In this thesis we propose a distributed-memory parallel-computer simulation system called PUPPET (Performance Under a Pseudo-Parallel EnvironmenT). It allows the evaluation of parallel programs run in a pseudo-parallel system, where a single processor is used to multitask the program's processes, as if they were run on the simulated system. This allows development of applications and teaching of parallel programming without the use of valuable supercomputing resources. We use a standard message-passing language, MPI, so that when desired (e. g. , development is complete) the program can be run on a truly parallel system without any changes. There are several features in PUPPET that do not exist in any other simulation system. Support for all deterministic MPI features is available, including collective and non-blocking communication. Multitasking (more processes than processors) can be simulated, allowing the evaluation of load-balancing schemes. PUPPET is very loosely coupled with the program, so that a program can be run once and then evaluated on many simulated systems with multiple process-to-processor mappings. Finally, we propose a new model of direct networks that ignores network traffic, greatly improving simulation speed and often not signficantly affecting accuracy.

In this thesis we propose a distributed-memory parallel-computer simulation system called PUPPET (Performance Under a Pseudo-Parallel EnvironmenT). It allows the evaluation of parallel programs run in a pseudo-parallel system, where a single processor is used to multitask the program's processes, as if they were run on the simulated system. This allows development of applications and teaching of parallel programming without the use of valuable supercomputing resources. We use a standard message-passing language, MPI, so that when desired (e. g. , development is complete) the program can be run on a truly parallel system without any changes. There are several features in PUPPET that do not exist in any other simulation system. Support for all deterministic MPI features is available, including collective and non-blocking communication. Multitasking (more processes than processors) can be simulated, allowing the evaluation of load-balancing schemes. PUPPET is very loosely coupled with the program, so that a program can be run once and then evaluated on many simulated systems with multiple process-to-processor mappings. Finally, we propose a new model of direct networks that ignores network traffic, greatly improving simulation speed and often not signficantly affecting accuracy.

辭賦在兩漢四百多年間，由於作者身分逐漸轉換，傳播方式的改易，還有文人對五七言句的接受，及政治環境的崩解等因素，導致其語言形式產生明顯變化，有漸趨駢偶、篇幅縮減等傾向。為了說明其語言風格與時俱「變」的軌跡，本文以169篇現存完整的漢賦為觀察對象，具體地描述並比較兩漢賦的種種異同，也嘗試將原本以作者等單「點」研究為主的語言風格學，延伸為一斷代賦史的「線」性觀察，更全面地回應賦學和文學史的研究成果。 本文第一章交代研究動機、方法及範圍，第二章則針對漢賦排比成篇的特徵，討論其句式風格及與五七言詩的關係；第三章進一步分析排比句中的「假平行」現象，並指出其與近體詩「假平行」不同的對仗習慣。第四章從較為宏觀的「篇章架構」著手，一方面呈現西漢著重時空順序的特徵，另方面也說明東漢建安小賦以首句概括全篇的安排。在第五章，筆者敘述漢賦「鋪彩摛文」的設計，包括使用長主語、長賓語以炫耀博學，竭力排比長謂語的種種動態，乃至多採「奔行」等手法；第六章則援引俄國形式主義學者所謂的「陌生化」概念，說明漢賦穿插「零句」和倒置語序，以引起聽眾或讀者新鮮感的安排。最後，第七章結論略述各章梗概，說明本文價值、研究限制和可繼續發展的相關議題。此外，〈附錄一〉〈附錄二〉是第二章的補充資料，分別為各篇句式分析表，以及二三、四三節奏賦句列表。 / Researchers of Han Rhapsody often suggest that, as a dominant literary genre of the Han Dynasty, rhapsody had changed its linguistic style gradually owing to the differences from the changes of authors’ social identities, the growing popularity and development of five and seven syllables(五七言詩), and the decline and fall of the Han empire. However, research that describes the specific and concrete features of this genre during the four hundred years of Han Dynasty is scant. To illustrate how the varying line length, loose parallelism, and extensive themes in Han Rhapsody was built up, interacted with the five and seven syllables(the representative genre of the six dynasty(魏晉六朝)), and influenced other rhythm works for the following millennium, I described, grouped, and integrated all the distinguishing details in Han Rhapsodies with the method which Leo Spitzer had mentioned in his work, Linguistics and Literary History: Essays in Stylistics. By analyzing the syntactic mode(句式), the pseudo parallel(假平行),the discourse- oriented topics, and the strategies the authors took to extend the length of the rhapsody and to unfamiliarize the readers with the incomplete or inverted sentence, this study showed how the complicated expressions, exhaustive details, and magnificent structures had been simplified and shortened, and both the authors and readers paid more attention to the emotions expressed rather than to the exaggerated language adapted step by step. To conclude, this study may be of importance in providing researchers with a better understanding of how the changes within a genre had taken place, as well as enriching the realm of the traditional Chinese literary criticism, which usually explains the literature phenomenon by subjective impression.

The thesis deals with image classifiers and their implementation using FPGA technology. There are discussed weak and strong classifiers in the work. As an example of strong classifiers, the AdaBoost algorithm is described. In the case of weak classifiers, basic types of feature classifiers are shown, including Haar and Gabor wavelets. The rest of work is primarily focused on LBP, LRP and LR classifiers, which are well suitable for efficient implementation in FPGAs. With these classifiers is designed pseudo-parallel architecture. Process of classifications is divided on software and hardware parts. The thesis deals with hardware part of classifications. The designed classifier is very fast and produces results of classification every clock cycle.