UWA Logo
     
           
    

Western Australian Supercomputer Program

Home
Home Home Home
Location Location Location
Staff Staff Staff
Access Grid Access Grid Access Grid
HPC HPC HPC
Visualisation Visualisation Visualisation
Podcasting Podcasting Podcasting
News News News
EventsEvents Events Events
RegistrationRegistration Registration Registration
20092009 2009 2009
20082008 2008 2008
2007 4th QTR2007 4th QTR 2007 4th QTR 2007 4th QTR
2007 3rd QTR2007 3rd QTR 2007 3rd QTR 2007 3rd QTR
2007 2nd QTR2007 2nd QTR 2007 2nd QTR 2007 2nd QTR
2007 1st QTR2007 1st QTR 2007 1st QTR 2007 1st QTR
20062006 2006 2006
Courses Courses Courses
Site Map Site Map Site Map

News (2009)

GPU Computing Tutorial


[click to enlarge pdf]

Where: WASP Teaching Laboratory, UWA 
             Ground Floor, Physics Building
Times:  9am - 1pm
Date:    8 May 2009
Map:     www.wasp.uwa.edu.au/home/location

Over the past decade, advances in graphics processing units (GPUs) have seen them evolve into highly generalised parallel processors that can be applied to a wide range of computational problems. Impressive performance increases have been observed using GPUs in many computational applications including molecular dynamics, astrophysics simulations, pattern and sequence matching, three-dimensional imaging, and many more. Following the GPU workshop, Mark Harris will present a hands-on tutorial session, which will give attendees the opportunity to experience GPU programming with CUDA. The tutorials will present examples important for understanding and optimizing GPU programs. You must attend the GPU Workshop on 7 May to attend this tutorial session. Attendance is FREE for all participants and limited to researchers, academics and students associated with iVEC partners which are Curtin University, Edith Cowan University, Murdoch University, UWA, and CSIRO. Contact Rosie Radica (rosie.radica@uwa.edu.au) to register with your name, organisation, occupation, associated iVEC Partner, and any dietary requirements. Please use the header – GPU Tutorial in email sent to register. Sign-in on the day will be from 8:30am. Please only register if you are genuinely planning to attend.

Presenter: Mark Harris, PhD
Mark Harris is a Senior Developer Technology Engineer at NVIDIA, where he works with developers around the world on software for computer graphics and high-performance computing. His research interests include parallel algorithms, general-purpose computation on GPUs, physically based simulation, real-time rendering, and gastronomy. Mark earned his Ph.D. in computer science from the University of North Carolina at Chapel Hill in 2003 and his B.S. from the University of Notre Dame in 1998. Mark founded and maintains GPGPU.org, a web site dedicated to general-purpose computation on GPUs. Mark has recently moved to Brisbane after living in the United Kingdom for five years.

GPU Computing Workshop

Presentations Slides

  • Xenon HPC - Mr Dragan Dimitrovici Application of GPUs to Gravitational -Wave Searches - Linqing Wen, PhD
  • GPU Accelerated Image Morphology - Luke Domanski, PhD
  • GPU Fluid Simulation - Mr Neil Osborne


    [click to enlarge pdf]

    7 May 2009
    UWA University Club

    Over the past decade, advances in graphics processing units (GPUs) have seen them evolve into highly generalised parallel processors that can be applied to a wide range of computational problems. Impressive performance increases have been observed using GPUs in many computational applications including molecular dynamics, astrophysics simulations, pattern and sequence matching, three-dimensional imaging, and many more. This is your opportunity to meet and discuss the latest developments in general purpose computing on GPUs  with other researchers and industry professionals, learn about GPU architectures and programming, and hear from others about their GPU applications. This workshop and discussion forum aims to provide a detailed introduction to GPU computing with CUDA and NVIDIA Tesla computing solutions, and to present research in GPU and Heterogeneous computing being undertaken in Western Australia.  CUDA is a revolutionary parallel computing architecture from NVIDIA that is built upon a unified computing architecture and multiple software components. The architecture consists of an ISA and hardware compute engine. The available software tools include a C compiler and NVIDIA drivers for developers to build applications using C for CUDA, as well as useful libraries for high-performance computing.

    Talks will range from demonstrating application capabilities of GPUs, all the way down to the low level hardware and programming. Research experts Dr. Mark Harris (NVIDIA) and Professor Karen Haines (WASP@UWA) will present and provide the latest information on their work and other GPU and Heterogeneous computing topics. Topics to be covered will include an introduction to the CUDA architecture, programming model, and the programming environment of C for CUDA, as well as an overview of the Tesla GPU architecture, a live programming demo, and strategies for optimizing CUDA applications for the GPU. To better enable the uptake of this technology, Dragan Dimitrovici from XENON systems will provide an overview of CUDA enabled hardware options. The workshop will also include brief presentations of some of the projects using CUDA within Western Australia, including a background of Parallel Computing strategies required for optimizing your approach to GPU and heterogeneous programming as well as a review of the hardware requirements for getting started with CUDA.

    Attendance is FREE for all participants (both iVEC and non-iVEC partners). The number of places for external (non-iVEC) attendees will be limited, so please express your interest as soon as possible Contact Rosie Radica (rosie.radica@uwa.edu.au) to register with your name, organisation, occupation, iVEC Partner (if applicable), and any dietary requirements. Please use the header – GPU Workshop – in email sent to register. Sign-in on the day will be from 8:30am. Please only register if you are genuinely planning to attend.

    iVEC OpenCL Summer School at the WASP - OPENCL U (Jan to Feb 09)

    Registration is now closed.

    Group will be meeting every tuesday at the WASP at 6pm.

    Computing has reached a point where the interaction of hardware and software capabilities will change radically.  In answer to the demand to improve overall performance and provide better power efficiency, future-computing systems will include general and specialized processors and are focussed on creating heterogeneous multicore computer systems.  The increasing availability of  heterogeneous parallel systems will, in turn, produce a demand for programmers proficient in developing cross-platform and cross-device software.

    The overall goal of the school is to provide students with a reference frame for developing complex parallel programs. The intent is to broaden the students appreciation for and interest in the field of heterogeneous computer science while also strengthening them technically.

    Over the summer, seminars and workshops will be held to explore the coming paradigm shift in computing. Focus will be given to the OpenCL (Open Computing Language) programming standard as a way to improve workload specific processing performance for computing applications. OpenCL is under development by the Khronos Group as an open, royalty-free standard for parallel programming of heterogeneous systems. It provides a common hardware abstraction layer to expose the computational capabilities of systems that include a diverse mix of multicore CPUs, GPUs and other parallel processors such as DSPs and the Cell, for use in accelerating a variety of compute-intensive applications.

    Students will be provided a personal storage disk with a programming environment that supports OpenCL. Access will be provided to the WASP teaching lab at UWA, which houses computers suitable for developing OpenCL programs. Those wanting to continue in OpenCL developments will be encouraged to apply to the Apple University Consortium WWDC scholarship program. This is Nationally competitive program that provides a financial subsidy to attend WWDC in San Francisco, USA in Jun 2009.

    All students are expected to have previous experience in the C programming language and have a strong interest in computer programming and hardware. Online registration is now open. Application deadline is 19 December 2008.

    Download promotional flyer

  • Accelerating Radio Correlation Algorithms using Parallel Architecture - Chris Harris, PhD
Top of Page