High-performance parallel algorithms for the Tucker decomposition of higher order sparse tensors - Inria - Institut national de recherche en sciences et technologies du numérique
Reports (Research Report) Year : 2015

High-performance parallel algorithms for the Tucker decomposition of higher order sparse tensors

Abstract

We investigate an efficient parallelization of a class of algorithms for the well-known Tucker decomposition of general $N$-dimensional sparse tensors. The targeted algorithms are iterative and use the alternating least squares method. At each iteration, for each dimension of an $N$-dimensional input tensor, the following operations are performed: (i) the tensor is multiplied with $(N - 1)$ matrices (TTM step); (ii) the product is then converted to a matrix; and (iii) a few leading left singular vectors of the resulting matrix are computed (SVD step) to update one of the matrices for the next TTM step. We propose an efficient parallelization of these algorithms for current supercomputers comprised of compute nodes, where each node is a multi-core system. We reformulate the computation of $N$ successive TTM-steps to increase the reuse of intermediate computation, which is of interest on its own. We discuss a set of preprocessing steps which takes all computational decisions out of the main iteration of the algorithm and provide an intuitive row-wise shared-memory parallelism for the TTM and SVD steps. We consider a coarse and a fine grain computational scheme, investigate their data dependencies, and identify efficient communication schemes. We demonstrate how the computation of singular vectors in the SVD step can be carried out efficiently following the TTM step. Finally, we develop a hybrid MPI-OpenMP based implementation of the overall algorithm and report speedup results on up to 2048 cores.
Fichier principal
Vignette du fichier
RR-8801.pdf (794.1 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01219316 , version 1 (22-10-2015)

Licence

Copyright

Identifiers

  • HAL Id : hal-01219316 , version 1

Cite

Oguz Kaya, Bora Uçar. High-performance parallel algorithms for the Tucker decomposition of higher order sparse tensors. [Research Report] RR-8801, Inria - Research Centre Grenoble – Rhône-Alpes. 2015. ⟨hal-01219316⟩
402 View
1658 Download

Share

More