hyPACK-2013 Mode-1 : Threads I/O - Performance Issues
The I/O on multi-core processors or cluster of Multi-Core processors
plays an important role to understand and enhance the performance of your application.
In fact, many applications of parallel computes are memory-bound rather than CPU-bound
or I/O bound. In typical large-scale parallel and Cluster
platforms, a system bus provides slots to connect I/O devices, such as disk, drives,
tape drives, and network interfaces cards. Efforts have been made in both software
development and hardware design to improve the I/O bandwidth between computational
units and storage systems. Although most of these works only consider exclusive
file access
among the concurrent I/O requests, more scientific applications require data
partitioning with overlap among the requesting processes. In hyPACK-2013,
Multi-threaded I/O test programs are provided to understand performance issues and selective
benchmarks will be discussed.
Click here ...... to know more about I/O Performane/Codes
List of Programs based on I/O in multi-theaded environment :
-
Write a simple MPI I/O program performing sequential I/O to multiple files
-
Write a Pthread I/O program performing each thread writing to separate file
-
Write an MPI program performing MPI I/O to separate files (Using MPI 2.0)
-
Write an MPI program performing MPI I/O to single file (Using MPI 2.0)
-
Write a Pthreads I/O program reading the file with different number of threads
-
Write a MPI I/O program to read the file with different number of processes (Using MPI 2.0)
|
|