Setareh Behroozi

Position title: Ph.D. Candidate

Email: sbehroozi@wisc.edu

Phone: (618) 305-9132

Address:
3605 Engineering Hall

[ cv ] [ google scholar ]

Biography

I was born and raised in Tehran, Iran. I received my BS degree in Computer Engineering from Iran University of Science and Technology, Tehran, Iran. I hold a master’s degree from the Sharif University of Technology in Computer Engineering. Currently, I am a Ph.D. candidate under the supervision of Prof. Kim in the Department of Electrical and Computer Engineering at the University of Wisconsin–Madison.

Education

Ph.D. in Computer Engineering
2017-present
University of Wisconsin–Madison.

Master of Science in Computer Engineering – Computer Architecture
2013-2015
Sharif University of Technology, Tehran, Iran.

Bachelor of Science in Computer Engineering
2009-2013
Iran University of Science and Technology, Tehran, Iran.

Research Interests

My research interest includes energy-quality scalable systems, approximate computing, low power software, and hardware for embedded devices, Internet-of-Things, and computer architecture.

Awards and Honors

  • Foxconn “Smart Cities-Smart Futures” Competition Final Winner for “ReadyVue” proposal, 2020
  • Foxconn “Smart Cities-Smart Futures” Competition Final Winner for “SmartID” proposal, 2019
  • Foxconn “Smart Cities-Smart Futures” Competition Final Winner for “Nightshift” proposal, 2019
  • CRA-W Grad Cohort for Women Workshop Student Scholarship, 2019
  • Electrical and Computer Engineering Chancellor’s Opportunity Fellowship (COF), 2018
  • ISLPED Low-Power Design Contest Award, International Symposium on Low Power Electronics and Design, 2018
    for “AxSerBus: A Quality-Configurable Approximate Serial Bus for Energy-Efficient Sensing”
  • Grace Hopper Celebration (GHC) Student Scholarship, 2018
  • A. Richard Newton Young Student Fellowship,  2017
  • SIGDA University Demo Finalist, Design Automation Conference (DAC), 2017
    for “AxSerBus: Approximate Serial Bus for Energy-Efficient Sensing”
  • IEEE ISCAS 2017 Student Travel Grant,  2017
  • Master’s Degree Admission Examination, Ranked 23 in the field of Computer Engineering among
    32276 participants, 2013
  • Iran Game Development Cup (Iran GDC), Second place, Kashan, Iran, 2012
  • Best Game Design Award, Iran Game Development Cup (Iran GDC), Kashan, Iran, 2012
  • Virtual Robot Competition, Third place, Iran Open Robotic Competition, Tehran, Iran, 2010

Publications

UNO: Virtualizing and Unifying NonlinearOperations for Emerging Neural Networks
Di Wu, Jingjie Li, Setareh Behroozi, Younghyun Kim, Joshua San Miguel
ISLPED (International Symposium on Low Power Electronics and Design), Virtual, 2021.

Scheduling of Iterative Computing Hardware Units for Accuracy and Energy Efficiency
Setareh Behroozi, Yao Yao, Hoeseok Yang, and Younghyun Kim
IEEE ISCAS (IEEE International Symposium on Circuits and Systems), Daegu, Korea, 2021.

Approximate Hardware Techniques for Energy-Quality Scaling Across the System
Younghyun Kim, Joshua San Miguel, Setareh Behroozi, Tianen Chen, Kyuin Lee, Yongwoo Lee, Jingjie Li, and Di Wu
ICEIC, (International Conference on Electronics, Information, and Communication), 2020

SAADI-EC: A Quality-Configurable Approximate Divider for Energy Efficiency
Jackson Melchert, Setareh Behroozi, Jingjie Li, Younghyun Kim
TVLSI, (IEEE Transactions on VLSI Systems), 2019

SAADI: A Scalable Accuracy Approximate Divider for Dynamic Energy-Quality Scaling
Setareh Behroozi, Jingjie Li, Jackson Melchert, Younghyun Kim
ASP-DAC, (Asia South Pacific Design Automation Conference), 2019.

A Quality-Configurable Approximate Serial Bus for Energy-Efficient Sensory Data Transfer
Setareh Behroozi, Vijay Raghunathan, Anand Raghunathan, Younghyun Kim
IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2018.

AxSerBus: A Quality-Configurable Approximate Serial Bus for Energy-Efficient Sensing
Younghyun Kim, Setareh Behroozi, Vijay Raghunathan, Anand Raghunathan
ISLPED (International Symposium on Low Power Electronics and Design), Taipei, Taiwan, 2017.

Application Resource Management for Exploitation of NVM in Distributed Shared Memory Systems
Setareh Behroozi, Iraklis Anagnostopoulos
IEEE ISCAS (IEEE International Symposium on Circuits and Systems), Baltimore, MD, 2017.

Presentations

Featured projects:

Scheduling of Energy-Quality Scalable Hardware

Iterative computing, where the output accuracy gradually improves over multiple iterations, enables dynamic reconfiguration of energy-quality trade-offs by adjusting the latency (i.e., number of iterations). In order to take full advantage of the dynamic reconfigurability of iterative computing hardware, an efficient method for determining the optimal latency is crucial. In this paper, we introduce an integer linear programming (ILP)- based scheduling method to determine the optimal latency of iterative computing hardware. We consider the input-dependence of output accuracy of approximate hardware using data-driven error modeling for accurate quality estimation. The proposed method finds optimal or near-optimal latency with a significant speedup compared to exhaustive search and decision tree-based optimization.

Paper: ISCAS-2021

AxSerBus: Approximate Serial Bus 

Mobile, wearable, and implantable devices integrate an increasing number and variety of sensors such as microphones, image sensors, and accelerometers. These devices spend substantial amounts of time reading the sensors within them, thereby incurring significant energy dissipation over off-chip serial interconnects. The high capacitance of off-chip buses, high data rate, and high utilization of the sensor-to-processor communication bus results in significant energy dissipation for sensory data transfer. In this project, we propose AxSerBus, a quality-configurable approximate serial bus that exploits the locality of sensory data and the error resiliency of sensing applications to reduce energy dissipation of off-chip buses.

Papers: ISLPED-2017, JETCAS-2018
Demo: ISPLED Design Contest-2018
Video

SAADI: Approximate Divider 

Division is an arithmetic operation crucial in signal processing. A hardware divider is a costly module in terms of latency and energy consumption due to the high complexity of division algorithms. In this project, we propose SAADI (Scalable Accuracy Approximate Divider) an approximate divider design that facilitates dynamic energy-quality scaling. It finds the approximate reciprocal of the divisor, which is multiplied by the dividend to obtain the division result. The iterative reciprocal approximation process, where the accuracy gradually increases as more number of iterations are performed, enables the accuracy-energy trade-off.

Papers: ASP-DAC-2019, TVLSI-2019
Presentation slides

Lifetime improvement of NVM memory

Current trends in many-core system design show an increasing desire to integrate several cores and accelerators on a single chip in order to support better parallel applications. Moreover, the increasing number of parallel applications and tasks result in heavy memory utilization. Non-Volatile Memories (NVMs) prevail as a replacement of DRAM due to low leakage power and higher density. However, NVMs support limited number of write operations and consequently suffer from short lifetime issues. In this project, we propose an application mapping framework for parallel applications exploiting and improving the lifetime of NVMs in distributed shared memory systems.

Paper: ISCAS-2017 

Experiences:

  • Doctoral Research Assistant, WISEST Lab, University of Wisconsin-Madison (January 2017 – present).
  • Instructor
    • ECE 352-Digital System Fundamentals, Fall 2021, University of Wisconsin–Madison, WI.
    • ENG 222-Computational Methods for Engineers and Technologists, Fall 2016, Southern Illinois University, Carbondale, IL.
    • ECE 222-Intro to Digital Computation, Spring 2016, Southern Illinois University, Carbondale, IL
    • CE 40401-Industrial Automation Laboratory, Fall 2014, Sharif University of Technology, Tehran, Iran
  • Teaching Assistant
    • CS 537-Introduction to Operating Systems, Spring 2020, University of Wisconsin–Madison, WI.
    • CS 537-Introduction to Operating Systems, Spring 2019, University of Wisconsin–Madison, WI.
    • CE 551-Digital System Design and Synthesis, Spring 2018, University of Wisconsin–Madison, Madison, WI.
    • CE 409123-Computer Fundamentals and Programming, Fall 2010, Iran University of Science and Technology, Tehran, Iran
  • Doctoral Research Assistant, Embedded System Software Group, Southern Illinois University, Carbondale, IL (August 2015 – Dec 2016).
  • Graduate Research Assistant, High-Performance Computing Architecture and Networks (HPCAN) Laboratory, Computer Engineering Department, Sharif University of Technology, Tehran, Iran (2013- 2015).
  • Undergraduate Research Assistant, High-Performance Computing Laboratory, Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran (2011- 2014).
  • Texture and Material Designer, Game Development Laboratory, Computer Engineering Department, Iran University of Science and Technology, Tehran, Iran (2010- 2013).
  • Tutor and Educational Consultant, Ghalamchi Institute, Tehran, Iran (2010).

Services

  • External reviewer:
    • Transaction on Computers, 2020
    • ESL (Embedded System Letters), 2020
    • DAC (Design Automation Conference), 2018, 2019, 2020
    • ISLPED (International Symposium on Low Power Electronics and Design), 2017, 2018, 2019
    • ASP-DAC (Asia and South Pacific Design Automation Conference), 2018, 2019
    • VLSID (International Conference on VLSI Design), 2019
    • TCAS II (IEEE Transactions on Circuits and Systems II), 2019
    • SAC (Symposium on Applied Computing), 2018
  • Electrical and computer engineering department representative in the College of Engineering, Aug 2017 – May 2019
  • Graduate Student Association (GSA) member, Aug 2017 – Aug 2019