Multiprocessor platform using LEON3 processor

The recent advances in embedded systems world, lead us to more complex systems with application specific blocks (IP cores), the System on Chip (SoC) devices. A good example of these complex devices can be encountered in the cell phones that can have image processing cores, communication cores, memory card cores, and others. The need of augmenting systems’ processing performance with lowest power, leads to a concept of Multiprocessor System on Chip (MSoC) in which the execution of multiple tasks can be distributed along various processors. This thesis intends to address the creation of a synthesizable multiprocessing system to be placed in a FPGA device, providing a good flexibility to tailor the system to a specific application. To deliver a multiprocessing system, will be used the synthesisable 32-bit SPARC V8 compliant, LEON3 processor.

Supporting intra-task parallelism in real-time multiprocessor systems

Os sistemas de tempo real modernos geram, cada vez mais, cargas computacionais pesadas e dinâmicas, começando-se a tornar pouco expectável que sejam implementados em sistemas uniprocessador. Na verdade, a mudança de sistemas com um único processador para sistemas multi- processador pode ser vista, tanto no domínio geral, como no de sistemas embebidos, como uma forma eficiente, em termos energéticos, de melhorar a performance das aplicações. Simultaneamente, a proliferação das plataformas multi-processador transformaram a programação paralela num tópico de elevado interesse, levando o paralelismo dinâmico a ganhar rapidamente popularidade como um modelo de programação. A ideia, por detrás deste modelo, é encorajar os programadores a exporem todas as oportunidades de paralelismo através da simples indicação de potenciais regiões paralelas dentro das aplicações. Todas estas anotações são encaradas pelo sistema unicamente como sugestões, podendo estas serem ignoradas e substituídas, por construtores sequenciais equivalentes, pela própria linguagem. Assim, o modo como a computação é na realidade subdividida, e mapeada nos vários processadores, é da responsabilidade do compilador e do sistema computacional subjacente. Ao retirar este fardo do programador, a complexidade da programação é consideravelmente reduzida, o que normalmente se traduz num aumento de produtividade. Todavia, se o mecanismo de escalonamento subjacente não for simples e rápido, de modo a manter o overhead geral em níveis reduzidos, os benefícios da geração de um paralelismo com uma granularidade tão fina serão meramente hipotéticos. Nesta perspetiva de escalonamento, os algoritmos que empregam uma política de workstealing são cada vez mais populares, com uma eficiência comprovada em termos de tempo, espaço e necessidades de comunicação. Contudo, estes algoritmos não contemplam restrições temporais, nem outra qualquer forma de atribuição de prioridades às tarefas, o que impossibilita que sejam diretamente aplicados a sistemas de tempo real. Além disso, são tradicionalmente implementados no runtime da linguagem, criando assim um sistema de escalonamento com dois níveis, onde a previsibilidade, essencial a um sistema de tempo real, não pode ser assegurada. Nesta tese, é descrita a forma como a abordagem de work-stealing pode ser resenhada para cumprir os requisitos de tempo real, mantendo, ao mesmo tempo, os seus princípios fundamentais que tão bons resultados têm demonstrado. Muito resumidamente, a única fila de gestão de processos convencional (deque) é substituída por uma fila de deques, ordenada de forma crescente por prioridade das tarefas. De seguida, aplicamos por cima o conhecido algoritmo de escalonamento dinâmico G-EDF, misturamos as regras de ambos, e assim nasce a nossa proposta: o algoritmo de escalonamento RTWS. Tirando partido da modularidade oferecida pelo escalonador do Linux, o RTWS é adicionado como uma nova classe de escalonamento, de forma a avaliar na prática se o algoritmo proposto é viável, ou seja, se garante a eficiência e escalonabilidade desejadas. Modificar o núcleo do Linux é uma tarefa complicada, devido à complexidade das suas funções internas e às fortes interdependências entre os vários subsistemas. Não obstante, um dos objetivos desta tese era ter a certeza que o RTWS é mais do que um conceito interessante. Assim, uma parte significativa deste documento é dedicada à discussão sobre a implementação do RTWS e à exposição de situações problemáticas, muitas delas não consideradas em teoria, como é o caso do desfasamento entre vários mecanismo de sincronização. Os resultados experimentais mostram que o RTWS, em comparação com outro trabalho prático de escalonamento dinâmico de tarefas com restrições temporais, reduz significativamente o overhead de escalonamento através de um controlo de migrações, e mudanças de contexto, eficiente e escalável (pelo menos até 8 CPUs), ao mesmo tempo que alcança um bom balanceamento dinâmico da carga do sistema, até mesmo de uma forma não custosa. Contudo, durante a avaliação realizada foi detetada uma falha na implementação do RTWS, pela forma como facilmente desiste de roubar trabalho, o que origina períodos de inatividade, no CPU em questão, quando a utilização geral do sistema é baixa. Embora o trabalho realizado se tenha focado em manter o custo de escalonamento baixo e em alcançar boa localidade dos dados, a escalonabilidade do sistema nunca foi negligenciada. Na verdade, o algoritmo de escalonamento proposto provou ser bastante robusto, não falhando qualquer meta temporal nas experiências realizadas. Portanto, podemos afirmar que alguma inversão de prioridades, causada pela sub-política de roubo BAS, não compromete os objetivos de escalonabilidade, e até ajuda a reduzir a contenção nas estruturas de dados. Mesmo assim, o RTWS também suporta uma sub-política de roubo determinística: PAS. A avaliação experimental, porém, não ajudou a ter uma noção clara do impacto de uma e de outra. No entanto, de uma maneira geral, podemos concluir que o RTWS é uma solução promissora para um escalonamento eficiente de tarefas paralelas com restrições temporais.

Laxity dynamics and LLF schedulability analysis on multiprocessor platforms

LLF (Least Laxity First) scheduling, which assigns a higher priority to a task with a smaller laxity, has been known as an optimal preemptive scheduling algorithm on a single processor platform. However, little work has been made to illuminate its characteristics upon multiprocessor platforms. In this paper, we identify the dynamics of laxity from the system’s viewpoint and translate the dynamics into LLF multiprocessor schedulability analysis. More specifically, we first characterize laxity properties under LLF scheduling, focusing on laxity dynamics associated with a deadline miss. These laxity dynamics describe a lower bound, which leads to the deadline miss, on the number of tasks of certain laxity values at certain time instants. This lower bound is significant because it represents invariants for highly dynamic system parameters (laxity values). Since the laxity of a task is dependent of the amount of interference of higher-priority tasks, we can then derive a set of conditions to check whether a given task system can go into the laxity dynamics towards a deadline miss. This way, to the author’s best knowledge, we propose the first LLF multiprocessor schedulability test based on its own laxity properties. We also develop an improved schedulability test that exploits slack values. We mathematically prove that the proposed LLF tests dominate the state-of-the-art EDZL tests. We also present simulation results to evaluate schedulability performance of both the original and improved LLF tests in a quantitative manner.

Makespan computation for GPU threads running on a single streaming multiprocessor

Graphics processors were originally developed for rendering graphics but have recently evolved towards being an architecture for general-purpose computations. They are also expected to become important parts of embedded systems hardware -- not just for graphics. However, this necessitates the development of appropriate timing analysis techniques which would be required because techniques developed for CPU scheduling are not applicable. The reason is that we are not interested in how long it takes for any given GPU thread to complete, but rather how long it takes for all of them to complete. We therefore develop a simple method for finding an upper bound on the makespan of a group of GPU threads executing the same program and competing for the resources of a single streaming multiprocessor (whose architecture is based on NVIDIA Fermi, with some simplifying assunptions). We then build upon this method to formulate the derivation of the exact worst-case makespan (and corresponding schedule) as an optimization problem. Addressing the issue of tractability, we also present a technique for efficiently computing a safe estimate of the worstcase makespan with minimal pessimism, which may be used when finding an exact value would take too long.

Preemption-light multiprocessor scheduling of sporadic tasks with high utilisation bound

Known algorithms capable of scheduling implicit-deadline sporadic tasks over identical processors at up to 100% utilisation invariably involve numerous preemptions and migrations. To the challenge of devising a scheduling scheme with as few preemptions and migrations as possible, for a given guaranteed utilisation bound, we respond with the algorithm NPS-F. It is configurable with a parameter, trading off guaranteed schedulable utilisation (up to 100%) vs preemptions. For any possible configuration, NPS-F introduces fewer preemptions than any other known algorithm matching its utilisation bound. A clustered variant of the algorithm, for systems made of multicore chips, eliminates (costly) off-chip task migrations, by dividing processors into disjoint clusters, formed by cores on the same chip (with the cluster size being a parameter). Clusters are independently scheduled (each, using non-clustered NPS-F). The utilisation bound is only moderately affected. We also formulate an important extension (applicable to both clustered and non-clustered NPS-F) which optimises the supply of processing time to executing tasks and makes it more granular. This reduces processing capacity requirements for schedulability without increasing preemptions.

The generalized multiprocessor periodic resource interface model for hierarchical multiprocessor scheduling

Composition is a practice of key importance in software engineering. When real-time applications are composed it is necessary that their timing properties (such as meeting the deadlines) are guaranteed. The composition is performed by establishing an interface between the application and the physical platform. Such an interface does typically contain information about the amount of computing capacity needed by the application. In multiprocessor platforms, the interface should also present information about the degree of parallelism. Recently there have been quite a few interface proposals. However, they are either too complex to be handled or too pessimistic.In this paper we propose the Generalized Multiprocessor Periodic Resource model (GMPR) that is strictly superior to the MPR model without requiring a too detailed description. We describe a method to generate the interface from the application specification. All these methods have been implemented in Matlab routines that are publicly available.

Provably good scheduling of sporadic tasks with resource sharing on a two-type heterogeneous multiprocessor platform

Consider the problem of scheduling a set of implicit-deadline sporadic tasks to meet all deadlines on a two-type heterogeneous multiprocessor platform where a task may request at most one of |R| shared resources. There are m1 processors of type-1 and m2 processors of type-2. Tasks may migrate only when requesting or releasing resources. We present a new algorithm, FF-3C-vpr, which offers a guarantee that if a task set is schedulable to meet deadlines by an optimal task assignment scheme that only allows tasks to migrate when requesting or releasing a resource, then FF-3Cvpr also meets deadlines if given processors 4+6*ceil(|R|/min(m1,m2)) times as fast. As far as we know, it is the first result for resource sharing on heterogeneous platforms with provable performance.

A conjecture about provably good task assignment on heterogeneous multiprocessor platforms but with a stronger adversary

Consider the problem of scheduling a set of implicit-deadline sporadic tasks to meet all deadlines on a heterogeneous multiprocessor platform. We use an algorithm proposed in [1] (we refer to it as LP-EE) from state-of-the-art for assigning tasks to heterogeneous multiprocessor platform and (re-)prove its performance guarantee but for a stronger adversary.We conjecture that if a task set can be scheduled to meet deadlines on a heterogeneous multiprocessor platform by an optimal task assignment scheme that allows task migrations then LP-EE meets deadlines as well with no migrations if given processors twice as fast. We illustrate this with an example.

Two-type heterogeneous multiprocessor scheduling: Is there a phase transition? (Extended Abstract)

Consider the problem of non-migratively scheduling a set of implicit-deadline sporadic tasks to meet all deadlines on a two-type heterogeneous multiprocessor platform. We ask the following question: Does there exist a phase transition behavior for the two-type heterogeneous multiprocessor scheduling problem? We also provide some initial observations via simulations performed on randomly generated task sets.

Provably good task assignment on heterogeneous multiprocessor platforms for a restricted case but with a stronger adversary

Consider the problem of scheduling a set of implicit-deadline sporadic tasks to meet all deadlines on a heterogeneous multiprocessor platform. We consider a restricted case where the maximum utilization of any task on any processor in the system is no greater than one. We use an algorithm proposed in [1] (we refer to it as LP-EE) from state-of-the-art for assigning tasks to heterogeneous multiprocessor platform and (re-)prove its performance guarantee for this restricted case but for a stronger adversary. We show that if a task set can be scheduled to meet deadlines on a heterogeneous multiprocessor platform by an optimal task assignment scheme that allows task migrations then LP-EE meets deadlines as well with no migrations if given processors twice as fast.

Intra-type migrative scheduling of implicit-deadline sporadic tasks on two- type heterogeneous multiprocessor

Consider the problem of scheduling a set of implicit-deadline sporadic tasks to meet all deadlines on a two-type heterogeneous multiprocessor platform. Each processor is either of type-1 or type-2 with each task having different execution time on each processor type. Jobs can migrate between processors of same type (referred to as intra-type migration) but cannot migrate between processors of different types. We present a new scheduling algorithm namely, LP-Relax(THR) which offers a guarantee that if a task set can be scheduled to meet deadlines by an optimal task assignment scheme that allows intra-type migration then LP-Relax(THR) meets deadlines as well with intra-type migration if given processors 1/THR as fast (referred to as speed competitive ratio) where THR <= 2/3.

Maximizing contention-free executions in multiprocessor scheduling

It is widely assumed that scheduling real-time tasks becomes more difficult as their deadlines get shorter. With deadlines shorter, however, tasks potentially compete less with each other for processors, and this could produce more contention-free slots at which the number of competing tasks is smaller than or equal to the number of available processors. This paper presents a policy (called CF policy) that utilizes such contention-free slots effectively. This policy can be employed by any work-conserving, preemptive scheduling algorithm, and we show that any algorithm extended with this policy dominates the original algorithm in terms of schedulability. We also present improved schedulability tests for algorithms that employ this policy, based on the observation that interference from tasks is reduced when their executions are postponed to contention-free slots. Finally, using the properties of the CF policy, we derive a counter-intuitive claim that shortening of task deadlines can help improve schedulability of task systems. We present heuristics that effectively reduce task deadlines for better scheduability without performing any exhaustive search.

Partitioned scheduling of multimode systems on multiprocessor platforms: when to do the mode transition?

Systems composed of distinct operational modes are a common necessity for embedded applications with strict timing requirements. With the emergence of multi-core platforms protocols to handle these systems are required in order to provide this basic functionality.In this work a description on the problems of creating an effective mode-transition protocol are presented and it is proven that in some cases previous single-core protocols can not be extended to handle the mode-transition in multi-core.

On the implementation of real-time slotbased task-splitting scheduling algorithms for multiprocessor systems

In this paper we discuss challenges and design principles of an implementation of slot-based tasksplitting algorithms into the Linux 2.6.34 version. We show that this kernel version is provided with the required features for implementing such scheduling algorithms. We show that the real behavior of the scheduling algorithm is very close to the theoretical. We run and discuss experiments on 4-core and 24-core machines.

Implementing slot-based task-splitting multiprocessor scheduling

Consider the problem of scheduling a set of sporadic tasks on a multiprocessor system to meet deadlines using a task-splitting scheduling algorithm. Task-splitting (also called semi-partitioning) scheduling algorithms assign most tasks to just one processor but a few tasks are assigned to two or more processors, and they are dispatched in a way that ensures that a task never executes on two or more processors simultaneously. A particular type of task-splitting algorithms, called slot-based task-splitting dispatching, is of particular interest because of its ability to schedule tasks with high processor utilizations. Unfortunately, no slot-based task-splitting algorithm has been implemented in a real operating system so far. In this paper we discuss and propose some modifications to the slot-based task-splitting algorithm driven by implementation concerns, and we report the first implementation of this family of algorithms in a real operating system running Linux kernel version 2.6.34. We have also conducted an extensive range of experiments on a 4-core multicore desktop PC running task-sets with utilizations of up to 88%. The results show that the behavior of our implementation is in line with the theoretical framework behind it.