Hai Wang (王海)
中文主页(Chinese Homepage)
Education
Research Areas
- Artificial intelligence (AI) assisted integrated circuit design
- Electronic design automation of integrated systems (EDA)
- Computer design
Short Bio
Hai Wang received the B.S. degree from Huazhong University of Science and
Technology, China, and the M.S. and Ph.D. degrees from University of
California, Riverside, in 2007, 2008, and 2012, respectively. He is
currently a professor with the University of Electronic
Science and Technology of China. His research interests include
modeling, optimization, and artificial intelligence assisted design
automation of VLSI circuits and systems.
Dr. Wang has served on the organizing
committee of International Conference on Computer Design (ICCD), technical program committee of
Design Automation and Test Conference in Europe (DATE), Asia and South
Pacific Design Automation Conference (ASP-DAC), International
Symposium on Quality Electronic Design (ISQED), and International
Green and Sustainable Computing Conference (IGSC, formerly called IGCC). He also served as reviewer of many journals
including IEEE Transactions on Computers (TC), IEEE Transactions on
Computer-Aided Design of Integrated Circuits and Systems (TCAD), IEEE
Transactions on Parallel and Distributed Systems (TPDS), and ACM
Transactions on Design Automation of Electronic Systems (TODAES).
Dr. Wang was a recipient of the Best Paper Award nomination from Asia
and South Pacific Design Automation Conference (ASP-DAC) in 2019, at
Tokyo, Japan.
Click here for the
slides which introduce our recent research advances.
Selected Publications (since 2016)
The authors with star marker * are my students.
- H. Wang, X. Long*, and X.-X. Liu, "FastESN: Fast echo
state network", IEEE Transactions on Neural Networks and
Learning Systems (TNNLS), 2022. (early access, JCR Q1, IF 10.4, CCF B rank)
- H. Wang, W. He*, Q. Yang*, X. Peng, and H. Tang, "DBP: Distributed power
budgeting for many-core systems in dark silicon", IEEE Transactions on Computer-Aided Design of Integrated Circuits and
Systems (TCAD), 2022. (early access, CCF A rank)
- H. Wang, W. Li*, W. Qi*, D. Tang*, L. Huang, and H. Tang, "Runtime performance optimization of 3-D
microprocessors in dark silicon", IEEE Transactions on
Computers (TC), vol. 70, no. 10, pp. 1539-1554, October 2021. (CCF A
rank)
- H. Wang, L. Hu*, X. Guo*, Y. Nie, and H. Tang,
"Compact piecewise linear model based
temperature control of multi-core systems
considering leakage power", IEEE Transactions on Industrial Informatics (TII), vol. 16, no. 12,
pp. 7556-7565, December 2020. (JCR Q1, IF 10.2)
- H. Wang, X. Guo*, S. Tan, C. Zhang, H. Tang, and Y. Yuan,
"Leakage-aware predictive thermal management for multi-core systems
using echo state network", IEEE Transactions on Computer-Aided Design
of Integrated Circuits and Systems (TCAD), vol. 39, no. 7,
pp. 1400-1413, July 2020. (CCF A rank)
- H. Wang, T. Xiao*, D. Huang*, L. Zhang*, C. Zhang, H. Tang, and Y. Yuan,
"Runtime stress estimation for three-dimensional IC reliability management using
artificial neural network", ACM Transactions on
Design Automation of Electronic Systems (TODAES), vol. 24, no. 6,
pp. 69:1-69:29, November 2019. (CCF B rank)
- H. Wang, D. Huang*, R. Liu, C. Zhang, H. Tang, and Y. Yuan,
"STREAM: Stress and thermal aware
reliability management for 3-D ICs",
IEEE Transactions on Computer-Aided Design of Integrated Circuits and
Systems (TCAD), vol. 38, no. 11, pp. 2058-2071, November 2019. (CCF A rank)
- H. Wang, D. Tang*, M. Zhang*, S. Tan, C. Zhang, H. Tang, and
Y. Yuan, "GDP: A greedy based dynamic power budgeting method for
multi/many-core systems in dark silicon", IEEE Transactions on
Computers (TC), vol. 68, no. 4, pp. 526-541, April 2019. (CCF A rank)
- X. Guo*, H. Wang (corresponding author), C. Zhang, H. Tang,
and Y Yuan, "Leakage-aware thermal management for multi-core systems
using piecewise linear model based predictive control", Asia and South
Pacific Design Automation Conference (ASP-DAC), January 2019, Tokyo,
Japan. (Best Paper Award nomination) (CCF C rank)
- H. Wang, J. Wan*, S. Tan, C. Zhang, H. Tang, K. Huang,
and Z. Zhang, "A fast leakage-aware full-chip transient thermal estimation
method", IEEE Transactions on Computers (TC), vol. 67, no.5,
pp. 617-630, May 2018. (CCF A rank)
- H. Wang, J. Ma*, S. Tan, C. Zhang, H. Tang, K. Huang,
and Z. Zhang, "Hierarchical dynamic thermal management method for
high-performance many-core microprocessors", ACM Transactions on
Design Automation of Electronic Systems (TODAES), vol. 22, no.1,
pp.1:1-1:21, July 2016. (CCF B rank)
- L. Zhang*, H. Wang (corresponding author), and S. Tan, "Fast stress analysis for
runtime reliability enhancement of 3D IC using artificial neural
network", Proc. International Symposium on Quality Electronic Design
(ISQED), San Jose, CA, March 2016.
- H. Wang, M. Zhang*, S. Tan, C. Zhang, Y. Yuan, K. Huang,
and Z. Zhang, "New power budgeting and thermal management scheme for
multi-core systems in dark silicon", Proc. IEEE Internation
System-on-Chip Conference (SOCC), Seattle, WA, September 2016.
- W. Liu*, H. Wang, H. Zhao, S. Wang, H. Chen, Y. Fu, J. Ma*,
X. Li, and S. Tan, "Thermal modeling for energy-efficient smart building
with advanced overfitting technique", Asia and South Pacific Design
Automation Conference (ASP-DAC), Macao,
China, January 2016. (invited) (CCF C rank)
Open Source Software
1. Greedy Dynamic Power (GDP)
Greedy dynamic power (GDP) is a dynamic power budgeting method which
provides a high power budget for the multi/many-core systems. It
contains an optimized active core mapping strategy as well as a
transient temperature-aware power budget computing methodology. Both
the unintegrated GDP code and an implementation of GDP integrated into
the HotSniper simulator are provided:
-
The unintegrated GDP code. You can
integrate it into a performance-thermal simulator or into your
own performance-thermal simulation flow.
-
A
ready-to-run implementation of integrating GDP into the HotSniper
simulator. By running this program, one can readily analyze the performance/power/thermal behavior of a multi/many-core system running multi-threaded benchmarks like the PARSEC benchmark, with optimized active core distributions and power budgets provided by GDP dynamically at runtime.
-
Related publication: H. Wang, D. Tang, M. Zhang, S. Tan, C. Zhang, H. Tang, and
Y. Yuan, "GDP: A greedy based dynamic power budgeting method for
multi/many-core systems in dark silicon", IEEE Transactions on
Computers (TC), vol. 68, no. 4, pp. 526-541, April 2019.
Selected Projects
- Power budgeting and runtime performance optimization of
multi-core systems in dark silicon, funded by National Natural
Science Fundation of China (NSFC), 2020-2023.
- Fast analysis and runtime optimization for thermal induced
reliability of 3D ICs, funded by National Natural
Science Fundation of China (NSFC), 2015-2017.
pennergame besucherzähler
Last modified: Wed Oct 5 18:03:36 CST 2022