Hardware techniques to improve the robustness of a computing system can be very expensive, difficult to implement and validate. Moreover, they require long evaluation processes that could lead to the redesign of the hardware itself when reliability requirements are not satisfied. This chapter will cover the software techniques that allow improving the tolerance of the system to hardware faults by acting at software level only. We will cover the recently proposed approaches to detect and correct transient and permanent faults.

Chapter Contents:

• 4.1 Introduction
• 4.2 Fault taxonomy
• 4.2.1 Software faults
• 4.3 Software-Implemented Hardware Fault Tolerance
• 4.3.1 Modify the software in order to reduce the probability of fault occurrences
• 4.3.2 Detecting/tolerating the presence of an error
• 4.4 Software-Based Self-Test
• 4.4.1 Basics on SBST
• 4.5 SBST for GPGPUs
• 4.5.1 Introduction
• 4.5.2 Effects of permanent faults in GPGPU devices
• 4.5.3 SBST techniques for testing the GPGPU scheduler
• References

Inspec keywords: fault diagnosis; fault tolerant computing

Other keywords: computing system; hardware fault techniques; reliability requirements; long evaluation processes; software layer techniques

Subjects: Systems analysis and programming