Enregistré dans:
Détails bibliographiques
Auteurs principaux: Malenza, Giulio, Targa, Francesco, Garcia, Adriano Marques, Aldinucci, Marco, Birke, Robert
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2504.03774
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913777713152000
author Malenza, Giulio
Targa, Francesco
Garcia, Adriano Marques
Aldinucci, Marco
Birke, Robert
author_facet Malenza, Giulio
Targa, Francesco
Garcia, Adriano Marques
Aldinucci, Marco
Birke, Robert
contents In today's era of rapid technological advancement, artificial intelligence (AI) applications require large-scale, high-performance, and data-intensive computations, leading to significant energy demands. Addressing this challenge necessitates a combined approach involving both hardware and software innovations. Hardware manufacturers are developing new, efficient, and specialized solutions, with the RISC-V architecture emerging as a prominent player due to its open, extensible, and energy-efficient instruction set architecture (ISA). Simultaneously, software developers are creating new algorithms and frameworks, yet their energy efficiency often remains unclear. In this study, we conduct a comprehensive benchmark analysis of machine learning (ML) applications on the 64-core SOPHON SG2042 RISC-V architecture. We specifically analyze the energy consumption of deep learning inference models across three leading AI frameworks: PyTorch, ONNX Runtime, and TensorFlow. Our findings show that frameworks using the XNNPACK back-end, such as ONNX Runtime and TensorFlow, consume less energy compared to PyTorch, which is compiled with the native OpenBLAS back-end.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03774
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring energy consumption of AI frameworks on a 64-core RV64 Server CPU
Malenza, Giulio
Targa, Francesco
Garcia, Adriano Marques
Aldinucci, Marco
Birke, Robert
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Hardware Architecture
In today's era of rapid technological advancement, artificial intelligence (AI) applications require large-scale, high-performance, and data-intensive computations, leading to significant energy demands. Addressing this challenge necessitates a combined approach involving both hardware and software innovations. Hardware manufacturers are developing new, efficient, and specialized solutions, with the RISC-V architecture emerging as a prominent player due to its open, extensible, and energy-efficient instruction set architecture (ISA). Simultaneously, software developers are creating new algorithms and frameworks, yet their energy efficiency often remains unclear. In this study, we conduct a comprehensive benchmark analysis of machine learning (ML) applications on the 64-core SOPHON SG2042 RISC-V architecture. We specifically analyze the energy consumption of deep learning inference models across three leading AI frameworks: PyTorch, ONNX Runtime, and TensorFlow. Our findings show that frameworks using the XNNPACK back-end, such as ONNX Runtime and TensorFlow, consume less energy compared to PyTorch, which is compiled with the native OpenBLAS back-end.
title Exploring energy consumption of AI frameworks on a 64-core RV64 Server CPU
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2504.03774