iMCU: A 28-nm Digital In-Memory Computing-Based Microcontroller Unit for TinyML

Tiny machine learning (TinyML) envisions executing a deep neural network (DNN)-based inference on an edge device for improving battery life, latency, security, and privacy. Toward this vision, recent microcontroller units (MCUs) integrate in-memory computing (IMC) hardware to leverage its high energ...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE journal of solid-state circuits Ročník 59; číslo 8; s. 2684 - 2693
Hlavní autoři: Lin, Chuan-Tung, Huang, Paul Xuanyuanliang, Oh, Jonghyun, Wang, Dewei, Seok, Mingoo
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.08.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Artificial neural networks
Computation
Computer architecture
Data models
Deep learning
Density
Energy efficiency
Hardware
hardware/software co-design
In-memory computing
in-memory computing (IMC)
Machine learning
microcontroller units (MCUs)
Microcontrollers
Multiplication
neural network accelerators
Random access memory
Software
Software development
State-of-the-art reviews
Static random access memory
tiny machine learning (TinyML)
ISSN:0018-9200, 1558-173X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Tiny machine learning (TinyML) envisions executing a deep neural network (DNN)-based inference on an edge device for improving battery life, latency, security, and privacy. Toward this vision, recent microcontroller units (MCUs) integrate in-memory computing (IMC) hardware to leverage its high energy efficiency and throughput in vector-matrix multiplication (VMM). However, those existing works require large IMC hardware, severely increasing the area overhead. In addition, most existing works use analog-mixed-signal (AMS) IMC hardware, exhibiting limited robustness over process, voltage, and temperature (PVT) variations. Finally, none can support a practical software development framework such as TensorFlow Lite for Microcontrollers (TFLite-micro). Due to these limitations, those MCUs did not present the performance for the standard benchmark MLPerf-Tiny, which makes it difficult to evaluate them against the state-of-the-art neural (not necessarily IMC-based) MCUs. In this article, we design a new IMC-based MCU, titled iMCU, for TinyML to address those challenges. In the design process, we: 1) define the optimal set of acceleration targets and 2) devise an area-efficient computation flow that requires the least amount of IMC hardware yet still provides a significant acceleration. In addition, we develop: 1) state-of-the-art digital IMC macros and 2) create the accelerator based on the macros, which can support the proposed computation flow in a fully pipelined manner. Combining those innovations, we prototyped the iMCU in a 28-nm CMOS. The measurement results show that the iMCU significantly outperforms the prior IMC-based MCUs in compute density, energy efficiency, and SRAM density (total SRAM size/total SRAM area). It also achieves a compact footprint of 2.73 mm2.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9200
1558-173X
DOI:10.1109/JSSC.2024.3362274