No description available.

Στη διπλωματική αυτή υλοποιήσαμε την παράλληλη αρχιτεκτονική Pisma στο περιβάλλον εξομοίωσης Simics. Η αρχιτεκτονική PiSMA αφορά τη διασύνδεση επεξεργαστών και μνημών πάνω στο ίδιο τσιπ σε μορφή σκακιέρας έτσι ώστε κάθε επεξεργαστής να είναι συνδεδεμένος με τέσσερις μνήμες και κάθε μνήμη να είναι συνδεδεμένη με τέσσερις επεξεργαστές. Αυτή η διάταξη επιτρέπει σε κάθε επεξεργαστή να επικοινωνεί άμεσα διαμέσου των μνημών με οκτώ γειτονικούς του επεξεργαστές. Η επικοινωνία με κάποιον επεξεργαστή εκτός των οκτώ γειτονικών γίνεται με τη μετάδοση μηνυμάτων μεταξύ των μνημών. Η αρχιτεκτονική Pisma είναι επεκτάσιμη σε αυθαίρετο αριθμό επεξεργαστών και μνημών και το κύριο πλεονέκτημά της εμφανίζεται σε εφαρμογές που παρουσιάζουν μεγάλη τοπικότητα καθώς έτσι τα δεδομένα μπορούν να επεξεργαστούν από περισσότερους επεξεργαστές ταυτόχρονα ενώ παράλληλα μειώνεται και το overhead της μεταφοράς των δεδομένων μέσω των μνημών. Στη διπλωματική θα δοθεί επίσης περιγραφή της σύγχρονης, αξιόπιστης και ολοκληρωμένης πλατφόρμας εξομοίωσης Simics. Συγκεκριμένα θα περιγραφούν τα εργαλεία που προσφέρει για την υλοποίηση των διάφορων εξομοιώσεων μέσω των κλάσεων που διαθέτει, ο τρόπος λειτουργίας του και ποια συστήματα έχουν εξομοιωθεί και έχουν προστεθεί στο περιβάλλον μέχρι τώρα. / In this thesis we implemented the parallel PiSMA architecture on Simics simulator. The PiSMA architecture forms an expandable toroidal grid with alternating processors and memories so that its processor is connected to four memories and each memory to four processors. This structure enables every processor to communicate through the common memories to other eight adjacent processors. The communication between remote processors is performed by message passing. PiSMA architecture is scalable to hundreds of processors. The most important advantage of this new architecture is that it can process applications that can divide in independent granules more efficiently by mapping them to as much as many processors this can be done on the grid. Simics is an efficient, instrumented, system level instruction set simulator. It implements a lot of tools and provides the user with many capabilities as much as system simulation is concerned. In this thesis an inclusive presentation of Simics simulator is given.

CONTEXT. Full-system simulators provide benefits to developers in terms of a more rapid development cycle; since development may begin prior to that of next-generation hardware being available. However, there is a distinct lack of graphics virtualization in industry-grade virtual platforms, leading to performance issues that may obfuscate the benefits virtual platforms otherwise have over execution on actual hardware. OBJECTIVES. This dissertation concerns the implementation of graphics acceleration by the means of paravirtualizing OpenGL ES 2.0 in the Simics full-system simulator. Furthermore, this study illustrates the benefits and drawbacks of paravirtualized methodology, in addition to performance analysis and comparison with the Android emulator; which likewise utilize paravirtualization to accelerate simulated graphics. METHODS. In this study, we propose a solution for paravirtualized graphics using Magic Instructions; the implementation of which is subsequently described. Additionally, three benchmarks are devised to stress key points in the developed solution; comprising areas such as inter-system communication latency and bandwidth. Additionally, the solution is evaluated based on computationally intensive applications. RESULTS. For the purpose of this study, elapsed frame times for respective benchmarks are collected and compared with four platforms; i.e. the hardware accelerated Host machine, the paravirtualized Android emulator, the software rasterized Simics- and the paravirtualized Simics platforms. CONCLUSIONS. This thesis establishes paravirtualization as a feasible method to achieve accelerated graphics in virtual platforms. The study shows graphics acceleration of up to 34 times of that of its software rasterized counterparts. Furthermore, the study establishes magic instructions as the primary bottleneck of communication latency in the devised solution. Classification: E.1.1 [Software infrastructure]: Virtual machines; K.6.4 [Graphics systems and interfaces]: Graphics processors; N.1.0 [Companies]: Intel Corporation; Keywords: Paravirtualization; Simics; / Arkitekturella simulatorer förser utvecklare med medel till snabbare utvecklingscykler genom att tillåta utveckling av mjukvara för nya plattformar innan dessa finns tillgängliga. Dessvärre finns det få lösningar för GPU-accelerering i moderna virtuella plattformar; vilket leder till prestandaproblem som kan hämma de fördelar som virtuella plattformar har över exekvering på hårdvara. Denna uppsats angår implementering av grafikaccelerering genom paravirtualisering av OpenGL ES 2.0 i systemsimulatorn Simics. Studien sammanfattar fördelar och nackdelar av paravirtualiserade metoder, med hänsyn till prestandaanalys och jämförelse med Android-emulatorn; som också nyttjar paravirtualisering för att accelerera simulerad grafik. Vi föreslår grafikaccelering genom paravirtualisering m.h.a. magiska instruktioner; vars implementation sammanfattas i uppsatsen. Vidare presenteras tre utvärderingsprov vars syfte är att påfresta nyckelpunkter i den paravirtualiserade lösningen, så som systemlatens och bandbredd i kommunikation mellan simulering och den verkliga världen. Lösningen evalueras även baserat på ett prestandakrävande utvärderingstest. För experimentet, som presenteras i denna uppsats, samlas uppdateringsfrekvens för de grafiska utvärderingstesten och jämförs med exekvering på fyra olika plattformar. Dessa plattformar omfattar ett hårdvaruaccelerat referens-system, paravirtualiserad simulering m.h.a. Android-emulator, mjukvarurastrerad Simics-simulering, och paravirtualiserad Simics-simulering. Uppsatsen fastställer paravirtualisering som en god metod för att uppnå grafikaccelering i virtuella plattformar. Studien påvisar prestandaförbättringar motsvarande 34 gånger jämförelsevis med dess mjukvarurastrerade motpart. Vidare presenterar uppsatsen magiska instruktioner som den primära flaskhalsen i den utvecklade lösningen. / <p>OFFICE eric.nilsson@intel.com +46 8 690 0734 HOME EricNNilsson@gmail.com +46 73 656 4535</p>

TSP (or Telecommunication Server Platform) is a scalable, high availability cluster operating system developed by Ericsson for use in the telecommunications industry. This thesis describes an attempt to simulate a TSP cluster in the full system simulator Simics, and talks about some of the possibilities offered by such a setup and full system simulation in general. This attempt to simulate TSP was unsuccessful in completely booting the cluster in Simics, but some of the experiences and problems encountered are described. A proposed development environment for working with TSP in Simics is also presented, along with scripts that were created during this thesis to alleviate the working process. / TSP (eller Telecommunication Server Platform) är en skalbar, högt tillgängligt kluster-operativsystem utvecklat av Ericsson för användning inom telekommunikationsindustrin. Den här rapporten beskriver ett försök att simulera TSP-kluster i full-system simulatorn Simics, och beskriver en del av de möjligheter med detta och full-system simulering i allmänhet. Det här försöket att simulera TSP lyckades inte att fullständigt boota klustret i Simics, men några av de erfarenheter och problem som stöttes på är beskrivna. En föreslagen utvecklingsmiljö presenteras också, tillsammans med script som skapades under det här arbetet för att underlätta arbetet. / Olle Eriksson, Contact info at www.olle-eriksson.com Emil Erlandsson, Contact info at www.buglix.org

A reliable embedded real-time system has many requirements to fulfil. It must meet target deadlines in a number of situations, most of them in a situation that puts heavy stress on the system. To meet these demands, numerous tests have been created which test the hardware for any possible errors the developers might think of, in order to maximise system reliability and stability. These tests will take a lot of time to execute, and as system complexity grows, more tests are introduced leading to even longer testing times. In this thesis, a method to reduce the testing time of the software and, to a lesser extent, the hardware is examined. By using the full system simulator Simics, an existing industry system from ABB was integrated and tests were performed. A proof of concept test suite for automatic redundancy tests was also implemented. By looking at the test results, it was concluded that the method shows promise. However, problems with the average latency and performance troubles with Simics shows that more work must be put into this research before the system can be run at full speed.

This thesis is a comparative study of three computer system simulators. These computer programs are commonly used to test the efficiency and feasibility of new computer architectures, as well for debugging and testing software. With this study, we evaluate the fundamental differences of three simulators: SimICS, SimpleScalar and ML-RSIM. A comprehensive study of simulation techniques is presented, and each evaluated simulator is classified using those premises. Quantification the performance differences using a benchmark suite is made. The results show that the most feature-rich of the simulators also seems to have the highest performance in the group.