Proceedings of the 36th ACM International Conference on Supercomputing 2022
DOI: 10.1145/3524059.3532363
|View full text |Cite
|
Sign up to set email alerts
|

Efficient, out-of-memory sparse MTTKRP on massively parallel architectures

Abstract: Tensor decomposition (TD) is an important method for extracting latent information from high-dimensional (multi-modal) sparse data. This study presents a novel framework for accelerating fundamental TD operations on massively parallel GPU architectures. In contrast to prior work, the proposed Blocked Linearized CoOrdinate (BLCO) format enables efficient out-of-memory computation of tensor algorithms using a unified implementation that works on a single tensor copy. Our adaptive blocking and linearization strat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 8 publications
references
References 46 publications
0
0
0
Order By: Relevance