arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.04804cs.LG
收藏

一种用于统一机器学习预测服务的张量分类器

A Tensor Compiler for Unified Machine Learning Prediction Serving

UC San Diego(加利福尼亚大学圣地亚哥分校);Microsoft(微软);Seoul National University(首尔国立大学)

Supun Nakandala, Karla Saur, Gyeong-In Yu, Konstantinos Karanasos, Carlo Curino, Markus Weimer, Matteo Interlandi

摘要:

机器学习(ML)在企业中的采用需要更简单、更高效的软件基础设施--大型网络公司中典型的定制解决方案根本站不住脚。模型评分是从训练模型中获得对新数据的预测的过程,是基础设施复杂性和成本的主要贡献者,因为模型只训练一次,但使用多次。在本文中,我们提出了HUMMINGBIRD,一种新的模型评分方法,它编译了特征化运算符和传统的ML模型(例如,决策树)分解成一小组张量运算。这种方法本质上降低了基础设施的复杂性,并直接利用神经网络编译器和运行时的现有投资,为CPU和硬件加速器生成高效的计算。我们的性能结果很有趣:尽管替换了命令式计算(例如,树遍历)与张量计算抽象,HUMMINGBIRD具有竞争力,并且在CPU和GPU上的微基准测试中通常优于手工制作的内核,同时实现ML管道的无缝端到端加速。我们已经将HummingBird作为开源发布。

英文摘要:

Machine Learning (ML) adoption in the enterprise requires simpler and more efficient software infrastructure---the bespoke solutions typical in large web companies are simply untenable. Model scoring, the process of obtaining predictions from a trained model over new data, is a primary contributor to infrastructure complexity and cost as models are trained once but used many times. In this paper we propose HUMMINGBIRD, a novel approach to model scoring, which compiles featurization operators and traditional ML models (e.g., decision trees) into a small set of tensor operations. This approach inherently reduces infrastructure complexity and directly leverages existing investments in Neural Network compilers and runtimes to generate efficient computations for both CPU and hardware accelerators. Our performance results are intriguing: despite replacing imperative computations (e.g., tree traversals) with tensor computation abstractions, HUMMINGBIRD is competitive and often outperforms hand-crafted kernels on micro-benchmarks on both CPU and GPU, while enabling seamless end-to-end acceleration of ML pipelines. We have released HUMMINGBIRD as open source.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑