Session

· Contributors · Organizations · Search Program · Flagged · Happening Now

Research Manuscript

: Storage Meets Computing Power for Advancing AI and Data Processing Efficiency

Session Chairs

DescriptionCompute-in-Memory (CIM) is emerging as a transformative approach for efficient AI acceleration, addressing challenges in data movement, energy efficiency, and computational bottlenecks. As deep learning evolves with diverse network topologies like GNNs and point-cloud models, CIM architectures and frameworks are being optimized for a wide range of use cases, from edge devices to data centers. This session explores novel CIM-based accelerators for tasks such as kNN search, graph neural networks, and point cloud neural networks, alongside hybrid CIM solutions for edge AI. It also covers optimization techniques for neural network models and presents a systematic framework for implementing and evaluating CIM platforms.

Event Type

Research Manuscript

TimeTuesday, June 243:30pm - 5:30pm PDT

Location3001, Level 3

Topics

Tracks

Similar Sessions

Breaking Barriers: Compute-in-Memory for Transformer Acceleration

Spike It, See It, Say It: Next-Gen AI Processing

Unleashing the Power of Accelerators: ASICs, FPGAs, and PIMs

Presentations

3:30pm - 3:45pm PDT	PICK: An SRAM-based Processing-in-Memory Accelerator for K-Nearest-Neighbor Search in Point Clouds* Authors Chen Nie Chao Jiang Limin Xiao Weifeng Zhang Zhezhi He	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems
3:45pm - 4:00pm PDT	HH-PIM: Dynamic Optimization of Power and Performance with Heterogeneous-Hybrid PIM for Edge AI Devices Authors Sangmin Jeon Kangju Lee Kyeongwon Lee Woojoo Lee	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems
4:00pm - 4:15pm PDT	Anchor First, Accelerate Next: Revolutionizing GNNs with PIM by Harnessing Stationary Data Authors Jiaxian Chen Yuxuan Qi Yongbiao Zhu Jianan Yuan Kaoyi Sun Tianyu Wang Chenlin Ma Yi Wang	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems
4:15pm - 4:30pm PDT	3D-SubG: A 3D Stacked Hybrid Processing Near/In-Memory Accelerator for Subgraph GNNs Authors Guoxiang Li Runnan Xu Ruohang Xu Yikan Qiu Renati Tuerhong Muhan Zhang Le Ye Yufei Ma	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems
4:30pm - 4:45pm PDT	PIMDup: An Optimized Deduplication Design on a Real Processing-in-Memory System Authors Chun-Le Yeh Liang-Chi Chen Chien-Chung Ho Yu-Ming Chang Da-Wei Chang	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems
4:45pm - 5:00pm PDT	An Efficient Compute-in-Memory based Accelerator for Point-based Point Cloud Neural Networks Authors Xipeng Lin Cong Wang Shanshi Huang Hongwu Jiang	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems
5:00pm - 5:15pm PDT	NDFT: Accelerating Density Functional Theory Calculations via Hardware/Software Co-Design on Near-Data Computing System Authors Buxin Tu Qingcai Jiang Xiaoyu Hao Junshi Chen Hong An	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems
5:15pm - 5:30pm PDT	CIMFlow: An Integrated Framework for Systematic Design and Evaluation of Digital CIM Architectures Authors Yingjie Qi Jianlei Yang Yiou Wang Yikun Wang Dayu Wang Ling Tang Cenlin Duan Xiaolin He Weisheng Zhao	DES2B: In-memory and Near-memory Computing Architectures, Applications and Systems

62dac.conference-program.com