This paper presents a novel approach to efficiently perform early system level design space exploration (DSE) of MultiProcessor System-on-Chip (MPSoC) based embedded systems. By modeling dynamic multi-application workloads using application scenarios, optimal designs can be quickly identified using a combination of a scenario-based DSE and a feature selection algorithm. The feature selection algorithm identifies a representative subset of scenarios, which is used to predict the fitness of the MPSoC design instances in the genetic algorithm of the scenario-based DSE. Results show that our scenario-based DSE provides a tradeoff between the speed and accuracy of the early DSE.
Modularity is a desirable characteristic for software systems. In this article we propose to use a quantitative method from complex network sciences to estimate the coherence between the modularity of the dependency network of large open source Java projects and their decomposition in terms of Java packages. The results presented in this article indicate that our methodology offers a promising and reasonable quantitative approach with potential impact on software engineering processes.
We describe a task model and dynamic scheduling and resource allocation mechanism for synchronous parallel tasks to be executed on SPMD-programmed synchronous shared-memory MIMD parallel architectures with uniform, unit-time memory access and strict memory consistency, also known in the literature as PRAMs (Parallel Random Access Machines). Our task model provides a two-tier programming model for PRAMs that flexibly combines SPMD and fork-join parallelism within the same application. It offers flexibility by dynamic scheduling and late resource binding while preserving the PRAM execution properties within each task, the only limitation being that the maximum number of threads that can be assigned to a task is limited to what the underlying architecture provides. In particular, our approach opens for automatic performance tuning at run-time by controlling the thread allocation for tasks based on run-time predictions. By a prototype implementation of a synchronous parallel task API in the SPMD-based PRAM language Fork and experimental evaluation with example programs on the SBPRAM simulator, we show that a realization of the task model on a SPMD-programmable PRAM machine is feasible with moderate runtime overhead per task.
Many years of research on dependable, fault-tolerant software systems yielded many tool implementations for vulnerability analysis and experimental validation of resilience measures. We identify two disjoint classes of fault-injection (FI) experiment tools in the field, and argue that both are plagued by inherent deficiencies, such as insufficient target state access, little or no means to switch to another target system, and non-reusable experiment code. In this article, we present a novel design approach for a FI infrastructure that aims at combining the strengths of both classes. Our Fail∗ experiment framework provides carefully-chosen abstractions simplifying both the implementation of different simulator/hardware target backends and the reuse of experiment code, while retaining the ability for deep targetstate access for specialized FI experiments. An exemplary report on first experiences with a prototype implementation based on existing x86 and ARM simulators demonstrates the tool's versatility.
Efficient computation of regional land-surface parameters for large-scale digital elevation models becomes more and more important, in particular for web-based applications. This paper studies the possibilities of decreasing computing time for such tasks by parallel processing using multi-threads on multi-core processors. As an example of calculations of regional land-surface parameters we investigate the computation of flow directions and propose a modified D8 algorithm using an extended neighborhood. In this paper, we discuss two parallelization strategies, one based on a spatial decomposition, the other based on a two-phase approach. Three datasets of high resolution digital elevation models with different geomorphological types of landscapes are used in our evaluation. While local surface parameters allow for an almost ideal speed-up, the situation is different for the calculation of non-local parameters due to data dependencies. Nevertheless, still a significant decrease of computation time has been achieved. A task pool-based strategy turns out to be more efficient for calculations on datasets with many data dependencies.
