Memory---CellSs

TLDR

The focus is on the simplicity and flexibility of the programming model. This work presents Cell superscalar (CellSs), which automatically exploits functional parallelism of sequential programs across the Cell BE architecture’s processing elements. CellSs uses source‑to‑source compilation with simple annotations to generate code, while a runtime library builds a task dependency graph, schedules tasks, handles data transfers, and employs locality‑aware scheduling to reduce overhead. Implementation and testing on example programs show promising results.

Abstract

In this work we present Cell superscalar (CellSs) which addresses the automatic exploitation of the functional parallelism of a sequential program through the different processing elements of the Cell BE architecture. The focus in on the simplicity and flexibility of the programming model. Based on a simple annotation of the source code, a source to source compiler generates the necessary code and a runtime library exploits the existing parallelism by building at runtime a task dependency graph. The runtime takes care of the task scheduling and data handling between the different processors of this heterogeneous architecture. Besides, a locality-aware task scheduling has been implemented to reduce the overhead of data transfers. The approach has been implemented and tested with a set of examples and the results obtained since now are promising.