hyPACK-2013 Topics of Interest : Mode-1 - Host-CPU Cores
The Mode-1 programme covers the practical
aspects of performance enhancement through software multi-threading on Multi-Core Processors
focusing on Programming & Performance Tuning aspects,
System Overview of Threading, Software tools, Mixed Programming, Memory Allocators, & Distributed shared Memory
Programming & PGAS model from application point of view.
The Mode-1 discusses an overview of programming on
host-cpu cores of HPC Cluster with coprocessors and GPU accelerators and performance of codes on numerical & non-numerical computations
is discussed. Topics of interest are listed below.
Mode-1: Tuning & Performance of programs on Multi-Core Processors &
Distributed Shared Address Space (PGAS) memory Models
-
Example Programs based on Thread Programming constructs will be made available.
-
Example Programs based on Thread/OpenMP/MPI/TBB focusing on numerical computations
(Numerical Linear Algebra Dense / Sparse Matrix Computations) will be discussed.
-
Demonstrate the compiler capabilities for Numerical Kernels & Benchmarks based on
PGAS Memory Models ( UPC, & Global Arrays)
-
Walk-through parallel programs using Pthreads, OpenMP, TBB, Fortran90,
MPI 2.0, MPI-Pthreads, MPI-OpenMP on Clusters of Multi-Core Systems
-
Demonstrate the use of Performance tools (Intel Thread checker, Thread Vtune Analyzer,
and Open Source Software tools) on Multi-Core Processor Systems.
-
Understand and execute Numerical Kernels & Benchmarks based on PGAS Memory
Models
-
Understand the performance of Numerical Kernels based on MPI & PGAS Memory Models such
as UPC.
-
Example Programs based on Thread/OpenMP/MPI/TBB focusing on non-numerical computations
(Graph Coloring, Sorting algorithms) will be discussed.
-
Example programs based on special class of problems- Producer Consumer,
Fast Search Algorithms, and Partial Differential Equation (PDEs) will be
discussed.
-
Multi Core Processors - An Overview of Software Multi-threading & Memory allocators & System Overview of threading;
An Overview of Programming (MPI 2.0, POSIX Threads, Intel TBB, OpenMP 3.0, Java threading, Charm++)
-
Tuning & Performance: Code Optimization for Performance; Compiler Switches;
An Overview of Math Kernel Libraries (AMD ACML, Intel MKL) on Multi-Cores
System and Application Benchmarks and Multi-Threaded I/O Suites
-
An Overview of Application Level tuning - Software tools, Profilers on Intel /AMD systems &
Open Source Software tools tuning & Performance aspects
|