报告题目： grape: parallelizing sequential graph computations
报告人： 尹强 博士 阿里巴巴达摩院
主持人： 邓玉欣 教授
报告时间： 2019年3月29日 周五13:30-14:30
报告地点： 中北校区数学馆201
报告摘要：
grape is a parallel system for graph computations. it differsfrom prior systems in its ability to parallelize existin sequential
graph algorithms as a whole. underlying grape are a simple programming model and a principled approach, based on partial evaluation and incremental computation. in this talk, i will show that sequential graph algorithms can be "plugged into" grape with minor changes, and get parallelized. as long as the sequential algorithms are correct, their grape parallelization guarantees to terminate with correct answers under a monotonic condition. moreover, algorithms in mapreduce, bsp and pram can be optimally simulated on grape. in addition to the ease of programming, our experiments results verify that grape achieves comparable performance to the state-of-the-art graph systems, using real-life and synthetic graphs.
报告人简介：
dr. qiang yin is a senior engineer of data analytics and intelligence lab, alibaba damo academy. prior to joining alibaba, he
worked as a postdoc researcher in beihang university. he received his master and ph.d degrees from shanghai jiao tong university in 2012 and2016, respectively. his current main research interests lie in parallel and distributed graph data processing.