Téléchargez le livre : Data Orchestration in Deep Learning Accelerators

Data Orchestration in Deep Learning Accelerators



de

Éditeur :

Springer


Collection :

Synthesis Lectures on Computer Architecture

Paru le : 2022-05-31



eBook Téléchargement , DRM LCP 🛈 DRM Adobe 🛈
72,59 €
Téléchargement immédiat
Dès validation de votre commande
Ajouter à ma liste d'envies
Image Louise Reader présentation

Louise Reader

Lisez ce titre sur l'application Louise Reader.

badge apple Application Louise Reader
badge Android Application Louise Reader
Description
This Synthesis Lecture focuses on techniques for efficient data orchestration within DNN accelerators. The End of Moore's Law, coupled with the increasing growth in deep learning and other AI applications has led to the emergence of custom Deep Neural Network (DNN) accelerators for energy-efficient inference on edge devices. Modern DNNs have millions of hyper parameters and involve billions of computations; this necessitates extensive data movement from memory to on-chip processing engines. It is well known that the cost of data movement today surpasses the cost of the actual computation; therefore, DNN accelerators require careful orchestration of data across on-chip compute, network, and memory elements to minimize the number of accesses to external DRAM. The book covers DNN dataflows, data reuse, buffer hierarchies, networks-on-chip, and automated design-space exploration. It concludes with data orchestration challenges with compressed and sparse DNNs and future trends. The target audience is students, engineers, and researchers interested in designing high-performance and low-energy accelerators for DNN inference.
Pages
146 pages
Collection
Synthesis Lectures on Computer Architecture
Parution
2022-05-31
Marque
Springer
EAN papier
9783031006395
EAN PDF
9783031017674
Informations sur l'ebook
Nombre pages copiables
1
Nombre pages imprimables
14
Taille du fichier
8315 Ko
Ce livre est accessible aux handicaps Voir les informations sur l'accessibilité
Prix
72,59 €

Suggestions personnalisées