Training course "Vectorisation and portable programming using OpenCL" @ JSC

begin

21.Nov.2017 09:00

end

22.Nov.2017 16:30

venue

JSC, Jülich

OpenCL provides an open, portable C-based programming model for highly parallel processors. In contrast to NVIDIA's proprietary programming API CUDA, a primary goal of OpenCL is portability across a diverse set of computing devices including CPUs, GPUs, and other accelerators.

Topics covered will include:

• Introduction to vectorization
• Programming model OpenCL
  
• Datatypes and OpenCL vectorization features
  
• Tuning for architectures like CPUs, accelerators (GPUs), and co-processors (Xeon Phi)
  
• Heterogeneous multi-device programming