From Variability Tolerance to Approximate Computing in Parallel Integrated Architectures and Accelerators
This book focuses on computing devices and their design at various levels to combat variability. The authors provide a review of key concepts with particular emphasis on timing errors caused by various variability sources. They discuss methods to predict and prevent, detect and correct, and finally...
Uloženo v:
| Hlavní autor: | |
|---|---|
| Další autoři: | |
| Korporace: | |
| Médium: | E-kniha |
| Jazyk: | angličtina |
| Vydáno: |
Cham :
Springer International Publishing,
2017
|
| Žánr/forma: | elektronické knihy |
| ISBN: | 978-3-319-53768-9 9783319537672 |
| Témata: | |
| On-line přístup: | Plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!
|
Obsah:
- Introduction
- Part 1. Predicting and Preventing Errors
- Instruction-Level Tolerance
- Sequence-Level Tolerance
- Procedure-Level Tolerance
- Kernel-Level Tolerance
- Hierarchically Focused Guardbanding
- Part 2. Detecting and Correcting Errors
- Work-Unit Tolerance
- Memristive-Based Associative Memory for Error Recovery
- Part 3. Accepting Errors
- Accuracy-Configurable OpenMP
- An Approximation Workflow for Exploiting Data-Level Parallelism in FPGA Acceleration
- Memristive-Based Associative Memory for Approximate Computational Reuse
- Spatial and Temporal Memoization
- Outlook