Home Publications Research Grants Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

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

Nguyen A, Helal AE, Checconi F, Laukemann J, Tithi JJ, Soh Y, Ranadive T, Petrini F, Choi JW (2022)

---

Publication Type: Conference contribution

Publication year: 2022

Publisher: Association for Computing Machinery

Conference Proceedings Title: Proceedings of the International Conference on Supercomputing

Event location: Online

ISBN: 9781450392815

DOI: 10.1145/3524059.3532363

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 strategies not only meet the resource constraints of GPU devices, but also accelerate data indexing, eliminate control-flow and memory-access irregularities, and reduce kernel launching overhead. To address the substantial synchronization cost on GPUs, we introduce an opportunistic conflict resolution algorithm, in which threads collaborate instead of contending on memory access to discover and resolve their conflicting updates on-the-fly, without keeping any auxiliary information or storing non-zero elements in specific mode orientations. As a result, our framework delivers superior in-memory performance compared to prior state-of-the-art, and is the only framework capable of processing out-of-memory tensors. On the latest Intel and NVIDIA GPUs, BLCO achieves 2.12-2.6X geometric-mean speedup (with up to 33.35X speedup) over the state-of-the-art mixed-mode compressed sparse fiber (MM-CSF) on a range of real-world sparse tensors.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Nguyen, A., Helal, A.E., Checconi, F., Laukemann, J., Tithi, J.J., Soh, Y.,... Choi, J.W. (2022). Efficient, out-of-memory sparse MTTKRP on massively parallel architectures. In Proceedings of the International Conference on Supercomputing. Online: Association for Computing Machinery.

MLA:

Nguyen, Andy, et al. "Efficient, out-of-memory sparse MTTKRP on massively parallel architectures." Proceedings of the 36th ACM International Conference on Supercomputing, ICS 2022, Online Association for Computing Machinery, 2022.

BibTeX: Download