ISLPED 2025 Schedule


1	ISLPED 2025 Detailed Program
2	From	To
3	Wednesday August 6
4	7:30	8:00	Registration
5	8:00	8:30	Welcome	General Co-chairs and TPC Co-chairs
6	8:30	9:30	Keynote: Michaela Blott, AMD, "Enabling the AI Revolution"
7	9:30	9:50	Coffee Break
8	9:50	11:10	Session 1A: "Energy Efficient Computing and Storage"	Frank K. Gurkaynak	Session 1B: "Next-Gen EDA: Physical Design Optimization and AI-Driven Methodologies"	Francesco Regazzoni
9			Partial-Sum Quantization Based on Pseudo-Quantization Noise for Variation-Tolerant Analog In-Memory Computing BEST PAPER CANDIDATE	Nameun Kang, EunHyeok Park, Sangsu Park, Jongil Kim, Jaeyun Yi, Jae-Joon Kim	Simultaneous Optimization of Placement Legalization and Multi-bit Flip-flop Allocation in Physical Design Automation	Seoyoung Bang, Taewhan Kim
10			An Analog Multiplier Utilizing an Unconventional Bit-Weighting Scheme with Application to Neural Network Quantization	Mehdi Kamal, Massoud Pedram	Development of a Physics-Informed Neural Network Model for Rapid Power Integrity Analysis in Die-Level and Die-Package Co-Design for 2.5-D Chiplet Solutions	Xi Chen, Yuhao Ju, Jie Gu
11			LoRASensE: Learnable Low-Rank Acquisition in Sensors for Efficient Edge Machine Vision	Yiwen Liang, Zhiqiang Yi, Tianrui Ma, Weidong Cao	GenSoC: A Multi-Agent-Assisted SoC Generation Methodology Leveraging Open-Source Hardware BEST PAPER CANDIDATE	Peiran Yan, Qinzhe Zhi, Lifeng Liu, Tianyu Jia
12			AdaGray: An Energy-Efficient Adaptive Gray-Code Strategy for QLC Flash-Memory Storage Systems	Han-Yu Liao, Jen-Wei Hsieh, Yi-Shen Chen, Chang-Lin Tsai, Yuan-Hao Chang	Timing-Driven Macro Placement with Connectivity-Aware Clustering	Gangmin Jeon, Heechun Park
13	11:10	12:40	Special Session 1: "Cold War: Don't Close Your Eyes on Temperature"	Mircea Stan	Special Session 2: "Neuromorphic Edge Computing: Challenges, Opportunities, and Current Solutions"	Federico Corradi, Farhad Merchant
14			Power Map Characterization and Modeling for Commercial CPU/GPUs Considering Temperature Dependence	Jincong Lu, Sachin Sachdeva, Haotian Lu, Sheldon X.-D. Tan	Dynamic Neuromorphic Processing for Energy-Efficient Cognitive Sensing	Amir Zjajo
15			Thermal Aware Design Methodologies for System On Chip Application Processor	Youngsang Cho, Jun So Pak, Seungwook Yoon, Ilryong Kim	Harnessing Sparsity for Low-Power Event-Driven Computing at the Edge	Orlando Moreira
16			Thermal Challenges and Opportunities for Off-the-shelf 3D-stacked CPUs	Jae Yoon Lee, Chae Young Sim, Seung Hun Choi, Sung Woo Chung	Reliable and Low-Power Neuromorphic Computing	Miloš Krstić
17			Transistor-to-GDS Reliability Analysis in Sub-3nm: Impact of Self-Heating and Aging on Timing	Swati Deshwal, Hadi Nour Eddine, Mahdi Benkhelifa, Albi Mema, Yogesh S. Chauhan, Hussam Amrouch	Low-Power Neuromorphic Systems: Mixed-Signal Design and Computing-in-Memory for Edge AI	Farhad Merchant, Federico Corradi
18	12:40	14:10	Lunch
19	14:10	15:30	Session 2A: "Brains on a Budget – Smart, Small, and Power-Efficient"	Hussam Amrouch	Session 2B: "Next-Gen Edge AI: Flash Memory, RISC-V, and Hybrid Architectures"	Thierry Tambe
20			Exploration of Low-Power Flexible Stress Monitoring Classifiers for Conformal Wearables	Florentia Afentaki, Sri Sai Rakesh Nakkilla, Konstantinos Balaskas, Paula Carolina Lozano Duarte, Shiyi Jiang, Georgios Zervakis, Farshad Firouzi, Krishnendu Chakrabarty, Mehdi Tahoori	E-Flash: Energy-Efficient DNN Mapping on NAND Flash Memory with State-Switching Algorithm BEST PAPER CANDIDATE	Gisan Ji, Sanghun Shin, Jangho Baik, Wonbo Shim, Sungju Ryu
21			ASAP-FE: Energy-Efficient Feature Extraction Enabling Multi-Channel Keyword Spotting on Edge Processors	Jongin Choi, Jina Park, Jae-Jin Lee, Massoud Pedram and Woojoo Lee	Hybrid Systolic Array Accelerator with Optimized Dataflow for Edge Large Language Model Inference	Chun-Ting Chen, HanGyeol Mun, Jian Meng, Mohamed Abdelfattah and Jae-sun Seo
22			Minimizing Redundant Checkpoint Triggers for Efficient Intermittent Systems BEST PAPER CANDIDATE	Youngbin Kim, Yoojin Lim	ID-VSA: Independent and Dynamic Vector Symbolic Architecture for Energy-Efficient Edge AI	Mehran Shoushtari Moghadam, Abu Kaisar Mohammad Masum, Sercan Aygun, M. Hassan Najafi
23			AridWalk: Efficient Graph Random Walks on a Resource-Limited Computational Storage Device	Liang-Chi Chen, Chien-Chung Ho, Tei-Wei Kuo, Yuan-Hao Chang	RIMIX: RISC-V Core with MIXed-Precision SIMD Instruction Extensions Supported by Oracle-Assisted Sub-Network Search for Efficient TinyML	Jiyong Park, Dahoon Park, Yeeun Hong, Jaeha Kung
24	15:30	16:00	Coffee Break
25	16:00	17:30	Panel 1: "Workforce Development in the Era of AI"	Organizers: Kahty Hoover, Priyadarshini Panda Panelists: Michaela Blott, Chaitali Chakrabarti, Suman Datta, Vivek De, Sree Menon, Kaushik Roy
26
27
28	Thursday August 7
29	7:30	8:00	Registration
30	8:00	9:00	Keynote: Kenichi Okada, Institute of Science Tokyo, "Synthesizable Analog Circuit Design Using Digital Standard Cell"
31	9:00	9:30	Coffee Break
32	9:30	10:50	Session 3A: "Accelerators for LLM and Edge AI Applications"	M. Hassan Najafi	Session 3B: "Twisting AI and Hardware in 3D"	Bokyung Kim
33			Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator BEST PAPER CANDIDATE	Akshat Ramachandran, Souvik Kundu, Arnab Raha, Shamik Kundu, Deepak K. Mathaikutty, Tushar Krishna	MIX-3D: AI-based Architecture-Circuit Co-design Methodology for Mixed-Node, Mixed-Area 3D ICs	Min Gyu Park, Doyun Kim, Sung Kyu Lim
34			A Scalable External Memory Access and On-Chip Storage Architecture for Edge-AI Accelerators – Multi-Path Rolling Data Refresh and Layer-Wise Bank Allocation –	Quan Cheng, Huizi Zhang, Qiufeng Li, Yuan Liang, Mingtao Zhang, Zhenzhe Chen, Ruilin Zhang, Jinjun Xiong, Mingqiang Huang, Longyang Lin, Masanori Hashimoto	GAVINA: flexible aggressive undervolting for bit-serial mixed-precision DNN acceleration	Jordi Fornt, Pau Fontova-Musté, Adrian Gras, Omar Lahyani, Martí Caro, Jaume Abella, Francesc Moll Echeto, Josep Altet
35			FLASH-D: FlashAttention with Hidden Softmax Division	Kosmas Alexandridis, Vasileios Titopoulos, Giorgos Dimitrakopoulos	An Open-Source HW-SW Co-Development Framework Enabling Efficient Multi-Accelerator Systems	Ryan Antonio, Joren Dumoulin, Xiaoling Yi, Josse Van Delm, Yunhao Deng, Guilherme Paim, Marian Verhelst
36			A Compact, Low Power Transprecision ALU for Smart Edge Devices	Ayushi Dube, Gian Singh, Sarma Vrudhula	MemRaptor: Magnetoresistive Array as Matrix Vector Multiplication and Transcendental Function Operator for NLP Applications	Dong Eun Kim, Tanvi Sharma, Anushka Mukherjee, Mainakh Mukherjee and Kaushik Roy
37	10:50	12:20	Tutorial 1: "The Energy Cost of Privacy and Security"	Francesco Regazzoni	Tutorial 2: "Autonomy with Neuromorphic System"	Saibal Mukhopadhyay
38			Introduction to Security Primitives and Privacy Preserving Technologies	Paolo Palmieri	Neuromorphic Circuits	Amit Trivedi
39			Energy Assessment of Security Primitives	Ayse Kivilcim Coskun	Neuromorphic and Hybrid Computing Models	Priya Panda
40			Energy Efficient Design and Implementation of Security Primitives	Francesco Regazzoni	Algorithms for Neuromorphic Sensing Systems	Saibal Mukhopadhyay
41					Neuromorphic Approach to End-to-end Navigation	Kaushik Roy
42	12:20	13:50	Lunch
43	13:50	15:50	Posters and Design Contest Demos with Coffee
44			Posters		Design Contest Demos
45			On-chip Integrated Voltage Regulators: Frontside, Backside, or Off-Chip?	Amaan Rahman, Seungmin Woo, Zheng Yang, Sung Kyu Lim	A Sub-10Hz Sub-nW 65nm CMOS Timer with Voltage-Stacking of an Oscillator and Frequency Dividers for Small-Formfactor Scaling-Friendly IoTs	You Wu, Kei Awano, Hiroaki Kitaike, Kiichi Niitsu
46			J3DAI: A tiny DNN-Based Edge AI Accelerator for 3D-Stacked CMOS Image Sensor	Benoit Tain, Raphael Millet, Romain Lemaire, Michal Szczepanski, Laurent Alacoque, Emmanuel Pluchart, Sylvain Choisnet, Rohit Prasad, Jerome Chossat, Pascal Pierunek, Pascal Vivet, Sebastien Thuries	ECO: Low Power Context-Aware Multimodal AI on NPUs	Arghadip Das, Yatharth Agarwal, Arnab Raha, Soumendu Ghosh, Vijay Raghunathan
47			MTA-Coded PAM-4 Receiver with Decision Feedback Power Saving Scheme and Partial DFE for Low-Power Memory Interfaces	Jusung Lee, Younghwan Chang, Jaekwang Yun, Sanghyuk Seo, Yong-Un Jeong, Suhwan Kim	Radar-PIM-Lite: Ultra-Low-Power PIM Processor for Real-Time UWB Radar Respiration Detection on UAVs	Kyeongwon Lee, Hyunseok Kwak, Kyeongpil Min, Chaebin Jung, Sangmin Jeon, Woojoo Lee, Jina Park, Massoud Pedram
48			A High-Performance Dataflow-Based ORB Extractor Accelerator for SLAM	Rui Xue, Wenming Li, Haibin Wu, Cheng Guo, Yi Li, Xiaochun Ye, Dongrui Fan	A Low-Power Real-Time Hardware Accelerator for Edge Detection Using Stochastic Computing	Priyajit Ghosh, Rajarshi Mukherjee, Auro Anand Saha, Sutirtha Naha, Arghadip Das, Arnab Raha, Mrinal K Naskar
49			Jack Unit: An Area- and Energy-Efficient Multiply-Accumulate (MAC) Unit Supporting Diverse Data Formats	Seock-Hwan Noh, Sungju Kim, Seohyun Kim, Daehoon Kim, Jaeha Kung, Yeseong Kim
50			Repurpose Accel-Sim for Next Generation NVIDIA Jetson GPU Architectural Design	Tianhao Huang, Lingyu Sun, Chao Li, Xiaofeng Hou, Yaqian Zhao, Jingwen Leng, Li Li, Minyi Guo
51			ML-Power: Machine Learning based Power Estimation for SoCs	Sujay Pandit, Sujit Dey, Anand Raghunathan
52			Diffusion-Enhanced Graph Transformer with Reinforcement Learning for Transferable Analog Circuit Optimizer	Ho-Jin Lee, Kyeong-Jun Lee, Jaehoon Lee, Kyu-Jin Choi, Geunyong Choi, Youngchang Choi, Kyongsu Lee, Seokhyeong Kang, Jae-Yoon Sim
53			SHIFT ECC: A Value Converting HBM ECC Approach for Refresh Energy Efficient Integer Quantized DNN Inference	Jae Yoon Lee, Young Seo Lee, Young-Ho Gong, Seon Wook Kim, Sung Woo Chung
54			Optimizing Heterogeneous Compute-in-Memory with Hybrid Dataflow and In-Network Reduction for Vision Transformer	Zexin Fu, Yihang Zuo, Yuzhe Ma, Jiayi Huang
55			Revisiting Reconfigurable Acceleration of Vision Transformer with Patch Pruning	Hanning Chen, Yang Ni, Wenjun Huang, Hyunwoo Oh, Tamoghno Das, Fei Wen, Mohsen Imani
56			TEE-SFL: Time and Energy-efficient solution for addressing communication heterogeneity in Split Federated Learning Schemes	Ziyi Zhao, Qifeng Chen, Jingtao Li, Deliang Fan, Chaitali Chakrabarti
57			MEbots: Integrating a RISC-V Virtual Platform with a Robotic Simulator for Energy-aware Design	Giovanni Pollo, Mohamed Amine Hamdi, Matteo Risso, Lorenzo Ruotolo, Pietro Furbatto, Matteo Isoldi, Yukai Chen, Alessio Burrello, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari, Sara Vinco
58			Enhancing Low-Precision Deep Learning: A Posit8 Framework for Energy Efficient DNN Training	Dongyang Wu, Mehdi Kamal, Massoud Pedram
59			Towards Zero-Stall Matrix Multiplication on Energy-Efficient RISC-V Clusters for Machine Learning Acceleration	Luca Colagrande, Lorenzo Leone, Maximilian Coco, Andrei Deaconeasa, Luca Benini
60			Efficient Precision-Scalable Hardware for Microscaling (MX) Processing in Robotics Learning	Stef Cuyckens, Xiaoling Yi, Nitish Satya Murthy, Chao Fang, Marian Verhelst
61			SITRA: Exploiting Temporal Silence in Spiking Transformers for Fast & Energy-efficient Inference	Abhiroop Bhattacharjee, Abhishek Moitra, Ruokai Yin, Priyadarshini Panda
62			DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation	Kunming Shao, Zhipeng Liao, Jiangnan Yu, Liang Zhao, Qiwei Li, Xijie Huang, Jingyu He, Fengshi Tian, Yi Zou, Xiaomeng WANG, Tim Cheng, Chi Ying Tsui
63			upGEMV: A Bandwidth-Efficient and Scalable GEMV Accelerator for PIM Systems	Fan Yang, Shunchen Shi, Peiheng Zhang, Xueqi Li
64			Can Photonic Interconnects be used for High-Throughput Memory Access in FHE Accelerators?	Dewan Saiham, Mariam Rabadi, Di Wu, Sazadur Rahman
65			Sustainably Secure: ChaCha20 Encryption Based on In-Memory Compute	Samridhi Jain, Mohd Aamir, Anuj Grover
66	15:50	17:20	Panel 2: "30 Years of ISLPED"	Organizer: Massoud Pedram
67	18:30	21:00	Banquet
68
69	Friday August 8
70	8:00	9:00	Keynote 3: Brucek Khailany, Nvidia, "From VLSI through Software: Optimizing the Computing Stack for Generative AI"
71	9:00	9:30	Coffee Break
72	9:30	10:50	Session 4A: "Precision, Performance, and Efficiency: Modern Strategies in ML systems"	Donghwa Shin	Session 4B: "Compute-in-Memory Macros"	Jaehyun Park
73			Faster Ternary and Binary Neural Network Inference on CPU by Reducing Popcount Overhead BEST PAPER CANDIDATE	Olivier Fischer, Shien Zhu, Gustavo Alonso	CAM-CIM: A Hybrid Compute-in-Memory Using Content-Addressable Memory with Subword Split Mapping for Reduced ADC Resolution	Sangwoo Jung, Hojin Lee, Yejin Lee, Jiyong Park, Dahoon Park, Hyunseob Shin, Jong-Hyeok Yoon, Jaeha Kung
74			ECLIP: Energy-efficient and Practical Co-Location of ML Inference on Spatially Partitioned GPUs	Ryan Quach, Yidi Wang, Ali Jahanshahi, Daniel Wong, Hyoseung Kim	A 20.98TOPS/W Energy-Efficient Binary BERT Model on Group Vector Systolic CIM Accelerator	Dingbang Liu, Ziyi Guan, Qilong Chen, Jingyun Gu, Jiaqi Yang, Kai Li, Wei Mao, Ngai Wong, Changwen Chen, Hao Yu
75			SmartMS: Efficient Hierarchical Database Search for Mass Spectrometry	Flavio Ponzina, Sumukh Pinge, Zheyu Li, Abhijay Deevi, Yilin Ge, Mingu Kang, Tajana Rosing	Cost-efficient Processing-in-Memory Architecture with Training-free and Universal Error Compensation BEST PAPER CANDIDATE	MyeongJi Yun, Jung Gyu Min, Sein Oh, Jiwoung Choi, Minkyu Je, Jang-Sik Lee, Youngjoo Lee
76			TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision	Jinhee Kim, Seoyeon Yoon, Taeho Lee, Joo Chan Lee, Kang Eun Jeon, Jong Hwan Ko	Design Techniques for Ultra-low Power Cryogenic CMOS for Quantum Computing Applications (Industry)	Sudipto Chakraborty, Pat Rosno, John Bulzacchelli, David Frank, Rajiv Joshi, Daniel Friedman
77	10:50	12:10	Session 5A: "Transceivers and Stochastic Logic Design"	Alexandre Levisse	Session 5B: "Emerging Technologies for Secure and Efficient Computing"	TBD
78			A Spectral-Efficient Low-Power NRZ/PAM-4 Dual-Mode Wireline Transmitter for Multidrop Interfaces	Donggeon Kim, Kiarash Gharibdoust, Armin Tajalli, Kyungtae Lee, Gain Kim	DPIMA: A DRAM-Based Processing-in-Memory Accelerator for Privacy-Preserving Machine Learning BEST PAPER CANDIDATE	Bokyung Kim
79			Energy-Efficient Single-Ended Capacitive PAM-4 Transceiver for Next-Generation HBM Interfaces	Jaeyoon Kim, Sangyoon Lee, Jaekwang Yun, Sanghyuk Seo, Kwangyeon Lee, Yong-Un Jeong, Suhwan Kim	QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities	Sai Kiran Narayanaswami, Gopalakrishnan Srinivasan, Ravindran Balaraman
80			Always-On Sensing in Energy-Harvested Systems via Stochastic Intermittent Computing	Sepehr Tabrizchi, Mehran Shoushtari Moghadam, Ali Shafiee Sarvestani, Sercan Aygun, M. Hassan Najafi, Arman Roohi	Meta-Heuristic Optimization of Karatsuba Multiplier Designed ECC Processor	Pruthvi Parate, Daksh Sharma, Alwin Shaju, Vasanthi D R, Madhav Rao
81			Design of a correlation-insensitive HFQ stochastic adder by local two-phase clocking	Yuki Matsumoto, Masamitsu Tanaka, Takatsugu Ono	Unicorn-CIM: Unconvering the Vulnerability and Improving the Resilience of High-Precision Compute-in-Memory	Qiufeng Li, Yiwen Liang, Weidong Cao
82	12:10	12:40	Closing Remark and Award Ceremony	General Co-chairs