讲座题目：Spintronic Memory: From Memory to Computing-in-Memory 主讲人：康旺 教授 主持人：石亮 教授 开始时间：2019-05-14 15:00:00 结束时间：2019-05-14 16:00:00 讲座地址：理科大楼B616 主办单位：计算机科学与软件工程学院
报告人简介：
Dr. Wang KANG received the double Ph.D degrees in Physics from University of Paris-Sud, France, and in Microelectronics from Beihang University, China in 2014. From 2015 to 2017, he was a Postdoc in Computer Engineering at Beihang University. Since 2018, he has been an Associate Professor in School of Microelectronics at Beihang University. His research interest includes spintronics and its related device, circuit and architecture designs. He is now focusing on skyrmion-electronics and computing in spintronic memories. He has authored or co-authored 2 book chapters, 20 Chinese patents and more than 80 scientific papers, including Proc. IEEE, IEEE Trans. Computers, IEEE Trans. Circ. Syst. I: Reg. Papers, IEEE Trans. Electron Devices., IEEE Electron Devices Lett., IEEE Trans. Nanotechnology, DAC, DATE, ASP-DAC, GLSVLSI etc. He is a guest editor of Microelectronics Journal. 报告内容： Spintronic memory has been considered as one of the most promising nonvolatile memory candidates to address the leakage power consumption in the post-Moore’s era. To date, the spintronic memory family has evolved in four-generation technology advancement, from toggle-MRAM (product in 2006), to STT-MRAM (product in 2012), to SHE-MRAM (intensive R&D today), and to VCMA-MRAM (intensive R&D today). The trend from field-controlled, to current-controlled, and to voltage-controlled devices, allows for more energy efficiency of the memory itself, because of the significant decrease of the ohmic loss or joule heating. Meanwhile, novel spintronic memory paradigms are emerging, e.g., racetrack memory, for ultra-high-density storage to replace HDD or SDD. On the other hand, from the architectural perspective, data transfer bandwidth and the related power consumption has become the most critical bottleneck in von-Neumann computing architecture, owing to the separation of the processor and the memory units and the performance mismatch between the two. Realization of the unity of computing and memory in the same chip has opened up a promising research direction of computing-in-memory (CIM). Spintronic memory could be a promising technology to implement the CIM paradigm, owing to its intrinsic processing capability. Lots of interests have been attracted and a number of attempts have been made in this field. In this talk, I will review the R&D evolution of spintronic memory: from memory to computing-in-memory. Particularly, I will introduce our recent work on advanced spintronic memories as well as CIM paradigms implemented within spintronic memories.
|
