Welcome to the Scalable Energy-efficient Architecture Lab

The Scalable Energy-efficient Architecture Lab (SEAL) is a research group at The University of California, Santa Barbara. SEAL research focuses on, but not limited to, VLSI design, electronic design automation, computer architecture, compiler, programming langauage, and  systems design. Current research projects include domain specific accelerator, novel memory architecture, interconnect architecture, and heterogeneous system architecture.  Specifically, recent research projects focus on technology-driven and application-driven design/architecture innovations. The technology-driven research projects include EDA/architecture for emerging memory technologies and 3D integrated circuits,  and heterogeneous computing with CPU/GPU/FPGA. The application-driven research projects include novel architectures for artificial intelligence (AI), such as computer architecture for deep learning neural network, and bio-inspired computing, hardware acceleration for emerging applications such as bio-informatics applications, graphics analytics, and VR/AR applications.

 

 

Recent News

[Faculty Position] [Fall 2022] Dr. Liu Liu finished his Ph.D. Defense and will join in Rensselaer Polytechnic Institute RPI as Assistant Professor at ECE department.
[Faculty Position] Gushu Li will join Upenn as Assistant Professor in Jan. 2023
[Award] Yuan Xie and his former student, Xiangyu Dong, received the 10-Year Retrospective Most Influential Paper Award at Asia and South-Pacific Design Automation Conference (ASP-DAC'21) for their paper entitled "AdaMS: Adaptive MLC/SLC phase-change memory design for file storage" published in ASP-DAC in 2011. 
[Award] Prof. Yufei Ding received the prestigious NSF CAREER award.
[Award] Gushu Li received Distinguished Paper Award at OOPSLA 2020 for the paper titled "Projection-Based Runtime Assertions for Testing and Debugging Quantum Programs"
[Honor] Yuan Xie was elected as ACM Fellow and AAAS Fellow in 2019, and received the IEEE Computer Society Edward J. McCluskey Technical Achievement Award.
[Award] Dong's 2009 ASP-DAC paper received 10-Year Retrospective Most Influential Paper Award in 2019
[Award]  Kaisheng Ma's ASPDAC 2017 paper received the Best Paper Award. He will Join Tsinghua University as Assistant Professor
[Award] Cong Xu's dissertation has been selected as the honorable mention of SPEC Distinguished Dissertation Award 2015, for contributions to modeling, circuit design and microarchitecture for emerging resistive memory.
[Service] Professor Xie has been appointed as the next Editor-in-Chief of ACM Journal on Emerging Technologies in Computing (JETC) by ACM Publications Board.
[Award] Kaisheng Ma, Yang Zheng, and Shuangchen Li, together with PSU and Tsinghua collaborators, won [HPCA 2015 Best Paper Award].
[IEEE Fellow] Yuan Xie is elevated to IEEE Fellow due to contributions in design automation and architecture for 3D ICs.

Research Highlights

Hardware Acceleration for AI applications and Neuromorphic Computing

Artificial Intelligent algorithms are exerting an evolutionary influence on human society covering a wide spectrum of applications, including image recognition, speech understanding, robots intelligence, traffic control, and data analytics. The improving performance of Artificial Intelligent... more

Three-Dimensional Integrated Circuits (3D ICs)

A three dimensional (3D) chip is a stack of multiple device layers with direct vertical interconnects tunneling through them. A key benefit of this approach over a traditional two dimensional chip is the ability to reduce the length of long interconnects.

MAAEMO*: Modeling, Architecture and Application for Emerging Memory Technologies

In recent years, emerging non-volatile memory (NVM) technologies, e.g., Phase-Change RAM (PCRAM), STT-RAM (MRAM) Resistive RAM (RRAM), and Memristors, have gained substantial attentions and a

Variation-Aware Synthesis and Design

The challenges in fabricating transistors with diminutive feature sizes in the nanometer regimes have resulted in significant variations in key transistor parameters, such as transistor channel length, gate-oxide thickness, and threshold voltage. This manufacturing variability can  cause... more

Low Power Design and Thermal-Aware Design Techniques

Process scaling and aggressive performance improvements have resulted in power consumption becoming a first-order design criterion. For example, the latest Intel Pentium 4 processor (Prescott, 2004) has a power consumption of 103 Watts, almost four times larger than that of the Pentium III (1999).... more

Embedded System Design

Embedded systems are of great economic importance. Embedded applications include consumer electronics appliance, signal processing, automobile control, aircraft autopilot, and so on. It is estimated that the embedded system market sales was approximately $46 billion in 2004 and expected to grow at... more