No abstract

The digital signal processing (DSP) applications are one of the biggest consumers of computing. They process a big data volume which is represented with a high accuracy. They use complex algorithms, and must satisfy a time constraints in most of cases. In the other hand, it's necessary today to use parallel and heterogeneous architectures in order to speedup the processing, where the best examples are the supercomputers "Tianhe-2" and "Titan" from the top500 ranking. These architectures could contain several connected nodes, where each node includes a number of generalist processor (multi-core) and a number of accelerators (many-core) to finally allows several levels of parallelism. However, for DSP programmers, it's still complicated to exploit all these parallelism levels to reach good performance for their applications. They have to design their implementation to take advantage of all heterogeneous computing units, taking into account the architecture specificities of each of them: communication model, memory management, data management, jobs scheduling and synchronization. .. etc. In the present work, we characterize DSP applications, and based on their distinctiveness, we propose a high level visual programming model and an execution model in order to drop down their implementations and in the same time make desirable performances.

The biomedical imagery, the numeric communications, the acoustic signal processing and many others digital signal processing (DSP) applications are present more and more in the numeric world. They process growing data volume which is represented with more and more accuracy, and use complex algorithms with time constraints to satisfying. Consequently, a high requirement of computing power characterize them.To satisfy this need, it's inevitable today to use parallel and heterogeneous architectures in order to speedup the processing, where the best examples are today's supercomputers like "Tianhe-2" and "Titan" of Top500 ranking. These architectures with their multi-core nodes supported by many-core accelerators offer a good response to this problem. However, they are still hard to program to make performance because of many reasons: Parallelism expression, task synchronization, memory management, hardware specifications handling, load balancing . . . In the present work, we are characterizing DSP applications and propose a programming model based on their distinctiveness in order to implement them easily and efficiently on heterogeneous clusters.

International audienceNowadays, computing hardware continues to move toward more parallelism and more heterogeneity, to obtain more computing power. From personal computers to supercomputers, we can find several levels of parallelism expressed by the interconnections of multi-core and many-core accelerators. On the other hand, computing software needs to adapt to this trend, and programmers can use parallel programming models (PPM) to fulfil this difficult task. There are different PPMs available that are based on tasks, directives, or low level languages or library. These offer higher or lower abstraction levels from the architecture by handling their own syntax. However, to offer an efficient PPM with a greater (additional) high-levelabstraction level while saving on performance, one idea is to restrict this to a specific domain and to adapt it to a family of applications. In the present study, we propose a high-level PPM specific to digital signal processing applications. It is based on data-flow graph models of computation, and a dynamic runtime model of execution (StarPU). We show how the user can easily express this digital signal processing application, and can take advantage of task, data and graph parallelism in the implementation, to enhance the performances of targeted heterogeneous clusters composed of CPUs and different accelerators (e.g., GPU, Xeon Phi