[HTML][HTML] Survey of deep learning accelerators for edge and emerging computing

S Alam, C Yakopcic, Q Wu, M Barnell, S Khan… - Electronics, 2024 - mdpi.com
The unprecedented progress in artificial intelligence (AI), particularly in deep learning
algorithms with ubiquitous internet connected smart devices, has created a high demand for …

Trending IC design directions in 2022

CH Chan, L Cheng, W Deng, P Feng… - Journal of …, 2022 - iopscience.iop.org
For the non-stop demands for a better and smarter society, the number of electronic devices
keeps increasing exponentially; and the computation power, communication data rate, smart …

Diana: An end-to-end hybrid digital and analog neural network soc for the edge

P Houshmand, GM Sarda, V Jain… - IEEE Journal of Solid …, 2022 - ieeexplore.ieee.org
DIgital-ANAlog (DIANA), a heterogeneous multi-core accelerator, combines a reduced
instruction set computer-five (RISC-V) host processor with an analog in-memory computing …

A 28nm 16.9-300TOPS/W computing-in-memory processor supporting floating-point NN inference/training with intensive-CIM sparse-digital architecture

J Yue, C He, Z Wang, Z Cong, Y He… - … Solid-State Circuits …, 2023 - ieeexplore.ieee.org
Computing-in-memory (CIM) has shown high energy efficiency on low-precision integer
multiply-accumulate (MAC)[1–3]. However, implementing floating-point (FP) operations …

A 95.6-TOPS/W deep learning inference accelerator with per-vector scaled 4-bit quantization in 5 nm

B Keller, R Venkatesan, S Dai, SG Tell… - IEEE Journal of Solid …, 2023 - ieeexplore.ieee.org
The energy efficiency of deep neural network (DNN) inference can be improved with custom
accelerators. DNN inference accelerators often employ specialized hardware techniques to …

Deeploy: Enabling Energy-Efficient Deployment of Small Language Models on Heterogeneous Microcontrollers

M Scherer, L Macan, VJB Jung, P Wiese… - … on Computer-Aided …, 2024 - ieeexplore.ieee.org
With the rise of embodied foundation models (EFMs), most notably small language models
(SLMs), adapting Transformers for the edge applications has become a very active field of …

16.5 DynaPlasia: An eDRAM in-memory-computing-based reconfigurable spatial accelerator with triple-mode cell for dynamic resource switching

S Kim, Z Li, S Um, W Jo, S Ha, J Lee… - … Solid-State Circuits …, 2023 - ieeexplore.ieee.org
In-memory computing (IMC) processors show significant energy and area efficiency for deep
neural network (DNN) processing [1–3]. As shown in Fig. 16.5. 1, despite promising macro …

22.1 A 12.4 TOPS/W@ 136GOPS AI-IoT system-on-chip with 16 RISC-V, 2-to-8b precision-scalable DNN acceleration and 30%-boost adaptive body biasing

F Conti, D Rossi, G Paulin, A Garofalo… - … Solid-State Circuits …, 2023 - ieeexplore.ieee.org
Emerging Artificial Intelligence-enabled Internet-of-Things (Al-loT) SoCs 1–4 for augmented
reality, personalized healthcare and nano-robotics need to run a large variety of tasks within …

Benchmarking in-memory computing architectures

NR Shanbhag, SK Roy - IEEE Open Journal of the Solid-State …, 2022 - ieeexplore.ieee.org
In-memory computing (IMC) architectures have emerged as a compelling platform to
implement energy-efficient machine learning (ML) systems. However, today, the energy …

DynaPlasia: An eDRAM in-memory computing-based reconfigurable spatial accelerator with triple-mode cell

S Kim, Z Li, S Um, W Jo, S Ha, J Lee… - IEEE Journal of Solid …, 2023 - ieeexplore.ieee.org
This article presents DynaPlasia, a reconfigurable eDRAM-based in-memory computing
(IMC) processor with a novel triple-mode cell. It enables higher system-level performance …