DLPlib： A Library for Deep Learning Processor  

作　　者：Hui-Ying Lan Lin-Yang Wu Xiao Zhang Jin-Hua Tao Xun-Yu Chen Bing-Rui Wang Yu-Qing Wang Qi Guo Yun-Ji Chen 

机构地区：[1]State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences Beijing 100190, China [2]Microprocessor Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China [3]University of Chinese Academy of Sciences, Beijing 100049, China [4]Department of Computer Science, University of Science and Technology of China, Hefei 230026, China

出　　处：《Journal of Computer Science & Technology》2017年第2期286-296,共11页计算机科学技术学报（英文版）

基　　金：This work is partially supported by the National Natural Science Foundation of China under Grant Nos. 61432016, 61472396, 61473275, 61522211, 61532016, 61521092, 61502446, 61672491, 61602441, and 61602446, the National Basic Research 973 Program of China under Grant No. 2015CB358800, and the Strategic Priority Research Program of the Chinese Academy of Sciences under Grant No. XDB02040009.

摘　　要：Recently, deep learning processors have become one of the most promising solutions of accelerating deep learning algorithms. Currently, the only method of programming the deep learning processors is through writing assembly instructions by bare hands, which costs a lot of programming efforts and causes very low efficiency. One solution is to integrate the deep learning processors as a new back-end into one prevalent high-level deep learning framework （e.g., TPU （tensor processing unit） is integrated into Tensorflow directly）. However, this will obstruct other frameworks to profit from the programming interface, The alternative approach is to design a framework-independent low-level library for deep learning processors （e.g., the deep learning library for GPU, cuDNN）. In this fashion, the library could be conveniently invoked in high-level programming frameworks and provides more generality. In order to allow more deep learning frameworks to gain benefits from this environment, we envision it as a low-level library which could be easily embedded into current high-level frameworks and provide high performance. Three major issues of designing such a library are discussed. The first one is the design of data structures. Data structures should be as few as possible while being able to support all possible operations. This will allow us to optimize the data structures easier without compromising the generality. The second one is the selection of operations, which should provide a rather wide range of operations to support various types of networks with high efficiency. The third is the design of the API, which should provide a flexible and user-friendly programming model and should be easy to be embedded into existing deep learning frameworks. Considering all the above issues, we propose DLPIib, a tensor-filter based library designed specific for deep learning processors. It contains two major data structures, tensor and filter, and a set of operators including basic neural network primitives and matrix/vecRecently, deep learning processors have become one of the most promising solutions of accelerating deep learning algorithms. Currently, the only method of programming the deep learning processors is through writing assembly instructions by bare hands, which costs a lot of programming efforts and causes very low efficiency. One solution is to integrate the deep learning processors as a new back-end into one prevalent high-level deep learning framework （e.g., TPU （tensor processing unit） is integrated into Tensorflow directly）. However, this will obstruct other frameworks to profit from the programming interface, The alternative approach is to design a framework-independent low-level library for deep learning processors （e.g., the deep learning library for GPU, cuDNN）. In this fashion, the library could be conveniently invoked in high-level programming frameworks and provides more generality. In order to allow more deep learning frameworks to gain benefits from this environment, we envision it as a low-level library which could be easily embedded into current high-level frameworks and provide high performance. Three major issues of designing such a library are discussed. The first one is the design of data structures. Data structures should be as few as possible while being able to support all possible operations. This will allow us to optimize the data structures easier without compromising the generality. The second one is the selection of operations, which should provide a rather wide range of operations to support various types of networks with high efficiency. The third is the design of the API, which should provide a flexible and user-friendly programming model and should be easy to be embedded into existing deep learning frameworks. Considering all the above issues, we propose DLPIib, a tensor-filter based library designed specific for deep learning processors. It contains two major data structures, tensor and filter, and a set of operators including basic neural network primitives and matrix/vec

关 键 词：deep learning processor API LIBRARY DLPlib 

分 类 号：TP[自动化与计算机技术]