FERMI-ML: A Flexible and Resource-Efficient Memory-In-Situ SRAM Macro for TinyML acceleration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lokhande, Mukul, Sankhe, Akash, Chand, S. V. Jaya, Vishvakarma, Santosh Kumar
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918331705982976
author Lokhande, Mukul
Sankhe, Akash
Chand, S. V. Jaya
Vishvakarma, Santosh Kumar
author_facet Lokhande, Mukul
Sankhe, Akash
Chand, S. V. Jaya
Vishvakarma, Santosh Kumar
contents The growing demand for low-power and area-efficient TinyML inference on AIoT devices necessitates memory architectures that minimise data movement while sustaining high computational efficiency. This paper presents FERMI-ML, a Flexible and Resource-Efficient Memory-In-Situ (MIS) SRAM macro designed for TinyML acceleration. The proposed 9T XNOR-based RX9T bit-cell integrates a 5T storage cell with a 4T XNOR compute unit, enabling variable-precision MAC and CAM operations within the same array. A 22-transistor (C22T) compressor-tree-based accumulator facilitates logarithmic 1-64-bit MAC computation with reduced delay and power compared to conventional adder trees. The 4 KB macro achieves dual functionality for in-situ computation and CAM-based lookup operations, supporting Posit-4 or FP-4 precision. Post-layout results at 65 nm show operation at 350 MHz with 0.9 V, delivering a throughput of 1.93 TOPS and an energy efficiency of 364 TOPS/W, while maintaining a Quality-of-Result (QoR) above 97.5% with InceptionV4 and ResNet-18. FERMI-ML thus demonstrates a compact, reconfigurable, and energy-aware digital Memory-In-Situ macro capable of supporting mixed-precision TinyML workloads.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FERMI-ML: A Flexible and Resource-Efficient Memory-In-Situ SRAM Macro for TinyML acceleration
Lokhande, Mukul
Sankhe, Akash
Chand, S. V. Jaya
Vishvakarma, Santosh Kumar
Hardware Architecture
Emerging Technologies
Machine Learning
Image and Video Processing
The growing demand for low-power and area-efficient TinyML inference on AIoT devices necessitates memory architectures that minimise data movement while sustaining high computational efficiency. This paper presents FERMI-ML, a Flexible and Resource-Efficient Memory-In-Situ (MIS) SRAM macro designed for TinyML acceleration. The proposed 9T XNOR-based RX9T bit-cell integrates a 5T storage cell with a 4T XNOR compute unit, enabling variable-precision MAC and CAM operations within the same array. A 22-transistor (C22T) compressor-tree-based accumulator facilitates logarithmic 1-64-bit MAC computation with reduced delay and power compared to conventional adder trees. The 4 KB macro achieves dual functionality for in-situ computation and CAM-based lookup operations, supporting Posit-4 or FP-4 precision. Post-layout results at 65 nm show operation at 350 MHz with 0.9 V, delivering a throughput of 1.93 TOPS and an energy efficiency of 364 TOPS/W, while maintaining a Quality-of-Result (QoR) above 97.5% with InceptionV4 and ResNet-18. FERMI-ML thus demonstrates a compact, reconfigurable, and energy-aware digital Memory-In-Situ macro capable of supporting mixed-precision TinyML workloads.
title FERMI-ML: A Flexible and Resource-Efficient Memory-In-Situ SRAM Macro for TinyML acceleration
topic Hardware Architecture
Emerging Technologies
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2511.12544