No abstract

Defining a dual role for spare processing elements (PES) in reliability-challenged processing arrays is the major focus of the paper. The paper also explores 0 practical way to include reconfiguration hardware in single-package arrays. The implementation of away processor systems may include spare PES for fault tolerance. These systems typically require a host f o r fault diagnosis, while the healthy spares sit idle. It is proposed to utilize the idling spare PES f o r purposes of fault diagnosis, giving the array the capability of self diagnosis. Fault tolerance must incorporate additional hardware for reconfiguration, and existing plans have not found widespread use in single-package systems due to the extra cost and extra real estate. Multichip modules (MCMs) have the potential to offer fault tolerance with no increase an p r i m a y circuit area. It is proposed to contain the reconfiguration hardware in the active substrate of a silicon-based MCM. Ferrther, the switches TepuiTed for spares coverage can aid in the job of compan'son based self-testing. We oser a complete solution to faulttolerant arrays in the sense that diagnosis, reconfiguration and switching details are all addressed. 1: IntroductionIn order to obtain reliable high speed operation, singlepackage array processor systems must employ fault tolerance. One way to tolerate faults is to commission redundant processors (spares) to cover (replace) faulty processing elements (PES). A method must be in place to diagnose faulty nodes. We consider a method of fault tolerance which employs spares and provides a means of self diagnosis. The identification of faults will be able to take place during normal operation and computational throughput will not be degraded. Most existing works consider diagnosis as a separate problem, generally administered by a central host. In such systems, it is common to find healthy spare PES sitting idle on the silicon real estate. By developing proper isolation schemes, the idling spares can be used to perform supplementary tasks or other "administrative" functions.Much research has been done in wafer scale integration (WSI) to obtain reliable, single-package arrays. Unresolved practical issues such as extra cost and extra chip area (for additional links and switches) have kept these solutions from finding widespread use in the field. The multichip module (MCM) will make a good packaging candidate for fault tolerance because it has the potential to offer reconfiguration without increasing primary array area. Reconfiguration hardware can be housed outside the array and can be fabricated independently. The technology of silicon substrates will be taken advantage of so that transistor switches can be fabricated on the substrate.Self-diagnosis of processing arrays has been examined significantly as a separate concern and generally involves one of two methods. One plan employs the traditional off-line test vector approach. In the method of comparison testing, units pair up during normal operation and duplicate tasks while compari...

No abstract

No abstract

A previous goal of the microprocessor/microcontroller class in the Buffalo State College Engineering Technology Program was to develop proficiency with an assembly language in order that students could write assembly language code for various microprocessors and microcontrollers. The goal has been modified such that students become familiar with assembly language programming as well as understanding the role of a high-level language such as C in microcontroller applications. Concepts of portability, variable storage space, and hardware registers are presented to help students understand the strengths and weaknesses of programming a microcontroller with highlevel language such as C. A high-level language brings features like loops, arrays, and decisionmaking capability to the very rudimentary assembly language. Standard C languages such as ANSI C are portable, meaning they are independent of the microcontroller that will ultimately be used to execute the code. However, to best utilize the microcontroller for digital I/O and timing delays as well as many other tasks, read and write access to the specific hardware registers of that microcontroller are needed and therefore portability must be sacrificed. In this case, a "special compiler" is required that recognizes the specific hardware of the microcontroller. An example of such a compiler is the Rigel Corporation 8051 C compiler, which provides two methods for communicating with specific hardware in the 8051 Note: Microcontroller will refer to both microcontrollers and microprocessors in this paper.