Transactional memory (TM) aims to bring the benefits of ACID transactions to the volatile world of program synchronization. Architectural trends are making software transactions more appealing, as more programmers struggle with the problems of locks as they exploit multi-core processors. This thesis applies TM, which until recently has been restricted to small benchmarks, to a large, real-life system: the Linux operating system kernel. I describe TxLinux, a version of Linux, which is the first OS to use transactional memory for synchronization. TxLinux runs on MetaTM, a simulator co-designed with TxLinux, which models an x86-based Hardware Transactional Memory (HTM) system. The TxLinux/MetaTM effort yields a characterization of real-life OS transactions, exposes previously unconsidered complications (including interaction with interrupts and stack memory) and allows sensitivity studies of various TM microarchitectural parameters. It also provides a flexible platform for future OS, TM and architecture research. Next, I examine ways to increase concurrency by investigating the factors that inhibit concurrency in existing TM models and systems. These include avoidable implementation limitations, overly restrictive serialization models, and inexpressive APIs. After examining the nature of each limitation, I propose a solution for each one. I postulate that the conventional wisdom that every transaction is "for itself" and primarily relates to other transactions by conflicting with them, is a pervasive misperception. This thesis aims to demonstrate that there are other ways of thinking about the relation of one transaction to another. I present three different transaction models to show how (i) co-existence, (ii) cooperation, and (iii) coordination, can each solve important problems facing TM programmers today. Co-existence of multiple transactions on the same processor is enabled using the suspended transactions model. This model, used by TxLinux, can reduce aborts and removes transaction length limitations imposed by interrupts. Cooperation of transactions that access the same data, using the dependence-aware transactions model, can transparently turn transaction aborts into commits. Drawing on serializability theory and notions of spheres of control (which predate ACID transactions), this model is able to accept more execution schedules than any existing TM design. Lastly, the coordination of multiple transactions in the coordinated sibling transactions model, provides programmers a simple and unified way of expressing intratransaction parallelism. This helps move transactions beyond being a drop-in replacement for locks (SLE-style) to instead helping programmers find more parallel work within their programs (both in speculative and non-speculative forms). All three models aim at increasing concurrency, while shifting complexity away from the programmer and into the TM system. I evaluate all three models, using either the MetaTM HTM, or one of the several software (STM) systems this thesis also develops. / text

Αντικείμενο της παρούσας μεταπτυχιακής εργασίας είναι ο σχεδιασμός και η ανάπτυξη συστήματος κατανεμημένης διαμοιραζόμενης μνήμης ως τμήμα της αρχιτεκτονικής πολυεπεξεργαστικού συστήματος SiScape. Λόγω των ιδιαιτεροτήτων της αρχιτεκτονικής αυτής, το σύστημα μνήμης της και συγκεκριμένα η κρυφή μνήμη δευτέρου επιπέδου που καθιστά δυνατή τη λειτουργία του, κρίθηκε απαραίτητο να σχεδιαστεί και να αναπτυχθεί από το μηδέν, προκειμένου να ανταποκριθεί στις απαιτήσεις της. Ο σχεδιασμός της κρυφής μνήμης δευτέρου επιπέδου περιγράφηκε στη γλώσσα περιγραφής υλικού VHDL. / The purpose of this master thesis is the design and development of a shared distributed memory system as part of the multiprocessor architecture SiScape. Because of the architecture's irregular structure, it was imperative that the memory system and particularly the second level cache that enables its functionality, was designed from scratch, to fill all of its requirements. The design of the second level cache was described using the VHDL hardware description language.

No description available.

No description available.

This thesis investigates the origin of spontaneous activity in the uterus. This organ does not show any activity until shortly before delivery, where fast and efficient contractions are generated. The aim of this work is to provide insight into the origin of spontaneous oscillations and into the transition from asynchronous to synchronized activity in the pregnant uterus. One intriguing aspect in the uterus is the absence of any pacemaker cell. The organ is composed of muscular cells, which are excitable, and connective cells, whose behavior is purely passive; None of these cells, taken in isolation, spontaneously oscillates. We develop an hypothesis based on the observed strong increase in the electrical coupling between cells in the last days of pregnancy. The study is based on a mathematical model of excitable cells, coupled to each other on a regular lattice, and to a fluctuating number of passive cells, consistent with the known structure of the uterus. The two parameters of the model, the coupling between excitable cells, and between excitable and passive cells, grow during pregnancy.Using both a model based on measured electrophysiological properties, and a generic model of excitable cell, we demonstrate that spontaneous oscillations can appear when increasing the coupling coefficients, ultimately leading to coherent oscillations over the entire tissue. We study the transition towards a coherent regime, both numerically and semi-analytically, using the simple model of excitable cells. Last, we demonstrate that, the realistic model reproduces irregular action potential propagation patterns as well as the bursting behavior, observed in the in-vitro experiments.

Darbe nagrinėjama ryšio tinklo sinchronizacijos sistema, sudaryta iš keturių tarpusavyje sinchronizuotų generatorių. Darbo tikslas - sudaryti sinchronizacijos sistemos matematinį modelį, rasti sistemos pereinamųjų funkcijų ir generatorių virpesių fazių skirtumų tikslias analizines išraiškas, ištirti sistemos pereinamuosius procesus ir jos darbą nusistovėjusiame režime. Nagrinėjamos sistemos matematinis modelis - matricinė diferencialinė lygtis su vėluojančiu argumentu. Ši lygtis sprendžiama „žingsnių“ metodu. Tuo tikslu intervalas dalijamas į vienodo ilgio dalinius intervalus. Kiekviename daliniame intervale lygtis sprendžiama atskirai, kaip paprasta matricinė diferencialinė lygtis be vėluojančio argumento. Naudojantis gautu sprendiniu, rastos tikslios sinchronizacijos sistemos pereinamųjų funkcijų analizinės išraiškos. Remiantis šiomis išraiškomis, atliktas pereinamųjų procesų sinchronizacijos sistemoje tyrimas. / The mutual synchronization system of the communication network, composed of four oscillators, is investigated in the work. Following aims were raised in this work: to compose the mathematical model of the synchronization system, to find the exact expressions of the step responses of the system and of the phase differences of the oscillations of oscillators, to investigate the transients in the synchronization system. The mathematical model of the system is the matrix differential equation with delayed argument. This equation is solved applying the method of consequent integration (method of “steps”). For this purpose the interval is divided to subintervals of equal length. The equation in each subinterval is solved separately, as ordinary differential equation without delayed argument. Using obtained expression of the solution, the expressions of step responses of the system are got. The expressions of step responses are applied investigating the transients in the synchronization system.

There are numerous synchronization methodologies available in solving the problem of network synchronization. This paper presents an analytical analysis of the mathematical model of forced synchronization system composed of four oscillators. Exact analytical and graphical expressions of transition functions and exact expressions of the phase differences between signals of oscillators of this synchronization system are obtained.

Ultra-wideband (UWB) is a wireless system which transmits signals across a much wider frequency spectrum than traditional wireless systems. The impulse radio (IR) UWB technique uses ultra-short duration pulses of nanoseconds or less. The objective of this thesis is to provide the design, implementation and testing of the timing recovery between the transmitter and receiver of the recently emerging differential code-shifted reference (DCSR) Impulse radio (IR) ultra-wideband (UWB) system. A new non-coherent energy detection based technique and its algorithm are proposed for timing recovery by means of a phase-locked loop (PLL) circuit. Simulations are presented first to verify the proposed algorithm. Then, it is implemented and tested in the Lattice ECP2 field-programmable gate array (FPGA) evaluation board with VHDL codes (a VHSIC hardware description language). The simulation and implementation results show that the proposed timing recovery scheme can be effectively achieved without much error.

The mutual in the synchronization system is analyzed in this work. The mutual in the synchronization is a double – side synchronization of interdependent tactical oscillators. Every of interdependent oscillators has influence on the frequency of other oscillators. The frequency of all oscillators will be the same and equal to the certain medium frequency which depends upon, the frequency and distances among separate oscillators of all in the settled regime of them joined into the net. The objective of the work is to analyze the synchronization system which is joined of four interdependent oscillators. The mathematical model of synchronization system is formed, analytic expressions of transitional function and differences among phases of oscillation are set transitional processes of synchronization system and differences among phases of oscillation are researched. The mathematical model of synchronization system is matrixal rectilinear dif. Equation with the argument to be late. It is solved using the method of steps and the transformation of Laplace. Exact analytical expressions of the solution components are found using Jordan’s form of descriptive matrix which describes the structure of inherent relations among the blocks of the system analytical expressions of transitional functions in the system and differences of phases of oscillation are obtained on the basis of the solution.

This paper examines the synchronization of business cycles across the G7 countries during US recessions since the 1870s. Using a dynamic measure of correlations, results depend on the globalization period under consideration. During the 2007-2009 recession, business cycles co-movements increased to unprecedented levels. (author's abstract)