A challenge in designing resource-constrained embedded systems for digital signal processing (DSP) is their complexity due to their vast design spaces, where only a fraction of implementations are feasible or optimal. A crucial tool to aid in this challenge is automated design space exploration (DSE). However, no exact, multi-objective, and preference-free DSE approach exists for DSP applications on resource-constrained embedded platforms. We propose a novel DSE solution with these ideal characteristics to perform DSE of analyzable DSP applications for tile-based multiprocessing embedded platforms. Our proposal harmonizes the exactness of constraint programming (CP) and the exploration efficiency of genetic algorithms (GA). Through this synergy, no single-objective reduction strategy or a priori objective preferences is required. We evaluate the proposal through state-of-the-art single-objective case studies and multi-objective case studies inspired by these. The evaluations show that our proposal improves the single-objective state-of-the-art and finds high-quality approximate Pareto-frontiers for the multi-objective case study. Therefore, our proposal is a more performant single-objective DSE solution than the state-of-the-art, and it is the first exact, multi-objective, and preference-free DSE approach for the problem addressed.

System level optimization for multiple mixed-criticality applications on shared networked multiprocessor platforms is extremely challenging. Substantial complexity arises from the interdependence between the multiple subproblems of mapping, scheduling and platform configuration under the consideration of several, potentially orthogonal, performance metrics and constraints. Instead of using heuristic algorithms and problem decomposition, novel unified design space exploration (DSE) approaches based on Constraint Programming (CP) have in the recent years shown promising results. The work in this paper takes advantage of the modularity of CP models, in order to support heterogeneous multiprocessor Network-on-Chip (NoC) with Temporally Disjoint Networks (TDNs) aware message injection. The DSE supports a range of design criteria, in particular the optimization and satisfaction of power and throughput. In addition, the DSE now provides a valid configuration for the TDNs that guarantees the performance required to fulfil the design goals. The experiments show the capability of the approach to find low-power and high-throughput designs, and validate a resulting design on a physical TDN-based NoC implementation.

Due to its complexity, the problem of mapping and scheduling streaming applications on heterogeneous MPSoCs under real-time and performance constraints has traditionally been tackled by incomplete heuristic algorithms. In recent years, approaches based on Constraint Programming (CP) have shown promising results as complete methods for finding optimal mappings, in particular concerning throughput. However, so far none of the available CP approaches consider the tradeoff between throughput and buffer requirements or throughput and power consumption. This article integrates tradeoff awareness into the CP model and introduces a two-step solving approach that utilizes the advantages of heuristics, while still keeping the completeness property of CP. With a number of experiments considering several streaming applications and different platform models, the article illustrates not only the efficiency of the presented model but also its suitability for solving different problems with various combinations of performance constraints.

The increasing processing power of today's HW/SW platforms leads to the integration of more and more functions in a single device. Additional design challenges arise when these functions share computing resources and belong to different criticality levels. CONTREX complements current activities in the area of predictable computing platforms and segregation mechanisms with techniques to consider the extra-functional properties, i.e., timing constraints, power, and temperature. CONTREX enables energy efficient and cost aware design through analysis and optimization of these properties with regard to application demands at different criticality levels. This article presents an overview of the CONTREX European project, its main innovative technology (extension of a model based design approach, functional and extra-functional analysis with executable models and run-time management) and the final results of three industrial use-cases from different domain (avionics, automotive and telecommunication).

When designing complex mixed-critical systems on multiprocessor platforms, a huge number of design alternatives has to be evaluated. Therefore, there is a need for tools which systematically find and analyze the ample alternatives and identify solutions that satisfy the design constraints. The recently proposed design space exploration (DSE) tool DeSyDe uses constraint programming (CP) to find implementations with performance guarantees for multiple applications with potentially mixed-critical design constraints on a shared platform. A key component of the DeSyDe tool is its throughput analysis component, called a throughput propagator in the context of CP. The throughput propagator guides the exploration by evaluating each design decision and is therefore executed excessively throughout the exploration. This paper presents two throughput propagators based on different analysis methods for DeSyDe. Their performance is evaluated in a range of experiments with six different application graphs, heterogeneous platform models and mixed-critical design constraints. The results suggest that the MCR throughput propagator is more efficient.

Embedded system designers often face a large number of design alternatives when designing complex systems. A designer must select an alternative which satisfies application constraints (e.g. timing requirements) while optimizing system level objectives such as overall energy consumption. The size of design space is often very large giving rise to the need for systematic Design Space Exploration (DSE) methods. In this paper we address the DSE problem for real-time applications that belong to two different domains: (i) streaming applications modeled using the synchronous dataflow graphs; (ii) feedback control tasks modeled using the periodic task model. We consider a heterogeneous multiprocessor platform in which processors communicate through a predictable bus architecture. We present our DSE tool in which the DSE problem is modeled as a constraint satisfaction problem, and it is solved using a constraint programming solver. This approach provides a modular framework in which different constraints such as deadline, throughput and energy consumption can easily be plugged depending on the system being designed.

The increasing processing power of today's HW/SW platforms leads to the integration of more and more functions in a single device. Additional design challenges arise when these functions share computing resources and belong to different criticality levels. The paper presents the CONTREX European project and its preliminary results. CONTREX complements current activities in the area of predictable computing platforms and segregation mechanisms with techniques to consider the extra-functional properties, i.e., timing constraints, power, and temperature. CONTREX enables energy efficient and cost aware design through analysis and optimization of these properties with regard to application demands at different criticality levels.

Recent work has proposed two-phase joint analytical and simulation-based design space exploration (JAS-DSE) approaches. In such approaches, a first analytical phase relies on static performance estimation and either on exhaustive or heuristic search, to perform a very fast filtering of the design space. Then, a second phase obtains the Pareto solutions after an exhaustive simulation of the solutions found as compliant by the analytical phase. However, the capability of such approaches to find solutions close to the actual Pareto set at a reasonable time cost is compromised by current system complexities. This limitation is due to the fact that such approaches do not support an heuristic exploration on the simulation-based phase. It is not straightforward because in the second phase the heuristic is constrained to consider only the custom set of solutions found in the first phase. This set is in general unconnected and irregularly distributed, which prevents the application of existing heuristics. This paper provides as a solution a novel search heuristic called ARS (Adaptive Random Sampling). The ARS strategy enables the application of heuristic search in the two phases of the JAS-DSE flow, by enabling the application of heuristic in the second phase, regardless the type of performance estimation done at each phase. Moreover, it enables the definition of N-phase DSE flows. The paper shows on an experiment focused on predictable multi-core systems how this enhanced JAS-DSE is capable to find more efficient solutions and to tune the trade-off between exploration time and accuracy in finding actual Pareto solutions.

Design space exploration (DSE) is a critical step in the design process of real-time multiprocessor systems. Combining a formal base in form of SDF graphs with predictable platforms providing guaranteed QoS, the paper proposes a flexible and extendable DSE framework that can provide performance guarantees for multiple applications implemented on a shared platform. The DSE framework is formulated in a declarative style as interprocess communication-aware constraint programming (CP) model. Apart from mapping and scheduling of application graphs, the model supports design constraints on several cost and performance metrics, as e.g. memory consumption and achievable throughput. Using constraints with different compliance level, the framework introduces support for mixed criticality in the CP model. The potential of the approach is demonstrated by means of experiments using a Sobel filter, a SUSAN filter, a RASTA-PLP application and a JPEG encoder.

SYLVA is a system level synthesis framework that transforms DSP sub-systems modeled as synchronous data flow into hardware implementations in ASIC, FPGAs or CGRAs. SYLVA synthesizes in terms of pre-characterized function implementations (FTMPs). It explores the design space in three dimensions, number of FTMPs, type of FTMPs and pipeline parallelism between the producing and consuming FTMPs. We introduce timing and interface model of FTMPs to enable reuse and automatic generation of Global Interconnect and Control (GLIC) to glue the FTMPs together into a working system. SYLVA has been evaluated by applying it to five realistic DSP applications and results analyzed for design space exploration, efficacy in generating GLIC by comparing to manually generated GLIC and accuracy of design space exploration by comparing the area and energy costs considered during the design space exploration based on pre-characterized FIMPs and the final results.