Final Program


Day 1: July 26th

10:00 am – 10:05 am (ET)

Welcome by General and Program Co-Chairs

10:05 am – 10:50 am (ET)

Keynote Talk 1

10:50 am – 11:30 am (ET)

Session 1A: Low-Power Neural Networks

11:30 am – 12:10 pm (ET)

Session 1B: Optimizations for Edge, IoT and Wearables devices

12:10 pm – 12:40 pm (ET)

Session 1C: Low Power challenges in Emerging Technologies: 3D and Optical

12:40 pm – 01:15 pm (ET)

Design contest

 

 

 

10:05 am – 10:50 am (ET): Keynote Talk 1

Matthew Mattina, ARM Research

Co-Designing Hardware and Models for Efficient Neural Network Inference




Session 1A: Low-Power Neural Networks

Chair: Ganapati Bhat, Washington State University


10:50 am – 11:00 am (ET)


HTNN: Deep Learning in Heterogeneous Transform Domains with Sparse-Orthogonal Weights
Yu Chen, Bowen Liu, Pierre Abillama and Hun Seok Kim

11:00 am – 11:10 am (ET)

Co-optimizing accuracy, latency and energy of SNNs for neuromorphic vision sensors
Sonali Singh, Anup Sarma, Sen Lu, Abhronil Sengupta, Vijaykrishnan Narayanan and Chita Das

11:10 am – 11:20 am (ET)

DIAN: Differentiable Accelerator-Network Co-Search Towards Maximal DNN Efficiency
Yongan Zhang, Yonggan Fu, Weiwen Jiang, Chaojian Li, Haoran You, Meng Li, Vikas Chandra and Yingyan Lin

11:20 am – 11:30 am (ET)

UNO: Virtualizing and Unifying Nonlinear Operations for Emerging Neural Networks Authors
Di Wu, Jingjie Li, Setareh Behroozi, Younghyun Kim and Joshua San Miguel

 

 

 


Session 1B: Optimizations for Edge, IoT and Wearables devices

Chair: Yingyan Lin, Rice University


11:30 am – 11:40 am (ET)


DOSAGE: Generating Domain-Specific Accelerators for Resource-Constrained Computing
Ankur Limaye and Tosiron Adegbija

11:40 am – 11:50 am (ET)

Online Solar Energy Prediction for Energy-Harvesting Internet of Things Devices
Nuzhat Yamin and Ganapati Bhat

11:50 am – 12:00 pm (ET)

EExNAS: Early-Exit Neural Architecture Search Solutions for Low-Power Wearable Devices
Mohanad Odema, Nafiul Rashid and Mohammad Al Faruque

12:00 pm – 12:10 pm (ET)

An Instruction-Level Power and Energy Model for the Rocket Chip Generator
Zhiping Wang and William Davis



Session 1C: Low Power challenges in Emerging Technologies: 3D and Optical

Chair: Hai Li (Duke University)


12:10 pm – 12:20 pm (ET)


Power, Performance, Area and Cost Analysis of Memory-on-Logic Face-to-Face Bonded 3D Processor Designs (Best Paper Candidate)
Anthony Agnesina, Moritz Brunion, Jinwoo Kim, Alberto Garcia-Ortiz, Dragomir Milojevic, Francky Catthoor, Manu Perumkunnil and Sung Kyu Lim

12:20 pm – 12:30 pm (ET)

Power Delivery and Thermal-Aware Arm-Based Multi-Tier 3D Architecture
Lingjun Zhu, Saurabh Sinha, Tuan Ta, Rossana Liu, Rahul Mathur, Xiaoqing Xu, Shidhartha Das, Ankit Kaul, Alejandro Rico, Doug Joseph, Brian Cline and Sung Kyu Lim

12:30 pm – 12:40 pm (ET)

Pho$: A Case for Shared Optical Cache Hierarchies (Best Paper Candidate)
Haiyang Han, Theoni Alexoudi, Chris Vagionas, Nikos Pleros and Nikos Hardavellas



12:40 pm – 01:15 pm (ET) : Design Contest
Chair: Kapil Dev, Nvidia
Co-Chair: Marco Donato, Tufts University


1


Experimental Demonstration of STT-MRAM based Nonvolatile Instantly On/Off Systems for Low Power IoT Applications

Yueting Li, Wang Kang, Kunyu Zhou, Keni Qiu, Geifei Wang, Weisheng Zhao


2


A Low-Power Neural Network Training Processor with 8-bit Floating Point with a Shared Exponent Bias and Fused-Multiply Add Trees (Best Design Contest Award!)

Jeongwoo Park, Sunwoo Lee, Dongsuk Jeon


3


WiChronos: Energy-Efficient Modulation for Long-Range,Large-Scale Wireless Networks

Yaman Sangar, Bhuvana Krishnaswamy


4


Low-Power Convolutional Neural Network Accelerator on Embedded FPGA: A Hardware-Software Co-Design Approach

Yunqian Fan, Jinyu Bai, Jinghan Xu, Chenguang Liu, Haoyi Zhang, Wang Kang

Day 2: July 27th

10:00 am – 10:45 am (ET)

Keynote Talk 2

10:45 am – 11:15 am (ET)

Session 2A: Optimizations for SRAMs and SSDs

11:15 am – 12:00 pm (ET)

ISLPED 25th anniversary panel

12:00 pm – 12:30 pm (ET)

Poster session

12:30 pm – 1:00 pm (ET)

Session 2B: Energy-Efficient Emerging Memory Technologies

 

 

 

10:00 am – 10:45 am (ET): Keynote talk 2

Diana Marculescu, Univ. of Texas, Austin


When Climate Meets Machine Learning: Edge to Cloud ML Energy Efficiency




Session 2A: Optimizations for SRAMs and SSDs

Chair: Dr. Wei Wu, Intel Corporation


10:45 am – 10:55 am (ET)


SpartanSSD: a Reliable SSD under Capacitance Constraints
Hyungyu Lee, Juwon Lee, Minwook Kim, Donghwa Shin, Sungjin Lee, Bryan Kim, Eunji Lee and Sang Min

10:55 am – 11:05 am (ET)

RVO: Unleashing SSD’s Parallelism by Harnessing the Unused Power (Best Paper Candidate)
Hasan Alhasan, Yun-Chih Chen and Chien-Chung Ho

11:05 am – 11:15 am (ET)

SRAM Gauge: SRAM Health Monitoring via Cells Race
Nezam Rohbani and Masoumeh Ebrahimi

 


11:15 am – 12:00 pm (ET): ISLPED 25th Anniversary Panel

Moderator: Massoud Pedram

Panelists: Vivek De, Diana Marculescu, Renu Mehra, Luca Benini, Jan Rabaey, Kaushik Roy

 



12:00 pm – 12:45 pm (ET): Poster Session

Session Chair: Helen Li, Duke University and Charles Augustine, Intel Corporation


1


Efficacy of Pruning in Ultra-Low Precision DNNs

Sanchari Sen, Swagath Venkataramani and Anand Raghunathan


2


ACME: An Energy-Efficient Approximate Bus Encoding for I2C

Chen Xie, Daniele Jahier Pagliari, Andrea Calimera, Enrico Macii and Massimo Poncino


3


55nm CMOS Analog Circuit Implementation of LIF and STDP Functions for Low-Power SNNs

Zhitao Yang, Jianghan Zhu, Yucong Huang and Terry Ye


4


How Much Energy Can We Harvest Daily for Wearable Applications?

Yigit Tuncel, Toygun Basaklar and Umit Ogras


5


Application-driven Design Exploration for Dense Ferroelectric Embedded Non-volatile Memories

Mohammad Mehdi Sharifi, Lillian Pentecost, Ramin Rajaei, Arman Kazemi, Qiuwen Lou, Gu-Yeon Wei, David Brooks, Kai Ni, X. Sharon Hu, Michael Niemier and Marco Donato


6


Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks

Abhinav Goel, Caleb Tung, Xiao Hu, Haobo Wang, James Davis, George Thiruvathukal and Yung-Hsiang Lu


7


TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
Alessio Burrello, Alberto Dequino, Daniele Jahier Pagliari, Francesco Conti, Marcello Zanghieri, Enrico Macii, Luca Benini and Massimo Poncino


8


PUFFIN: An Efficient DNN Training Accelerator for Direct Feedback Alignment in FeFET

Fan Chen


9


A Flash-Based Multi-Bit Content-Addressable Memory with Euclidean-Squared Distance

Arman Kazemi, Shubham Sahay, Ayush Saxena, Mohammad Mehdi Sharifi, Michael Niemier and X. Sharon Hu


10


CoPIM: A Concurrency-aware PIM Workload Offloading Architecture for Graph Applications

Liang Yan, Mingzhe Zhang, Rujia Wang, Xiaoming Chen, Xingqi Zou, Xiaoyang Lu, yinhe han and Xianhe Sun

Session 2B: Energy-Efficient Emerging Memory Technologies

Chair: Abhronil Sengupta, Pennsylvania State University


12:45 pm – 12:55 pm (ET)


MC2-RAM: An In-8T-SRAM Computing Macro Featuring Multi-Bit Charge-Domain Computing and ADC-Reduction Weight Encoding
Zhiyu Chen, Qing Jin, Jingyu Wang, Yanzhi Wang and Kaiyuan Yang

12:55 pm – 01:05 pm (ET)

Enabling Robust SOT-MTJ Crossbars for Machine Learning using Sparsity-Aware Device-Circuit Co-design
Tanvi Sharma, Cheng Wang, Amogh Agrawal and Kaushik Roy

01:05 pm – 01:15 pm (ET)

Space-efficient Graph Data Placement to Save Energy of ReRAM Crossbar
Ting-Hsuan Lo, Chun-Feng Wu, Yuan-Hao Chang, Tei-Wei Kuo and Wei-Chen Wang


Day 3: July 28th

10:00 am (ET)

Best Paper Announcement

10:00 am – 11:00 am (ET)

Session 3A: Low-Power Health-Based implantable and Wearable Devices

11:00 am – 11:30 am (ET)

Session 3B: Low-Power Circuit Optimizations

11:30 am – 12:15 pm (ET)

Embedded Tutorial: UPM/IEEE 2416 Power Modeling Standard: A Practitioner’s Perspective

12:10 pm – 12:45 pm (ET)

Session 3C: Efficient In-Memory Computing

 

Session 3A: (Invited) Low-Power Health-Based implantable and Wearable Devices
Chair: Sherief Reda

10:00 am – 10:20 am (ET)

Wearable Devices and Low-Power Design for Smart Health Applications: Challenges and Opportunities
Toygun Basaklar, Yigit Tuncel, Sizhe An, Umit Y. Ogras

10:20 am – 10:40 am (ET)

Power-aware Heart Rate Monitoring using Particle Filters
Ali Akbari, Roozbeh Jafari

10:40 am – 11:00 am (ET)

Wireless Power Transfer and Data Communication for Low-Power Micro Electronic Devices Deeply Implanted within the Human Body
Mingui Sun, Qi Xu, Tianfeng Wang, Shitong Mao, Gusphyl A. Justin, Wenyan Jia and Zhi-Hong Mao

 

Session 3B: Low-Power Circuit optimizations
Chair: Mohsen Imani


11:00 am – 11:10 am (ET)


Active Cell Balancing for Life Cycle Extension of Lithium-Ion Batteries under Thermal Gradient
Philipp Kremer, Francesco Cigarini, Dietmar Göhlich and Sangyoung Park

11:10 am – 11:20 am (ET)

A High-Performance Low-Power Barrett Modular Multiplier for Cryptosystems
Bo Zhang, Zeming Cheng and Massoud Pedram

 

11:20 am – 11:30 am (ET)

BEACON BEst Approximations for Complete BehaviOral HeterogeNeous SoCs
Prattay Chowdhury and Benjamin Carrion Schaefer

 

11:30 am – 12:15 pm (ET): Embedded Tutorial

UPM/IEEE 2416 Power Modeling Standard: A Practitioner’s Perspective

Nagu Dhanwada (IBM), Rhett Davis (North Carolina State University), Nagu Dhanwada (IBM Corporation), Jerry Frenkil (Si2)



Session 3C: Efficient In-Memory Computing

Chair: Benjamin Carrion Schaefer


12:15 pm – 12:25 pm (ET)


Statistical Optimization of Compute In-Memory Performance Under Device Variation (Best Paper Award!)
Brian Crafton, Samuel Spetalnick, Jong-Hyeok Yoon and Arijit Raychowdhury

12:25 pm – 12:35 pm (ET)

MIMHD: Accurate and Efficient Hyperdimensional Inference using Multi-Bit In-Memory Computing
Arman Kazemi, Mohammad Mehdi Sharifi, Zhuowen Zou, Michael Niemier, X. Sharon Hu and Mohsen Imani

 

12:35 pm – 12:45 pm (ET)

FPRA: A Fine-grained Parallel RRAM
Xiao Liu, Minxuan Zhou, Rachata Ausavarungnirun, Sean Eilert, Ameen Akel, Tajana Rosing, Vijaykrishnan Narayanan and Jishen Zhao