A Nonvolatile AI-Edge Processor With Lossless-Compressed-Computing STT-MRAM Near-Memory-Compute Macro Using Dynamic Floating-/Fixed-Point Accumulation
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 61 (10) , 1-13
Abstract
No abstract availableFunding Information
- Taiwan Semiconductor Manufacturing Company (TSMC)-Joint Developed Project
- National Science and Technology Council (NSTC) of Taiwan
This publication has 45 references indexed in Scilit:
- TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba2025
- A mixed-precision memristor and SRAM compute-in-memory AI processorNature, 2025
- A full spectrum of computing-in-memory technologiesNature Electronics, 2023
- A CMOS-integrated spintronic compute-in-memory macro for secure AI edge devicesNature Electronics, 2023
- A compute-in-memory chip based on resistive random-access memoryNature, 2022
- A 40nm 60.64TOPS/W ECC-Capable Compute-in-Memory/Digital 2.25MB/768KB RRAM/SRAM System with Embedded Cortex M3 Microprocessor for Edge Recommendation Systems2022
- A crossbar array of magnetoresistive memory devices for in-memory computingNature, 2022
- 13.3 A 22nm 32Mb Embedded STT-MRAM with 10ns Read Speed, 1M Cycle Write Endurance, 10 Years Retention at 150°C and High Immunity to Magnetic Field Interference2020
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Deep Residual Learning for Image Recognition2016