Dnn-chip predictor: An analytical performance predictor for dnn accelerators with various dataflows and hardware architectures

Y Zhao, C Li, Y Wang, P Xu, Y Zhang… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
The recent breakthroughs in deep neural networks (DNNs) have spurred a tremendously
increased demand for DNN accelerators. However, designing DNN accelerators is non …

From cnn to dnn hardware accelerators: A survey on design, exploration, simulation, and frameworks

LR Juracy, R Garibotti, FG Moraes - Foundations and Trends® …, 2023 - nowpublishers.com
Over the past decade, a massive proliferation of machine learning algorithms has emerged,
from applications for surveillance to self-driving cars. The turning point occurred with the …

An automotive case study on the limits of approximation for object detection

M Caro, H Tabani, J Abella, F Moll, E Morancho… - Journal of Systems …, 2023 - Elsevier
The accuracy of camera-based object detection (CBOD) built upon deep learning is often
evaluated against the real objects in frames only. However, such simplistic evaluation …

A fast, accurate, and comprehensive PPA estimation of convolutional hardware accelerators

LR Juracy, A de Morais Amory… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Convolutional Neural Networks (CNN) are widely adopted for Machine Learning (ML) tasks,
such as classification and computer vision. GPUs became the reference platforms for both …

[LLIBRE][B] AI Computing Systems: An Application Driven Perspective

Y Chen, L Li, W Li, Q Guo, Z Du, Z Xu - 2022 - books.google.com
AI Computing Systems: An Application Driven Perspective adopts the principle of"
application-driven, full-stack penetration" and uses the specific intelligent application of" …

A Survey on Design Methodologies for Accelerating Deep Learning on Heterogeneous Architectures

F Ferrandi, S Curzel, L Fiorin, D Ielmini… - arxiv preprint arxiv …, 2023 - arxiv.org
In recent years, the field of Deep Learning has seen many disruptive and impactful
advancements. Given the increasing complexity of deep neural networks, the need for …

Blackthorn: latency estimation framework for CNNs on embedded Nvidia platforms

M Lechner, A Jantsch - IEEE Access, 2021 - ieeexplore.ieee.org
With more powerful yet efficient embedded devices and accelerators being available for
Deep Neural Networks (DNN), machine learning is becoming an integral part of edge …

Annette: Accurate neural network execution time estimation with stacked models

M Wess, M Ivanov, C Unger, A Nookala, A Wendt… - IEEE …, 2020 - ieeexplore.ieee.org
With new accelerator hardware for Deep Neural Networks (DNNs), the computing power for
Artificial Intelligence (AI) applications has increased rapidly. However, as DNN algorithms …

DASM: Data-streaming-based computing in nonvolatile memory architecture for embedded system

L Chang, X Ma, Z Wang, Y Zhang… - … Transactions on Very …, 2019 - ieeexplore.ieee.org
Emerging nonvolatile memories (NVMs), including resistive RAM (RRAM), phase-change
memory (PCM), and magnetic RAM (MRAM), have opened up new pathways for Computing …

Data scheduling and placement in deep learning accelerator

SYH Mirmahaleh, M Reshadi, N Bagherzadeh… - Cluster …, 2021 - Springer
Deep neural networks (DNNs) have been employed to different devices as a popular
machine learning algorithm (ML) owing to deploy the Internet of Things (IoT), data mining in …