June 23, 2016
Germany
This workshop will take place within the ISC High Performance conference 2016. It is intended to provide a venue for the broader HPC community to Further understand OpenPOWER technologies and discuss how they can be Harnessed for HPC applications needs. The latest advances in OpenPOWER and how they might be used to address challenges regarding system architecture, networking, memory designs, exploitation of accelerators, programming models, and porting applications are of current interest within the HPC community and this workshop. The workshop is currently planned as a half-day workshop, but may be extended to a full-day workshop.
Porting applications experiences to OpenPOWER nodes to exploit its HPC and data analytics capabilities
Designs and use models for FPGA-accelerated applications
Co-designing the HPC software stack (scientific libraries, compilers, runtimes)
Programming models for HPC and data analytics, including hybrid heterogeneous programming (e.g. MPI with OpenCL, OpenACC, CUDA, OpenMP4) models, DSLs, PGAS, and exascale runtimes
Tools eco-system to improve productivity on OpenPOWER architectures (compilers, performance analysis, auto-tuning, debugging, verification, static analysis tools)
System architectural choices including memory designs, networking
Low level communication APIs, I/O frameworks
Runtime environments and schedulers
Benchmarking and validation studies on OpenPOWER architectures
User Name : MANI
Posted on