Paper Info
Title
Affinity-aware optimization of multithreaded two-phase I/O for high throughput collective I/O
Abstract
Collective MPI-IO for non-contiguous accesses has been playing a big role in not only direct MPI-IO API calls but also scientific applications using parallel I/O libraries such as HDF5, which utilizes MPI-IO APIs underneath its parallel I/O APIs. We have been focusing on performance improvements in such a collective MPI-IO by using a representative MPI-IO library named ROMIO. Inside ROMIO, an optimization scheme named two-phase I/O achieves higher performance even if we have non-contiguous accesses. We have developed multithreaded ROMIO using Pthreads for further performance improvement. In this paper, we present a better performance optimization in collective write operations by using a newly implemented functionality to manage CPU core bindings for invoked I/O threads in addition to a multiple I/O request queueing scheme. We achieved performance gains up to 29% with the CPU core bindings compared to I/O throughput without CPU core bindings. Furthermore, we noted that a multiple number of I/O request slots in queues mitigated the internal unbalanced data-exchange phase times among MPI processes.
Year
DOI
Venue
2014
10.1109/HPCSim.2014.6903688
High Performance Computing & Simulation
Keywords
Field
DocType
application program interfaces,input-output programs,multi-threading,MPI-IO API calls,Pthreads,ROMIO library,affinity-aware optimization,application program interfaces,collective MPI-IO,high throughput collective input-output,multithreaded two-phase input-output,optimization scheme,parallel I/O libraries,two-phase I/O achieves,CPU core bindings,MPI-IO,Pthreads,multiple I/O request queueing,multithreaded two-phase I/O
Computer architecture,Computer science,Parallel computing,Input/output,Throughput
Conference
Citations 
PageRank 
References 
0
0.34
9
Authors
3
Name
Order
Citations
PageRank
Yuichi Tsujita16212.62
Atsushi Hori215023.37
Yutaka Ishikawa31449188.06