Parallel out-of-core matrix inversion

Caron, Eddy; Utard, Gil

doi:10.1109/ipdps.2002.1015575

Cited by 7 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system approach [3] proposes a technique adapted to large amount of data to improve the virtual memory management from the operating system. The algorithmic approach [5] optimizes I/O in high-level linear algebra algorithms, in which the out-of-core computation is split in in-core blocks. Many applications benefit from these outof-core techniques but the content of this paper can not be applied to every kind of out-of-core applications as it is specific to wavefront algorithms.…”

Section: Related Workmentioning

confidence: 99%

Out-of-Core and Pipeline Techniques for Wavefront Algorithms

Caron¹,

Desprez²,

Suter³

19th IEEE International Parallel and Distributed Processing Symposium

Self Cite

View full text Add to dashboard Cite

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

show abstract

Section: Related Workmentioning

confidence: 99%