计算机工程与应用2016，Vol.52Issue(7)：17-23,7.DOI:10.3778/j.issn.1002-8331.1407-0328
面向异构众核的CUDA程序二进制翻译
Binary translation of CUDA program for heterogeneous and many-core architecture
摘要
Abstract
Porting CUDA program to other heterogeneous and many-core architectures by the way of binary translation is significant for extending the range of the CUDA application, leveraging the advantage of many cores and supporting national industry. Begin with the CUDA executive code, a translation framework is designed in which the host-end codes and device-end codes are translated separately based on a method of Divide-and-Conquer. In the course of migration, the solu-tions of several key problems are described emphatically such as the extraction of device-end codes, the mapping of com-puting model and storage model, synchronization barrier and instruction translation. The experimental results validate the system’s correctness.关键词
CUDA程序/二进制翻译/计算模型映射/存储模型映射/栅栏同步/指令翻译Key words
CUDA program/binary translation/computing model mapping/storage model mapping/synchronization barrier/instruction translation分类
信息技术与安全科学引用本文复制引用
李男,庞建民,单征..面向异构众核的CUDA程序二进制翻译[J].计算机工程与应用,2016,52(7):17-23,7.基金项目
国家高技术研究发展计划（863）（No.2009AA012201）；国家核高基重大专项（No.2009ZX01036-001-001，No.0412-7）。 （）
