The new CS4: Complexity Systems Simulation Seminar Series 2012/13, commences this Wednesday, 10 October.
All talks are free and will take place fortnightly on Wednesdays, 4-5pm, B53/4025, Highlfield Campus. All are warmly welcome to attend. Please find attached the Autumn Semester Schedule which includes a series of six talks or alternatively please see the Complexity USRG webpage.
The first talk is this Wednesday 10th October by Thomas Nowotny (University of Sussex) “General purpose GPU computing: Transforming your desktop into a personal super-computer”. Please see details below.
Complex Systems Simulation Seminar Series no 1:
General purpose GPU computing: Transforming your desktop into a personal super-computer
By Thomas Nowotny (University of Sussex)
10th October
4-5pm, B53/4025, Highfield Campus
Abstract:
Driven by the ever-increasing computational demands of the games industry graphical processing units (GPUs) have developed from simple co-processors to powerful computer platforms. Unlike modern CPUs that are still essentially using a sequential model of computing, GPUs are massively parallel with half a thousand cores on a single chip in modern graphics cards. With the introduction of the CUDA (common unified device architecture) application programming interface, NVIDIA, one of the leading GPU manufacturers, has made their GPUs accessible to general purpose computing applications. Given a suitable computational problem and an optimized parallel implementation, modern GPUs can achieve speed-ups of up to 50 to 100 times over a classical CPU core of a recent CPU.
In this talk I will introduce the opportunities and challenges of general purpose GPU computing and illustrate them with the GPU enhanced neuronal network (GeNN) framework we are developing at Sussex. I will argue that building meta-compilers that generate code from a simpler domain-specific problem description is one of the better approaches to GPU programming. GeNN is based on such an approach which offers many decisive advantages:
(i) The system can provide for a large number of potential model elements,
(ii) it can optimise for specific model structures and GPU hardware properties at compile time, and
(iii) it can be extended more easily than pre-compiled solutions.
The present alpha version of GeNN shows encouraging competitive computing performance and is available under the GPL v2 licenses at http://genn.sourceforge.net.
Refreshments will be provided from 5pm and no registration is required.