StarMPI-SVD:分布式内存并行 Star-M 张量 SVD
StarMPI-SVD: Distributed-Memory Parallel Star-M Tensor SVD
Naman Pesricha, Grey Ballard, Srinivas Eswar, Md Taufique Hussain, Vishwas Rao, Phani Motamarri
AI 速读 基于摘要
作者提出 t-SVDM-I 与 t-SVDM-II 的首个分布式内存实现,面向 N 维张量,并用异步非阻塞通信优化数据重分布与关键计算内核。
cs.DC
查看原文摘要
The star-M tensor algebra generalizes the optimal compression guarantees of the matrix singular value decomposition (SVD) to higher-order tensors. The t-SVDM-I decomposition is computed using a set of invertible transformations and slice-wise truncated SVDs with a prescribed rank, and its adaptive, multirank variant t-SVDM-II can determine slice-wise ranks to satisfy a prescribed error tolerance. Existing implementations of these algorithms are limited to shared-memory environments, restricting their applicability to modern large-scale datasets. In this work, we present the first distributed-memory implementations of t-SVDM-I and t-SVDM-II, which are generalized to N-way tensors. To address computational and communication bottlenecks, we design asynchronous, non-blocking communication strategies for efficient data redistribution to obtain highly efficient key computational kernels. Strong-scaling experiments demonstrate the efficiency and scalability of our approach (at least 70% parallel efficiency on up to 128 nodes, or 6144 cores), and we apply the star-M compression techniques to a set of application datasets of size up to 768 GB.