A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
This paper presents a modeling method particularly suited to analyze interactions between Message Passing Interface MPI library execution and distributed cache coherence protocol. The method is applied to the Ping-Pong benchmark. In addition to overall performance figures like message exchange latency, it also provides detailed analysis elements such as cache miss counts per variable. It is based on formal modeling where functional aspects and performance aspects are integrated by compositiondoi:10.1109/waina.2009.117 dblp:conf/aina/ChehaibarZM09 fatcat:6sj2w4jx4vh3rfmkv3bj77quo4