并行计算实验课程建设的实践与探讨

Exploration and Practice on Construction of Parallel Computing Experiment Course

并行计算一直是计算机和软件工程学科的专业基础课程,具有较强的综合性、方法性和实践性。结合天津大学高性能计算实验室多年来在并行计算课程建设上的实际经验和成果,从知识体系、实验设计、创新训练、实验平台、实验考核等多方面进行总结,并针对不同专业和年级的学生对并行计算课程的实际需求,重点说明了利用虚拟化和云计算技术构建综合实验平台的方法,以及以具体任务和问题为驱动的实验教学模式和多角度的考核机制。探讨了并行计算实验教学如何紧跟前沿技术发展的途径,以便有效地应对云计算、大数据时代对专业人才培养的基本要求。

Parallel computing, which is comprehensive, methodological and practical, is always a fundamental course of computer science and software engineering. Based on the practical experiences and achievements of parallel computing course from the High Performance Computing Lab of Tianjin university, a detailed summary was made on experiment design, innovation training, experiment platform, and experiment evaluation etc. In order to satisfy the actual demand of students from different majors and grades, it presented an approach of constructing comprehensive experiment platform by using virtualization and cloud computing technology, the real task driven experimental teaching method, and the multi-dimensional evaluation mechanism. An effective way was also explored so that parallel computing experiment teaching can keep up with the cutting edge of technologies, in order to satisfy the basic requirement for qualified personnel training and education in the era of big data and cloud computing.