With the growing demand of embedded graphics applications, how to provide an efficient graphics hardware acceleration solution has drawn much attention. It is well known that computer graphics contains two major domains: two-dimensional (2D) and three-dimensional (3D) graphics. Each domain owns large amounts of applications, such that general embedded platforms will require both graphics acceleration supports. This thesis proposes an advanced texture unit architecture which can provide various 3D texture filtering functions including trilinear, anistrophics filtering etc , and 2D coloring, painting, and texturing functions. Our proposed design consists of a core computation unit, and a set of data registers. The equations for those supported functions are decomposed into a series of basic arithmetic operations such as multiply-add-accumulation, multiply, etc executed by the core computation unit. To evaluate those equations for each pixel may require some pre-computed parameters which will be computed outside our unit in advance by the system¡¦s micro-controller. The equations can be computed by our texture unit based on the selected finite-state machine sequences which is stored in the on-chip control table. By updating those sequences can change the functionality provided by our chip. The overall cost of the proposed unit is about 28.36k gates. In addition to various texturing functions, this thesis also proposes an implementation of texture function for high-dynamic range (HDR) textures. HDR textures can provide various color details according to the frame¡¦s global illumination environment. Therefore, the 3D rendering system has to incorporate a tone-mapping mechanism to map the HDR image into normal color range of output display system. To reduce the overall tone-mapping implementation cost, this thesis uses an extra accumulator between the standard per-fragment rendering pipeline stages to accumulate the global illumination intensity based on the depth comparison result of the incoming pixel. After all of the pixels have passed through the pipeline stages, every pixel of the stored rendering result will be fetched into a mapping unit which will generate its mapping color in the normal dynamic range. The overall cost of the additional hardware for the realization of HDR textures is about 6.98k gates.

In the past few years, due to the rapid advance in technology and the aid of 3D graphics applications the world of 3D graphics is rapidly expanding from desktop computers and dedicated gaming consoled to handheld devices, such as cellular phones, PDAs, laptops etc.,. However, unlike traditional desktop computers and gaming consoles, mobile computing devices typically have slower processors that have less capability for handling large computation-intensive workloads like 3D graphics application. In addition, the power consumption is one of the major design specifications to realize the 3D graphics accelerating engine for mobile devices because handheld batteries have limited lifetimes. Moreover, the size of chip is depend on the Moore¡¦s Law: The number of transistors in a chip are double in every eighteen months. Even though the produce cost is decrease, but the capacity of battery cannot increase like the transistors. Therefore, how to reduce power consumption by using efficient power management techniques has become a very important research topic in 3D graphics SoC design. For 3D graphics applications, dynamic voltage and frequency scaling (DVFS) is a good candidate to reduce the power consumption of 3D graphics accelerating engine. So many relative papers have researched in how to accurately predict the workload and scale the voltage and frequency. The prediction policy can divide into History-based predictor [1] and Frame-structure predictor [2-4]. The History-based predictor predicts the latter frame workload by previous frame workload to scale the voltage, and the frame-structure predictor performs offline and then determine the different kind of frame for an application. A table is used to save the mapping of different kind of frame to the voltage, and then the voltage is scaled according to the mapping table. A lot of researchers put the power management policy in software i.e. processors, but our proposed workload prediction scheme has been realized into the hardware circuit. Therefore, it can not only reduce the overhead of processor but also quickly adjust the voltage and frequency of 3D graphics accelerating engine. Our prediction policy is one of the History-based predictor ,and it is an adaptive PID predictor [5-6] in which the parameters of Proportional controller and Integral controller can be adaptively adjusted so that it can obtain more accurate prediction results than non-adaptive predictor. In general, the workload that the selected voltage can handle is usually over than the predicted workload. That is, actual workload is usually less than predicted workload. So that the slack time will be generated. We can utilize the slack time through Inter-frame compensation [7-10] to save more energy while maintaining the similar output quality. We use a simple policy to adaptively select the parameters for compensation between the frames to simplify the hardware architecture of the power management policy. Experimental results show that, we can get more energy saving and more accurate workload prediction when the adaptive PI predictor and adaptive Inter-frame compensation are utilized.

This report describes the architecture and implementation of a memory profiler for 3D graphics applications. The memory profiling is done for parts of the program which runs on the graphics processor and is responsible for rendering the image. The shaders are parsed and every memory instruction is instrumented with additional instruction for profiling. The results are then transferred from the video memory to CPU memory. Profiling is done for a frame and completes in less than three minutes. The report also describes various analyses that can be done using the results obtained from this profiler. The report discusses the design of an analytical cache model that can be used to identify candidate memory buffers suitable for caching among all the buffers used by an application. The profiler can segregate results for reads and writes separately, can handle all formats of texture access instructions and predicated instructions. / text

Στην παρούσα εργασία παρουσιάζεται η διαδικασία ανάλυσης απαιτήσεων, σχεδιασμού και υλοποίησης ενός δικτυακού τρισδιάστατου μουσείου. Παρουσιάζονται τα αποτελέσματα συνεντεύξεων με πιθανούς χρήστες, και η διαδικασία ανάλυσης των απαιτήσεων που θα έχουν από μία τέτοια εφαρμογή, η διαδικασία σχεδιασμού των υποσυστημάτων της εφαρμογής και η υλοποίηση τους. Η εφαρμογή έχει ικανοποιητική απόδοση, ενώ με τον σχεδιασμό και την υλοποίηση του συστήματος δυναμικής μεταφόρτωσης αντικειμένων, δίνει την δυνατότητα στον χρήστη να ξεκινάει την περιήγηση του στον χώρο του μουσείου ενώ ταυτόχρονα να μεταφορτώνονται τα αντικείμενα στο παρασκήνιο. Έτσι ο χρόνος αναμονής για την εκκίνηση της εφαρμογής είναι μικρός και σε εφαρμογές όπου αναμένεται ο χρήστης να κινείται αργά μέσα στον χώρο ζητώντας πληροφορίες για τα εκθέματα η περιήγηση γίνεται ομαλά, χωρίς να αντιληφθεί την διαδικασία μεταφόρτωσης. Επίσης ο σχεδιασμός της βάσης δεδομένων είναι τέτοιος ώστε να είναι επεκτάσιμος και να μπορεί να ακολουθήσει τα πρότυπα (standards) που δίνονται από διεθνείς οργανισμούς για την περιγραφή μουσειακών εκθεμάτων, ενώ είναι εύκολη η χρήση της ίδιας βάσης για την εξόρυξη της πληροφορίας σε απλή πύλη (portal). / The process of collection and analysis of requirements and the design and development of the application is presented in this project. The performance of application that is developed is considered to be satisfactory. By embedding the dynamic downloading algorithm, there is no need for prefetching of the 3D objects and that leads to very small waiting time for the application to start running. Meanwhile the 3D objects are downloaded while the user walks through the scene. In scenes like virtual museums etc where the user doesn’t walk fast from one room to the other, but stays in front of an object to get more info, the walkthrough is continuous and the downloading process isn’t noticeable by the user. Also, the database has such a design that can easily include well known standards for museum exhibits. Apart from the client application, the data stored can be retrieved from portals and thus a site edition of the virtual museum is easy to be done.

Šiame magistro darbe nagrinėjamas M3G standartas, skirtas 3D grafikai mobiliuose telefonuose, tiriamos 3D modelių eksportavimo į M3G formatą galimybės bei M3G standarto suderinamumas. Apžvelgiamos 3D modeliavimo bei eksportavimo priemonės bei pasirinkta modeliavimo priemonė Blender, įgalinanti pasiekti 3D modelio duomenis naudojant Python skriptus. Sukurta eksportavimo iš Blender modeliavimo priemonės į M3G formatą schema. Schema realizuojama suprogramavus eksportavimo priemonę vartojant Python bei Java programavimo kalbas. Eksportavimo priemonė veikia kaip papildomas įrankis Blender modeliavimo priemonėje ir gali būti iškviesta iš pagrindinio meniu. Python programavimo kalba eksportavimo priemonėje naudojama nuskaityti 3D scenos duomenis ir juos išsaugoti XML formatu. Ekportavimo priemonėje Java programavimo kalba nuskaitomas bei apdorojamas XML failas, sudaromas 3D elementų hierarchinis medis, sukuriamas M3G failas, sukuriami duomenų masyvai bei sektoriai, kuriuose saugomi 3D scenos duomenys ir į M3G failą eksportuojami 3D scenos duomenys. Eksportavimo priemonė turi galimybę įkrauti eksportuotą M3G failą į mobiliąją aplikaciją ir atidaryti ją Java emuliatoriuje – mobiliajame telefone. Eksportavimo priemonė palyginta su kitomis eksportavimo priemonėmis eksportavus skirtingus 3D modelius į M3G formatą bei palyginus gautus rezultatus pagal 3D objektų savybių bei transformacijų atitikimą pradiniam 3D modeliui, eksportavimo priemonės patikimumą bei kitus kriterijus. / In the master thesis the M3G standard for 3D graphics in mobile phones, its compatibility and possibilities of exporting 3D models to M3G format are investigated. Most popular 3D modelling and exporting to M3G format tools are analyzed. Blender was selected as main master thesis modelling tool for possibility to reach 3D model data using Python scripts. An exporting scheme from Blender to M3G format was created and realized using Python and Java programming languages. The exporter works as a plug-in for the Blender modelling tool. It can be accessed in the main Blender menu. The Python programming language in the exporter was used for extracting data from 3D scene and saving it in XML format. The Java programming language was used for reading 3D data from XML file, making hierarchical 3D elements tree, creating 3D elements tree, constructing data arrays and sectors, where 3D data arrays and sectors are kept and exporting data to M3G file. The exporter can load an exported M3G file to mobile application and show it in Java emulator – mobile phone. On the basis of several 3D models, the created exporter was compared to other exporters using the quality of performance, reliability and other criteria.

Our goal with this study is to examine how much optimization of 3D game models can affect the overall performance of a game. After a previous pilot study we decided on use a method where we worked with a 3D scene which was made earlier unconnected to this study. We created two versions of the scene in Unreal Development Kit, one with none of the meshes optimized and the second scene where the meshes are optimized. From these two scenes we wrote down the different stats: the draw calls, frame rate, millisecond per frame and visible static mesh elements as well as the memory usage. Comparing these stats from the two scenes, we found that there was a change in the stats. Draw calls and frame rate had dropped in the second scene, as well as the memory usage which made the game run more smoothly without losing much of its aesthetic quality. / Målet med vår studie var att se hur stor skillnad optimering av 3D-modeller i spel gör för att förbättra spelprestandan. Efter att ha utfört en pilotstudie beslutade vi oss för att använda en tidigare byggd 3D-scen för undersökningen i vår C-uppsats. Vi skapade två versioner av scenen i Unreal Development Kit, en där inga modeller var optimerade och den andra där vi optimerat modellerna. Vi skrev därefter ner statistik från de olika scenerna, nämligen draw calls, frame rate, millisecond per frame och visible static mesh elements liksom minnesanvändning. Efter att ha jämfört resultaten såg vi att det fanns en väsentlig skillnad mellan scenerna prestandamässigt. Både draw calls, frame rate och minnesanvändningen hade minskat efter optimeringen vilket ledde till att spelet kördes smidigare.

Nowadays the World Wide Web increasingly provides rich multimedia contents to its users.In order to further enhance the experience of web-users, researchers have sought solutions to integrate yet another modality into the web experience by augmenting web content with haptic properties. In those applications, users are able to interact with web virtual environments (such as games and e-learning systems) enriched with haptic contents. However, it is not easy for designers without pro cient web programming background and basic knowledge regarding haptics, to develop a web application with haptic content enabled. Additionally, there is currently no standard to describe and reuse a well-described haptic application which can be played in web browsers. In this thesis, I present an MPEG-V based authoring tool for facilitating the development procedure of haptics-enabled web applications. The system provides an interface for users to create their own application, add custom 3D models, and modify their graphic and haptic properties. Haptic properties include the speci cation of collision detection mechanism and object surface properties which in turn directly a ect the force simulations. Finally, the user is able to export a haptic-enabled 3D scene in a standard MPEG-V format which can be reconstructed in a web haptic player. A detailed experiment is conducted to evaluate the force simulations, application development process and design of user interface. The results not only verify my proposed methodology, but also show the high acceptance level by users with all levels of programming knowledge of the system.

Στα πλαίσια αυτής της διπλωματικής αναπτύχθηκε ένα σύνολο συναρτήσεων και κλάσεων το οποίο αποσκοπεί στην διευκόλυνση της συγγραφής προγραμμάτων τρισδιάστατων γραφικών. Σκοπός είναι η δημιουργία ενός API το οποίο να μην απαιτεί από τον χρήστη – προγραμματιστή βαθειά γνώση των τρισδιάστατων γραφικών αλλά μόνο ορισμένες θεμελιώδεις έννοιες και μια επιφανειακή γνώση του OpenGL προκειμένου να στήσει και να σχεδιάσει μια τρισδιάστατη σκηνή γρήγορα και εύκολα. Παράλληλα μπορεί να φανεί χρήσιμο εργαλείο και στον έμπειρο προγραμματιστή ο οποίος χρειάζεται ένα περιβάλλον που να τον απαλλάσσει από τετριμμένες και επαναλαμβανόμενες διαδικασίες που αποτελούν τροχοπέδη στην μελέτη και ανάπτυξη νέων αλγορίθμων και τεχνικών. Όλα αυτά έχουν γίνει με κύριο γνώμονα την αποδοτική σχεδίαση και την απόρριψη μη ορατής γεωμετρίας έτσι ώστε να είναι δυνατή η σχεδίαση πολυπλοκότερων σκηνών. / -

De plus en plus de contenus 3D interactifs sont disponibles sur la toile. Visualiser et manipuler ces contenus 3D en temps réel, de façon naturelle et intuitive, devient donc une nécessité. Les applications visées sont nombreuses : le e-commerce, l'éducation et la formation en ligne, la conception, ou l'architecture dans le contexte par exemple de musées virtuels ou de communautés virtuelles. L'utilisation de contenus 3D en ligne ne propose pas de remplacer les contenus traditionnels, tels que les textes, les images ou les vidéos, mais plutôt d'utiliser la 3D en complément, pour enrichir ces contenus. La toile est désormais une plate-forme où les contenus hypertexte, hypermédia, et 3D sont simultanément disponibles pour les utilisateurs. Cette utilisation des contenus 3D pose cependant deux questions principales. Tout d'abord, les interactions 3D sont souvent lourdes puisqu'elles comprennent de nombreux degrés de liberté; la navigation dans les contenus 3D peut s'en trouver inefficace et lente. Nous abordons ce problème en proposant un nouveau paradigme basé sur l'analyse des interactions (crowdsourcing). En analysant les interactions d'utilisateurs 3D, nous identifions des régions d'intérêt (ROI), et générons des recommandations pour les utilisateurs suivants. Ces recommandations permettent à la fois de réduire le temps d'interaction pour identifier une ROI d'un objet 3D et également de simplifier les interactions 3D nécessaires. De plus, les scènes ou objets 3D contiennent une information visuelle riche. Les sites Web traditionnels contiennent, eux, principalement des informations descriptives (textuelles) ainsi que des hyperliens pour permettre la navigation. Des sites contenants d'une part de l'information textuelle, et d'autre part de l'information 3D peuvent s'avérer difficile à appréhender pour les utilisateurs. Pour permettre une navigation cohérente entre les informations 3D et textuelles, nous proposons d'utiliser le crowdsourcing pour la construction d'associations sémantiques entre le texte et la visualisation en 3D. Les liens produits sont proposés aux utilisateurs suivants pour naviguer facilement vers un point de vue d'un objet 3D associé à un contenu textuel. Nous évaluons ces deux méthodes par des études expérimentales. Les évaluations montrent que les recommandations réduisent le temps d'interaction 3D. En outre, les utilisateurs apprécient l'association sémantique proposée, c'est-à-dire, une majorité d'utilisateurs indique que les recommandations ont été utiles pour eux, et préfèrent la navigation en 3D proposée qui consiste à utiliser les liens sémantiques ainsi que la souris par rapport à des interactions utilisant seulement la souris. / Recent years have seen the development of interactive 3D graphics on the Web. The ability to visualize and manipulate 3D content in real time seems to be the next evolution of the Web for a wide number of application areas such as e-commerce, education and training, architecture design, virtual museums and virtual communities. The use of online 3D graphics in these application domains does not mean to substitute traditional web content of texts, images and videos, but rather acts as a complement for it. The Web is now a platform where hypertext, hypermedia, and 3D graphics are simultaneously available to users. This use of online 3D graphics, however, poses two main issues. First, since 3D interactions are cumbersome as they provide numerous degrees of freedom, 3D browsing may be inefficient. We tackle this problem by proposing a new paradigm based on crowdsourcing to ease online 3D interactions, that consists of analyzing 3D user interactions to identify Regions of Interest (ROIs), and generating recommendations to subsequent users. The recommendations both reduce 3D browsing time and simplify 3D interactions. Second, 3D graphics contain purely rich visual information of the concepts. On the other hand, traditional websites mainly contain descriptive information (text) with hyperlinks as navigation means. The problem is that viewing and interacting with the websites that use two very different mediums (hypertext and 3D graphics) may be complicated for users. To address this issue, we propose to use crowdsourcing for building semantic associations between texts and 3D visualizations. The produced links are suggested to upcoming users so that they can readily locate 3D visualization associated with a textual content. We evaluate the proposed methods with experimental user studies. The evaluations show that the recommendations reduce 3D interaction time. Moreover, the results from the user study showed that our proposed semantic association is appreciated by users, that is, a majority of users assess that recommendations were helpful for them, and browsing 3D objects using both mouse interactions and the proposed links is preferred compared to having only mouse interactions.

The purpose of this thesis is to find ways to make the extent and constant movement in the blogosphere visible. An application has been developed using C# and OpenGL. The application is an interactive screensaver to be run on the Windows platform. It visualizes data combining 3D and 2D elements. Geographical data is rendered using a model of the Earth, where the blog posts are constantly updated. Various statistics are displayed to give information on the current state of the blogosphere.