Out-of-Core and Pipeline Techniques for Wavefront Algorithms

Eddy Caron 1 Frédéric Desprez 1 Frédéric Suter 2
1 GRAAL - Algorithms and Scheduling for Distributed Heterogeneous Platforms
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
2 ALGORILLE - Algorithms for the Grid
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Several numerical computation algorithms exhibit dependences that lead to a wavefront of the computation. Depending on the data distribution chosen, pipelining communication and computation can be the only way to avoid a sequential execution of the parallel code. The computation grain has to be wisely chosen to obtain at the same time a maximum parallelism and a small communication overhead. On the other hand, when the size of data exceeds the memory capacity of the target platform, data have to be stored on disk. The concept of out-of-core computation aims at minimizing the impact of the I/O needed to compute on such data. It has been applied successfully on several linear algebra applications. In this paper we apply out-of-core techniques to wavefront algorithms. The originality of our approach is to overlap computation, communication, and I/O. An original strategy is proposed using several memory blocks accessed in a cyclic way. The resulting pipeline algorithm achieves a saturation of the disk resource which is the bottleneck in out-of-core algorithms.
Keywords : Out-of-Core Pipeline
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00008798
Contributor : Frederic Suter <>
Submitted on : Friday, September 16, 2005 - 12:32:17 PM
Last modification on : Friday, April 20, 2018 - 3:44:23 PM

Identifiers

Citation

Eddy Caron, Frédéric Desprez, Frédéric Suter. Out-of-Core and Pipeline Techniques for Wavefront Algorithms. IEEE, 2005, Denver/ USA, pp.9b, ⟨10.1109/IPDPS.2005.318⟩. ⟨hal-00008798⟩

Share

Metrics

Record views

366