Quick search Find article
Quick search
Find article

Multithreading for synchronization tolerance in matrix factorization

Alfredo Buttari1, Jack Dongarra1,2, Parry Husbands3, Jakub Kurzak1 and Katherine Yelick3,4

Show affiliations


Physical constraints such as power, leakage and pin bandwidth are currently driving the HPC industry to produce systems with unprecedented levels of concurrency. In these parallel systems, synchronization and memory operations are becoming considerably more expensive than before. In this work we study parallel matrix factorization codes and conclude that they need to be re-engineered to avoid unnecessary (and expensive) synchronization. We propose the use of multithreading combined with intelligent schedulers and implement representative algorithms in this style. Our results indicate that this strategy can significantly outperform traditional codes.


PACS

07.05.Bx Computer systems: hardware, operating systems, computer languages, and utilities

02.10.Yn Matrix theory

Subjects

Mathematical physics

Instrumentation and measurement

Dates

Issue 1 (2007)



Related review articles

What's this?
View review articles related to this research to gain an insight into the key trends in this subject area. Related review articles are selected based on PACS/MSC codes, and are no more than three years old.

  1. FPGA-based, specialized trigger and data acquisition systems for high-energy physics experiments

View by subject




Export








Please login to access our web services, or create an account if you don't yet have one.

You must have cookies enabled in your web browser to be able to login.

Username
Password

Forgotten your password? Get a new one here.