Application-Specific Arithmetic Computing Just Right for the Reconfigurable Computer and the Dark Silicon Era /

Written by two experts of the domain, this book presents the most recent advances in computer arithmetic hardware, with a focus on application-specific arithmetic beyond the classic operators and the standard precisions. It targets silicon designers who have to do better with less in the post-Moore...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: de Dinechin, Florent (Autor), Kumm, Martin (Autor)
Autor Corporativo: SpringerLink (Online service)
Formato: Electrónico eBook
Lenguaje:inglés
Publicado: Cham : Springer International Publishing : Imprint: Springer, 2024.
Edición:1st ed. 2024.
Materias:
Acceso en línea:https://doi.org/10.1007/978-3-031-42808-1
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • Chapter 1 Introduction
  • Chapter 2 Number Formats
  • Chapter 3 Computing Just Right: Accuracy Specification and Error Analysis
  • Chapter 4 Field Programmable Gate Arrays
  • Part 1 Revisiting Classic Arithmetic
  • Chapter 5 Fixed-Point Addition
  • Chapter 6 Fixed-Point Comparison
  • Chapter 7 Sums of Weighted Bits
  • Chapter 8 Fixed-Point Multiplication
  • Chapter 9 Fixed-Point Division
  • Chapter 10 Shifters and Leading Bit Counters
  • Chapter 11 Basic Floating-Point Operators
  • Part 2 Operator Specialization
  • Chapter 12 Multiplication by Constants
  • Chapter 13 Division by Constants
  • Chapter 14 Fixed-Point Squares, Cubes, and Other Integer Powers
  • Chapter 15 Specialization and Fusion of Floating-Point Operators
  • Part 3 Generic Methods for Fixed-Point Function Approximation
  • Chapter 16 Generalities on Fixed-Point Function Approximation
  • Chapter 17 Function Evaluation Using Tables and Additions
  • Chapter 18 Polynomial-Based Architectures for Function Evaluation
  • Chapter 19 Digit Recurrence for Algebraic Functions
  • Part 4 Example Composite Operators
  • Chapter 20 Fixed-Point Sine and Cosine
  • Chapter 21 Floating-Point Accumulation and Sum-of-Products
  • Chapter 22 Floating-Point Exponential
  • Part 5 Application Domains
  • Chapter 23 Arithmetic in The Design of Linear Time-Invariant Filters
  • Chapter 24 Arithmetic for Deep Learning
  • Part 6 Appendix
  • Chapter 25 Appendix A Custom Arithmetic Datapath Design with FloPoCo
  • Chapter 26 Appendix B Optimization Using Integer Linear Programming.