Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ramírez, Cristian, Castelló, Adrián, Martínez, Héctor, Quintana-Ortí, Enrique S.
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.07731
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914711050649600
author Ramírez, Cristian
Castelló, Adrián
Martínez, Héctor
Quintana-Ortí, Enrique S.
author_facet Ramírez, Cristian
Castelló, Adrián
Martínez, Héctor
Quintana-Ortí, Enrique S.
contents The devices designed for the Internet-of-Things encompass a large variety of distinct processor architectures, forming a highly heterogeneous zoo. In order to tackle this, we employ a simulator to estimate the performance of the matrix-matrix multiplication (GEMM) kernel on processors designed to operate at the edge. Our simulator adheres to the modern implementations of GEMM, advocated by GotoBLAS2, BLIS, OpenBLAS, etc., to carefully account for the amount of data transfers across the memory hierarchy of different algorithmic variants of the kernel. %Armed with this tool, A small collection of experiments provide the necessary data to calibrate the simulator and deliver highly accurate estimations of the execution time for a given processor architecture.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07731
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Performance Analysis of Matrix Multiplication for Deep Learning on the Edge
Ramírez, Cristian
Castelló, Adrián
Martínez, Héctor
Quintana-Ortí, Enrique S.
Hardware Architecture
The devices designed for the Internet-of-Things encompass a large variety of distinct processor architectures, forming a highly heterogeneous zoo. In order to tackle this, we employ a simulator to estimate the performance of the matrix-matrix multiplication (GEMM) kernel on processors designed to operate at the edge. Our simulator adheres to the modern implementations of GEMM, advocated by GotoBLAS2, BLIS, OpenBLAS, etc., to carefully account for the amount of data transfers across the memory hierarchy of different algorithmic variants of the kernel. %Armed with this tool, A small collection of experiments provide the necessary data to calibrate the simulator and deliver highly accurate estimations of the execution time for a given processor architecture.
title Performance Analysis of Matrix Multiplication for Deep Learning on the Edge
topic Hardware Architecture
url https://arxiv.org/abs/2403.07731