Computer Engineering Commons^™

Modular Injection System And Sampling Template (M.I.S.S.T) Design Report, Froylan M. Aguirre

Computer Engineering

Digital systems are ubiquitous throughout modern life and their applications continue to grow. Thus system designers engineer and test modular systems to mitigate error rates. Smaller systems and their increasing importance in many applications demand the utmost reliability. Fault injection is the most common method used by researchers and engineers to test system reliability. However, most hardware fault injection implementations are ad hoc and only used to test a specific system or for specific tests. There is also software-implemented fault injection that adds overhead in the benchmark source code. The aim of this project is to develop a general use, …

Improving Large Scale Application Performance Via Data Movement Reduction, Dewan M. Ibtesham

Computer Science ETDs

The compute capacity growth in high performance computing (HPC) systems is outperforming improvements in other areas of the system for example, memory capacity, network bandwidth and I/O bandwidth. Therefore, the cost of executing a floating point operation is decreasing at a faster rate than moving that data. This increasing performance gap causes wasted CPU cycles while waiting for slower I/O operations to complete in the memory hierarchy, network, and storage. These bottlenecks decrease application time to solution performance, and increase energy consumption, resulting in system under utilization. In other words, data movement is becoming a key concern for future HPC …

Barrier Coverage In Wireless Sensor Networks, Zhibo Wang

Doctoral Dissertations

Barrier coverage is a critical issue in wireless sensor networks (WSNs) for security applications, which aims to detect intruders attempting to penetrate protected areas. However, it is difficult to achieve desired barrier coverage after initial random deployment of sensors because their locations cannot be controlled or predicted. In this dissertation, we explore how to leverage the mobility capacity of mobile sensors to improve the quality of barrier coverage.

We first study the 1-barrier coverage formation problem in heterogeneous sensor networks and explore how to efficiently use different types of mobile sensors to form a barrier with pre-deployed different types of …

Hard And Soft Error Resilience For One-Sided Dense Linear Algebra Algorithms, Peng Du

Doctoral Dissertations

Dense matrix factorizations, such as LU, Cholesky and QR, are widely used by scientific applications that require solving systems of linear equations, eigenvalues and linear least squares problems. Such computations are normally carried out on supercomputers, whose ever-growing scale induces a fast decline of the Mean Time To Failure (MTTF). This dissertation develops fault tolerance algorithms for one-sided dense matrix factorizations, which handles Both hard and soft errors.

For hard errors, we propose methods based on diskless checkpointing and Algorithm Based Fault Tolerance (ABFT) to provide full matrix protection, including the left and right factor that are normally seen in …

A Sustainable Autonomic Architecture For Organically Reconfigurable Computing Systems, Rashad S. Oreifej

Electronic Theses and Dissertations

A Sustainable Autonomic Architecture for Organically Reconfigurable Computing System based on SRAM Field Programmable Gate Arrays (FPGAs) is proposed, modeled analytically, simulated, prototyped, and measured. Low-level organic elements are analyzed and designed to achieve novel self-monitoring, self-diagnosis, and self-repair organic properties. The prototype of a 2-D spatial gradient Sobel video edge-detection organic system use-case developed on a XC4VSX35 Xilinx Virtex-4 Video Starter Kit is presented. Experimental results demonstrate the applicability of the proposed architecture and provide the infrastructure to quantify the performance and overcome fault-handling limitations. Dynamic online autonomous functionality restoration after a malfunction or functionality shift due to changing …

Sustainable Fault-Handling Of Reconfigurable Logic Using Throughput-Driven Assessment, Carthik Sharma

Electronic Theses and Dissertations

A sustainable Evolvable Hardware (EH) system is developed for SRAM-based reconfigurable Field Programmable Gate Arrays (FPGAs) using outlier detection and group testing-based assessment principles. The fault diagnosis methods presented herein leverage throughput-driven, relative fitness assessment to maintain resource viability autonomously. Group testing-based techniques are developed for adaptive input-driven fault isolation in FPGAs, without the need for exhaustive testing or coding-based evaluation. The techniques maintain the device operational, and when possible generate validated outputs throughout the repair process. Adaptive fault isolation methods based on discrepancy-enabled pair-wise comparisons are developed. By observing the discrepancy characteristics of multiple Concurrent Error Detection (CED) configurations, …