Cover Image

Performance–energy trade-offs of deep learning convolution algorithms on ARM processors

CC BY

Saved in:
Bibliographic Details
Main Authors: Manuel F., Dolz, Sergio, Barrachina, Héctor, Martínez
Format: Book
Language:English
Published: Springer 2023
Subjects:
ARM-based processor architectures
NVIDIA Denver2
Online Access:https://link.springer.com/article/10.1007/s11227-023-05050-4
https://dlib.phenikaa-uni.edu.vn/handle/PNK/8247
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-8247
record_format dspace
spelling oai:localhost:PNK-82472023-04-25T01:26:40Z Performance–energy trade-offs of deep learning convolution algorithms on ARM processors Manuel F., Dolz Sergio, Barrachina Héctor, Martínez ARM-based processor architectures NVIDIA Denver2 CC BY In this work, we assess the performance and energy efficiency of high-performance codes for the convolution operator, based on the direct, explicit/implicit lowering and Winograd algorithms used for deep learning (DL) inference on a series of ARM-based processor architectures. Specifically, we evaluate the NVIDIA Denver2 and Carmel processors, as well as the ARM Cortex-A57 and Cortex-A78AE CPUs as part of a recent set of NVIDIA Jetson platforms. The performance–energy evaluation is carried out using the ResNet-50 v1.5 convolutional neural network (CNN) on varying configurations of convolution algorithms, number of threads/cores, and operating frequencies on the tested processor cores. The results demonstrate that the best throughput is obtained on all platforms with the Winograd convolution operator running on all the cores at their highest frequency. However, if the goal is to reduce the energy footprint, there is no rule of thumb for the optimal configuration. 2023-04-25T01:26:40Z 2023-04-25T01:26:40Z 2023 Book https://link.springer.com/article/10.1007/s11227-023-05050-4 https://dlib.phenikaa-uni.edu.vn/handle/PNK/8247 en application/pdf Springer
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic ARM-based processor architectures
NVIDIA Denver2
spellingShingle ARM-based processor architectures
NVIDIA Denver2
Manuel F., Dolz
Sergio, Barrachina
Héctor, Martínez
Performance–energy trade-offs of deep learning convolution algorithms on ARM processors
description CC BY
format Book
author Manuel F., Dolz
Sergio, Barrachina
Héctor, Martínez
author_facet Manuel F., Dolz
Sergio, Barrachina
Héctor, Martínez
author_sort Manuel F., Dolz
title Performance–energy trade-offs of deep learning convolution algorithms on ARM processors
title_short Performance–energy trade-offs of deep learning convolution algorithms on ARM processors
title_full Performance–energy trade-offs of deep learning convolution algorithms on ARM processors
title_fullStr Performance–energy trade-offs of deep learning convolution algorithms on ARM processors
title_full_unstemmed Performance–energy trade-offs of deep learning convolution algorithms on ARM processors
title_sort performance–energy trade-offs of deep learning convolution algorithms on arm processors
publisher Springer
publishDate 2023
url https://link.springer.com/article/10.1007/s11227-023-05050-4
https://dlib.phenikaa-uni.edu.vn/handle/PNK/8247
_version_ 1764177434900430848
score 8.891695

Similar Items