analog compute-in-memory (ACIM)

  • No Comments

HyFPCiM: A 65-nm 417-μW Error-Sensitivity-Aware FP8 Compute-in-Memory Macro

HyFPCiM: A 65-nm 417-μW Error-Sensitivity-Aware FP8 Compute-in-Memory Macro 150 150
Author(s): Gaurav Kumar K, Yatharth Agarwal, Kaushik Roy

Abstract:

This letter presents HyFPCiM, a 65-nm FP8 compute-in-memory (CiM) macro that enables sub-mW floating-point (FP) inference using error-sensitivity-aware FP partitioning (EAP). EAP maps exponent processing to a digital CiM (DCiM) path and mantissa accumulation to an analog CiM (ACiM), avoiding the power- and area-intensive adder-tree-based accumulation used in prior FP-CiM …

Published in: IEEE Solid-State Circuits Letters
Page(s): 146 – 149
Year of Publication: 2026
Electronic ISSN: 2573-9603
DOI: 10.1109/LSSC.2026.3688988
Publisher: IEEE

View on IEEE Xplore

  • No Comments

MIX-ACIM: A 28-nm Mixed-Precision Analog Compute-in-Memory With Digital Feature Restoration for Vector-Matrix Multiplication

MIX-ACIM: A 28-nm Mixed-Precision Analog Compute-in-Memory With Digital Feature Restoration for Vector-Matrix Multiplication 150 150
Author(s): Wei-Chun Wang, Shida Zhang, Laith Shamieh, Narasimha Vasishta Kidambi, Isha Chakraborty, Saibal Mukhopadhyay

Abstract:

A mixed-precision analog compute-in-memory (Mix-ACIM) is presented for mixed-precision vector-matrix multiplication (VMM). The design features an all-analog current-domain fixed-point (FxP) VMM with floating-point conversion and feature restoration. A 28 nm CMOS test chip shows 41 TOPS/W and 24 TOPS/mm2 for FxP (8-bit input/weight and 12-bit output) and 24.18 TFLOPS/W and 3.3 …

Published in: IEEE Solid-State Circuits Letters
Page(s): 213 – 216
Year of Publication: 2025
Electronic ISSN: 2573-9603
DOI: 10.1109/LSSC.2025.3590757
Publisher: IEEE

View on IEEE Xplore

Search this website