• Mode-1 Multi-Core • Memory Allocators • OpenMP • Intel TBB • Pthreads • Java - Threads • Charm++ Prog. • Message Passing (MPI) • MPI - OpenMP • MPI - Intel TBB • MPI - Pthreads • Compiler Opt. Features • Threads-Perf. Math.Lib. • Threads-Prof. & Tools • Threads-I/O Perf. • PGAS : UPC / CAF / GA • Power-Perf. • Home




hyPACK-2013 Mode 1 : Tuning & Performance of Benchmarks

Tuning and Performance of Application Programs using Compiler optimization techniques, Code restructuring techniques on Multi-Core Processors is challenging. Understanding Programming Programming Paradigms (MPI, OpenMP, Pthreads), effective use of right Compiler Optimization flags and obtaining correct results for given application is important. Enhance performance and scalability on multiple core processors for given application with respect to increase in problem size require serious efforts. Several Optimization techniques are discussed below.

Cache Overview      Classical Optimization      Loop Optimization     

Memory Reference Optimization     Common Errors in Threaded Prog.    

Threads Versus OpenMP     Benchmarks     Tuning - Perf. on multi-cores & Clusters    

Intel / AMD (Quad Core) :    Prog. Environment : Compilation & Execution of Prg.

References : Multi-threading     OpenMP     Java Threads     Books     MPI   Benchmarks  



Example programs on numerical computations (Dense Matrix Computations) are discussed to understand Performance issues on multi-core processors. Efforts on tuning and Performance of several programs written in MPI, OpenMP, PThreads using mathematical libraries can be made on the Multi-core Processors. Examples programs on vector-vector multiplication, matrix-vector multiplication and matrix-matrix Multiplication algorithms on single-core & multi-core processors are considered.


Centre for Development of Advanced Computing