Many-core approach to 2D-DCT calculation using an FPGA

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Electrónica e Telecomunicações

A system model and stack for the parallelization of time-critical applications on many-core architectures

3rd Workshop on High-performance and Real-time Embedded Systems (HIRES 2015). 21, Jan, 2015. Amsterdam, Netherlands.

P-SOCRATES: A parallel software framework for time-critical many-core systems

Article in Press, Corrected Proof

Fine-grained multi-phase array designs

Hybrid multiprocessor architectures which combine re-configurable computing and multiprocessors on a chip are being proposed to transcend the performance of standard multi-core parallel systems. Both fine-grained and coarse-grained parallel algorithm implementations are feasible in such hybrid frameworks. A compositional strategy for designing fine-grained multi-phase regular processor arrays to target hybrid architectures is presented in this paper. The method is based on deriving component designs using classical regular array techniques and composing the components into a unified global design. Effective designs with phase-changes and data routing at run-time are characteristics of these designs. In order to describe the data transfer between phases, the concept of communication domain is introduced so that the producer–consumer relationship arising from multi-phase computation can be treated in a unified way as a data routing phase. This technique is applied to derive new designs of multi-phase regular arrays with different dataflow between phases of computation.

Multi Processor Systems On Chip with Configurable Hardware Acceleration

The evolution of the electronics embedded applications forces electronics systems designers to match their ever increasing requirements. This evolution pushes the computational power of digital signal processing systems, as well as the energy required to accomplish the computations, due to the increasing mobility of such applications. Current approaches used to match these requirements relies on the adoption of application specific signal processors. Such kind of devices exploits powerful accelerators, which are able to match both performance and energy requirements. On the other hand, the too high specificity of such accelerators often results in a lack of flexibility which affects non-recurrent engineering costs, time to market, and market volumes too. The state of the art mainly proposes two solutions to overcome these issues with the ambition of delivering reasonable performance and energy efficiency: reconfigurable computing and multi-processors computing. All of these solutions benefits from the post-fabrication programmability, that definitively results in an increased flexibility. Nevertheless, the gap between these approaches and dedicated hardware is still too high for many application domains, especially when targeting the mobile world. In this scenario, flexible and energy efficient acceleration can be achieved by merging these two computational paradigms, in order to address all the above introduced constraints. This thesis focuses on the exploration of the design and application spectrum of reconfigurable computing, exploited as application specific accelerators for multi-processors systems on chip. More specifically, it introduces a reconfigurable digital signal processor featuring a heterogeneous set of reconfigurable engines, and a homogeneous multi-core system, exploiting three different flavours of reconfigurable and mask-programmable technologies as implementation platform for applications specific accelerators. In this work, the various trade-offs concerning the utilization multi-core platforms and the different configuration technologies are explored, characterizing the design space of the proposed approach in terms of programmability, performance, energy efficiency and manufacturing costs.

Gpu-based many-core architecture emulation: A double level approach

The efficient emulation of a many-core architecture is a challenging task, each core could be emulated through a dedicated thread and such threads would be interleaved on an either single-core or a multi-core processor. The high number of context switches will results in an unacceptable performance. To support this kind of application, the GPU computational power is exploited in order to schedule the emulation threads on the GPU cores. This presents a non trivial divergence issue, since GPU computational power is offered through SIMD processing elements, that are forced to synchronously execute the same instruction on different memory portions. Thus, a new emulation technique is introduced in order to overcome this limitation: instead of providing a routine for each ISA opcode, the emulator mimics the behavior of the Micro Architecture level, here instructions are date that a unique routine takes as input. Our new technique has been implemented and compared with the classic emulation approach, in order to investigate the chance of a hybrid solution.

Many-Core Architectures: Hardware-Software Optimization and Modeling Techniques

During the last few decades an unprecedented technological growth has been at the center of the embedded systems design paramount, with Moore’s Law being the leading factor of this trend. Today in fact an ever increasing number of cores can be integrated on the same die, marking the transition from state-of-the-art multi-core chips to the new many-core design paradigm. Despite the extraordinarily high computing power, the complexity of many-core chips opens the door to several challenges. As a result of the increased silicon density of modern Systems-on-a-Chip (SoC), the design space exploration needed to find the best design has exploded and hardware designers are in fact facing the problem of a huge design space. Virtual Platforms have always been used to enable hardware-software co-design, but today they are facing with the huge complexity of both hardware and software systems. In this thesis two different research works on Virtual Platforms are presented: the first one is intended for the hardware developer, to easily allow complex cycle accurate simulations of many-core SoCs. The second work exploits the parallel computing power of off-the-shelf General Purpose Graphics Processing Units (GPGPUs), with the goal of an increased simulation speed. The term Virtualization can be used in the context of many-core systems not only to refer to the aforementioned hardware emulation tools (Virtual Platforms), but also for two other main purposes: 1) to help the programmer to achieve the maximum possible performance of an application, by hiding the complexity of the underlying hardware. 2) to efficiently exploit the high parallel hardware of many-core chips in environments with multiple active Virtual Machines. This thesis is focused on virtualization techniques with the goal to mitigate, and overtake when possible, some of the challenges introduced by the many-core design paradigm.

Um método de otimização da relação desempenho/consumo de energia para arquiteturas multi-cores heterogêneas em FPGA

Devido às tendências de crescimento da quantidade de dados processados e a crescente necessidade por computação de alto desempenho, mudanças significativas estão acontecendo no projeto de arquiteturas de computadores. Com isso, tem-se migrado do paradigma sequencial para o paralelo, com centenas ou milhares de núcleos de processamento em um mesmo chip. Dentro desse contexto, o gerenciamento de energia torna-se cada vez mais importante, principalmente em sistemas embarcados, que geralmente são alimentados por baterias. De acordo com a Lei de Moore, o desempenho de um processador dobra a cada 18 meses, porém a capacidade das baterias dobra somente a cada 10 anos. Esta situação provoca uma enorme lacuna, que pode ser amenizada com a utilização de arquiteturas multi-cores heterogêneas. Um desafio fundamental que permanece em aberto para estas arquiteturas é realizar a integração entre desenvolvimento de código embarcado, escalonamento e hardware para gerenciamento de energia. O objetivo geral deste trabalho de doutorado é investigar técnicas para otimização da relação desempenho/consumo de energia em arquiteturas multi-cores heterogêneas single-ISA implementadas em FPGA. Nesse sentido, buscou-se por soluções que obtivessem o melhor desempenho possível a um consumo de energia ótimo. Isto foi feito por meio da combinação de mineração de dados para a análise de softwares baseados em threads aliadas às técnicas tradicionais para gerenciamento de energia, como way-shutdown dinâmico, e uma nova política de escalonamento heterogeneity-aware. Como principais contribuições pode-se citar a combinação de técnicas de gerenciamento de energia em diversos níveis como o nível do hardware, do escalonamento e da compilação; e uma política de escalonamento integrada com uma arquitetura multi-core heterogênea em relação ao tamanho da memória cache L1.

Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.

FPGA-based soft-core processors for image processing applications

With security and surveillance, there is an increasing need to process image data efficiently and effectively either at source or in a large data network. Whilst a Field-Programmable Gate Array (FPGA) has been seen as a key technology for enabling this, the design process has been viewed as problematic in terms of the time and effort needed for implementation and verification. The work here proposes a different approach of using optimized FPGA-based soft-core processors which allows the user to exploit the task and data level parallelism to achieve the quality of dedicated FPGA implementations whilst reducing design time. The paper also reports some preliminary
progress on the design flow to program the structure. An implementation for a Histogram of Gradients algorithm is also reported which shows that a performance of 328 fps can be achieved with this design approach, whilst avoiding the long design time, verification and debugging steps associated with conventional FPGA implementations.

Towards a Multi-device Constraints Solver

To reduce the amount of time needed to solve the most complex Constraint Satisfaction Problems (CSPs) usually multi-core CPUs are used. There are already many applications capable of harnessing the parallel power of these devices to speed up the CSPs solving process. Nowadays, the Graphics Processing Units (GPUs) possess a level of parallelism that surpass the CPUs, containing from a few hundred to a few thousand cores and there are much less applications capable of solving CSPs on GPUs, leaving space for possible improvements. This article describes the work in progress for solving CSPs on GPUs and CPUs and compares results with some state-of-the-art solvers, presenting already some good results on GPUs.

Scalable Unified Transform Architecture for Advanced Video Coding Embedded Systems

A novel high throughput and scalable unified architecture for the computation of the transform operations in video codecs for advanced standards is presented in this paper. This structure can be used as a hardware accelerator in modern embedded systems to efficiently compute all the two-dimensional 4 x 4 and 2 x 2 transforms of the H.264/AVC standard. Moreover, its highly flexible design and hardware efficiency allows it to be easily scaled in terms of performance and hardware cost to meet the specific requirements of any given video coding application. Experimental results obtained using a Xilinx Virtex-5 FPGA demonstrated the superior performance and hardware efficiency levels provided by the proposed structure, which presents a throughput per unit of area relatively higher than other similar recently published designs targeting the H.264/AVC standard. Such results also showed that, when integrated in a multi-core embedded system, this architecture provides speedup factors of about 120x concerning pure software implementations of the transform algorithms, therefore allowing the computation, in real-time, of all the above mentioned transforms for Ultra High Definition Video (UHDV) sequences (4,320 x 7,680 @ 30 fps).

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.

Revisiting transactions in Ada

Classical lock-based concurrency control does not scale with current and foreseen multi-core architectures, opening space for alternative concurrency control mechanisms. The concept of transactions executing concurrently in isolation with an underlying mechanism maintaining a consistent system state was already explored in fault-tolerant and distributed systems, and is currently being explored by transactional memory, this time being used to manage concurrent memory access. In this paper we discuss the use of Software Transactional Memory (STM), and how Ada can provide support for it. Furthermore, we draft a general programming interface to transactional memory, supporting future implementations of STM oriented to real-time systems.

SPARTS: simulator for power aware and real-time systems

Real-time systems demand guaranteed and predictable run-time behaviour in order to ensure that no task has missed its deadline. Over the years we are witnessing an ever increasing demand for functionality enhancements in the embedded real-time systems. Along with the functionalities, the design itself grows more complex. Posed constraints, such as energy consumption, time, and space bounds, also require attention and proper handling. Additionally, efficient scheduling algorithms, as proven through analyses and simulations, often impose requirements that have significant run-time cost, specially in the context of multi-core systems. In order to further investigate the behaviour of such systems to quantify and compare these overheads involved, we have developed the SPARTS, a simulator of a generic embedded real- time device. The tasks in the simulator are described by externally visible parameters (e.g. minimum inter-arrival, sporadicity, WCET, BCET, etc.), rather than the code of the tasks. While our current implementation is primarily focused on our immediate needs in the area of power-aware scheduling, it is designed to be extensible to accommodate different task properties, scheduling algorithms and/or hardware models for the application in wide variety of simulations. The source code of the SPARTS is available for download at [1].