Computational Science Community Wiki

University GPU Club: Thurs 2 May 2013


alt="NVIDIA CUDA Research Centre"

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


14:00-15:15, Thursday 2 May
1.001 Roscoe

Agenda

Mark Mawson, Lessons learned from GTC 2013

A summary of this year’s GPU Technology Conference from an attendee’s perspective; we will discuss upcoming GPU architecture changes, the move towards mobile and cloud based computing, and other highlights from the presentations and exhibitions at GTC 2013.

Mark Mawson is a final year PhD student at the University of Manchester. He is currently working on Lattice Boltzmann and Immersed Boundary Methods for GPU, including optimization of an LBM solver to allow real-time user interaction with fluid flow via a 3D depth sensor.

"Jen-Hsun Huang (CEO, NVIDIA)"

Andy Porter, Experiences with an ocean model on Intel Xeon Phi and Sandy Bridge

We look at the performance of the NEMO ocean model on these two recent offerings from Intel. The performance of a single OpenMP kernel taken from the code is examined in detail and the lessons learned from the work done to achieve scaling up to large numbers of threads are discussed.

The image on the right shows the ean sea temperature for a day during June taken from a simulation of the shelf seas around the UK. The horizontal plane shows temperature just above the sea bed and the vertical plane shows the temperature variation between the surface and the sea bed. Data courtesy Jason Holt, NOC.

Andrew Porter has worked in the Scientific Computing Department of STFC's Daresbury Laboratory for the past five years. He specialises in optimising and developing scientific software for a variety of high-performance computing platforms. In particular, he has ported parts of the NEMO ocean model to GPU and has experimented with NEMO kernels on the Knights Ferry and Knights Corner hardware provided as part of an ongoing collaboration between Intel and the Department.

"model output"

Prof Ser-huang Poon, "Some preliminary HPC finance experience on Intel Xeon Phi

The project team, funded by two Marie Curie FP7 contracts, looks at the selection and the implementation of high-performance platforms in finance from the end-user’s point of view considering the advantages and disadvantages of competing HPC technologies. The team works on a number of financial applications important to the banking and insurance industry and produces comparative metrics from GPU and Xeon Phi.

Dr. Ser-Huang Poon is a Professor of Finance at Manchester University and a Member of NAG, Oxford. In 2008, she led a European consortium on a €3.7 million funding for research training in Risk Management and Risk Reporting. In 2012, she is part of another consortium in HPC in Finance with £220,400 direct funding on computer platform comparison for the purpose of real-time risk management. Her volatility research is cited as reference readings on Nobel website. (The image on the right is the volatility surface of the euro and dollar exchange rate.) She has written three books and published widely in peer reviewed journals. She is the joint recipient of two best paper awards. She speaks regularly at practitioners meetings in Europe such as Incisive Media London, Quant Congress London and Global Derivatives Amsterdam.

"volatility surface of the Euro & Dollar"


GPU Club Meetings

Previous Meetings

  • Tues 26 Nov 2013: 2-3pm, B8 George Begg. Christian Obrecht on GPU implementations of fluid dynamics simulations on regular meshes: some recent advances

  • Weds 13 Nov: 2pm, Univ Place. John Michalakes (NOAA) and Craig Davies (Maxeler Dataflow)

  • Weds 30 Oct: Intermediate CUDA training run by NVIDIA

  • Tues 29 Oct: 2pm, Univ Place, NVIDIA and Stephen Longshaw.

  • Weds 2 Oct 2013 - Large Scale Optimization and High Performance Computing for Asset Management, Daniel Egloff (QuantAlea)

  • Tuesday 23 July MathWorks (GPUs for MATLAB) and NVIDIA (GPUs & CUDA)

  • Thur 2 May 2013 Lessons from GTC and on using the Intel Xeon Phi

  • Mon 10 Dec 2012 Dataflow and MultiGPU SPH

  • Tues 25 Sept Seminar on implementing financial models on GPUs, FPGAs and in the Cloud

  • Mon 15 Oct: OpenCL training from UoM IT Services

  • Thurs 25 Oct: Hands-on "OpenACC" workshop run by Cray UK Ltd.

  • 17 May 2012 Speakers on healthcare policy simulation in OpenCL, MHD algorithms in CUDA, Tridiagonal Solvers in CUDA

  • 20 April 2012 Francois Bodin, CAPS: "Programming Heterogeneous Many-Cores using Directives" using HMPP

  • 23 March 2012 Roko Grubisic, ARM: "Embedded Computer Graphics and ARM Mali GPUs"

  • 02 March 2012 Speakers on profiling, sparse matrix algebra and atmospheric chemistry

  • 09 Dec 2011 MPI and GPUs, directives-based programming, FPGA and GPU comparison, ideas for 2012

  • 30 Sept 2011 GPU programming in FORTRAN, multiple GPUs, image reconstruction

  • 15 July 2011 Jack Dongarra key note on Emerging Technologies

  • 18 Mar 2011 OpenCL, debugging and profiling tools, porting C to CUDA, real time analysis

  • 26 Nov 2010 biological MD, smoothed particle hydrodynamics, Monte Carlo financial models, Markov models