A Framework for Out of Memory SVD Algorithms

TitleA Framework for Out of Memory SVD Algorithms
Publication TypeJournal Article
Year of Publication2017
AuthorsKabir, K., A. Haidar, S. Tomov, A. Bouteiller, and J. Dongarra
JournalISC High Performance 2017
Date Published2017-06
AbstractMany important applications – from big data analytics to information retrieval, gene expression analysis, and numerical weather prediction – require the solution of large dense singular value decompositions (SVD). In many cases the problems are too large to fit into the computer’s main memory, and thus require specialized out-of-core algorithms that use disk storage. In this paper, we analyze the SVD communications, as related to hierarchical memories, and design a class of algorithms that minimizes them. This class includes out-of-core SVDs but can also be applied between other consecutive levels of the memory hierarchy, e.g., GPU SVD using the CPU memory for large problems. We call these out-of-memory (OOM) algorithms. To design OOM SVDs, we first study the communications for both classical one-stage blocked SVD and two-stage tiled SVD. We present the theoretical analysis and strategies to design, as well as implement, these communication avoiding OOM SVD algorithms. We show performance results for multicore architecture that illustrate our theoretical findings and match our performance models.
Project Tags: 
External Publication Flag: