Use of shared memory in the context of embedded multi-core processors: exploration of the technology and its limits

Modern embedded systems embrace many-core shared-memory designs. Due to constrained power and area budgets, most of them feature software-managed scratchpad memories instead of data caches to increase the data locality. It is therefore programmers’ responsibility to explicitly manage the memory transfers, and this make programming these platform cumbersome. Moreover, complex modern applications must be adequately parallelized before they can the parallel potential of the platform into actual performance. To support this, programming languages were proposed, which work at a high level of abstraction, and rely on a runtime whose cost hinders performance, especially in embedded systems, where resources and power budget are constrained. This dissertation explores the applicability of the shared-memory paradigm on modern many-core systems, focusing on the ease-of-programming. It focuses on OpenMP, the de-facto standard for shared memory programming. In a first part, the cost of algorithms for synchronization and data partitioning are analyzed, and they are adapted to modern embedded many-cores. Then, the original design of an OpenMP runtime library is presented, which supports complex forms of parallelism such as multi-level and irregular parallelism. In the second part of the thesis, the focus is on heterogeneous systems, where hardware accelerators are coupled to (many-)cores to implement key functional kernels with orders-of-magnitude of speedup and energy efficiency compared to the “pure software” version. However, three main issues rise, namely i) platform design complexity, ii) architectural scalability and iii) programmability. To tackle them, a template for a generic hardware processing unit (HWPU) is proposed, which share the memory banks with cores, and the template for a scalable architecture is shown, which integrates them through the shared-memory system. Then, a full software stack and toolchain are developed to support platform design and to let programmers exploiting the accelerators of the platform. The OpenMP frontend is extended to interact with it.

Constraint handling rules. Compositional semantics and program transformation

This thesis intends to investigate two aspects of Constraint Handling Rules (CHR). It proposes a compositional semantics and a technique for program transformation. CHR is a concurrent committed-choice constraint logic programming language consisting of guarded rules, which transform multi-sets of atomic formulas (constraints) into simpler ones until exhaustion [Frü06] and it belongs to the declarative languages family. It was initially designed for writing constraint solvers but it has recently also proven to be a general purpose language, being as it is Turing equivalent [SSD05a]. Compositionality is the first CHR aspect to be considered. A trace based compositional semantics for CHR was previously defined in [DGM05]. The reference operational semantics for such a compositional model was the original operational semantics for CHR which, due to the propagation rule, admits trivial non-termination. In this thesis we extend the work of [DGM05] by introducing a more refined trace based compositional semantics which also includes the history. The use of history is a well-known technique in CHR which permits us to trace the application of propagation rules and consequently it permits trivial non-termination avoidance [Abd97, DSGdlBH04]. Naturally, the reference operational semantics, of our new compositional one, uses history to avoid trivial non-termination too. Program transformation is the second CHR aspect to be considered, with particular regard to the unfolding technique. Said technique is an appealing approach which allows us to optimize a given program and in more detail to improve run-time efficiency or spaceconsumption. Essentially it consists of a sequence of syntactic program manipulations which preserve a kind of semantic equivalence called qualified answer [Frü98], between the original program and the transformed ones. The unfolding technique is one of the basic operations which is used by most program transformation systems. It consists in the replacement of a procedure-call by its definition. In CHR every conjunction of constraints can be considered as a procedure-call, every CHR rule can be considered as a procedure and the body of said rule represents the definition of the call. While there is a large body of literature on transformation and unfolding of sequential programs, very few papers have addressed this issue for concurrent languages. We define an unfolding rule, show its correctness and discuss some conditions in which it can be used to delete an unfolded rule while preserving the meaning of the original program. Finally, confluence and termination maintenance between the original and transformed programs are shown. This thesis is organized in the following manner. Chapter 1 gives some general notion about CHR. Section 1.1 outlines the history of programming languages with particular attention to CHR and related languages. Then, Section 1.2 introduces CHR using examples. Section 1.3 gives some preliminaries which will be used during the thesis. Subsequentely, Section 1.4 introduces the syntax and the operational and declarative semantics for the first CHR language proposed. Finally, the methodologies to solve the problem of trivial non-termination related to propagation rules are discussed in Section 1.5. Chapter 2 introduces a compositional semantics for CHR where the propagation rules are considered. In particular, Section 2.1 contains the definition of the semantics. Hence, Section 2.2 presents the compositionality results. Afterwards Section 2.3 expounds upon the correctness results. Chapter 3 presents a particular program transformation known as unfolding. This transformation needs a particular syntax called annotated which is introduced in Section 3.1 and its related modified operational semantics !0t is presented in Section 3.2. Subsequently, Section 3.3 defines the unfolding rule and prove its correctness. Then, in Section 3.4 the problems related to the replacement of a rule by its unfolded version are discussed and this in turn gives a correctness condition which holds for a specific class of rules. Section 3.5 proves that confluence and termination are preserved by the program modifications introduced. Finally, Chapter 4 concludes by discussing related works and directions for future work.

Ottimizzazione delle reti di distribuzione idrica tramite algoritmi genetici multi-obiettivo

Water distribution networks optimization is a challenging problem due to the dimension and the complexity of these systems. Since the last half of the twentieth century this field has been investigated by many authors. Recently, to overcome discrete nature of variables and non linearity of equations, the research has been focused on the development of heuristic algorithms. This algorithms do not require continuity and linearity of the problem functions because they are linked to an external hydraulic simulator that solve equations of mass continuity and of energy conservation of the network. In this work, a NSGA-II (Non-dominating Sorting Genetic Algorithm) has been used. This is a heuristic multi-objective genetic algorithm based on the analogy of evolution in nature. Starting from an initial random set of solutions, called population, it evolves them towards a front of solutions that minimize, separately and contemporaneously, all the objectives. This can be very useful in practical problems where multiple and discordant goals are common. Usually, one of the main drawback of these algorithms is related to time consuming: being a stochastic research, a lot of solutions must be analized before good ones are found. Results of this thesis about the classical optimal design problem shows that is possible to improve results modifying the mathematical definition of objective functions and the survival criterion, inserting good solutions created by a Cellular Automata and using rules created by classifier algorithm (C4.5). This part has been tested using the version of NSGA-II supplied by Centre for Water Systems (University of Exeter, UK) in MATLAB® environment. Even if orientating the research can constrain the algorithm with the risk of not finding the optimal set of solutions, it can greatly improve the results. Subsequently, thanks to CINECA help, a version of NSGA-II has been implemented in C language and parallelized: results about the global parallelization show the speed up, while results about the island parallelization show that communication among islands can improve the optimization. Finally, some tests about the optimization of pump scheduling have been carried out. In this case, good results are found for a small network, while the solutions of a big problem are affected by the lack of constraints on the number of pump switches. Possible future research is about the insertion of further constraints and the evolution guide. In the end, the optimization of water distribution systems is still far from a definitive solution, but the improvement in this field can be very useful in reducing the solutions cost of practical problems, where the high number of variables makes their management very difficult from human point of view.

Multi-level models and infrastructures for simulating biological system development

The hierarchical organisation of biological systems plays a crucial role in the pattern formation of gene expression resulting from the morphogenetic processes, where autonomous internal dynamics of cells, as well as cell-to-cell interactions through membranes, are responsible for the emergent peculiar structures of the individual phenotype. Being able to reproduce the systems dynamics at different levels of such a hierarchy might be very useful for studying such a complex phenomenon of self-organisation. The idea is to model the phenomenon in terms of a large and dynamic network of compartments, where the interplay between inter-compartment and intra-compartment events determines the emergent behaviour resulting in the formation of spatial patterns. According to these premises the thesis proposes a review of the different approaches already developed in modelling developmental biology problems, as well as the main models and infrastructures available in literature for modelling biological systems, analysing their capabilities in tackling multi-compartment / multi-level models. The thesis then introduces a practical framework, MS-BioNET, for modelling and simulating these scenarios exploiting the potential of multi-level dynamics. This is based on (i) a computational model featuring networks of compartments and an enhanced model of chemical reaction addressing molecule transfer, (ii) a logic-oriented language to flexibly specify complex simulation scenarios, and (iii) a simulation engine based on the many-species/many-channels optimised version of Gillespie’s direct method. The thesis finally proposes the adoption of the agent-based model as an approach capable of capture multi-level dynamics. To overcome the problem of parameter tuning in the model, the simulators are supplied with a module for parameter optimisation. The task is defined as an optimisation problem over the parameter space in which the objective function to be minimised is the distance between the output of the simulator and a target one. The problem is tackled with a metaheuristic algorithm. As an example of application of the MS-BioNET framework and of the agent-based model, a model of the first stages of Drosophila Melanogaster development is realised. The model goal is to generate the early spatial pattern of gap gene expression. The correctness of the models is shown comparing the simulation results with real data of gene expression with spatial and temporal resolution, acquired in free on-line sources.