Computational Science Community Wiki

GPU Club: Tues 29 Oct


alt="NVIDIA CUDA Research Centre"

  • Software for GPUs inc. compiler/directives, maths libs & tools (debuggers and profilers)


29th October 2013, 14:00 – 15:30, University Place 4.206

Followed by light refreshments.

Introduction Slides: ITS GPU Club 29Oct2013

Timothy Lanfear: GPU Computing and the Future of HPC

Slides:

The biggest challenge computer architects are facing in the push towards exascale computing is the problem of power consumption. The physical scaling laws that have delivered ever higher performance at constant power consumption have reached their limits. Further improvements in the efficiency of devices must rely on innovation in the processor architecture. The graphics processing unit (GPU) combines high floating-point arithmetic capability with a power efficient design. The past five years have seen explosive growth in the adoption of GPUs until a Cray supercomputer with NVIDIA GPUs occupied the #1 spot on the Top500 list in November 2012. NVIDIA will continue to innovate in the area of GPU architecture to develop ever more capable and efficient devices.

Timothy Lanfear manages the European solution architecture group in NVIDIA’s Professional Solutions Group. He has twenty years’ experience in HPC, starting as a computational scientist in British Aerospace’s corporate research centre, and then moving to technical pre-sales roles with Hitachi, ClearSpeed, and most recently NVIDIA. He has a degree in Electrical Engineering and a PhD for research in the field of graph theory, both from Imperial College London.

Levi Barnes is a high-performance computing software engineer with NVIDIA. He fine-tunes GPU-accelerated applications in such fields as quantum chemistry, fluid dynamics and seismic simulation. Before coming to NVIDIA, Levi wrote lithographic simulation software for Synopsys, Inc. He holds a PhD in physics from University of California-San Diego and a BS in physics from Brigham Young University.

Stephen Longshaw: Minke Whale Turbine Impact Using CUDA Driven Smoothed Particle Hydrodynamics

Slides & associated videos:

As the prospect of underwater turbine farms for the purpose of harvesting tidal energy become a reality, a key question is what effect do they have on the wildlife around them. This work, as part of the EPSRC funded X-MED project, aims to model the macroscopic effects of a Minke whale impacting a rotating turbine blade whilst both are submerged in water. In order to achieve this, a new method that integrates elastic behaviour, by way of spring mechanics, in to the standard Newtonian fluid Smoothed Particle Hydrodynamics (SPH) method has been developed. Due to the computational overhead of the SPH method combined with extra overhead introduced by the spring mechanics, this work has been achieved by extending the CUDA and OpenMP based DualSPHysics SPH simulation software (a joint development between the University of Manchester & the University of Vigo, Spain).

Dr Longshaw is from the School of Mechanical, Aerospace & Civil Engineering and is a member of the Smoothed Particle Hydrodynamics Expert Group. He completed his PhD in Computer Science at the University of Manchester in 2011 with a thesis that explored the use of novel computing hardware, such as GPUs, and associated software frameworks to solve demanding numerical simulation problems such as Discrete Element Modelling and Smoothed Particle Hydrodynamics.