Improving performance portability for GPU-specific Open CL kernels on multi-core/many-core CPUs by analysis-based transformations  

使用“基于分析的代码转换方法”来提升GPU特定的OpenCL kernel在多核/众核CPU上的性能移植性(英文)

作　　者：Mei WEN Da-fei HUANG Chang-qing XUN Dong CHEN 

机构地区：[1]School of Computer, National University of Defense Technology [2]National Key Laboratory of Parallel and Distributed Processing

出　　处：《Frontiers of Information Technology & Electronic Engineering》2015年第11期899-916,共18页信息与电子工程前沿（英文版）

基　　金：Project supported by the National Natural Science Foundation of China(No.61272145);the National High-Tech R&D Program(863)of China(No.2012AA012706)

摘　　要：OpenCL is an open heterogeneous programming framework. Although OpenCL programs are func- tionally portable, they do not provide performance portability, so code transformation often plays an irreplaceable role. When adapting GPU-specific OpenCL kernels to run on multi-core/many-core CPUs, coarsening the thread granularity is necessary and thus has been extensively used. However, locality concerns exposed in GPU-specific OpenCL code are usually inherited without analysis, which may give side-effects on the CPU performance. Typi- cally, the use of OpenCL＇s local memory on multi-core/many-core CPUs may lead to an opposite performance effect, because local-memory arrays no longer match well with the hardware and the associated synchronizations are costly. To solve this dilemma, we actively analyze the memory access patterns using array-access descriptors derived from GPU-specific kernels, which can thus be adapted for CPUs by （1） removing all the unwanted local-memory arrays together with the obsolete barrier statements and （2） optimizing the coalesced kernel code with vectorization and locality re-exploitation. Moreover, we have developed an automated tool chain that makes this transformation of GPU-specific OpenCL kernels into a CPU-friendly form, which is accompanied with a scheduler that forms a new OpenCL runtime. Experiments show that the automated transformation can improve OpenCL kernel performance on a multi-core CPU by an average factor of 3.24. Satisfactory performance improvements axe also achieved on Intel＇s many-integrated-core coprocessor. The resultant performance on both architectures is better than or comparable with the corresponding OpenMP performance.目的:针对面向GPU设计的Open CL kernel程序在CPU上性能移植性欠佳这一问题,设计一种基于访存特征分析的代码转换方法,提升性能移植性。创新点:通过分析Open CLkernel中的访存模式,去除不必要的局部存储数组及其带来的同步语句,并使用向量化和局域性重开发进一步优化代码,最终取得显著的性能提升。方法:首先,针对Open CL kernel代码中的数组访问,设计一种精确的线性化访问描述子(图2)。然后,利用该描述子,分两步对GPU特定的Open CL kernel代码进行转换,以提高其在CPU上的性能(图7)。第一步为基于分析的work-item折叠,即通过分析访问描述子,找出并去除不必要的局部存储数组及其带来的同步语句,然后完成work-item折叠。第二步为适应架构的代码优化,即针对CPU架构的特点,使用向量化和局域性重开发进一步优化折叠后的代码。最后,上述代码转换过程被整合为一个工具链,连同一个调度程序,嵌入到一个开源的Open CL运行时系统中(图11)。实验结果表明,这种转换方法可以显著提升GPU特定的Open CL kernel在Intel Sandy Bridge架构CPU和Intel Knights Corner架构协处理器上的性能。结论:准确分析Open CL kernel代码中的访存模式,不仅利于判断局部存储数组是否适合于CPU架构,还能用于指导之后的代码优化过程,因此是提高性能移植性的重要步骤。

关 键 词：OpenCL Performance portability Multi-core/many-core CPU Analysis-based transformation 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP311.54[自动化与计算机技术—计算机科学与技术]