Conference Programme
09:30 Coffee and pastries
10:00 Welcome from the organisers
10:05 Keynote talk:
"Software is key. Intel MIC: GPU level performance with CPU level programmability"
Jim Cownie (Intel)
11:00 Porting a Fortran Oceanographic code to GPUs; the GNEMO Project
Andrew Porter, Stephen Pickles and Mike Ashworth (Daresbury Labs)
11:30 Efficient sparse matrix-vector products on Fermi GPUs
Istvan Reguly and Mike Giles (Oxford University)
12:00 Anisotropic adaptive mesh coarsening and refinement on GPU architecture
Matthew Potter (JP Morgan)
12:30 Lunch
13:30 The landscape of GPU programming: a view from ARM
Anton Lokhmotov (ARM)
14:00 A heterogeneous image reconstruction system for clinical Magnetic Resonance
Grzegorz Kowalik, Jennifer Steeden, Bejal Pandya,
David Atkinson, Andrew Taylor and Vivek Muthurangu (UCL)
14:30 BarraCUDA - a Fast Sequence Mapping Software using Graphics Processing Units
Brian Lam, Petr Klus, Simon Lam, Graham Pullan and Giles Yeo (Cambridge University)
15:00 Application acceleration and optimisation with directives on hybrid supercomputers
Alistair Hart (Cray)
15:30 Break
16:00 Exploiting OpenCL for heterogeneous computing: a case study
Simon Mcintosh-Smith, Richard Sessions, James Price,
Amaurys Ibarra, Tsuyoshi Hamada and Felipe Cruz (Bristol University)
16:30 Automatic Parallelisation: Code Generation for GPUs
Luke Cartey (Oxford University)
17:00 Using Graphics Processors for Real-Time Global Illumination
Graham Hazel (Geomerics)
17:30 Close
Last update 16.12.2011