一种面向通用众核CPU的软件调试器设计

J4 ›› 2014, Vol. 36 ›› Issue (10): 1854-1859.

一种面向通用众核CPU的软件调试器设计

王敬宇，范昊

（江南计算技术研究所，江苏无锡 214083）

收稿日期:2014-06-10 修回日期:2014-08-25 出版日期:2014-10-25 发布日期:2014-10-25
基金资助:
国家863计划资助项目(2012AA010901)

A software debugger for general many-core processors

WANG Jingyu，FAN Hao

（Jiangnan Institute of Computing Technology,Wuxi 214083,China）

Received:2014-06-10 Revised:2014-08-25 Online:2014-10-25 Published:2014-10-25

摘要/Abstract

摘要：

近年来，众核处理器技术飞速发展，而面向该体系架构的软件调试技术相对滞后。针对众核平台上软件调试的特点，提出了一种一对多的软件调试模型，基于开源调试器gdb，设计了指令移位断点算法。该设计克服了硬件断点数量的限制，提升了异常定位的精确度，改善了软件调试器的易用性。最后通过实例对采用该设计的软件调试器进行了验证。结果表明，该设计能够有效解决众核程序的调试问题，提高软件调试器的执行效率，帮助程序员快速定位软件错误。

关键词: 众核, 调试, 断点移位

Abstract:

Recently, the many-core processor technology has been rapidly developed, but the software debugging for such architecture is underdeveloped. According to the characteristics of software debugging for many-core processors, the debugging model of onetomany mapping is proposed. Using this model, we configure the open source debugger gdb and design a breakpoint algorithm based on displaced instruction. The design overcomes the limitations on hardware breakpoint number, improves the accuracy of abnormal localization and makes the improved gdb more efficiently and effectively on many-core processors. Finally, experiments are carried out by a debugging example, and results show that the debugging model and algorithm are helpful to solve the problem of debugging many-core programs and improve the execution efficiency of software debugger.

Key words: many-core;debug;displaced breakpoint

王敬宇，范昊. 一种面向通用众核CPU的软件调试器设计[J]. J4, 2014, 36(10): 1854-1859.

WANG Jingyu，FAN Hao. A software debugger for general many-core processors [J]. J4, 2014, 36(10): 1854-1859.

参考文献［11］

［1］	Free Software Foundation Inc. GDB:The GNU project debugger［EB/OL］.［20130811］.http://www.gnu.org/software/gdb/.
［2］	Chen Cping. The parallel debugging architecture in the intel debugger［C］∥Proc of the 7th International Conference on Parallel Computing Technologies,2003:444451.
［3］	Miller J E, Kasture H, Kurian G,et al. Graphite:A distributed parallel simulator for multicores［C］∥Proc of IEEE International Symposium on HighPerformance Computer Architecture,2010:112.
［4］	Voung J W,Jhala R, Lerner S. RELAY:Static race detection on millions of lines of code［C］∥Proc of ESECFSE’07,2007:205214.
［5］	ElRewini H, AbdElBarr M. Advanced computer architecture and parallel processing (Wiley series on parallel and distributed computing)［M］.1st ed. NJ:Wiley Interscience,2005.
［6］	Serebryany K,Bruening D,Potapenko A,et al. Address Sanitizer:A fast address sanity checker,USENIX ATC,2012:110.
［7］	Hilbrich T,de Supinski B R,Schulz M. A graph based approach for MPI deadlock detection［C］∥Proc of the 23rd International Conference on Supercomputing, 2009:296305.
［8］	Chen Zhezhe, Gao Qi, Zhang Wenbin,et al. FlowChecker:Detecting bugs in MPI libraries via message flow checking［C］∥Proc of the 2010 ACM/IEEE International Conference on High Performance Computing, Networking, Storage and Analysis, 2010:111.
［9］	Watson G R. The design and implementation of a parallel relative debugger［D］. Monash University,2000.
［10］	Arnold D C,Ahn D H,de Supinski B R,et al. Stack trace analysis for large scale debugging［C］∥Proc of the International Parallel and Distributed Processing Symposium,2007:110.
［11］	Ickolls J,Buck I,Garland M. Scalable parallel programming with CUDA［J］.ACM Queue,2008,6(2):4053.

[1]	张立, 黎铁军, 张建民. 一种面向蒙特卡洛程序的128核可扩展体系结构[J]. 计算机工程与科学, 2023, 45(04): 590-598.
[2]	臧照虎, 李晨, 王耀华, 陈小文, 郭阳. 面向众核系统的层次化栅栏同步机制[J]. 计算机工程与科学, 2022, 44(11): 1901-1908.
[3]	俞茂学, 贾东宁, 魏志强, 许佳立, 马广浩. 一种基于国产异构众核处理器的C++智能源码转换框架[J]. 计算机工程与科学, 2021, 43(06): 997-1005.
[4]	丁哲昭, 储根深, 胡长军, 李扬. 基于申威众核处理器的圣维南求解程序的并行与优化[J]. 计算机工程与科学, 2021, 43(05): 820-829.
[5]	王武1，王舒扬1,2，姜金荣1,孟虹松3. 快速多极子方法在申威众核处理器上的实现和优化[J]. 计算机工程与科学, 2019, 41(07): 1161-1167.
[6]	陈逸飞，朱蕾，李宏亮. 一种多线程阵列众核处理器的二级Cache划分机制[J]. 计算机工程与科学, 2019, 41(03): 400-408.
[7]	文艳军，罗宇. 一种以内核调试分析实验为线索的操作系统原理授课法[J]. 计算机工程与科学, 2018, 40(增刊S1): 37-41.
[8]	陈逸飞，李宏亮，刘骁，高红光. 一种阵列众核处理器的多级指令缓存结构[J]. 计算机工程与科学, 2018, 40(04): 571-579.
[9]	符鹤1，李春江2，王昊2，谢永芳1. 众核计算平台的高吞吐率密码算法加速[J]. 计算机工程与科学, 2018, 40(04): 580-586.
[10]	张昆,郑方,谢向辉. 以访存为中心的阵列众核处理器核心流水线设计[J]. 计算机工程与科学, 2017, 39(12): 2167-2175.
[11]	徐顺1,2,刘倩1,2,张宝花1,2,何连花1,2,金钟1,2. 基于Intel MIC平台大规模耗散粒子动力学模拟的设计与优化[J]. 计算机工程与科学, 2017, 39(08): 1391-1396.
[12]	张昆,刘骁,郑方,谢向辉. 众核处理器的共享一级指令缓存研究[J]. 计算机工程与科学, 2017, 39(05): 834-840.
[13]	陈继承，王洪伟，张闯. 一种面向三维众核微处理器的新型NoC拓扑结构[J]. 计算机工程与科学, 2016, 38(08): 1542-1549.
[14]	方民权1，张卫民1，张理论1,2，曾琅3,4，刘晓彦5，尹龙祥5. 基于集成众核的3D蒙特卡罗半导体器件模拟器[J]. J4, 2015, 37(04): 621-627.
[15]	万虎1,徐远超1,2,孙凤芸1,闫俊峰1. 面向大数据应用的众核处理器缓存结构设计[J]. J4, 2015, 37(01): 28-35.