Analysis and optimization of dynamic dataflow programs

Casale-Brunet, Simone

doi:10.5075/epfl-thesis-6663

Cited by 12 publications

(3 citation statements)

References 146 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At every stage, depending on its input token's value and the values of its state variables, a single action is allowed to be executed. The resultant lack of data race and critical section made the behavior of the dataflow software more robust to various computational policies, whether they were fully parallel or only interleaving the respective actor executions [7].…”

Section: Dataflow Programs and Design Space Explorationmentioning

confidence: 99%

“…Via software interpretation applied at the level of the RVC-CAL language supplied by the Orcc toolchain, it was possible to obtain a performance-aware, platform-independent, and high-level emulation of the abstract execution of an input application software. As outlined in Figure 2, during this step, TURNUS was capable of evaluating the execution trace graph (ETG) of the software application program [7]. The ETG is a graph-shaped replica of the dataflow program execution, in which every directed edge represents a runtime dependency (i.e., internal variable, finite state machine, guard, port, and tokens.)…”

Section: Design Space Explorationmentioning

confidence: 99%

“…This fact makes evident the necessity of having systematic and automatic methods of recognizing and assessing efficient configurations and designs. TURNUS [6,7] is a design space exploration software tool based on the research conducted by the authors of this article with this intent. The framework was designed using a high-level abstract model of computation (MoC) as a result of the dataflow network structure and the acting model of execution.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Performance Estimation of High-Level Dataflow Program on Heterogeneous Platforms by Dynamic Network Execution

Bloch

Casale-Brunet

Mattavelli

2022

JLPEA

View full text Add to dashboard Cite

The performance of programs executed on heterogeneous parallel platforms largely depends on the design choices regarding how to partition the processing on the various different processing units. In other words, it depends on the assumptions and parameters that define the partitioning, mapping, scheduling, and allocation of data exchanges among the various processing elements of the platform executing the program. The advantage of programs written in languages using the dataflow model of computation (MoC) is that executing the program with different configurations and parameter settings does not require rewriting the application software for each configuration setting, but only requires generating a new synthesis of the execution code corresponding to different parameters. The synthesis stage of dataflow programs is usually supported by automatic code generation tools. Another competitive advantage of dataflow software methodologies is that they are well-suited to support designs on heterogeneous parallel systems as they are inherently free of memory access contention issues and naturally expose the available intrinsic parallelism. So as to fully exploit these advantages and to be able to efficiently search the configuration space to find the design points that better satisfy the desired design constraints, it is necessary to develop tools and associated methodologies capable of evaluating the performance of different configurations and to drive the search for good design configurations, according to the desired performance criteria. The number of possible design assumptions and associated parameter settings is usually so large (i.e., the dimensions and size of the design space) that intuition as well as trial and error are clearly unfeasible, inefficient approaches. This paper describes a method for the clock-accurate profiling of software applications developed using the dataflow programming paradigm such as the formal RVL-CAL language. The profiling can be applied when the application program has been compiled and executed on GPU/CPU heterogeneous hardware platforms utilizing two main methodologies, denoted as static and dynamic. This paper also describes how a method for the qualitative evaluation of the performance of such programs as a function of the supplied configuration parameters can be successfully applied to heterogeneous platforms. The technique was illustrated using two different application software examples and several design points.

show abstract

Section: Dataflow Programs and Design Space Explorationmentioning

confidence: 99%

Section: Design Space Explorationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation