Evaluation of Memory Performance on the Cell BE with the SARC Programming Model Roger Ferrer

With the advent of multicore architectures, especially with the heterogeneous ones, both computational and memory top performance are difficult to obtain using traditional pro-gramming models. Usually, programmers have to fully re-organize the code and data of their applications in order to maximize resource usage, and work with the low-level interfaces offered by the vendor-provided SDKs, to obtain high computational and memory performances. In this pa-per, we present the evaluation of the SARC programming model on the Cell BE architecture, with respect to mem-ory performance. We show how we have annotated the HPL STREAM and RandomAccess applications, and the memory bandwidth obtained. Results indicate that the programming model provides good productivity and competitive perfor-mance on this kind of architectures. 1