Distributing Hot-Spot Addressing in Large-Scale Multiprocessors
- 1 April 1987
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. C-36 (4), 388-395
- https://doi.org/10.1109/tc.1987.1676921
Abstract
When a large number of processors try to access a common variable, referred to as hot-spot accesses in [6], not only can the resulting memory contention seriously degrade performance, but it can also cause tree saturation in the interconnection network which blocks both hot and regular requests alike. It is shown in [6] that even if only a small percentage of all requests are to a hot-spot, these requests can cause very serious performances problems, and networks that do the necessary combining of requests are suggested to keep the interconnection network and memory contention from becoming a bottleneck.Keywords
This publication has 10 references indexed in Scilit:
- Parallel Supercomputing Today and the Cedar ApproachScience, 1986
- On “hot spot” contentionACM SIGARCH Computer Architecture News, 1985
- “Hot spot” contention and combining in multistage interconnection networksIEEE Transactions on Computers, 1985
- The Performance of Multistage Interconnection Networks for MultiprocessorsIEEE Transactions on Computers, 1983
- The NYU Ultracomputer—Designing an MIMD Shared Memory Parallel ComputerIEEE Transactions on Computers, 1983
- Analysis and Simulation of Buffered Delta NetworksIEEE Transactions on Computers, 1981
- On a Class of Multistage Interconnection NetworksIEEE Transactions on Computers, 1980
- A large scale, homogeneous, fully distributed parallel machine, IPublished by Association for Computing Machinery (ACM) ,1977
- Access and Alignment of Data in an Array ProcessorIEEE Transactions on Computers, 1975
- Solution of a problem in concurrent programming controlCommunications of the ACM, 1965