ALO-NMF: Accelerated Locality-Optimized Non-negative Matrix Factorization
ALO-NMF: Accelerated Locality-Optimized Non-negative Matrix Factorization
复制标题
DOI：
10.1145/3394486.3403227
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Gordon E. Moon;J. Austin Ellis;Aravind Sukumaran-Rajam;S. Parthasarathy;P. Sadayappan
中科院分区：
文献类型：
--
作者：
Gordon E. Moon;J. Austin Ellis;Aravind Sukumaran-Rajam;S. Parthasarathy;P. Sadayappan
非负矩阵分解（NMF）是无监督降维的一个关键核心，广泛应用于图挖掘，推荐系统和自然语言处理。由于必须执行重复NMF的应用程序的计算密集型性质，已经开发了几种并行实现。然而，现有的并行NMF算法没有解决数据局部性优化，这是高性能的关键，因为数据移动成本大大超过了当前计算机系统上的算术/逻辑运算的成本。在本文中，我们提出了一种新的优化方法，并行NMF算法的基础上的HALS（分层交替最小二乘）计划，结合算法变换，以提高数据的局部性。该算法在多核CPU和GPU上的有效实现，展示了一种新的加速局部优化NMF（ALO-NMF），与现有的最先进的并行NMF算法相比，数据移动成本降低了2.29倍，加速了4.45倍。
Non-negative Matrix Factorization (NMF) is a key kernel for unsupervised dimension reduction used in a wide range of applications, including graph mining, recommender systems and natural language processing. Due to the compute-intensive nature of applications that must perform repeated NMF, several parallel implementations have been developed. However, existing parallel NMF algorithms have not addressed data locality optimizations, which are critical for high performance since data movement costs greatly exceed the cost of arithmetic/logic operations on current computer systems. In this paper, we present a novel optimization method for parallel NMF algorithm based on the HALS (Hierarchical Alternating Least Squares) scheme that incorporates algorithmic transformations to enhance data locality. Efficient realizations of the algorithm on multi-core CPUs and GPUs are developed, demonstrating a new Accelerated Locality-Optimized NMF (ALO-NMF) that obtains up to 2.29x lower data movement cost and up to 4.45x speedup over existing state-of-the-art parallel NMF algorithms.