Thesis (Ph. D.)--Stanford University, 1986. / Cover title. "March 1986." Includes bibliographical references.

Thesis (M.S.)--Rutgers University, 2009. / "Graduate Program in Electrical and Computer Engineering." Includes bibliographical references (p. 58-59).

Thesis (M.E.)--University of Florida, 2002. / Title from title page of source document. Includes vita. Includes bibliographical references.

Modern computer systems are power or energy limited. While the number of transistors per chip continues to increase, classic Dennard voltage scaling has come to an end. Therefore, architects must improve a design's energy efficiency to continue to increase performance at historical rates, while staying within a system's power limit. Throughput processors, which use a large number of threads to tolerate memory latency, have emerged as an energy-efficient platform for achieving high performance on diverse workloads and are found in systems ranging from cell phones to supercomputers. This work focuses on graphics processing units (GPUs), which contain thousands of threads per chip. In this dissertation, I redesign the on-chip storage system of a modern GPU to improve energy efficiency. Modern GPUs contain very large register files that consume between 15%-20% of the processor's dynamic energy. Most values written into the register file are only read a single time, often within a few instructions of being produced. To optimize for these patterns, we explore various designs for register file hierarchies. We study both a hardware-managed register file cache and a software-managed operand register file. We evaluate the energy tradeoffs in varying the number of levels and the capacity of each level in the hierarchy. Our most efficient design reduces register file energy by 54%. Beyond the register file, GPUs also contain on-chip scratchpad memories and caches. Traditional systems have a fixed partitioning between these three structures. Applications have diverse requirements and often a single resource is most critical to performance. We propose to unify the register file, primary data cache, and scratchpad memory into a single structure that is dynamically partitioned on a per-kernel basis to match the application's needs. The techniques proposed in this dissertation improve the utilization of on-chip memory, a scarce resource for systems with a large number of hardware threads. Making more efficient use of on-chip memory both improves performance and reduces energy. Future efficient systems will be achieved by the combination of several such techniques which improve energy efficiency. / text

In computer forensics, digital evidence related to time is both important and complex. The rules of changes in time associated with digital evidence, such as files or folders, can be used to analyze certain user behaviors like data access, modification or transfer. However, the format and the rules in time information for user actions are quite different for different file systems, even for different versions of operating systems with the same file system. Some research on temporal analysis has already been done on NTFS and FAT file systems, while there are few resources that describe temporal analysis on the Hierarchical File System Plus (HFS+), the default file system in Apple computer. Moreover, removable devices like USB disks are used frequently; transferring files and folders between different devices with different file systems and operating systems happens more and more frequently, so the changes of times across different file systems are also crucial in digital forensics and investigations. In this research, the changes in time attributes of files and folders resulting from user actions on the HFS+ file system and across file systems are analyzed, and the rules of time are generated by inductive reasoning to help reconstruct crime scenes in the digital forensic investigation. Since inductive reasoning is not definitely true compared with deductive reasoning, experiments are performed to validate the rules. The usage of the rules is demonstrated by analyzing a case in details. The methods proposed here are efficient, practical and easy to put into practice in real scenarios. / published_or_final_version / Computer Science / Master / Master of Philosophy

No description available.

No description available.

Thesis (M.S.)--West Virginia University, 1999. / Title from document title page. Document formatted into pages; contains iv, 43 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 42-43).

Thesis--Auburn University, 2009. / Abstract. Vita. Includes bibliographical references (p. 41-48).

Thesis (Ph. D.)--University of Tampere, 1985. / Includes 4 papers published by the author in various journals. Includes bibliographical references (4 p. near end of text).