Odyn: Deadlock Prevention and Hybrid Scheduling Algorithm for Real-Time Dataflow Applications

Abstract

In recent wireless communication standards (4G, 5G), the growing need for dynamic adjustments of transmission parameters (e.g., modulation, bandwidth, channel coding rate) makes traditional static scheduling approaches less and less efficient. The reason being that precomputed fixed mapping and scheduling prevent the system from dynamically adapting to changes of the operating conditions (e.g. wireless channel quality, available bandwidth). In this paper, we present Odyn, a hybrid approach for the scheduling and memory management of periodic dataflow applications on parallel, heterogeneous, Non-Uniform Memory Architecture (NUMA) platforms. In Odyn, the ordering of tasks and memory allocation are distributed and computed simultaneously at run-time for each Processing Element. Odyn also proposes a mechanism to prevent deadlocks caused by attempts to allocate buffers in size-limited memories. This technique, based on the static computation of exclusion relations among buffers in a target application, removes the need for backtracking that is typical of dynamic scheduling algorithms. We demonstrate the effectiveness of Odyn on a testbench that simulates the interactions of randomly generated concurrent applications. We also demonstrate its deadlock prevention technique on a selection of use cases.

Scheduling Algorithms Implementation for Real Time Operating Systems: A Review

“…Testing findings indicate that the suggested method beats two current algorithms in terms of project length (by up to 28.73 %) and resource consumption (up to 46.31 percent). Dauphin et al [103], On parallel, heterogeneous, Non-Uniform Memory Architecture (NUMA) systems, a hybrid technique for scheduling and memory management of periodical dataflow apps was proven. The task ordering and memory allocation for each Processing Element are distributed and computed concurrently in Odyn.…”