Exploiting Locality on the Cell/BE through Bypassing

Cell Superscalar (CellSs) provides a simple, flexible and easy programming approach for the Cell Broadband Engine (Cell/B.E.) that automatically exploits the inherent concurrency of applications at a function or task level. The CellSs environment is based on a source-to-source compiler that translates annotated C or Fortran code and a runtime library tailored for the Cell/B.E. that orchestrates the concurrent execution of the application. In the context of our parallel runtime we analyse the effect of the bandwidth of the Element Interconnect Bus (EIB) on an application's performance. We introduce a technique called bypassing that potentially increases the observed bandwidth and improves the execution time for applications with a distributed computation pattern. Although the integration of bypassing with CellSs is work in progress we present results for five fundamental linear algebra kernels to demonstrate the applicability of bypassing and to attempt to quantify the benefit that can be reaped.