Synchronizing processors through memory requests in a tightly coupled multiprocessor
ISCA '88 Proceedings of the 15th Annual International Symposium on Computer architecture
Towards a large number of pipeline processors in a tightly coupled multiprocessor using no cache
ICS '88 Proceedings of the 2nd international conference on Supercomputing
ACM Computing Surveys (CSUR)
Computer Architecture and Parallel Processing
Computer Architecture and Parallel Processing
Processor-memory interconnections for multiprocessors
ISCA '79 Proceedings of the 6th annual symposium on Computer architecture
Hi-index | 0.00 |
In order to reach high performance, many levels of parallelism should be exploited simultaneously on massively parallel architectures. The efficiency of a large system heavily depends on the interconnection between the processing elements and the memories: asynchronous buffering networks allow a high throughput of requests when independent tasks are run, but a strict control of the network is necessary for fine grain parallelism.We show that the ordering of the requests delivery can be controlled by a simple mechanism on an asynchronous buffering interconnection network, the @@@@ network. This network is shown to be efficient in various situations as MIMD, micro-tasked, vector and pipelined computations.