Jun 02

Print this Post

GCoE Presentations | June 2016 (ISC, …)

In “GCoE Presentations” we want to announce upcoming presentations from our GCoE members. In June 2016 the ISC in Frankfurt will be one highlight. Next month we want to post short insights from the conferences and workshops here. So these are the contributions in June 2016:

ISC High Performance & Workshops, 23/06/2016, Frankfurt

ISC, 23/06/2016, Frankfurt
Workshop On In-situ Visualization
Alexander Matthes
“ISAAC” is an in-situ visualization library with focus on fast rendering of scientific data already presented in the memory of computation accelerators like Nvidia GPUs using the abstraction library Alpaka. For this no copy of data is needed at all. Possibly needed data transformations of the raw scientific data are done on the fly with so called Functor Chains. Beside this it is also possible to steer the simulation while it’s running. The visualization and steering client is implemented as html5 webpage, but the open protocols also easily allow for alternative implementations.

ISC, 23/06/2016, Frankfurt
Tutorial Hands-on Practical Hybrid Parallel Application Performance Engineering
Markus Geimer, Michael Gerndt, Allen Malony, Ronny Tschüter
[…] Parallel performance tools from the Virtual Institute – High Productivity Supercomputing (VI-HPS) are introduced and featured in hands-on exercises with Scalasca, Vampir, Periscope Tuning Framework and TAU. We present the complete workflow of performance engineering, including instrumentation, measurement (profiling and tracing, timing and PAPI hardware counters), data storage, analysis, tuning, and visualization. […]

IWOPH workshop, 23/06/2016, Frankfurt
Performance-Portable Many-Core Plasma Simulations: Porting PIConGPU to OpenPower and Beyond
René Widera and Erik Zenker
We want to present an important step in porting our PIC code towards the OpenPower platform.

P^3MA workshop, 23/06/2016, Frankfurt
Porting the MPI parallelized LES model PALM to multi-GPU systems – An experience report
Helge Knoop , Christoph Knigge , Tobias Gronemeier , Peter Steinbach
[…] This paper is a report on our experience of porting the MPI+OpenMP parallelized large-eddy simulation model (PALM) to a multi-GPU environment using the directive based high level programming paradigm OpenACC. PALM is a Fortran-based computational fluid dynamics software package, used for the simulation of atmospheric and oceanic boundary layers to answer questions linked to fundamental atmospheric turbulence research, urban climate, wind energy and cloud physics. […] The porting took place during the Oak Ridge National Laboaratory GPU Hackathon 2016. The main challenges we faced are the legacy code base of PALM and its size. We report the methods used to disentangle performance effects from logical code defects as well as our experiences with state-of-the-art profiling tools. First performance tests comparing the execution time of all ported routines exhibit a twenty-fold speed-up on a GPU.

P^3MA workshop, 23/06/2016, Frankfurt
From Describing to Prescribing Parallelism: Translating the SPEC ACCEL OpenACC Suite to OpenMP Target Directives
Guido Juckeland, …
[…] One of the goals of OpenMP and OpenACC is to allow the user to specify parallelism via directives so that compilers can generate device specific code and optimizations. However, the challenge of porting codes becomes more complex because of the different types of parallelism and memory hierarchies available on different architectures. […] In this paper we discuss our experience with porting the SPEC ACCEL benchmarks from OpenACC to OpenMP 4.5 using a performance portable style that lets the compiler make platform-specific optimizations to achieve good performance on a variety of systems. The ported SPEC ACCEL OpenMP benchmarks were validated on different platforms including Xeon Phi, GPUs and CPUs. We believe that this experience can help the community and compiler vendors understand how users plan to write OpenMP 4.5 applications in a performance portable style.

Further Presentations in June

PASC16, 08/06/2016 – 10/06/2016, EPFL, Lausanne, Switzerland
Interactive Plasma Simulations on Next Generation Supercomputers for Everybody
Axel Huebl
We were explicitly invited by the gyro-kinetic PIC HPC community, after one of the organizers saw my last presentation in the US, to share our expertise in Nvidia GPU-powered algorithms and to participate in the porting efforts of their gyro-PIC codes to GPU systems. The talk will cover our plasma physics platform around PIConGPU, including our common work on libPMacc for general, accelerated particle-mesh methods, kernel acceleration via alpaka, our open data format for particle and mesh data sets (openPMD) and our in-situ processing and visualization strategies in the Minisymposia on “Advanced Computing in Plasma, Particle and Astrophysics on Emerging HPC Architectures.

INES, 30/06/2016 – 02/07/2016, Budapest, Hungary
Bit-Vectorized GPU Implementation of a Stochastic Cellular Automaton Model for Surface Growth
Jeffrey Kelling
In a symposium on GPU-accelerated research, I will present a proceedings paper about a very efficient, at bit level vectorized, implementation of a stochastic cellular automaton for the study of surfaces growing by ballistic deposition of particles and physical aging in these non-equilibrium systems.
Downloads: Paper

Permanent link to this article: https://gcoe-dresden.de/gcoe-presentations-june-2016/

1 ping

  1. GCOE Reports | June – July » Dresden GPU Center of Excellence

    […] with talks and workshops on visualization, porting and heterogeneous computing, see our past announcements here. For instance, Alexander Matthes (HZDR) gave a talk about ISAAC, an in-situ solution for […]

Comments have been disabled.