Fast and Efficient Synchronization and Communication Collective Primitives for Dual Cell-Based Blades

Abstract

The Cell Broadband Engine (Cell BE) is a heterogeneous multi-core processor specifically designed to exploit thread-level parallelism. Its memory model comprehends a common shared main memory and eight small private local memories. Programming of the Cell BE involves dealing with multiple threads and explicit data movement strategies through DMAs which make the task very challenging. This situation gets even worse when dual Cell-based blades are considered. In this context, fast and efficient collective primitives are indispensable to reduce complexity and optimize performance.

In this paper, we describe the design and implementation of three collective operations: barrier, broadcast and reduce. Their design takes into consideration the architectural peculiarities and asymmetries of dual Cell-based blades. Meanwhile, their implementation requires minimal resources, a signal register and a buffer. Experimental results show low latencies and high bandwidths, synchronization latency of 637 ns, broadcast bandwidth of 38.33 GB/s for 16 KB messages, and reduce latency of 1535 ns with 32 floats, on a dual Cell-based blade with 16 SPEs.

This work has been jointly supported by the Spanish MEC under grants “TIN2006-15516-C04-03” and European Comission FEDER funds under grant “Consolider Ingenio-2010 CSD2006-00046”. Epifanio Gaona is supported by fellowship 09503/FPI/08 from Comunidad Autónoma de la Región de Murcia (Fundación Séneca, Agencia Regional de Ciencia y Tecnología).

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.