Research:
1.
Big Data Accelerators Big
data applications are challenged by extremely large amount of data, usually
in terabytes (TB), or petabytes(PB), even exabytes (EB). Our research aims at
novel FPGA-based heterogeneous multi-core system, targeting at accelerating
the big data applications. In particular, we focus on following applications:
1) Machine Learning and Data Mining; 2) Graph Processing, and 3) Genome
Sequencing. Selected
Publications: 1. [TCBB] Chao Wang, Xi Li, Peng Chen, Xuehai
Zhou, Aili Wang and Hong Yu, “Heterogeneous Cloud Framework for Big Data Genome Sequencing”, IEEE/ACM Transactions on Computational Biology
and Bioinformatics. 2. [DATE] Chao Wang, Xi Li, Xuehai Zhou, SODA: Software Defined FPGA based Accelerators for Big Data, Design, Automation and Test in Europe, 2015. 3. [SPAA] Chao Wang, Xi Li, Aili Wang and Xuehai
Zhou: Brief Announcement:
MIC++: Accelerating Maximal Information Coefficient Calculation with GPUs and
FPGAs, 28th ACM
Symposium on Parallelism in Algorithms and Architectures. 2.
Neural Network Processors Neural
Network is playing an important role in Artificial Intelligence and Computer
Architecture research. Our study aims at novel FPGA-based processors and accelerators
for the cutting-edge neural network topology and applications including: 1) Convolutional
Neural Network, 2) Deep Belief Network, and 3) Sparse RNN and LSTM. Selected
Publications: 1. [TCAD]Chao Wang, Lei Gong, Qi Yu, Xi Li, Yuan Xie, Xuehai Zhou, DLAU: A Scalable Deep Learning Accelerator Unit on FPGA, IEEE Transactions on
Computer-Aided Design of Integrated Circuits and Systems. 2. [ICPADS]Yangyang Zhao, Qi Yu, Xuda Zhou, Xuehai Zhou, Chao Wang and Xi
Li, PIE: A Pipeline Energy-efficient Accelerator for Inference
Process in Deep Neural Networks, The 22nd IEEE International Conference on
Parallel and Distributed Systems. 3.
FPGA-based System and Scheduling FPGA
has been demonstrated as an energy efficient platform for accelerators.
However, how to accommodate heteronomous architectures with more task-level parallelism
is quite challenging. We focus on out-of-order execution on FPGA, and
services-based heterogeneous platforms. Selected
Publications: 1. [TPDS] Chao Wang,
Xi Li, Yunji Chen, Youhui Zhang, Oliver Diessel, Xuehai Zhou: Service-oriented
Architecture on FPGA-based MPSoC, IEEE Transactions on Parallel
and Distributed Systems. 2. [TPDS] Chao Wang, Xi Li,
Junneng Zhang, Aili Wang, Xuehai Zhou: Hardware Implementation
on FPGA for Task-level Parallel Dataflow Execution Engine, IEEE
Transactions on Parallel and Distributed Systems. 3. [TC] Chao Wang, Xi Li, Junneng
Zhang, Peng Chen, Yunji Chen, Xuehai Zhou, Ray C.C. Cheung: Architecture Support for
Task Out-of-order Execution in MPSoCs, IEEE Transactions on
Computers. 4. [TACO] Chao Wang, Xi Li, Junneng
Zhang, Xuehai Zhou, Xiaoning Nie. “MP-Tomasulo: a
Dependency-aware Automatic Parallel Execution Engine for Sequential Programs”.
ACM Transactions on Architecture and Code Optimization. |