Architecture design for soft errors / / Shubu Mukherjee

• Record Nr.: UNINA9911006624203321
• Autore: Mukherjee Shubu
• Pubbl/distr/stampa: Amsterdam ; ; Boston, : Morgan Kaufmann Publishers/Elsevier, c2008
• ISBN: 9786611272760; 9781281272768; 1281272760; 9780080558325; 0080558321
• Edizione: [1st edition]
• Descrizione fisica: 1 online resource (361 p.)
• Disciplina: 621.3815
• Soggetti: Integrated circuits; Integrated circuits - Effect of radiation on; Computer architecture; System design
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Description based upon print version of record.
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Front Cover; Architecture Design for Soft Errors; Copyright Page; Table of Contents; Foreword; Preface; Chapter 1. Introduction; 1.1 Overview; 1.2 Faults; 1.3 Errors; 1.4 Metrics; 1.5 Dependability Models; 1.6 Permanent Faults in Complementary Metal Oxide Semiconductor Technology; 1.7 Radiation-Induced Transient Faults in CMOS Transistors; 1.8 Architectural Fault Models for Alpha Particle and Neutron Strikes; 1.9 Silent Data Corruption and Detected Unrecoverable Error; 1.10 Soft Error Scaling Trends; 1.11 Summary; 1.12 Historical Anecdote; References; Chapter 2. Device and Circuit-Level Modeling Measurement and Mitigation2.1 Overview; 2.2 Modeling Circuit-Level SERs; 2.3 Measurement; 2.4 Mitigation Techniques; 2.5 Summary; 2.6 Historical Anecdote; References; Chapter 3. Architectural Vulnerability Analysis; 3.1 Overview; 3.2 AVF Basics; 3.3 Does a Bit Matter?; 3.4 SDC and DUE Equations; 3.5 ACE Principles; 3.6 Microarchitectural Un-ACE Bits; 3.7 Architectural Un-ACE Bits; 3.8 AVF Equations for a Hardware Structure; 3.9 Computing AVF with Little's Law; 3.10 Computing AVF with a ; Performance Model; 3.11 ACE Analysis Using the Point-of-Strike Fault Model3.12 ACE Analysis Using the Propagated Fault Model; 3.13 Summary; 3.14 Historical Anecdote; References; Chapter 4. Advanced Architectural Vulnerability Analysis; 4.1 Overview; 4.2 Lifetime Analysis of RAM Arrays; 4.3 Lifetime Analysis of CAM Arrays; 4.4 Effect of Cooldown in Lifetime Analysis; 4.5 AVF Results for Cache, Data Translation Buffer, and Store Buffer; 4.6 Computing AVFs Using SFI into an RTL Model; 4.7 Case Study of SFI; 4.8 Summary; 4.9 Historical Anecdote; References; Chapter 5. Error Coding Techniques; 5.1 Overview; 5.2 Fault Detection and ECC for State Bits5.3 Error Detection Codes for Execution Units; 5.4 Implementation Overhead of Error Detection and Correction Codes; 5.5 Scrubbing Analysis; 5.6 Detecting False Errors; 5.7 Hardware Assertions; 5.8 Machine Check Architecture; 5.9 Summary; 5.10 Historical Anecdote; References; Chapter 6. Fault Detection via Redundant Execution; 6.1 Overview; 6.2 Sphere of Replication; 6.3 Fault Detection via Cycle-by-Cycle Lockstepping; 6.4 Lockstepping in the Hewlett-Packard NonStop Himalaya Architecture; 6.5 Lockstepping in the IBM Z-series Processors; 6.6 Fault Detection via RMT6.7 RMT in the Marathon Endurance Server; 6.8 RMT in the Hewlett-Packard NonStop® Advanced Architecture; 6.9 RMT Within a Single-Processor Core; 6.10 RMT in a Multicore Architecture; 6.11 DIVA: RMT Using Specialized Checker Processor; 6.12 RMT Enhancements; 6.13 Summary; 6.14 Historical Anecdote; References; Chapter 7. Hardware Error Recovery; 7.1 Overview; 7.2 Classification of Hardware Error Recovery Schemes; 7.3 Forward Error Recovery; 7.4 Backward Error Recovery with Fault Detection before Register Commit; 7.5 Backward Error Recovery with Fault Detection before Memory Commit
• Sommario/riassunto: This book provides a comprehensive description of the architetural techniques to tackle the soft error problem. It covers the new methodologies for quantitative analysis of soft errors as well as novel, cost-effective architectural techniques to mitigate them. To provide readers with a better grasp of the broader problem deffinition and solution space, this book also delves into the physics of soft errors and reviews current circuit and software mitigation techniques. TABLE OF CONTENTSChapter 1: Introduction Chapter 2: Device- and Circuit-Level Modeling, Measurement, and Mitig