For semiconductor processors temperature increases leakage current, which in turn in- creases the temperature of the processor. This increase in heat is seen by other parts of the processor since heat is diffusive across a processor die. In this way, cores are thermally coupled to one another such that when the temperature of one core increases, the temperatures of all cores on the same die can also increase. This increase in temperature and power consumption is not accompanied by any increase in performance. Cores on a chip can also be performance coupled to one another since cores can share data between them. These interactions between cores present new challenges to microarchitects who seek to optimize the energy consumption of a chip multiprocessor (CMP) comprised of multiple symmetric or asymmetric processing cores. This thesis seeks to understand and model the impact of thermal coupling effects between adjacent cores in a chip multiprocessor starting with measurements with a commercial multi-core processor. The hypothesis is that the thermal coupling of compute cores will be influenced by the adjacent core’s performance characteristics. Specifically, we expect thermal coupling is related to the nature of the workloads, e.g. compute intensive workloads will increase coupling over memory intensive workloads. However, we find that simpler parameters such as frequency of operation have more impact on coupling behaviors than the workload behaviors such as memory intensity or instruction retirement rates. A model is developed to capture thermal coupling effects and enable schemes to mitigate its impact.

This thesis presents a top to bottom analysis on designing and implementing fast algorithms for current and future systems. We present new analysis, algorithmic techniques, and implementations of the Fast Multipole Method (FMM) for solving N- body problems. We target the FMM because it is broadly applicable to a variety of scientific particle simulations used to study electromagnetic, fluid, and gravitational phenomena, among others. Importantly, the FMM has asymptotically optimal time complexity with guaranteed approximation accuracy. As such, it is among the most attractive solutions for scalable particle simulation on future extreme scale systems. We specifically address two key challenges. The first challenge is how to engineer fast code for today’s platforms. We present the first in-depth study of multicore op- timizations and tuning for FMM, along with a systematic approach for transforming a conventionally-parallelized FMM into a highly-tuned one. We introduce novel opti- mizations that significantly improve the within-node scalability of the FMM, thereby enabling high-performance in the face of multicore and manycore systems. The second challenge is how to understand scalability on future systems. We present a new algorithmic complexity analysis of the FMM that considers both intra- and inter- node communication costs. Using these models, we present results for choosing the optimal algorithmic tuning parameter. This analysis also yields the surprising prediction that although the FMM is largely compute-bound today, and therefore highly scalable on current systems, the trajectory of processor architecture designs, if there are no significant changes could cause it to become communication-bound as early as the year 2015. This prediction suggests the utility of our analysis approach, which directly relates algorithmic and architectural characteristics, for enabling a new kind of highlevel algorithm-architecture co-design. To demonstrate the scientific significance of FMM, we present two applications namely, direct simulation of blood which is a multi-scale multi-physics problem and large-scale biomolecular electrostatics. MoBo (Moving Boundaries) is the infrastruc- ture for the direct numerical simulation of blood. It comprises of two key algorithmic components of which FMM is one. We were able to simulate blood flow using Stoke- sian dynamics on 200,000 cores of Jaguar, a peta-flop system and achieve a sustained performance of 0.7 Petaflop/s. The second application we propose as future work in this thesis is biomolecular electrostatics where we solve for the electrical potential using the boundary-integral formulation discretized with boundary element methods (BEM). The computational kernel in solving the large linear system is dense matrix vector multiply which we propose can be calculated using our scalable FMM. We propose to begin with the two dielectric problem where the electrostatic field is cal- culated using two continuum dielectric medium, the solvent and the molecule. This is only a first step to solving biologically challenging problems which have more than two dielectric medium, ion-exclusion layers, and solvent filled cavities. Finally, given the difficulty in producing high-performance scalable code, productivity is a key concern. Recently, numerical algorithms are being redesigned to take advantage of the architectural features of emerging multicore processors. These new classes of algorithms express fine-grained asynchronous parallelism and hence reduce the cost of synchronization. We performed the first extensive performance study of a recently proposed parallel programming model, called Concurrent Collections (CnC). In CnC, the programmer expresses her computation in terms of application-specific operations, partially-ordered by semantic scheduling constraints. The CnC model is well-suited to expressing asynchronous-parallel algorithms, so we evaluate CnC using two dense linear algebra algorithms in this style for execution on state-of-the-art mul- ticore systems. Our implementations in CnC was able to match and in some cases even exceed competing vendor-tuned and domain specific library codes. We combine these two distinct research efforts by expressing FMM in CnC, our approach tries to marry performance with productivity that will be critical on future systems. Looking forward, we would like to extend this to distributed memory machines, specifically implement FMM in the new distributed CnC, distCnC to express fine-grained paral- lelism which would require significant effort in alternative models.

Ultra-High-Performance Concretes (UHPCs) are a promising class of cementitious materials possessing mechanical properties superior to those of Normal Strength Concretes (NSCs). However, UHPCs have been slow to transition from laboratory testing to insertion in new applications, partly due to an intuitive trial-and-error materials development process. This research seeks to addresses this problem by implementing a materials design process for the design of UHPC materials and structures subject to blast loads with specific impulses between 1.25- and 1.5-MPa-ms and impact loads resulting from the impact of a 0.50-caliber bullet travelling between 900 and 1,000 m/s. The implemented materials design process consists of simultaneous bottom-up deductive mappings and top-down inductive decision paths through a set of process-structure-property-performance (PSPP) relations identified for this purpose. The bottom-up deductive mappings are constructed from a combination of analytical models adopted from the literature and two hierarchical multiscale models developed to simulate the blast performance of a 1,626-mm tall by 864-mm wide UHPC panel and the impact performance of a 305-mm tall by 305-mm wide UHPC panel. Both multiscale models employ models at three length scales – single fiber, multiple fiber, and structural – to quantify deductive relations in terms of fiber pitch (6-36 mm/revolution), fiber volume fraction (0-2%), uniaxial tensile strength of matrix (5-12 MPa), quasi-static tensile strength of fiber-reinforced matrix (10-20 MPa), and dissipated energy density (20-100 kJ/m²). The inductive decision path is formulated within the Inductive Design Exploration Method (IDEM), which determines robust combinations of properties, structures, and processing steps that satisfy the performance requirements. Subsequently, the preferred material and structural designs are determined by rank order of results of objective functions, defined in terms of mass and costs of the UHPC panel.

When compared to traditional concrete, steel fibre reinforced concrete (SFRC) shows several enhancements in performance, including improved tensile resistance, toughness and ductility. One potential application for SFRC is in columns where the provision of steel fibres can improve performance under axial and lateral loads. The use of SFRC can also allow for partial replacement of transverse reinforcement required by modern seismic codes. To improve workability, self-consolidating concrete (SCC) can be combined with steel fibres, leading to highly workable SFRC suitable for structural applications. Recent advances in material science have also led to the development of ultra-high performance fibre reinforced concretes (UHPFRC), a material which exhibits very high compressive strength, enhanced post-cracking resistance and high damage tolerance. In heavily loaded ground-story columns, the use of UHPFRC can allow for reduced column sections. This thesis presents the results from a comprehensive research program conducted to study the axial behaviour of columns constructed with highly workable SFRC and UHPFRC. As part of the experimental program, twenty-three full-scale columns were tested under pure axial compressive loading. In the case of the SFRC columns, columns having rectangular section and constructed with SCC and steel fibres were tested, with variables including fibre content and spacing of transverse reinforcement. The results confirm that use of fibres results in improved column behaviour due to enhancements in core confinement and cover behaviour. Furthermore, the results demonstrate that the provision of steel fibres in columns can allow for partial replacement of transverse reinforcement required by modern codes. The analytical investigation indicates that confinement models proposed by other researchers for traditional RC and SFRC can predict the response of columns constructed with SCC and highly workable SFRC. In the case of the UHPFRC columns, variables included configuration and spacing of transverse reinforcement. The results demonstrate that the use of appropriate detailing in UHPFRC columns can result in suitable ductility. Furthermore, the results demonstrate the improved damage tolerance of UHPFRC when compared to traditional high-strength concrete. The analytical investigation demonstrates the need for development of confinement models specific for UHPFRC.

This thesis introduces energy and performance optimization techniques for high-performance processors. Our optimization techniques target both single processors and chip multiprocessors (CMPs). In single processors, we exploit trivial instructions to improve energy and performance. Trivial instructions are those instructions whose output can be determined without performing the actual computations. We show that bypassing such unnecessary computations reduces energy while improve performance. Performance improvement achieved by skipping executing trivial instructions depends on how early such instructions are identified. We use value prediction to detect trivial instructions with high accuracy and as soon as possible. Consequently, we improve performance over a processor that bypasses trivial instructions without using speculation. In CMPs, we introduce two techniques to improve energy of interconnect and caches Conventional snoopy based chip multiprocessors take an aggressive approach broadcasting snoop requests to all nodes. In addition, each node checks all received requests. This approach reduces the latency of cache to cache transfer misses at the expense of increasing energy. We exploit this design inefficiency and introduce two optimization techniques in CMPs. First, and at the requester end, we introduce speculative selective request (SSR) to reduce energy consumption in the binary tree interconnect. In SSR, we send the request only to the node more likely to have the missing data. We reduce energy as we limit accesses only to the interconnect components between the requestor and the supplier node. Second, and at the receiving end, we propose speculative tag lookup (STL) to reduce energy consumption in data caches. We filter those accesses more likely to miss in the L1, cache. Using shared memory applications, we show that SSR and STL improve energy of interconnect and caches significantly with negligible performance loss and hardware overhead.

This work investigates the feasibility of the use of plasma spray deposition as a method of producing high performance polymer coatings. The work concentrates on the understanding of the processing of the plasma spraying of polymers, the behaviour of polymeric materials during deposition, and the study of process-structure-properties relationships. Processing modelling for the three stages of the evolution of a polymer deposit (droplet-splat-coating) has been carried out using heat transfer theory. A theoretical model is proposed which consists of three parts: the first part predicts the temperature profile of in-flight particles within plasma jet, the second part predicts the cooling of isolated splats impacting on a substrate and the third part, the heat transfer through the coating thickness. The heat transfer analysis predicts that the development of large temperature gradients within the particle is a general characteristics of polymers during plasma spraying. This causes difficulties for polymer particles to be effectively molten within the plasma jet without decomposition. The theoretical calculations have predicted the effect of processing parameters on the temperature, the degree of melting and decomposition of in-flight polymer particles. With the aid of the model, the conditions for the preparation of high integrity thermoplastic deposits have been established by the control of the plasma arc power, plasma spraying distance, feedstock powder injection, torch traverse speed and feedstock particle size. The optimal deposition conditions are designed to produce effective particle melting in the plasma, extensive flow on impact, and minimal thermal degradation. The experimental work on optimizing processing parameters has confirmed the theoretical predictions. Examination of polymer coating structures reveals that the major defects are unmelted particles, cracks and pores. Five major categories of pores have been classified. It also revealed a significant loss in crystallinity and the presence of a minor metastable phase in the plasma deposited polyamide coatings due to rapid solidification. The study has indicated that the molecular weight of a polymer plays an important role on the splat flow and coating structure. Under non-optimal deposition condition, substantial thermal degradation occurred for which a chain scission mechanism is proposed for plasma deposited polyamide coatings. There are difficulties in achieving cross-linking during plasma spray deposition of thermosets. The theoretical calculations predict that adequate cross-linking is unlikely in a coating deposited under normal conditions, but preheating the substrate to above the cross-linking temperature improves the degree of cross-linking of the coatings substantially. In addition, the coating thickness has a major effect on the degree of cross-linking of thermosets. The calculations also predict that lowering the thermal conductivity by applying a thermal barrier undercoat and using a faster curing agent to reduce time required for the cross-linking reaction can improve the degree of cross-linking of thermoset deposits. The experimental results for the degree of cross-linking and wear resistance confirmed these predictions.

A precise simulation requires a large amount of input data such as geometrical descriptions of the crystal structure, the external forces and loads, and quantitative properties of the material. Although some powerful applications already exist for research purposes, they are not widely used in education due to complex structure and unintuitive operation. To cater to the generic user base, a front-end application for material simulation software is introduced. With a graphic interface, it provides a more efficient way to conduct the simulation and to educate students who want to enlarge knowledge in relevant fields. We first discuss how we explore the solution for the front-end application and how to develop it on top of the material simulation software developed by mechanical engineering lab from Georgia Tech Lorraine. The user interface design, the functionality and the whole user experience are primary factors determining the product success or failure. This material simulation software helps researchers resolve the motion and the interactions of a large ensemble of dislocations for single or multi-layered 3D materials. However, the algorithm it utilizes is not well optimized and parallelized, so its performance of speedup cannot scale when using more CPUs in the cluster. This problem leads to the second topic on scientific computing, so in this thesis we offer different approaches that attempt to improve the parallelization and optimize the scalability.

Rykštenė yra daugiametis augalas, priklausantis astrinių šeimai. Ji pasižymi keliais farmakologiniais veikimais, tokiais kaip skatinančiu diurezę, priešuždegiminiu, analgetiniu, antispazmolitiniu, antibakteriniu ir antigrybeliniu, taip pat antioksidaciniu ir priešvėžiniu aktyvumu. Iš rykštenės žaliavos gaminami vaistai skatinantys diurezę. Ji taip pat įeina į Lietuvoje gaminamos arbatos „Diuretiko“ (UAB „Acorus Calamus”) sudėtį. Šio darbo tikslas - atlikti polifenolinių rūgščių kokybinę ir kiekybinę analizę rykštenės ekstraktuose taikant efektyviąją skysčių chromatografiją. Buvo paruošti Solidago virgaurea ir Solidago gigantea lapų ir žiedų ekstraktai naudojant vandeninį metanolio tirpalą (70%). Jie buvo analizuojami ESC metodu. Detekcijai naudojamas fotodiodų matricos detektorius. Gauti rezultatai buvo lyginami su standartinių junginių (chlorogeno ir neochlorogeno rūgščių) duomenimis. Polifenolinės rūgštys nustatomos bangos ilgiui esant 324nm. Buvo identifikuotos dvi polifenolinės rūgštys: chlorogeno ir neochlorogeno. Solidago virgaurea chlorageno rūgšties yra 1.31%, o neochlorogeno rūgšties – 0.06%. Solidago gigantea chlorogeno rūgšties procentinis kiekis yra 2.35%, o neochlorageno rūgšties – 0.02%. / Goldenrod is a perennial plant belonging to the Asteraceae family. It has several pharmacological functions, such as promoting diuresis, anti-inflammatory, analgesic, antispazmolitiniu, antibacterial and antifungal as well as anti-oxidative and anti-tumor activity. Of goldenrod made a medicaments stimulating diuresis. It also includes in production of tea „Diuretiko“ (UAB „Acorus Calamus”) composition in Lithuanian. The aim of this research was to make polyphenolic acids qualitative and quantitative analysis of the goldenrod extracts using high-performance liquid chromatography. Was prepared Solidago virgaurea and Solidago gigantea leaves and flowers extracts of aqueous methanol (70%). They were analyzed in HPLC method. For detection was used photodiode array detector. The results were compared with standard compounds (chlorogenic and neochlorogenic acids) data. Polyphenolic acids determined at the wave length of 324nm. Has been identified two polyphenolic acids: chlorogenic and neochlorogenic. In Solidago virgaurea chlorogenic acid is 1.31% and neochlorogenic acid - 0.06%. In Solidago gigantea chlorogenic acid percentage is 2.35%, and neochlorogenic acid - 0.02%.

Nuolatos plečiantis maisto papildų rinkai ir augant naujai sukuriamų papildų kiekiui būtina sukurti greitas, tikslias ir efektyvias papildų analizės metodikas, norint užtikrinti į rinką tiekiamų farmacinių prepartų kokybę. Vitamino E nustatymui efektyviosios skysčių chromatografijos būdu yra sukurta nemažai įvairių metodikų, tačiau svarbu žinoti, kuri metodika yra efektyviausia būtent vitamino E preparatams. Tyrimo tikslas - atlikti kokybinį ir kiekybinį tokoferolio acetato nustatymą pritaikant efektyviosios skysčių chromatografijos metodą bei surasti efektyviausią tokoferolio acetato ekstrakcijos metodiką vaistinių preparatų analizei. Tyrimo uždaviniai - surinkti ir apibendrinti informaciją apie vitaminą E, jo poveikį organizmui, maisto papildus su tokoferolio acetatu bei jų analizę; optimizuoti metodiką tokoferolio acetato preparatų analizei efektyviosios skysčių chromatografijos būdu ir ją validuoti; atlikti tokoferolio acetato preparatų (maisto papildo ir vaistinio preparato) paruošimą analizei įvairiomis ekstrakcijos metodikomis; išanalizuoti gautus duomenis ir padaryti išvadas apie efektyviausias ekstrakcijos metodikas bandinių paruošimui bei skirtumus tarp vaistinio preparato ir maisto papildo analizės. Metodas – tyrimas atliktas chromatografine sistema su fotodiodų matricos detektoriumi. Mobilioji fazė – metanolis:distiliuotas vanduo (95:5), tekėjimo greitis – 1.2 ml/min, bandinio tūris – 10 µl, trukmė – 14 min, bangos ilgis – 282 nm. Išbandytos preparatų... [toliau žr. visą tekstą] / The food supplements market is constantly growing and new products are entering it everyday. In order to assure the quality of these pharmaceuticals it is important to develop methods of analysis which are fast, precise and effective. There are many methods created for the analysis of vitamin E using high-performance liquid chromatography so it is important to know which of them are the most effective for vitamin E food supplements. The aim – to perform a qualitative and a quantitive assey of tochopherol acetate using high performance liquid chromatography and to find the most effective method of extracting tocopherol acetate from food suplements. The tasks – to collect and to summarize the data on vitamin E, its effects on human body, on the supplements containing tocopherol acetate and their analysis; to develop a high-performance liquid chromatography method of analysis suitable for the pharmaceuticals containing tocopherol acetate ant to validate it; to perform a tocopherol acetate (a food supplement and a drug) samples preparation using different techniques chosen; to analyze the data collected and to make conclusions about the most effective way of preparing samples for the analysis and about the differences between a drug and a food supplement analysis. The method – the study was conducted by high-performance liquid chromatography using a photodiode matrix detector. Mobile phase – methanol:purified water (95:5), flow-rate – 1.2 ml/min, injection volume – 10 µl... [to full text]

Tyrimo objektas ir metodai: Sorbus L. genties augalo S. aucuparia L. lapų ir žiedų tyrimas. Bendras fenolinių junginių kiekis paprastojo šermukšnio augalinėse žaliavose nustatytas UV spektrofotometriniu metodu, fenolinės rūgštys ir flavonoidai nustatyti ESC metodu. Darbo tikslas: nustatyti S. aucuparia L. lapuose ir žieduose esančius fenolinius junginius, jų kiekinės sudėties įvairavimą augalo vegetacijos metu ir augalinių žaliavų (lapų ir žiedų) laikymo metu. Darbo uždaviniai: Surinkti ir susisteminti literatūros duomenis apie Sorbus aucuparia L., paprastojo šermukšnio augalinių žaliavų cheminę sudėtį, fenolinių junginių analizės metodus, poveikį ir panaudojimą medicinos praktikoje; Ištirti S. aucuparia L. lapų ir žiedų kiekybinę fenolinių junginių sudėtį ir nustatyti bendro fenolinių junginių kiekio įvairavimą augalo vegetacijos metu; Ištirti S. aucuparia L. lapų ir žiedų kokybinę ir kiekybinę fenolinių rūgščių ir flavonoidų sudėtį ir nustatyti jų kiekinės sudėties kitimą augalų vegetacijos periodo metu; Nustatyti S. aucuparia L. lapuose ir žieduose esančių fenolinių junginių kiekybinės sudėties kitimus augalinių žaliavų laikymo metu. Išvados: S. aucuparia L. augalinės žaliavos gali būti kaip šaltinis išskiriant biologiškai aktyvius junginius, kurie gali būti naudojami medicinos praktikoje. S. aucuparia L. lapuose ir žieduose esančių junginių kiekis kinta augalo vegetacijos metu; lapuose daugiausia fenolinių junginių sukaupiama gegužės - birželio mėn., žieduose – žydėjimo... [toliau žr. visą tekstą] / Object and methods: Sorbus aucuparia L. leaves and flowers study. Total amaunt of phenolic compounds in mountain ash leaves and flowers were evaluated using UV spectrophotometry, phenolic acids and flavonoids were identified and evaluated using HPLC. Aim: to identify and evaluate the content of phenolic compounds in rowan leaves and flowers during mountain ash vegetation and during plant materials (leaves and flowers) storage. Objective: to collect and organise the information about the use of Sorbus aucuparia L., S. aucuparia L. leaves and flowers acumulated compounds, phenolic compounds analysis methods and the impact of the use in medical practice; to perform quantitative analysis of S. aucuparia L. leaves and flowers phenolic compounds and to determine the total phenolics content during rowan growing season; to perform qualitative and quantitative analysis of S. aucuparia L. leaves and flowers phenolic acids and flavonoids and to determine the variation of the phenolics content during rowan growing season; to determine phenolic compounds content changes in Sorbus aucuparia L. plant materials (flowers and leaves) during them storage. Conclusions: S. aucuparia L. leaves and flower is a source of biological active substances which can be used in medicinal practice. Phenolic compounds content in S. aucuparia L. leaves and flowers change during vegetation; mainly phenolic compounds in leaves was accumulated in May - June, in flowers - in the beginning of flowering and massive... [to full text]