OpenMP UK Users' Conference
 June 4-5, 2019 | Edinburgh
Join us at EPCC in Edinburgh for the 2nd OpenMP Users conference for two days of talks and tutorials aimed at furthering the collaboration and knowledge sharing amongst the UK community of high-performance computing specialist using OpenMP. The submission deadline has been extended to Sunday 7th April.
Details, Submission and Registration
|
|
OpenMP GPU Directives Workshop
 May 22, 2019 | University of Stuttgart
This workshop will cover the directive-based programming model based on OpenMP v4 whose multi-vendor support allows users to portably develop applications for parallel accelerated supercomputers. It also includes comparison to the predecessor interface OpenACC v2. The workshop will also demonstrate how to use the Cray Programming Environment tools to identify application bottlenecks, facilitate the porting, provide accelerated performance feedback and to tune the ported applications.
Details at: hlrs.de/events/training/detail-view/2019-05-22-GPU/
|
|
Get OpenMP 4.5 Validation and Verification Suite
 As part of the Exascale Computing Project, the SOLLVE project (Scaling OpenMP Via LLVM for Exascale Performance and Portability) is currently working on a framework that, through the use of simple test cases (e.g. unit tests, functional tests and micro-applications), assess compiler implementations and compliance for developers and system architectures.
|
|
OpenMP Webinar Video
 In case you missed the March webinar, see the video "OpenMP 5.0: A Story about Threads and Tasks." In this webinar, OpenMP ARB CEO Michael Klemm discusses how OpenMP works and what the future holds, and he reviews the new features in OpenMP 5.0.
For the Q&A session from the webinar, see: https://techdecoded.intel.io/webinar-qas-from-openmp-5-0-a-story-about-threads-and-tasks-webinar/#gs.1x4trg
|
|
Performance of OpenMP’s Target Construct on GPUs
Download the paper exploring the potential performance improvements of compiling and optimizing high-level programs for GPU execution using OpenMP. This paper shows OpenMP can reach the performance of hand-written CUDA and automatically-generated GPU programs by the IBM XL and clang/LLVM compilers, benchmarked on two NVIDIA Tesla GPUs (K80 and P100).
Download the paper at https://hgpu.org/?p=18745
|
|
 New OpenMP Implementation
Researchers from The STE||AR Group have developed an implementation of the OpenMP standard called hpxMP, which utilizes the underlying asynchronous many-task system to schedule and manage tasks.
arxiv.org/abs/1903.03023
hpxMP on Github
|
|
|
|
|
