L'architecture TSAR (Tera-Scale ARchitecture) développée conjointement par BULL, le Lip6 et le CEA-LETI est une architecture manycore CC-NUMA extensible jusqu'à 1024 cœurs. Le protocole de cohérence de cache DHCCP dans l'architecture TSAR repose sur le principe du répertoire global distribué en utilisant la stratégie d'écriture simultanée afin de passer à l'échelle, mais cette scalabilité a un coût énergétique important que nous cherchons à réduire. Actuellement, les plus grosses entreprises dans le domaine des semi-conducteurs, comme Intel ou AMD, utilisent les protocoles MESI ou MOESI dans leurs processeurs multicoeurs. Ces types de protocoles utilisent la stratégie d'écriture différée pour réduire la forte consommation énergétique due aux écritures. Mais la complexité d'implémentation et la forte augmentation de ce trafic de cohérence quand le nombre de processeurs augmente limite le passage à l'échelle de ces protocoles au-delà de quelques dizaines de coeurs. Dans cette thèse, nous proposons un nouveau protocole de cohérence de cache utilisant une méthode hybride pour traiter les écritures dans le cache L1 privé : pour les lignes non partagées, le contrôleur de cache L1 utilise la stratégie d'écriture différée, de façon à modifier les lignes localement. Pour les lignes partagées, le contrôleur de cache L1 utilise la stratégie d'écriture immédiate pour éviter l'état de propriété exclusive sur ces lignes partagées. Cette méthode, appelée RWT pour Released Write Through, passe non seulement à l'échelle, mais réduit aussi significativement la consommation énergétique liée aux écritures. Nous avons aussi optimisé la solution actuelle pour gérer la cohérence des TLBs dans l'architecture TSAR, en termes de performance et de consommation énergétique. Enfin, nous introduisons dans cette thèse un nouveau petit cache, appelé micro-cache, entre le coeur et le cache L1, afin de réduire le nombre d'accès au cache d'instructions. / The TSAR architecture (Tera-Scale ARchitecture) developed jointly by Lip6 Bull and CEA-LETI is a CC-NUMA manycore architecture which is scalable up to 1024 cores. The DHCCP cache coherence protocol in the TSAR architecture is a global directory protocol using the write-through policy in the L1 cache for scalability purpose, but this write policy causes a high power consumption which we want to reduce. Currently the biggest semiconductors companies, such as Intel or AMD, use the MESI MOESI protocols in their multi-core processors. These protocols use the write-back policy to reduce the high power consumption due to writes. However, the complexity of implementation and the sharp increase in the coherence traffic when the number of processors increases limits the scalability of these protocols beyond a few dozen cores. In this thesis, we propose a new cache coherence protocol using a hybrid method to process write requests in the L1 private cache : for exclusive lines, the L1 cache controller chooses the write-back policy in order to modify locally the lines as well as eliminate the write traffic for exclusive lines. For shared lines, the L1 cache controller uses the write-through policy to simplify the protocol and in order to guarantee the scalability. We also optimized the current solution for the TLB coherence problem in the TSAR architecture. The new method which is called CC-TLB not only improves the performance, but also reduces the energy consumption. Finally, this thesis introduces a new micro cache between the core and the L1 cache, which allows to reduce the number of accesses to the instruction cache, in order to save energy.

No description available.

Most of the data referenced by sequential and parallel applications running in current chip multiprocessors are referenced by a single thread, i.e., private. Recent proposals leverage this observation to improve many aspects of chip multiprocessors, such as reducing coherence overhead or the access latency to distributed caches. The effectiveness of those proposals depends to a large extent on the amount of detected private data. However, the mechanisms proposed so far either do not consider either thread migration or the private use of data within different application phases, or do entail high overhead. As a result, a considerable amount of private data is not detected. In order to increase the detection of private data, this thesis proposes a TLB-based mechanism that is able to account for both thread migration and private application phases with low overhead. Classification status in the proposed TLB-based classification mechanisms is determined by the presence of the page translation stored in other core's TLBs. The classification schemes are analyzed in multilevel TLB hierarchies, for systems with both private and distributed shared last-level TLBs. This thesis introduces a page classification approach based on inspecting other core's TLBs upon every TLB miss. In particular, the proposed classification approach is based on exchange and count of tokens. Token counting on TLBs is a natural and efficient way for classifying memory pages. It does not require the use of complex and undesirable persistent requests or arbitration, since when two ormore TLBs race for accessing a page, tokens are appropriately distributed classifying the page as shared. However, TLB-based ability to classify private pages is strongly dependent on TLB size, as it relies on the presence of a page translation in the system TLBs. To overcome that, different TLB usage predictors (UP) have been proposed, which allow a page classification unaffected by TLB size. Specifically, this thesis introduces a predictor that obtains system-wide page usage information by either employing a shared last-level TLB structure (SUP) or cooperative TLBs working together (CUP). / La mayor parte de los datos referenciados por aplicaciones paralelas y secuenciales que se ejecutan enCMPs actuales son referenciadas por un único hilo, es decir, son privados. Recientemente, algunas propuestas aprovechan esta observación para mejorar muchos aspectos de los CMPs, como por ejemplo reducir el sobrecoste de la coherencia o la latencia de los accesos a cachés distribuidas. La efectividad de estas propuestas depende en gran medida de la cantidad de datos que son considerados privados. Sin embargo, los mecanismos propuestos hasta la fecha no consideran la migración de hilos de ejecución ni las fases de una aplicación. Por tanto, una cantidad considerable de datos privados no se detecta apropiadamente. Con el fin de aumentar la detección de datos privados, proponemos un mecanismo basado en las TLBs, capaz de reclasificar los datos a privado, y que detecta la migración de los hilos de ejecución sin añadir complejidad al sistema. Los mecanismos de clasificación en las TLBs se han analizado en estructuras de varios niveles, incluyendo TLBs privadas y con un último nivel de TLB compartido y distribuido. Esta tesis también presenta un mecanismo de clasificación de páginas basado en la inspección de las TLBs de otros núcleos tras cada fallo de TLB. De forma particular, el mecanismo propuesto se basa en el intercambio y el cuenteo de tokens (testigos). Contar tokens en las TLBs supone una forma natural y eficiente para la clasificación de páginas de memoria. Además, evita el uso de solicitudes persistentes o arbitraje alguno, ya que si dos o más TLBs compiten para acceder a una página, los tokens se distribuyen apropiadamente y la clasifican como compartida. Sin embargo, la habilidad de los mecanismos basados en TLB para clasificar páginas privadas depende del tamaño de las TLBs. La clasificación basada en las TLBs se basa en la presencia de una traducción en las TLBs del sistema. Para evitarlo, se han propuesto diversos predictores de uso en las TLBs (UP), los cuales permiten una clasificación independiente del tamaño de las TLBs. En concreto, esta tesis presenta un sistema mediante el que se obtiene información de uso de página a nivel de sistema con la ayuda de un nivel de TLB compartida (SUP) o mediante TLBs cooperando juntas (CUP). / La major part de les dades referenciades per aplicacions paral·leles i seqüencials que s'executen en CMPs actuals són referenciades per un sol fil, és a dir, són privades. Recentment, algunes propostes aprofiten aquesta observació per a millorar molts aspectes dels CMPs, com és reduir el sobrecost de la coherència o la latència d'accés a memòries cau distribuïdes. L'efectivitat d'aquestes propostes depen en gran mesura de la quantitat de dades detectades com a privades. No obstant això, els mecanismes proposats fins a la data no consideren la migració de fils d'execució ni les fases d'una aplicació. Per tant, una quantitat considerable de dades privades no es detecta apropiadament. A fi d'augmentar la detecció de dades privades, aquesta tesi proposa un mecanisme basat en les TLBs, capaç de reclassificar les dades com a privades, i que detecta la migració dels fils d'execució sense afegir complexitat al sistema. Els mecanismes de classificació en les TLBs s'han analitzat en estructures de diversos nivells, incloent-hi sistemes amb TLBs d'últimnivell compartides i distribuïdes. Aquesta tesi presenta un mecanisme de classificació de pàgines basat en inspeccionar les TLBs d'altres nuclis després de cada fallada de TLB. Concretament, el mecanisme proposat es basa en l'intercanvi i el compte de tokens. Comptar tokens en les TLBs suposa una forma natural i eficient per a la classificació de pàgines de memòria. A més, evita l'ús de sol·licituds persistents o arbitratge, ja que si dues o més TLBs competeixen per a accedir a una pàgina, els tokens es distribueixen apropiadament i la classifiquen com a compartida. No obstant això, l'habilitat dels mecanismes basats en TLB per a classificar pàgines privades depenen de la grandària de les TLBs. La classificació basada en les TLBs resta en la presència d'una traducció en les TLBs del sistema. Per a evitar-ho, s'han proposat diversos predictors d'ús en les TLBs (UP), els quals permeten una classificació independent de la grandària de les TLBs. Específicament, aquesta tesi introdueix un predictor que obté informació d'ús de la pàgina a escala de sistema mitjançant un nivell de TLB compartida (SUP) or mitjançant TLBs cooperant juntes (CUP). / Esteve García, A. (2017). Design of Efficient TLB-based Data Classification Mechanisms in Chip Multiprocessors [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/86136

Datorspel behöver utnyttja hårdvara effektivt för att kunna vara tillgänglig på så många system som möjligt med varierande kapacitet. En viktig del i detta är att optimera användandet av processorns cacheminnen. Programmerare kan följa en dataorienterad design för att implementera cacheeffektiv kod. Detta förutsätter att programmeraren har kontroll över hur data lagras i minnet, vilket är svårt att uppnå i Java. Project Valhalla kan erbjuda funktioner för att åtgärda detta problem. I detta arbete jämfördes objektorienterad design med dataorienterad design i språken C++, Java och den pågående utvecklingen av Project Valhalla. En prototyp utvecklades och implementerades med olika kombinationer av dessa språk och designer. För varje implementation mättes prestanda och cacheeffektivitet. Resultatet visade att Java med Project Valhalla kan uppnå liknande prestanda som C++ vid dataorienterade implementationer. På grund av vissa begränsningar i Valhallas funktioner kommer det troligtvis inte bli ett praktiskt alternativ till lågnivåspråk inom en snar framtid. / Computer games need to utilize hardware efficiently in order to be available on as many systems as possible with varying capabilities. An important part of this is to optimize the use of the CPU’s cache. A programmer can follow a data-oriented design to implement cache-efficient code. This requires the programmer to have control over how data is stored in memory, which is difficult to achieve in Java. Project Valhalla may offer features to address this issue. In this thesis, object-oriented design was compared with data-oriented design in the languages C++, Java, and the ongoing development of Project Valhalla. A prototype was developed and implemented using different combinations of these languages and designs. For each implementation, performance and cache efficiency were measured. The result showed that Java with Project Valhalla can achieve similar performance to C++ in data-oriented implementations. Due to some limitations in Valhalla's features, it is unlikely that it will become a suitable alternative to low-level languages anytime soon.

Performance monitoring counters are implemented in most recent microprocessors. In this thesis, we describe various performance measurement experiments for a program and a system that we conducted on a Linux operating system using the Pentium performance counters. We carried out our performance measurements on a Pentium II microprocessor. The Pentium II performance counters can be configured to count events such as cache misses, TLB misses, instructions executed etc. We used a low intrusive overhead technique to access these performance counters. We used these performance counters to measure the cache miss overheads due to context switches in Linux system. Our methodology involves sampling the hardware counters every 50ps. The sampling was set up using signals related to interval timers. We describe an analytical cache performance model under multiprogrammed condition from the literature and validate it using the performance monitoring counters. We next explores the long term performance of a system under different workload conditions. Various performance monitoring events - data cache h, data TLB misses, data cache reads or writes, branches etc. - are monitored over a 24 hour period. This is useful in identifying activities which cause loss of system performance. We used timer interrupts for sampling the performance counters. We develop a profiling methodology to give a perspective of performance of the different functions of a program, not only on the basis of execution-time but also on the data cache misses. Available tools like prof on Unix can be used to pinpoint the regions of performance loss of programs, but they mainly rely on an execution-time profiles. This does not give insight into problems in cache performance for that program. So we develop this methodology to get the performance of each function of the program not only on the basis of its execution time but also on the basis of its cache behavior.

As threads de aplicações paralelas cooperam a fim de cumprir suas tarefas, dessa forma, comunicação é realizada entre elas. A latência de comunicação entre os núcleos em arquiteturas multiprocessadas diferem dependendo da hierarquia de memória e das interconexões. Com o aumento do número de núcleos por chip e número de threads por núcleo, esta diferença entre as latências de comunicação está aumentando. Portanto, é importante mapear as threads de aplicações paralelas levando em conta a comunicação entre elas. Em aplicações paralelas baseadas no paradigma de memória compartilhada, a comunicação é implícita e ocorre através de acessos à variáveis compartilhadas, o que torna difícil a descoberta do padrão de comunicação entre as threads. Mecanismos tradicionais usam simulação para monitorar os acessos à memória realizados pela aplicação, requerendo modificações no código fonte e aumentando drasticamente a sobrecarga. Nesta dissertação de mestrado, são introduzidos dois mecanismos inovadores com uma baixa sobrecarga para se detectar o padrão de comunicação entre threads. O primeiro mecanismo faz uso de informações sobre linhas compartilhadas de caches providas por protocolos de coerência de cache. O segundo mecanismo utiliza a Translation Lookaside Buffer (TLB) para detectar quais páginas de memória cada núcleo está acessando. Ambos os mecanismos dependem totalmente do hardware, o que torna o mapeamento de threads transparente aos programadores e permite que ele seja realizado dinamicamente pelo sistema operacional. Além disto, nenhuma tarefa de alta sobrecarga, como simulação, é requerida. As propostas foram avaliadas com o NAS Parallel Benchmarks (NPB), obtendo representações precisas dos padrões de comunicação. Mapeamentos para as threads foram gerados utilizando os padrões de comunicação descobertos e um algoritmo de mapeamento. O problema do mapeamento é NP-Difícil. Portanto, de forma a se atingir uma complexidade polinomial, o algoritmo empregado é heurístico, baseado no algoritmo de emparelhamento de grafos de Edmonds. Executando as aplicações com o mapeamento resultou em um ganho de desempenho de até 15; 3%. O número de faltas na cache, invalidações em linhas de cache e transações de espionagem foram reduzidos em até 31; 9%, 41% e 65; 4%, respectivamente. / The threads of parallel applications cooperate in order to fulfill their tasks, thereby communication is performed among themselves. The communication latency between the cores in a multiprocessor architecture differs depending on the memory hierarchy and the interconnections. With the increase in the number of cores per chip and the number of threads per core, this difference between the communication latencies is increasing. Therefore, it is important to map the threads of parallel applications taking into account the communication between them. In parallel applications based on the shared memory paradigm, the communication is implicit and occurs through accesses to shared variables, which makes difficult to detect the communication pattern between the threads. Traditional approaches use simulation to monitor the memory accesses performed by the application, requiring modifications to the source code and drastically increasing the overhead. In this master thesis, we introduce two novel light-weight mechanisms to find the communication pattern of threads. The first mechanism makes use of the information about shared cache lines provided by cache coherence protocols. The second mechanism makes use of the Translation Lookaside Buffer (TLB) to detect which memory pages each core is accessing. Both our mechanisms rely entirely on hardware features, which makes the thread mapping transparent to the programmer and allows it to be performed dynamically by the operating system. Moreover, no time consuming task, such as simulation, is required. We evaluated our mechanisms with the NAS Parallel Benchmarks (NPB) and obtained accurate representations of the communication patterns. We generated thread mappings from the detected communication patterns using a mapping algorithm. Mapping is a NP-Hard problem. Therefore, in order to achieve a polynomial complexity, we designed a heuristic method based on the Edmonds graph matching algorithm. Running the applications with these mappings resulted in performance improvements of up to 15.3% compared to the original scheduler of the operating system. The number of cache misses, cache line invalidations and snoop transactions were reduced by up to 31.9%, 41% and 65.4%, respectively.

As threads de aplicações paralelas cooperam a fim de cumprir suas tarefas, dessa forma, comunicação é realizada entre elas. A latência de comunicação entre os núcleos em arquiteturas multiprocessadas diferem dependendo da hierarquia de memória e das interconexões. Com o aumento do número de núcleos por chip e número de threads por núcleo, esta diferença entre as latências de comunicação está aumentando. Portanto, é importante mapear as threads de aplicações paralelas levando em conta a comunicação entre elas. Em aplicações paralelas baseadas no paradigma de memória compartilhada, a comunicação é implícita e ocorre através de acessos à variáveis compartilhadas, o que torna difícil a descoberta do padrão de comunicação entre as threads. Mecanismos tradicionais usam simulação para monitorar os acessos à memória realizados pela aplicação, requerendo modificações no código fonte e aumentando drasticamente a sobrecarga. Nesta dissertação de mestrado, são introduzidos dois mecanismos inovadores com uma baixa sobrecarga para se detectar o padrão de comunicação entre threads. O primeiro mecanismo faz uso de informações sobre linhas compartilhadas de caches providas por protocolos de coerência de cache. O segundo mecanismo utiliza a Translation Lookaside Buffer (TLB) para detectar quais páginas de memória cada núcleo está acessando. Ambos os mecanismos dependem totalmente do hardware, o que torna o mapeamento de threads transparente aos programadores e permite que ele seja realizado dinamicamente pelo sistema operacional. Além disto, nenhuma tarefa de alta sobrecarga, como simulação, é requerida. As propostas foram avaliadas com o NAS Parallel Benchmarks (NPB), obtendo representações precisas dos padrões de comunicação. Mapeamentos para as threads foram gerados utilizando os padrões de comunicação descobertos e um algoritmo de mapeamento. O problema do mapeamento é NP-Difícil. Portanto, de forma a se atingir uma complexidade polinomial, o algoritmo empregado é heurístico, baseado no algoritmo de emparelhamento de grafos de Edmonds. Executando as aplicações com o mapeamento resultou em um ganho de desempenho de até 15; 3%. O número de faltas na cache, invalidações em linhas de cache e transações de espionagem foram reduzidos em até 31; 9%, 41% e 65; 4%, respectivamente. / The threads of parallel applications cooperate in order to fulfill their tasks, thereby communication is performed among themselves. The communication latency between the cores in a multiprocessor architecture differs depending on the memory hierarchy and the interconnections. With the increase in the number of cores per chip and the number of threads per core, this difference between the communication latencies is increasing. Therefore, it is important to map the threads of parallel applications taking into account the communication between them. In parallel applications based on the shared memory paradigm, the communication is implicit and occurs through accesses to shared variables, which makes difficult to detect the communication pattern between the threads. Traditional approaches use simulation to monitor the memory accesses performed by the application, requiring modifications to the source code and drastically increasing the overhead. In this master thesis, we introduce two novel light-weight mechanisms to find the communication pattern of threads. The first mechanism makes use of the information about shared cache lines provided by cache coherence protocols. The second mechanism makes use of the Translation Lookaside Buffer (TLB) to detect which memory pages each core is accessing. Both our mechanisms rely entirely on hardware features, which makes the thread mapping transparent to the programmer and allows it to be performed dynamically by the operating system. Moreover, no time consuming task, such as simulation, is required. We evaluated our mechanisms with the NAS Parallel Benchmarks (NPB) and obtained accurate representations of the communication patterns. We generated thread mappings from the detected communication patterns using a mapping algorithm. Mapping is a NP-Hard problem. Therefore, in order to achieve a polynomial complexity, we designed a heuristic method based on the Edmonds graph matching algorithm. Running the applications with these mappings resulted in performance improvements of up to 15.3% compared to the original scheduler of the operating system. The number of cache misses, cache line invalidations and snoop transactions were reduced by up to 31.9%, 41% and 65.4%, respectively.

As threads de aplicações paralelas cooperam a fim de cumprir suas tarefas, dessa forma, comunicação é realizada entre elas. A latência de comunicação entre os núcleos em arquiteturas multiprocessadas diferem dependendo da hierarquia de memória e das interconexões. Com o aumento do número de núcleos por chip e número de threads por núcleo, esta diferença entre as latências de comunicação está aumentando. Portanto, é importante mapear as threads de aplicações paralelas levando em conta a comunicação entre elas. Em aplicações paralelas baseadas no paradigma de memória compartilhada, a comunicação é implícita e ocorre através de acessos à variáveis compartilhadas, o que torna difícil a descoberta do padrão de comunicação entre as threads. Mecanismos tradicionais usam simulação para monitorar os acessos à memória realizados pela aplicação, requerendo modificações no código fonte e aumentando drasticamente a sobrecarga. Nesta dissertação de mestrado, são introduzidos dois mecanismos inovadores com uma baixa sobrecarga para se detectar o padrão de comunicação entre threads. O primeiro mecanismo faz uso de informações sobre linhas compartilhadas de caches providas por protocolos de coerência de cache. O segundo mecanismo utiliza a Translation Lookaside Buffer (TLB) para detectar quais páginas de memória cada núcleo está acessando. Ambos os mecanismos dependem totalmente do hardware, o que torna o mapeamento de threads transparente aos programadores e permite que ele seja realizado dinamicamente pelo sistema operacional. Além disto, nenhuma tarefa de alta sobrecarga, como simulação, é requerida. As propostas foram avaliadas com o NAS Parallel Benchmarks (NPB), obtendo representações precisas dos padrões de comunicação. Mapeamentos para as threads foram gerados utilizando os padrões de comunicação descobertos e um algoritmo de mapeamento. O problema do mapeamento é NP-Difícil. Portanto, de forma a se atingir uma complexidade polinomial, o algoritmo empregado é heurístico, baseado no algoritmo de emparelhamento de grafos de Edmonds. Executando as aplicações com o mapeamento resultou em um ganho de desempenho de até 15; 3%. O número de faltas na cache, invalidações em linhas de cache e transações de espionagem foram reduzidos em até 31; 9%, 41% e 65; 4%, respectivamente. / The threads of parallel applications cooperate in order to fulfill their tasks, thereby communication is performed among themselves. The communication latency between the cores in a multiprocessor architecture differs depending on the memory hierarchy and the interconnections. With the increase in the number of cores per chip and the number of threads per core, this difference between the communication latencies is increasing. Therefore, it is important to map the threads of parallel applications taking into account the communication between them. In parallel applications based on the shared memory paradigm, the communication is implicit and occurs through accesses to shared variables, which makes difficult to detect the communication pattern between the threads. Traditional approaches use simulation to monitor the memory accesses performed by the application, requiring modifications to the source code and drastically increasing the overhead. In this master thesis, we introduce two novel light-weight mechanisms to find the communication pattern of threads. The first mechanism makes use of the information about shared cache lines provided by cache coherence protocols. The second mechanism makes use of the Translation Lookaside Buffer (TLB) to detect which memory pages each core is accessing. Both our mechanisms rely entirely on hardware features, which makes the thread mapping transparent to the programmer and allows it to be performed dynamically by the operating system. Moreover, no time consuming task, such as simulation, is required. We evaluated our mechanisms with the NAS Parallel Benchmarks (NPB) and obtained accurate representations of the communication patterns. We generated thread mappings from the detected communication patterns using a mapping algorithm. Mapping is a NP-Hard problem. Therefore, in order to achieve a polynomial complexity, we designed a heuristic method based on the Edmonds graph matching algorithm. Running the applications with these mappings resulted in performance improvements of up to 15.3% compared to the original scheduler of the operating system. The number of cache misses, cache line invalidations and snoop transactions were reduced by up to 31.9%, 41% and 65.4%, respectively.

Scientific computing is used frequently in an increasing number of disciplines to accelerate scientific discovery. Many such computing problems involve the numerical solution of partial differential equations (PDE). In this thesis we explore and develop methodology for high-performance implementations of PDE solvers for shared-memory multiprocessor architectures. We consider three realistic PDE settings: solution of the Maxwell equations in 3D using an unstructured grid and the method of conjugate gradients, solution of the Poisson equation in 3D using a geometric multigrid method, and solution of an advection equation in 2D using structured adaptive mesh refinement. We apply software optimization techniques to increase both parallel efficiency and the degree of data locality. In our evaluation we use several different shared-memory architectures ranging from symmetric multiprocessors and distributed shared-memory architectures to chip-multiprocessors. For distributed shared-memory systems we explore methods of data distribution to increase the amount of geographical locality. We evaluate automatic and transparent page migration based on runtime sampling, user-initiated page migration using a directive with an affinity-on-next-touch semantic, and algorithmic optimizations for page-placement policies. Our results show that page migration increases the amount of geographical locality and that the parallel overhead related to page migration can be amortized over the iterations needed to reach convergence. This is especially true for the affinity-on-next-touch methodology whereby page migration can be initiated at an early stage in the algorithms. We also develop and explore methodology for other forms of data locality and conclude that the effect on performance is significant and that this effect will increase for future shared-memory architectures. Our overall conclusion is that, if the involved locality issues are addressed, the shared-memory programming model provides an efficient and productive environment for solving many important PDE problems.

SIMLOX is a discrete-event simulation software developed by Systecon AB for analysing logistic support solution scenarios. To cope with ever larger problems, SIMLOX's simulation engine was recently enhanced with a parallel execution mechanism in order to take advantage of multi-core processors. However, this extension did not result in the desired reduction in runtime for all simulation scenarios even though the parallelisation strategy applied had promised linear speedup. Therefore, an in-depth analysis of the limiting scalability bottlenecks became necessary and has been carried out in this project. Through the use of a low-overhead profiler and microarchitecture analysis, the root causes were identified: atomic operations causing a high communication overhead, poor locality leading to translation lookaside buffer thrashing, and hot spots that consume significant amounts of CPU time. Subsequently, appropriate optimisations to overcome the limiting factors were implemented: eliminating the expensive operations, more efficient handling of heap memory through the use of a scalable memory allocator, and data structures that make better use of caches. Experimental evaluation using real world test cases demonstrated a speedup of at least 6.75x on an eight-core processor. Most cases even achieve a speedup of more than 7.2x. The various optimisations implemented further helped to lower run times for sequential execution by 1.5x or more. It can be concluded that achieving nearly linear speedup on a multi-core processor is possible in practice for discrete-event simulation. / SIMLOX är en kommersiell mjukvara utvecklad av Systecon AB, vars huvudsakliga funktion är en händelsestyrd simuleringskärna för analys av underhållslösningar för komplexa tekniska system. För hantering av stora problem så används parallellexekvering för simuleringen, vilket i teorin borde ge en nästan linjär skalning med antal trådar. Prestandaförbättringen som observerats i praktiken var dock ytterst begränsad, varför en ordentlig analys av skalbarheten har gjorts i detta projekt. Genom användandet av ett profileringsverktyg med liten overhead och mikroarkitektur-analys, så kunde orsakerna hittas: atomiska operationer som skapar mycket overhead för kommunikation, dålig lokalitet ger fragmentering vid översättning till fysiska adresser och dåligt utnyttjande av TLB-cachen, och vissa flaskhalsar som kräver mycket CPU-kraft. Därefter implementerades och testade optimeringar för att undvika de identifierade problem. Testade lösningar inkluderar eliminering av dyra operationer, ökad effektivitet i minneshantering genom skalbara minneshanteringsalgoritmer och implementation av datastrukturer som ger bättre lokalitet och därmed bättre användande av cache-strukturen. Verifiering på verkliga testfall visade på uppsnabbningar på åtminstone 6.75 gånger på en processor med 8 kärnor. De flesta fall visade på en uppsnabbning med en faktor större än 7.2. Optimeringarna gav även en uppsnabbning med en faktor på åtminstone 1.5 vid sekventiell exekvering i en tråd. Slutsatsen är därmed att det är möjligt att uppnå nästan linjär skalning med antalet kärnor för denna typ av händelsestyrd simulering.