Driven by Moore's Law, many computer architectures - ARM, x86, MIPS, PowerPC, SPARC - have evolved from 32-bit to 64-bit. To support existing applications, these have all kept support for a 32-bit compatibility mode. However, this comes at a cost in hardware complexity, power consumption and development time. Dynamic binary translation - recompiling binaries into the new instruction set at runtime - can be used instead of specific hardware for this purpose. While this approach has previously been used to assist architecture transition, these translators have all traded-off performance and transparency, a measure of how accurately they emulate the 32-bit environment. This thesis addresses ARM's transition from AArch32 to AArch64 through MAMBO-X64, a dynamic binary translator developed to support this transition. A range of novel optimizations were devised to improve translation performance while maintaining strict transparency. This follows a common theme of exploiting existing hardware features such as hardware return prediction, virtual memory and virtualization extensions to offset translation overheads. HyperMAMBO-X64 - a variant of MAMBO-X64 integrated in a hypervisor - was also developed to support system-level translation while remaining transparent to guest operating systems. Results demonstrate that the cost of binary translation is reduced, delivering performance competitive with the manufacturer's hardware. Performance in several benchmarks even exceeds that from the integrated compatibility mode. Thus MAMBO-X64 not only provides a means for architectural upgrade, but also an alternative to the expense of the legacy support currently employed.

Two possible sets of planning variables for human arm movement are point angles and hand position. Although one might expect these possibilities to be mutually exclusive, recently an apparently contradictory set of data has appeared that indicated straight-line trajectories in both hand space and joint space at the same time. To assist in distinguishing between these viewpoints applied to the same data, we have theoretically characterized the set of trajectories derivable from a joint based planning strategy and have compared them to experimental measurements. We conclude that the apparent straight-lines in joint space happen to be artifacts of movement kinematics near the workspace boundary.

All of the communication, IA, and the cellular phone need the capabilities which can be provided by the ARM microprocessor that has the advantages with high efficient, low power consumption, and low cost. According to the market research that Gartner proposed, ARM occupied the highest with 54% at the market of embedded microprocessor, and 70% of the cellular phones utilize the ARM kernel techniques in the whole world. The success of ARM is determined by the different on the hardware design compared with the general embedded microprocessor. In my thesis, the significant propose is to study the practicability and the essentiality of the hardware characters of the ARM microprocessor applied on different products. We design ¡§automatic register backup/restore system¡¨ to replace ARM¡¦s banked registers. This design is capable of reducing the circuit area of the register file by 27.6% and reducing the read delay of register file by 18.4%. We use a simpler method (TAP instruction) to select scan-chain for test mechanism.

Theories in operating systems are relatively matured, but implementations are hard compared to many areas in computer science. For example, virtual memory has been around for more than 20 years since its introduction, but, to understand how an operating system supports virtual memory is not a trivial task, let alone implementation. Minix is an operating system that has been designed for educational purpose. It¡¦s a good starting point for a novice who wants to learn operating systems. The third version of Minix has been moved towards a true microkernel design and targeted at small computers and embedded systems. The advantages of microkernel architecture is its high fault tolerance and high modularity design which can make it much more flexible for versatile applications on embedded systems. However, to the best of our knowledge, Minix 3 only runs on Intel-based machine so far. The objective of this thesis is thus to port Minix 3 to ARM-Based embedded systems, to make it an experimental microkernel for embedded systems. Also, due to the incompatibility between the segmented memory model used by Minix 3 on IA-32 and the unsegmented memory model support by ARM, we also provide an API to simplify the porting effort.

Thesis (M.Sc.)--York University, 2007. Graduate Programme in Kinesiology & Health Science. / Typescript. Includes bibliographical references (leaves 72-83). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&res_dat=xri:pqdiss&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:MR38803

The main purpose of this study was to measure the differences in ground reaction forces (GRFs) produced from an anteroposterior versus a mediolateral style hockey skating arm swing. Twenty four elite level female hockey players performed each technique while standing on a ground mounted force platform, all trials were filmed using two video cameras. Force data was assessed for peak scaled GRFs in the frontal and sagittal planes, and resultant GRF magnitude and direction. Upper limb kinematics were assessed from the video using Dartfish video analysis software, confirming that the subjects successfully performed two significantly distinct arm swing techniques. The mediolateral arm swing used a mean of 18.38° of glenohumeral flexion/extension and 183.68° of glenohumeral abduction/adduction while the anteroposterior technique used 214.17° and 28.97° respectively. The mediolateral arm swing produced 37% greater frontal plane and 33% lesser sagittal plane GRFs than the anteroposterior arm swing. The magnitudes of the resultant GRFs were not significantly different between the two techniques however the mediolateral technique produced a resultant GRF with a significantly larger angle from the direction of travel (44.44°) as compared to the anteroposterior technique (31.60°). The results of this study suggest that the direction of GRFs produced by the mediolateral arm swing more consistent with the direction of lower limb propulsion, perhaps resulting in a greater contribution to high velocity skating. Based on the findings from the present study ice hockey skaters should perform the mediolateral arm swing to maximize the effective GRFs produced with each stride.

The objective of this work was to evaluate and implement a number of energy saving functions for a specific embedded system. The functions were then grouped into a number of energy levels with known properties in terms of functionality, energy consumption, and transition time between the levels. The embedded system consisted of an AT91 ARM9 processor, GSM/GPRS modem, display, Ethernet and other peripheral units. Some energy saving methods that were considered were suspend to RAM, suspend to disk, frequency scaling, and methods for saving energy in the modem, Ethernet, USB and display backlight. The functions were grouped into levels and an interface was specified for controlling the energy level. It proved possible to get known properties within the defined energy levels, even though the paritioning of functions into these levels proved to be sub-optimal in a typical application usage scenario because it was designed for mainly energy consumption, not usage. The final result is a number of energy saving functions grouped into levels, which are controllable via an application interface. Each of the levels have a known energy consumption in both loaded and un-loaded mode.

The main purpose of this study was to measure the differences in ground reaction forces (GRFs) produced from an anteroposterior versus a mediolateral style hockey skating arm swing. Twenty four elite level female hockey players performed each technique while standing on a ground mounted force platform, all trials were filmed using two video cameras. Force data was assessed for peak scaled GRFs in the frontal and sagittal planes, and resultant GRF magnitude and direction. Upper limb kinematics were assessed from the video using Dartfish video analysis software, confirming that the subjects successfully performed two significantly distinct arm swing techniques. The mediolateral arm swing used a mean of 18.38° of glenohumeral flexion/extension and 183.68° of glenohumeral abduction/adduction while the anteroposterior technique used 214.17° and 28.97° respectively. The mediolateral arm swing produced 37% greater frontal plane and 33% lesser sagittal plane GRFs than the anteroposterior arm swing. The magnitudes of the resultant GRFs were not significantly different between the two techniques however the mediolateral technique produced a resultant GRF with a significantly larger angle from the direction of travel (44.44°) as compared to the anteroposterior technique (31.60°). The results of this study suggest that the direction of GRFs produced by the mediolateral arm swing more consistent with the direction of lower limb propulsion, perhaps resulting in a greater contribution to high velocity skating. Based on the findings from the present study ice hockey skaters should perform the mediolateral arm swing to maximize the effective GRFs produced with each stride.

Diss. (sammanfattning) Stockholm : Karol. inst. / Härtill 5 uppsatser.

Thesis (M.S.)--California Polytechnic State University, 2009. / Mode of access: Internet. Title from PDF title page; viewed on March 17, 2009. Major professor: Robert D. Clark, Ph.D. "Presented to the faculty of California Polytechnic State University, San Luis Obispo." "In partial fulfillment of the requirements for the degree [of] Master of Science in Kinesiology." "March 2009." Includes bibliographical references (p. 41-44). Also available on microfiche.