Design considerations for shared memory multiprocessor message systems
- 1 November 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 3 (6), 702-711
- https://doi.org/10.1109/71.180625
Abstract
The comparative performance is studied of different message passing system designs experimentally on a shared memory Encore Multimax multiprocessor. The systems are measured both by benchmarks and by running example parallel applications. To act as a control, the shared memory machine results are compared with the performance of the benchmarks and applications on the Intel iPSC/2 running the NX/2 operating system. The design alternatives considered are buffering, buffer organization, reference and value semantics, synchronization, coordination strategy and the location of the system in user or kernel space. The results include measurements of the effects of the design alternatives, memory caching, message sizes and copying.<>Keywords
This publication has 7 references indexed in Scilit:
- User-level interprocess communication for shared memory multiprocessorsACM Transactions on Computer Systems, 1991
- The effect of scheduling discipline on spin overhead in shared memory parallel systemsIEEE Transactions on Parallel and Distributed Systems, 1991
- The performance of spin lock alternatives for shared-money multiprocessorsIEEE Transactions on Parallel and Distributed Systems, 1990
- Efficient synchronization primitives for large-scale cache-coherent multiprocessorsPublished by Association for Computing Machinery (ACM) ,1989
- The NX/2 operating systemPublished by Association for Computing Machinery (ACM) ,1988
- The iPSC/2 node architecturePublished by Association for Computing Machinery (ACM) ,1988
- Basic Techniques for the Efficient Coordination of Very Large Numbers of Cooperating Sequential ProcessorsACM Transactions on Programming Languages and Systems, 1983