Die "Mitteilungen des URZ" informieren die Nutzer des Universitätsrechenzentrums der TU Chemnitz umfassend über neue Dienste und Projekte, vermitteln ggf. Hintergrundwissen und dienen der Berichterstattung.

Les systèmes embarqués sont de plus en plus intégrés dans les applications temps réel actuelles. Ils sont généralement constitués de composants matériels et logiciels profondément Intégrés mais hétérogènes. Ces composants sont développés sous des contraintes très strictes. En conséquence, le travail des ingénieurs de conception est devenu plus difficile. Pour répondre aux normes de haute qualité dans les systèmes embarqués de nos jours et pour satisfaire aux besoins quotidiens de l'industrie, l'automatisation du processus de développement de ces systèmes prend de plus en plus d'ampleur. Un défi majeur est de développer une approche automatisée qui peut être utilisée pour la vérification intégrée et la validation de systèmes complexes et hétérogènes.Dans le cadre de cette thèse, nous proposons une nouvelle approche compositionnelle pour la modélisation et la vérification des systèmes complexes décrits en langage SystemC. Cette approche est basée sur le modèle des SystemC Waiting State Automata (WSA). Les SystemC Waiting State Automata sont des automates permettant de modéliser le comportement abstrait des systèmes matériels et logiciels décrits en SystemC tout en préservant la sémantique de l'ordonnanceur SystemC au niveau des cycles temporels et au niveau des delta-cycles. Ce modèle permet de réduire la complexité de la modélisation des systèmes complexes due au problème de l'explosion combinatoire tout en restant fidèle au système initial. Ce modèle est compositionnel et supporte le rafinement. De plus, il est étendu par des paramètres temps ainsi que des compteurs afin de prendre en compte les aspects relatifs à la temporalité et aux propriétés fonctionnelles comme notamment la qualité de service. Nous proposons ensuite une chaîne de construction automatique des WSAs à partir de la description SystemC. Cette construction repose sur l'exécution symbolique et l'abstraction des prédicats. Nous proposons un ensemble d'algorithmes de composition et de réduction de ces automates afin de pouvoir étudier, analyser et vérifier les comportements concurrents des systèmes décrits ainsi que les échanges de données entre les différents composants. Nous proposons enfin d'appliquer notre approche dans le cadre de la modélisation et la simulation des systèmes complexes. Ensuite l'expérimenter pour donner une estimation du pire temps d'exécution (worst-case execution time (WCET)) en utilisant le modèle du Timed SystemC WSA. Enfin, on définit l'application des techniques du model checking pour prouver la correction de l'analyse abstraite de notre approche. / Embedded systems are increasingly integrated into existing real-time applications. They are usually composed of deeply integrated but heterogeneous hardware and software components. These components are developed under strict constraints. Accordingly, the work of design engineers became more tricky and challenging. To meet the high quality standards in nowadays embedded systems and to satisfy the rising industrial demands, the automatization of the developing process of those systems is gaining more and more importance. A major challenge is to develop an automated approach that can be used for the integrated verification and validation of complex and heterogeneous HW/SW systems.In this thesis, we propose a new compositional approach to model and verify hardware and software written in SystemC language. This approach is based on the SystemC Waiting State Automata (WSA). The SystemC Waiting State Automata are used to model the abstract behavior of hardware or software systems described in SystemC. They preserve the semantics of the SystemC scheduler at the temporal and the delta-cycle level. This model allows to reduce the complexity of the modeling process of complex systems due to the problem of state explosion during modeling while remaining faithful to the original system. The SystemC waiting state automaton is also compositional and supports refinement. In addition, this model is extended with parameters such as time and counters in order to take into account further aspects like temporality and other extra-functional properties such as QoS.In this thesis, we propose a stepwise approach on how to automatically extract the SystemC WSAs from SystemC descriptions. This construction is based on symbolic execution together with predicate abstraction. We propose a set of algorithms to symbolically compose and reduce the SystemC WSAs in order to study, analyze and verify concurrent behavior of systems as well as the data exchange between various components. We then propose to use the SystemC WSA to model and simulate hardware and software systems, and to compute the worst cas execution time (WCET) using the Timed SystemC WSA. Finally, we define how to apply model checking techniques to prove the correctness of the abstract analysis.

The Master's thesis Transformation of the microprocessor's description language to the hardware description language is aimed at design of application specific microprocessors with using ISAC language. It deals with design and implementation of transformation which converts description of microprocessor in ISAC language into equivalent description in VHDL language. The chapter Summary of research problems describes chosen problems, showing up some notions connected with problems and presents suggestion of transformation mentioned above. The chapter Suggestion of solution presents new extension of ISAC language. There is also described the way of design solution of transformation and solution of implementation of VHDL generator which performs transformation. Conclusion of thesis discusses next points of future work reached results.

Today’s embedded systems depend on the availability of hybrid platforms, that contain heterogeneous computing resources such as programmable processors units (CPU’s or DSP’s) and highly specialized hardware cores. These platforms have been scaled down to integrated embedded system-on-chip. Modern platform FPGAs enhance such systems by the flexibility of runtime configurable silicon. One of the major advantages that arises is the ability to use hardware (HW) and software (SW) resources in a time-shared manner. Though the ability to dynamically assign computing resources based on decisions taken at runtime is given.

The Convolutional Neural Networks are getting more and more popular due to their applications in revolutionary technologies like Autonomous Driving, Biomedical Imaging, and Natural Language Processing. With this increase in adoption, the complexity of underlying algorithms is also increasing. This trend entails implications for the computation platforms as well, i.e. GPUs, FPGA, or ASIC based accelerators, especially for the Address Generation Unit (AGU), which is responsible for the memory access. Existing accelerators typically have Parametrizable Datapath AGUs, which have minimal adaptability towards evolution in algorithms. Hence new hardware is required for new algorithms, which is a very inefficient approach in terms of time, resources, and reusability. In this research, six algorithms with different implications for hardware are evaluated for address generation, and a fully Programmable AGU (PAGU) is presented, which can adapt to these algorithms. These algorithms are Standard, Strided, Dilated, Upsampled and Padded convolution, and MaxPooling. The proposed AGU architecture is a Very Long Instruction Word based Application Specific Instruction Processor which has specialized components like hardware counters and zero-overhead loops and a powerful Instruction Set Architecture (ISA), which can model static and dynamic constraints and affine and non-affine Address Equations. The target has been to minimize the flexibility vs. area, power, and performance trade-off. For a working test network of Semantic Segmentation, results have shown that PAGU shows close to the ideal performance, one cycle per address, for all the algorithms under consideration excepts Upsampled Convolution for which it is 1.7 cycles per address. The area of PAGU is approx. 4.6 times larger than the Parametrizable Datapath approach, which is still reasonable considering the high flexibility benefits. The potential of PAGU is not just limited to neural network applications but also in more general digital signal processing areas, which can be explored in the future. / Convolutional Neural Networks blir mer och mer populära på grund av deras applikationer inom revolutionerande tekniker som autonom körning, biomedicinsk bildbehandling och naturligt språkbearbetning. Med denna ökning av antagandet ökar också komplexiteten hos underliggande algoritmer. Detta medför implikationer för beräkningsplattformarna såväl som GPU: er, FPGAeller ASIC-baserade acceleratorer, särskilt för Adressgenerationsenheten (AGU) som är ansvarig för minnesåtkomst. Befintliga acceleratorer har normalt Parametrizable Datapath AGU: er som har mycket begränsad anpassningsförmåga till utveckling i algoritmer. Därför krävs ny hårdvara för nya algoritmer, vilket är en mycket ineffektiv metod när det gäller tid, resurser och återanvändbarhet. I denna forskning utvärderas sex algoritmer med olika implikationer för hårdvara för adressgenerering och en helt programmerbar AGU (PAGU) presenteras som kan anpassa sig till dessa algoritmer. Dessa algoritmer är Standard, Strided, Dilated, Upsampled och Padded convolution och MaxPooling. Den föreslagna AGU-arkitekturen är en Very Long Instruction Word-baserad applikationsspecifik instruktionsprocessor som har specialiserade komponenter som hårdvara räknare och noll-overhead-slingor och en kraftfull Instruktionsuppsättning Arkitektur (ISA) som kan modellera statiska och dynamiska begränsningar och affinera och icke-affinerad adress ekvationer. Målet har varit att minimera flexibiliteten kontra avvägning av område, kraft och prestanda. För ett fungerande testnätverk av semantisk segmentering har resultaten visat att PAGU visar nära den perfekta prestanda, 1 cykel per adress, för alla algoritmer som beaktas undantar Upsampled Convolution för vilken det är 1,7 cykler per adress. Området för PAGU är ungefär 4,6 gånger större än Parametrizable Datapath-metoden, vilket fortfarande är rimligt med tanke på de stora flexibilitetsfördelarna. Potentialen för PAGU är inte bara begränsad till neurala nätverksapplikationer utan också i mer allmänna digitala signalbehandlingsområden som kan utforskas i framtiden.

Die Schriftenreihe informiert über die Entwicklung eines CMOS-Sensors mit OLED-Mikrodisplay für die Düngungsoptimierung bei Zierpflanzen. Die Grundannahme, dass sich der Ernährungszustand einer Pflanze in einem hochaufgelösten Bild bzw. Scan ihrer Blätter mit unterschiedlichen Lichtfarben frühzeitig erkennen lässt, konnte weder bestätigt noch widerlegt werden. Es wurden Grundlagen für weitere Forschungsarbeiten gelegt. Die Veröffentlichung richtet sich an Praktiker, Bildung, Forschung & Entwicklung. Redaktionsschluss: 21.11.2023

This research project reports on an empirical study on the suitability and feasibility of audio cassette lectures in solving the study problems of adult distance education students. Having reviewed relevant literature on the subject the researcher collected data through: (a) Empirical investigation by contituting a two-group (experimental/control) design. (b) Questionnaires to find out opinions of students on audio cassettes. The study reveals that there is a significnt difference between the academic achievement of students who study via audio cassette lectures in addition to textbooks and face-to-face lectures and those who study through textbooks and face-to-face lectures only. The study therefore validates audio cassette lectures in an integrated study package. Other outcomes of the study are: (a) Suggestions to l.E.M.S. authorities to introduce audio cassette lectures on l.E.M.S. part-time courses. (b) Suggestions to course organisers at 1.E.M.S. to liaise with distance education institutions to adopt their instructional strategies. / Teacher Education / M. Ed. (Didactics)

This research project reports on an empirical study on the suitability and feasibility of audio cassette lectures in solving the study problems of adult distance education students. Having reviewed relevant literature on the subject the researcher collected data through: (a) Empirical investigation by contituting a two-group (experimental/control) design. (b) Questionnaires to find out opinions of students on audio cassettes. The study reveals that there is a significnt difference between the academic achievement of students who study via audio cassette lectures in addition to textbooks and face-to-face lectures and those who study through textbooks and face-to-face lectures only. The study therefore validates audio cassette lectures in an integrated study package. Other outcomes of the study are: (a) Suggestions to l.E.M.S. authorities to introduce audio cassette lectures on l.E.M.S. part-time courses. (b) Suggestions to course organisers at 1.E.M.S. to liaise with distance education institutions to adopt their instructional strategies. / Teacher Education / M. Ed. (Didactics)