联系我们
意见反馈

关注公众号

获得最新科研资讯

分享到
实验室简介

RAPID team

Reconfigurable And Programmable Intelligent Device

TEAM LEAD

Dr. Shouyi Yin

Dr. Shouyi Yin received B.S, M.S. and Ph.D. from Tsinghua University in 2000, 2002 and 2005 respectively. He has been with Imperial College London, London, U.K., as a Research Associate. He is currently with the Institute of Microelectronics (IME), Tsinghua University, as an Associate Professor. He is now the vice director of IME and leading the division of Computer-Aided Design. His current research interests include reconfigurable computing, mobile computing and neuromorphic computing. Dr. Yin has published one book, a handful of book chapters, and more than 100 journal and conference papers. He has been granted with 45 China patents with other 39 pending applications.

还没有发布内容

Efficient Compiling on CGRAs

Reconfigurable Cloud Platform

Cloud computing provides shared computer processing resources and data to computers and other devices on demand. Most cloud platform is based on CPUs and GPUs, whose power consumption can be very high. Here we design a reconfigurable cloud platform, which uses our CHAMELEON CGRA chip as accelerator. Each CHAMELEON chip has 4x8x8 reconfigurable PEs using 65nm technology. We integrate two CHAMELEON chips onto a FPGA-assisted PCI-E board, and insert four PCI-E boards in one server. An elastic management system is build over a five-node (1 master + 4 slaves) cluster.  The computing speed shows a near-linear relationship with the number of computing nodes, and the computing efficiency is about three orders-of-magnitude better than Xeon CPU under 200MHz clock.

Thinker - Reconfigurable Neural Network Processor

"Thinker” is an energy-efficient hybrid neural network (NN) processor fabricated using 65nm technology. It has two 16x16 reconfigurable heterogeneous processing elements (PEs) arrays. To accelerate a hybrid-NN, PE array is designed to support on demand partitioning and reconfiguration for parallel processing different NNs. To improve the energy efficiency, each PE supports bit-width adaptive computing to meet variant bit-width of different neural layers. Measurement results show that this processor achieves a peak 409.6GOPS running at 200MHz and at most 5.09TOPS/W energy efficiency. It outperforms the state-of-the-art up to 5.2X in energy efficiency.

访问量:406