Throughput-bufering trade-of analysis for scenario-aware dataflow models

Rok vydání: 2018
Předmět:
Popis: In multi-media applications, bufers represent storage spaces that are used to store the data communicated between diferent tasks in the application, and throughput refers to the rate at which output data is produced by the application. The capacities of the bufers inluence the throughput, by altering the waiting times for tasks that need to read or write data from or to the bufers. The bufers are realized using memory. To minimize the memory usage, we look for algorithms to compute the minimal capacity requirements for bufers to execute an application under a given throughput constraint. Synchronous datalow (SDF) is a common formalism used to model applications in such algorithms. SDF however, is not suitable to describe today’s dynamic applications, as it cannot express task variations. Finite-State-Machine Scenario-Aware Datalow (FSM-SADF) is an extension of SDF that allows for not only task variations, but also structural variations, making it suitable for a wide range of dynamic applications. This paper provides the irst throughput-bufering trade-of analysis for FSM-SADF models. The analysis provides the Pareto space of throughput and storage space trade-ofs. The trade-of analysis is done by a guided Design Space Exploration (DSE) that cuts-of the exploration on non-critical bufers. The core of such a DSE is an FSM-SADF throughput analysis that, given the capacity of every bufer, obtains the throughput, as well as the critical bufers. We demonstrate the feasibility of our analysis with a number of examples. © 2018 Association for Computing Machinery.
Databáze: OpenAIRE