Load-balanced sparse mttkrp on gpus

I Nisa, J Li, A Sukumaran-Rajam… - 2019 IEEE …, 2019 - ieeexplore.ieee.org
Sparse matricized tensor times Khatri-Rao product (MTTKRP) is one of the most
computationally expensive kernels in sparse tensor computations. This work focuses on …

Efficient and effective sparse tensor reordering

J Li, B Uçar, ÜV Çatalyürek, J Sun, K Barker… - Proceedings of the ACM …, 2019 - dl.acm.org
This paper formalizes the problem of reordering a sparse tensor to improve the spatial and
temporal locality of operations with it, and proposes two reordering algorithms for this …

An efficient mixed-mode representation of sparse tensors

I Nisa, J Li, A Sukumaran-Rajam, PS Rawat… - Proceedings of the …, 2019 - dl.acm.org
The Compressed Sparse Fiber (CSF) representation for sparse tensors is a generalization of
the Compressed Sparse Row (CSR) format for sparse matrices. For a tensor with d modes …

Minimum cost loop nests for contraction of a sparse tensor with a tensor network

R Kanakagiri, E Solomonik - Proceedings of the 36th ACM Symposium …, 2024 - dl.acm.org
Sparse tensor decomposition and completion are common in numerous applications,
ranging from machine learning to computational quantum chemistry. Typically, the main …

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

A Nguyen, AE Helal, F Checconi… - Proceedings of the 36th …, 2022 - dl.acm.org
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 …

Exploiting hierarchical parallelism and reusability in tensor kernel processing on heterogeneous HPC systems

Y Chen, G Xiao, MT Özsu, Z Tang… - 2022 IEEE 38th …, 2022 - ieeexplore.ieee.org
Canonical Polyadic Decomposition (CPD) of sparse tensors is an effective tool in various
machine learning and data analytics applications, in which sparse Matricized Tensor Times …

Distributed-memory tensor completion for generalized loss functions in python using new sparse tensor kernels

N Singh, Z Zhang, X Wu, N Zhang, S Zhang… - Journal of Parallel and …, 2022 - Elsevier
Tensor computations are increasingly prevalent numerical techniques in data science, but
pose unique challenges for high-performance implementation. We provide novel algorithms …

Multi-level optimization of the canonical polyadic tensor decomposition at large-scale: Application to the stratification of social networks through deflation

A Gillet, É Leclercq, N Cullot - Information Systems, 2023 - Elsevier
Tensors are multi-dimensional mathematical objects that allow to model complex
relationships and to perform decompositions for analytical purpose. They are used in a wide …

Distributed-memory tensor completion for generalized loss functions in python using new sparse tensor kernels

N Singh, Z Zhang, X Wu, N Zhang, S Zhang… - arXiv preprint arXiv …, 2019 - arxiv.org
Tensor computations are increasingly prevalent numerical techniques in data science, but
pose unique challenges for high-performance implementation. We provide novel algorithms …

GPUTucker: Large-Scale GPU-Based Tucker Decomposition Using Tensor Partitioning

J Lee, D Han, OK Kwon, KW Chon, MS Kim - Expert Systems with …, 2024 - Elsevier
Tucker decomposition is used extensively for modeling multi-dimensional data represented
as tensors. Owing to the increasing magnitude of nonzero values in real-world tensors, a …