Overview | Venue : CMSD, UoH | Key-Note/Invited Talks | Speakers|
Proceedings | Downloads
Past Tech. Workshops| Target Audience |Benefits|Organisers |Accomodation|Sponsors
Feedback |Acknowledgements |Contacts |Local Travel |Home
|hyPACK-2013 Download Software|
hyPACK-2013 Soft-copy of CD proceedings will be made available on C-DAC web-site in November 2013 for a period of three months only.
The High-Performance Computing - Frontier Technologies Exploration (HPC-FTE) Group Members, C-DAC, Pune are being involved in development of these codes as a part of C-DAC on-going Technology Proliferation Projects & Research and Development projects on Emerging Parallel Processing Technology Projects in collaboration with leading academic institutions and IT private Sectors (Intel, NVIDIA, AMD, Cray,HP, IBM). Also, the soft-copy of proceedings of this workshops can be downloaded from C-DAC web-site after the workshop.
Mode 1 (Multi-Core Processors)
HPC GPU Cluster (Host-CPU : An Overview of Multi-Core Prog. Env. ) : An Overview of Memory Allocators & Performance Issues of I/O; Common Errors in Thread Prog. on Multi Core Processors; Practical aspects of Parallel Algorithms; Shared Memory Programming (OpenMP, Intel Threading Building Blocks (TBB),Pthreads); Explicit Message Passing (MPI); & Mixed Programming Environment; Pthreads - Tuning and Complier Optimization & Performance Issues Mathematical libraries on Multi-Core Processors
Mode 2 (ARM Multi-core Processors)
Prorgamming on ARM Multi-Core CPUs, Programmin Issues - Power aware Computing techniques; An overvie of tools - Power Measurement; Power-aware APIs for Computing Systems with Accelerators; Measure Power Consumption for Applcatyion Kernels, Tuning - Optimisation of Applicaiton Kernels
Mode 3 (Co-processors)
Prorgamming on Intel Xeon- Multi-Core CPUs, Intel Xeon-Coprocessors, Compilation and Vectorisation Techniques, An Overview of Shared address Space Programming - OpenMP, Pthreads, Intel TBB, Cilk Plus; Explicit Message Passing -MPI, Mixed Programming; Tuned Math Kernel Libraries; Tuning - Optimisation of Applicaiton Kernels
Prorgamming on GPGPUs, An Overview of CUDA enabled NVIDIA GPUs Programming on CUDA enabled NVIDIA GPUs - OpenCL - Memory Optmisation on CUDA enabled NVIDIA GPUs,; NVIDIA-PGI CUDA - OpenACC Programming on GPUs; Heterogeneous computing - OpenCL Prog., An Overview of Programmming on AMD APUS, AMD-APP OpenCL Prog.; Numerical Linear Algebra Kernels on GPUs (CUDA ↦ OpenCL) HPC GPU Cluster - Programming