VAST lab at UCLA

The VAST lab at UCLA investigates cutting-edge research topics at the intersection of VLSI technologies, design automation,  architecture and compiler optimization at multiple scales, from micro-architecture building blocks,  to heterogeneous compute nodes, and scalable data centers.  Current focuses include architecture and design automation for emerging technologies, customizable domain-specific computing with applications to multiple domains, such as imaging processing, bioinformatics, data mining and machine learning.

Latest News

March 3, 2022 | 0 comments

Congratulations to VAST Lab members Licheng Guo and Prof. Cong, together with collaborators from AMD/Xilinx and Cornell, Ghent University for winning the Best Paper Award at the 2022 ACM/SIGDA International Symposium on Field-...

March 1, 2022 | 0 comments

Prof. Jason Cong gave the Vision Address at the 35th International Conference on VLSI Design entitled "Democratize IC Designs and Customized Computing" on February 28, 2022 (...

January 19, 2022 | 0 comments

Congratulations to Prof. David Pan for being elected to ACM Fellow for "For contributions to electronic design automation, including design for manufacturing and physical design”.

Dr. Pan...

Latest Publications

StreamGCN: Accelerating Graph Convolutional Networks with Streaming Processing
Conference publication
Atefeh Sohrabizadeh, Yuze Chi, Jason Cong
Pyxis: An Open-Source Performance Dataset of Sparse Accelerators
Conference publication
Linghao Song, Yuze Chi, and Jason Cong
Accelerating SSSP for Power-Law Graphs
Conference publication
Yuze Chi, Licheng Guo, and Jason Cong
RapidStream: Parallel Physical Implementation of FPGA HLS Designs
Conference publication
Licheng Guo, Pongstorn Maidee, Yun Zhou, Chris Lavin, Jie Wang, Yuze Chi, Weikang Qiao, Alireza Kaviani, Zhiru Zhang, and Jason Cong
Sextans: A Streaming Accelerator for General-Purpose Sparse-Matrix Dense-Matrix Multiplication
Conference publication
Linghao Song, Yuze Chi, Atefeh Sohrabizadeh, Young-kyu Choi, Jason Lau, and Jason Cong
Optimal Qubit Mapping with Simultaneous Gate Absorption
Conference publication
Bochen Tan and Jason Cong
AutoDSE: Enabling Software Programmers to Design Efficient FPGA Accelerators
Journal publication
Atefeh Sohrabizadeh, Cody Hao Yu, Min Gao, and Jason Cong
Scaling Up Hardware Accelerator Verification using A-QED with Functional Decomposition
Conference publication
Saranyu Chattopadhyay, Florian Lonsing, Luca Piccolboni, Deepraj Soni, Peng Wei, Xiaofan Zhang, Yuan Zhou, Luca Carloni, Deming Chen, Jason Cong, Ramesh Karri, Zhiru Zhang, Caroline Trippel, Clark Barrett and Subhasish Mitra
[PDF]: Fast Calcium Trace Extraction for Large-Field-of-View Miniscope
Conference publication
Zhe Chen, Garrett J. Blair, Hugh T. Blair, Jason Cong
[PDF]: Live Demonstration: Real-Time Calcium Trace Extraction from Large-Field-of-View Miniscope
Conference publication
Zhe Chen, Garrett J. Blair, Changliang Guo, Daniel Aharoni, Hugh T. Blair, Jason Cong

Our Projects

Quantum computing (QC) has been shown, in theory, to hold huge advantages over classical computing. However, there remains many engineering challenges in the implementation of real-world QC applications. In order to devide-and-conquer, we can split the task as below.

...

Heterogeneous computing with extensive use of accelerators, such as FPGAs and GPUs, has shown great promise to bring in orders of magnitude improvement in computing efficiency for a wide range of applications. The latest advances in industry have led to highly integrated heterogeneous hardware...

Direction 1: Real-Time Neural Signal Processing for Closed-Loop Neurofeedback Applications.

The miniaturized fluorescence microscope (Miniscope) and the tetrodes assembly are emerging techniques in observing the activity of a large population of neuros in vivo. It opens up new research...

In the Big Data era, the volume of data is exploding, putting forward a new challenge to existing computer systems. Traditionally, the computer system is designed to be computing-centric, in which the data from IO devices is transferred and then processed by the CPU. However, this data movement...

In this project, we explore efficient algorithms and architectures for state-of-the-art deep learning based applications. In the first work, we are exploring learning algorithms and acceleration techniques on graph learning algorithms. The second work, Caffeine, offers a uniformed...

In the era of big data, many applications present siginificant compuational challenges. For example, in the field of bio-infomatics, the computation demand for personalized cancer treatment is prohibitively high for the general-purpose computing technologies, as tumor heterogeneity...

http://www.cdsc.ucla.edu

To meet ever-increasing computing needs and overcome power density limitations, the computing industry has entered theera of parallelization, with tens to hundreds of computing cores integrated into a single...

Software Releases

Pyxis collects open-source accelerator designs and the performance data.

https://github.com/UCLA-VAST/Pyxis

Sextans is an FPGA accelerator for general-purpose Sparse-Matrix Dense-Matrix Multiplication (SpMM).

https://github.com/UCLA-VAST/Sextans

https://github.com/UCLA-VAST/AutoDSE

 

Adopting FPGA as an accelerator in datacenters is becoming mainstream for customized computing, but the fact that FPGAs are hard to program creates a steep learning curve for software...