Free delivery for orders over 69.99 euro.

Check order status

Become part of a community of book lovers from all over the world and get access to a whole bunch of benefits. Create an account for free

Free delivery for purchases over 69.99 €

DPD courier 5.99 € Bpost point 7.99 € Bpost 7.49 € DPD point 3.49 € GLS courier 4.99 €

Contact

How to shop

Help

My account

▸ Empty :-(

Free delivery for orders over 69.99 euro.

Efficient Execution of Irregular Dataflow Graphs

Name: Efficient Execution of Irregular Dataflow Graphs
Brand: Springer, Berlin
SKU: 43225187
Price: 80.51 EUR
Availability: InStock
Author: Nimish Shah
ISBN: 9783031331350

Hardware/Software Co-optimization for Probabilistic AI and Sparse Triangular Systems

Nimish Shah

Marian Verhelst

Wannes Meert

Language

English

Book Hardback

Libristo code: 43225187

Publishers Springer, Berlin, September 2023

This book focuses on the acceleration of emerging irregular sparse workloads, posed by novel artific... Full description

Libristo code: 43225187

195 b

80.51 €

In stock at our supplier Shipping in 10-13 days

Up to 30 days for returns

Customers also purchased

Français-Serbe (Cyrillique) Véhicules Imagier bilingue pour les enfants Richard Carlson Jr

Paperback

11.61 €

Deutsches Seemaennisches Soerterbuch Alfred Stenzel

Paperback

25.05 €

Obsesion de la Narcisista Jairo E Lopez

Paperback

9.69 €

Landesverfassungsgerichte Werner Reutter

Hardback

75.26 €

Histoire De La Réformation De La Suisse, Volume 5 Louis Vulliemin

Paperback

30.70 €

This book focuses on the acceleration of emerging irregular sparse workloads, posed by novel artificial intelligent (AI) models and sparse linear algebra. Specifically, the book outlines several co-optimized hardware-software solutions for a highly promising class of emerging sparse AI models called Probabilistic Circuit (PC) and a similar sparse matrix workload for triangular linear systems (SpTRSV). The authors describe optimizations for the entire stack, targeting applications, compilation, hardware architecture, and silicon implementation, resulting in orders of magnitude higher performance and energy-efficiency compared to the existing state-of-the-art solutions. Thus, this book provides important building blocks for the upcoming generation of edge AI platforms.