhua Liao, Pei-Hung Lin, Markus Schordan and Ian Karlin
"A Semantics-Driven Approach to Improving DataRaceBench's OpenMP Standard Coverage"
2:30pm 5th Paper Session: Tasking Evaluations
Thierry Gautier, Christian Perez and Jérôme Richard
"On the Impact of OpenMP Task Granularity"
Jeremy Kemp and Barbara Chapman
"Mapping OpenMP to a Distributed Tasking Runtime"
Jannis Klinkenberg, Philipp Samfass, Christian Terboven, Alejandro Duran, Michael Klemm, Xavier Teruel, Sergi Mateo, Stephen L. Olivier and Matthias Mueller
"Assessing Task-to-Data Affinity in the LLVM OpenMP Runtime"