Close

Session

Research Manuscript: STCO for Embedded Compute in Memory Devices and Circuits
DescriptionCompute in Memory (CIM) is a promising approach to mitigate the data movement energy and latency costs in modern data-intensive workload applications. This session brings in recent developments in emerging embedded memory devices, circuits, design methodologies, and their impact on the system-level power performance metrics for various workloads.
Event TypeResearch Manuscript
TimeTuesday, June 253:30pm - 5:30pm PDT
Location3003, 3rd Floor
Topics
Design
Keywords
In-memory and Near-memory Computing Circuits
Presentations
3:30pm - 3:45pm PDTSeries-Parallel Hybrid SOT-MRAM Computing-in-Memory Macro with Multi-Method Modulation for High Area and Energy Efficiency
3:45pm - 4:00pm PDTEasyACIM: An End-to-End Automated Analog CIM with Synthesizable Architecture and Agile Design Space Exploration
4:00pm - 4:15pm PDTImproving the Efficiency of In-Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode for Lossless Neural Network Inference
4:15pm - 4:30pm PDTSynthesis of Compact Flow-based Computing Circuits from Boolean Expressions
4:30pm - 4:45pm PDTCAP: A General Purpose Computation-in-memory with Content Addressable Processing Paradigm
4:45pm - 5:00pm PDTModSRAM: Algorithm-Hardware Co-Design for Large Number Modular Multiplication in SRAM
5:00pm - 5:15pm PDTCompact and Efficient CAM Architecture through Combinatorial Encoding and Self-Terminating Searching for In-Memory-Searching Accelerator
5:15pm - 5:30pm PDTDyn-Bitpool: A Two-sided Sparse CIM Accelerator Featuring a Balanced Workload Scheme and High CIM Macro Utilization