Link to the news
University of Wisconsin-Madison engineers are part of a national effort to improve the future of computing across hardware, software and applications.
UW-Madison is one of 12 universities in the Center for Research in Intelligent Storage and Processing in Memory (CRISP), which is led by the University of Virginia. CRISP is funded through a $27.5 million grant from the Semiconductor Research Corporation under its Joint University Microelectronics Program, a five-year, $200 million national initiative to tackle fundamental computing questions through six university-based research centers.
Three researchers are heading up the UW-Madison group: Kevin Eliceiri, director of the Laboratory for Optical and Computational Instrumentation in the Department of Biomedical Engineering; Jing Li, an assistant professor and Dugald C. Jackson Faculty Scholar in the Department of Electrical and Computer Engineering; and Jignesh Patel, a professor in the Department of Computer Sciences in the College of Letters & Science.
UW-Madison will lead CRISP’s efforts to develop new data platforms and applications, as well as its overall data and imaging application themes.
The grant will also support nine graduate students and two postdoctoral researchers, allowing them to work on computing issues that cut across colleges and interact with major hardware vendors. The College of Engineering, College of Letters & Science and Morgridge Institute for Research all provided support for the grant proposal.
Maxwell Strange, an undergraduate researcher who has been working in our research group, will be joining the PhD program at Stanford. Hope all the best for your future endeavors Max! And we hope to see you often at future conferences.
Armed with the Cloud and a mission to push the limits of deep learning, Jing Li and her team of student “hackers” have bested industry titans and set a performance record.
With support from the WARF Accelerator Program, her latest project is developing a deep learning accelerator in the Cloud. The goal: faster, smarter and more energy-efficient systems for deep learning, with applications like improved speech recognition.
Jialiang Zhang, Soroosh Khoram and Jing Li, “ Efficient Large-scale Approximate Nearest Neighbor Search on the OpenCL-FPGA ”, Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Soroosh Khoram and Jing Li, “ Adaptive Quantization of Neural Networks”, International Conference on Learning Representations (ICLR), 2018
Prof. Li’s project, entitled “Associative In-Memory Graph Processing Paradigm: Towards Tera-TEPS Graph Traversal In a Box“, was recommended for 2018 NSF CAREER Award.
Soroosh Khoram, Yue Zha and Jing Li, “An Alternative Analytical Approach to Associative Processing,” in IEEE Computer Architecture Letters.
Yue Zha and Jing Li, “Liquid Silicon: A data-centric recongurable architecture enabled by RRAM technolog“, FPGA’18
Jialiang Zhang and Jing Li, “Degree-aware hybrid graph traversal on FPGA-HMC platform“, FPGA’18
Soroosh Khoram, Jialiang ZhangS, and Jing Li, “Accelerating graph analytics by co-optimizing storage and access on an FPGA-HMC platform“, FPGA’18