• Topics of Interest • Tech. Prog. Schedule • Topic : Multi-Core • Topic : ARM Proc • Topic : Coprocessor • Topic : GPGPUs • Topic : HPC Cluster • Topic : App. Kernels • Lab. Overview • Key-Note/Invited Talks • Home




HyPACK-2013 Topics of Interest : Mode-6 Application Kernels

The Mode-6 programme aims at understanding performance of application kernels on HPC GPU Cluster as well as power efficiency issues of modern HPC systems. Topics of interest are listed below.



Mode-6 : HPC GPU Cluster Application Kernels on HPC GPU Cluster (CUDA/OpenCL)
  • Implementation of Solution of Partial Differential Eqs.(PDEs) by Finite Difference Method (FDM) using MPI programming on host-cpu and CUDA enabled NVIDIA GPUs & AMD-APP OpenCL on GPUs

  • Measurement of Power Consumption and Performance Calculation for Solution of PDEs by FDM Methods on CUDA enabled NVIDIA GPUs.

  • Implementation of Solution of Partial Differential Eqs.(PDEs) by Finite Difference Method (FDM) using OpenMP Framework on Intel Xeon Phi Coprocessors

  • Implementation of Solution of Partial Differential Eqs.(PDEs) by Finite Element Method (FDM) using MPI programming on host-cpu and CUDA enabled NVIDIA GPUs & AMD-APP OpenCL on GPUs

  • Computational Physics : Monte Carlo Simulation on HPC GPU Cluster using CUDA /OpenCL prog.

  • Parallelisation of Fast Fourier Transformations (FFT) on HPC GPU Cluster

  • Computational Physics : n-body simulation on HPC Cluster with Intel Xeon Phi Coprocessors and GPU Accelerators

  • Development of programs to check the health of the HPC GPU Cluster pre-job allocation and post-job de-allocation

  • An Overview of String Search algorithms - CUDA enabled NVIDIA GPUs

  • An Overview of Intrusion and Detection Algorithms - OpenCL Implementaiton on Intel Xeon-Phi Coprocessors.

  • Implementation of String Search algorithms using OpenCL Framework on Intel Xeon-Phi Coprocessors

  • Image Processing : Edge Detection algorithms on HPC Cluster with GPU Acclerators

  • Image Processing : Implementation of Face Detection - on HPC GPU Cluster

  • Image Processing - Implementation of Image Inpainting Algorithms on HPC GPU Cluster.

  • An Overview of Molecular Dynamics - NAMD on HPC GPU Cluster

  • Parallelisation of CFD Applications in HPC Cluster environment based on CUDA / OpenCL programming environment.



Centre for Development of Advanced Computing