Anurag Sah

EECS Department, University of California, Berkeley

Technical Report No. UCB/CSD-91-631

, 1991

http://www2.eecs.berkeley.edu/Pubs/TechRpts/1991/CSD-91-631.pdf

The study of general purpose parallel computing requires efficient and inexpensive platforms for parallel program execution. This helps in ascertaining tradeoff choices between hardware complexity and software solutions for massively parallel systems design. In this report, we present an implementation of an efficient parallel execution model on shared memory multiprocessors based on a Threaded Abstract Machine. We discuss a k-way generalized locking strategy suitable for our model. We study the performance gains obtained by a queuing strategy which uses multiple queues with reduced access contention. We also present performance models in shared memory machines, related to lock contention and serialization in shared memory allocation. A bin-based memory management technique which reduces the serialization is presented. These issues are critical for obtaining an efficient parallel execution environment.


BibTeX citation:

@techreport{Sah:CSD-91-631,
    Author= {Sah, Anurag},
    Title= {Parallel Language Support on Shared Memory Multiprocessors},
    Year= {1991},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/1991/5646.html},
    Number= {UCB/CSD-91-631},
    Abstract= {The study of general purpose parallel computing requires efficient and inexpensive platforms for parallel program execution. This helps in ascertaining tradeoff choices between hardware complexity and software solutions for massively parallel systems design. In this report, we present an implementation of an efficient parallel execution model on shared memory multiprocessors based on a Threaded Abstract Machine. We discuss a k-way generalized locking strategy suitable for our model. We study the performance gains obtained by a queuing strategy which uses multiple queues with reduced access contention. We also present performance models in shared memory machines, related to lock contention and serialization in shared memory allocation. A bin-based memory management technique which reduces the serialization is presented. These issues are critical for obtaining an efficient parallel execution environment.},
}

EndNote citation:

%0 Report
%A Sah, Anurag 
%T Parallel Language Support on Shared Memory Multiprocessors
%I EECS Department, University of California, Berkeley
%D 1991
%@ UCB/CSD-91-631
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/1991/5646.html
%F Sah:CSD-91-631