Analysis of communications and overhead reduction in multithreaded execution

In a multithreaded execution, each thread can be thought of as running on its own virtual processor, with several virtual processors multiplexed onto a single physical processor. At any given time, some of these virtual processors are either sending or waiting for messages. When the degree of multithreading is high, there is a high potential load on the interconnection network. It is important to understand the aggregate behavior of these messages for the design of the memory hierarchy, network structure, and understand more concretely the behavior of multithreaded execution. In this paper, we study several issues related to communication patterns in a non-blocking, framelet-based multithreaded model. These issues include the sources of message generations and the locality of these messages. The results indicate that roughly a third of all tokens are memory-related, another third are involved in parallelism management, and the nal third are involved in intrafunction and intra-loop communications (e.g., scalar data values). Based upon these results, we examine two techniques designed to reduce the amount of communications involved and the associated overheads. The results indicate that about 80% of non-memory related inter-processor messages are eliminated, which results in an overall reduction of network tra c by about 50%.