Run-time reconfigurable RTOS for reconfigurable systems-on-chip

Götz, Marcelo; Rettberg, Achim; Pereira, Carlos Eduardo; Rammig, Franz J.

doi:10.3233/jec-2009-0077

Cited by 7 publications

(1 citation statement)

References 104 publications

(107 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Static server-based scheduling for FPGAs was first studied in [13] for independent periodic tasks. On-line server-based scheduling is described in [14], [15], in the context of a realtime operating system, also for independent tasks. Our work di ers from [13]- [15] as (i) we account for task dependencies and (ii) we provide a generic model for : resources whose requests are constant in time and independent of task scheduling.…”

Section: Rmentioning

confidence: 99%

Efficient Scheduling of FPGAs for Cloud Data Center Infrastructures

Bertolino

Pacalet

Apvrille

et al. 2020

2020 23rd Euromicro Conference on Digital System Design (DSD)

View full text Add to dashboard Cite

In modern cloud data centers, reconfigurable devices can be directly connected to a data center's network. This configuration enables FPGAs to be rented for acceleration of dataintensive workloads. In this context, novel scheduling solutions are needed to maximize the utilization (profitability) of FPGAs, e.g., reduce latency and resource fragmentation. Algorithms that schedule groups of tasks (clusters, packs), rather than individual tasks (list scheduling), well match the functioning of FPGAs. Here, groups of tasks that execute together are interposed by hardware reconfigurations. In this paper, we propose a heuristic based on a novel method for grouping tasks. These are gathered around a high-latency task that hides the latency of remaining tasks within the same group. We evaluated our solution on a benchmark of almost 30000 random workloads, synthesized from realistic designs (i.e., topology, resource occupancy). For this testbench, on average, our heuristic produces optimum makespan solutions in 71.3% of the cases. It produces solutions for moderately constrained systems (i.e., the deadline falls within 10% of the optimum makespan) in 88.1% of the cases.

show abstract