Computational Science Community Wiki

GPU Club Meeting: 30 September 2011

alt="NVIDIA CUDA Research Centre"

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

About 70 people attending the following presentations

After the presentations the following points were discussed and actions agreed.

On the presentations:

  1. Questions arose as to whether people had tried asynchronous operations to overlap data transfer, host work and gpu work. In general it hadn't been tried but was often something that people were considering.
  2. Where speed-up figures were shown it would be useful to know exactly what was being compared (type of CPU, single/multi-core code).
  3. Where data is partitioned across multi-GPUs how much overhead is there communicating bewteen GPUs. Also whether partitioning introduces error in to the results.
  4. Skeleton fortran-OpenCL code on community wiki FAQ

General questions:

  1. Did anyone know if the CUDA computeprof profiler supported asynchronous functions. It was reported that it does not currently.
  2. CUDA was still more popular amongst the audience mainly due to better drivers and maturity of tools.

On community involvement:

  1. It was asked if the community could contribute real application performance data so that we do not have to rely solely on vendor figures.
  2. That the community could add more the the GPU Club wiki


  1. AMD to provide OpenCL training on November 2nd, 2011.
  2. Cray to be invited to present eg at next GPU club

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