Date: May 21-22, 2013
Location: London, UK
New Tutorial on Developing Error Free OpenCL and CUDA Kernels
LEAP Conference in London to Host Tutorial on GPU Kernel Verification Presented by Imperial College
On Wed 22nd May 2013, Nathan Chong from the Department of Computing at Imperial College will present a lively and interactive tutorial on applying formal analysis and verification techniques to OpenCL and CUDA kernels.
Whether working on kernels for supercomputing, finance or mobile applications this tutorial will help developers overcome the common pitfalls in GPU programming such as data races and barrier divergence. Using plenty of worked examples and demos to encourage interactive discussion this session will highlight the practical benefits of using formal verification techniques to prove that kernels are free from defects.
- What: Tutorial on Formal Analysis Techniques for OpenCL & CUDA GPU Kernels
- When: 22nd May 2013, 10:00am Start
- Where: Central London (alongside the LEAP Conference)
- Price: £45 LEAP Conference Attendees, £90 Non Attendees (early bird pricing)
- Level: Developers with experience writing real-world OpenCL and CUDA Kernels
- Space: Limited Spaces Available
More details at the LEAP website: http://www.leapconf.com
About the Presenter
Nathan Chong is a researcher in the Department of Computing at Imperial College London, where he is a member of the Multicore Programming and Software Performance Optimisation groups, led by Alastair Donaldson and Paul H. J. Kelly, respectively. His research interests include parallel programming, computer architecture and formal reasoning and he is particularly interested in specifications and problems at the hardware/software boundary. He is a key contributor to GPUVerify, a verification technique and tool for the automatic analysis of GPU kernels written in OpenCL and CUDA. Before joining Imperial, Nathan was a researcher for ARM and worked on hardware and software at different levels of the system stack, including proofs of correctness for cache-coherence protocols, weak memory models, and CPU virtualisation. His work is supported by the FP7 CARP (Correct and Efficient Accelerator Programming) and EPSRC PSL (Particle Science Language) projects.