- Jialiang Zhang, et al. “Boosting the Performance of FPGA-based Graph Processor using Hybrid using Hybrid Memory Cube: A Case for Breadth First Search” accepted as FULL paper.
- Jialiang Zhang, et al. “Improving the Performance of OpenCL-based FPGA Accelerator for Convolutional Neural Network” accepted as FULL paper.
- Yue Zha, et al. – “A Data-Centric Mixed-Signal Reconfigurable Architecture enabled by RRAM Technology” accepted as poster.
Computer chips in development at the University of Wisconsin–Madison could make future computers more efficient and powerful by combining tasks usually kept separate by design.
Jing Li, an assistant professor of electrical and computer engineering at UW–Madison, is creating computer chips that can be configured to perform complex calculations and store massive amounts of information within the same integrated unit — and communicate efficiently with other chips. She calls them “liquid silicon.”
“Liquid means software and silicon means hardware. It is a collaborative software/hardware technique,” says Li. “You can have a supercomputer in a box if you want. We want to target a lot of very interesting and data-intensive applications, including facial or voice recognition, natural language processing, and graph analytics.”
The high-speed number-crunching of processors and the data warehousing of big storage memory in modern computers usually fall to two entirely different types of hardware.
“There’s a huge bottleneck when classical computers need to move data between memory and processor,” says Li. “We’re building a unified hardware that can bridge the gap between computation and storage.”
Processor and memory chips are typically separately produced by different manufacturing foundries, then assembled together by system engineers on printed circuit boards to make computers and smartphones. The separation means even simple operations, like searches, require multiple steps to accomplish: first fetching data from the memory, then sending that data all the way through the deep storage hierarchy to the processor core.
The chips Li is developing, by contrast, incorporate memory, computation and communication into the same device using a layered design called monolithic 3D integration: silicon and semiconductor circuitry on the bottom connected with solid-state memory arrays on the top using dense metal-to-metal links.
End users will be able to configure the devices to allocate more or fewer resources to memory or computation, depending on what types of applications a system needs to run.
“It can be dynamic and flexible,” says Li. “We originally worried it might be too hard to use because there are too many options. But with proper optimization, anyone can take advantage of the rich flexibility offered by our hardware.”
To help people harness the new chip’s potential, Li’s group also is developing software that translates popular programming languages into the chip’s machine code, a process called compilation.
“If I just handed you something and said, ‘This is a supercomputer in a box,’ you might not be able to use it if the programming interface is too difficult,” says Li. “You cannot imagine people programming in terms of binary zeroes and ones. It would be too painful.”
Thanks to her compilation software, programmers will be able to port their applications directly onto the new type of hardware without changing their coding habits.
To evaluate the performance of prototype liquid silicon chips, Li and her students established an automated testing system they built from scratch. The platform can reveal reliability problems better than even the most advanced industry testing, and multiple companies have sent their chips to Li for evaluation.
Given that testing accounts for more than half the consumer cost of computer chips, having such advanced infrastructure at UW–Madison can help make liquid silicon chips a reality and facilitate future research.
“We can do all types of device-level, circuit-level and system-level testing with our platform,” says Li. “Our industry partners told us that our testing system does the entire job of a test engineer automatically.”
Li’s work is supported by a Defense Advanced Research Projects Agency Young Faculty Award, a first for a computational researcher at UW–Madison. She is one of 25 recipients nationwide receiving as much as $500,000 for two years to fund research on topics ranging from gene therapy to machine learning.
– Source: http://news.wisc.edu/liquid-silicon-computer-chips-could-bridge-gap-between-computation-and-storage/#sthash.Ji0Ie4NU.dpuf
Prof. Li’s patent on high density TCAM nominated for UW WARF Annual Innovation Award Finalist (6 out of 400+ patented technologies).
Yue Zha, Jing Li, “Reconfigurable In-Memory Computing with Resistive Memory Crossbar” was accepted by ICCAD’16
As the computing field builds programs and machines to take on ever more demanding workloads, Jing Li sees an imbalance developing.
“Today, if you look at big data research, the emphasis is all in the software domain, but hardware is ultimately the foundation,” Li says.
Li, who joined the UW-Madison Department of Electrical and Computer Engineering in winter 2015 as an assistant professor, wants to close that gap by questioning the physical and structural principles at the heart of computer hardware. Li prides herself on building actual prototypes to prove her concepts in novel computer architecture, an approach she developed at the IBM T.J. Watson Research Center, where she spent five years as a research staff member after earning her PhD at Purdue University in 2009. This experience proved Li’s strengths in tackling problems across the realms of computer architecture, in particular memory and storage, and gave her a passion for developing computing technologies that will make a difference in people’s everyday lives.
“I always tell people I got my second PhD at IBM,” Li says. “In school, I used to work a lot on simulation and modeling. Working in industry, I got exposed to seeing how we can push new ideas into production.”
Each step in Li’s career has also demonstrated her tenacity in two countries where women are underrepresented in science and engineering. While growing up in China, Li discovered she liked mathematics, physics and chemistry, so even as a child she felt herself going counter to the social norm. “My parents always encouraged me, but in China, people’s opinions were that as a girl, you were better off learning art or music,” Li says.
But she went on to earn her bachelor’s degree in electrical engineering at Shanghai Jiao Tong University in 2004, then headed to grad school at Purdue. She has joined a department that is among the nation’s leaders in employing female faculty—18 percent of tenured or tenure-track ECE faculty at UW-Madison are women. Senior ECE faculty including Philip Dunham Reed Professor Susan Hagness and Professor Amy Wendt also are leaders in outreach programs that encourage female pre-college students to become interested in science and engineering.
Li’s formidable track record at Purdue and IBM includes her successful demonstration in 2013 of the world’s first heterogeneous chip for associative computing using emerging nonvolatile memory technology—one that can perform efficient in-memory computing i.e., real-time pattern recognition, essentially blurring the boundary between two activities that are separate in today’s computer architecture paradigm. Her research work on emerging nonvolatile memories including PCM and STT RAM earned her special recognition from the IEEE Journal of Solid State Circuits and IEEE Transactions on Very Large Scale Integration (VLSI) Systems.
As she begins her research work at UW-Madison, Li will focus on building on that very first prototype, in hopes of achieving a fundamental breakthrough in attaining increased computing power, energy efficiency and flexibility that a computer hardware would ever offer. “That first step was a technology test vehicle. Beyond that there are a lot of challenges that haven’t been addressed to truly turn this exciting concept into reality,” Li says.
Though Li has returned to academia in search of more wide-ranging and collaborative research, working at IBM gave her crucial perspective on the ever-evolving challenges of computing and the integrated approaches required to meet them. IBM has also donated lab equipment that will allow Li to continue to test prototypes here on campus. That concrete testing capacity will be vital for Li, because she looks at these challenges from both a top-down perspective—encompassing a computing system as a whole—and a bottom up one—opportunities to upend the physical sciences that form the basis of computing. “We have many different directions to explore now, in terms of spintronics, carbon-based devices, flexible electronics, photonics, bio-devices, and so on,” Li says. “It’s not just silicon anymore.”
And to neglect the hardware picture, Li says, would be to neglect some profound obstacles. The very nature of the data and processes computers need to handle is constantly changing, which means hardware needs to become more adaptable. “The workload is very dynamic,” Li says. “It’s very hard to predict, two years from today, what will happen.”
Li believes improvements in future computer systems will be made through collaborative software and hardware innovations, rather than just through the traditional technology advances driven by Moore’s Law. Her goal in research is to develop innovative techniques that can transform today’s software-hardware hierarchy, not just drop-in replacements.
Li also realizes that transforming the computing field will require a deeply collaborative environment. As she interviewed for faculty positions, Li found herself drawn to UW-Madison because of its breadth and a culture that encourages researchers to work across departmental and disciplinary boundaries. She points to the long-running history of collaboration between faculty in the College of Engineering and their counterparts in the computer sciences department (which is part of the College of Letters & Science), and to the diversity within the ECE department itself, especially researchers who work with flexible electronics, photonics and microelectromechanical systems. Li also hopes to collaborate with applied physics researchers across UW-Madison. Outside of work, Li also enjoys hiking and exploring new restaurants and cultures—so naturally she’s excited to be living as well as working in Madison.
“All the faculty here are very supportive, and we don’t have barriers across departments,” Li says. “We have a pretty balanced program here—every area is strong, and I have a lot of collaborative opportunities. And we have very good students. I feel like I have everything I need.”