Login
HomePublicationsJournal Paper

Bus-Contention Aware WCRT Analysis for the 3-Phase Task Model Considering a Work-Conserving Bus Arbitration Scheme
Ref: CISTER-TR-211004       Publication Date: 13 to 14, Jan, 2022

Bus-Contention Aware WCRT Analysis for the 3-Phase Task Model Considering a Work-Conserving Bus Arbitration Scheme

Ref: CISTER-TR-211004       Publication Date: 13 to 14, Jan, 2022

Abstract:
Today multicore processors are used in most modern systems that require computational logic. However, their applicability in systems with stringent timing requirements is still an ongoing research. This is due to the difficulty of ensuring the timing correctness of tasks executing on a multicore platform that comprises a number of shared hardware resources, e.g., caches, memory bus and the main memory. Concurrent accesses to any of these shared resources can generate uncontrolled interference, which complicates the estimations of tasks' worst-case execution time (WCET) and the worst-case response time (WCRT). The use of the 3-phase task execution model helps in upper bounding the contention due to the sharing of bus/main memory in multicore systems. It divides the execution of tasks into distinct memory and execution phases, where tasks can only access the bus/main memory during their memory phases. This makes bus/memory access patterns of tasks more predictable, enabling a preciser computation of bus/memory contention. In this work, we show how the bus contention can be computed for the 3-phase task model considering a work-conserving, i.e., round-robin (RR) based, arbitration policy at the memory bus. This is different from existing works that analyze the time-division multiple access (TDMA) and first-come-first-serve (FCFS) based bus arbitration policies. First, we present a solution to model the bus contention that can be suffered/caused by tasks executing on the same/remote cores of a multicore system under an RR-based bus arbitration scheme. We then evaluate the impact of resulting bus contention on taskset schedulability. Experimental results show that our proposed RR-based bus contention analysis can improve taskset schedulability by up to 100 percentage points than the TDMA-based analysis and up to 40 percentage points than the FCFS-based bus contention analysis.

Authors:
Jatin Arora
,
Cláudio Maia
,
Syed Aftab Rashid
,
Geoffrey Nelissen
,
Eduardo Tovar


Published in Journal of Systems Architecture (JSA), Elsevier.
2022.
(Best Paper of ICESS 2021) (ICESS 2021), Volume Technical Session.
Virtual, Australia.

DOI:doi.org/10.1016/j.sysarc.2021.102345.



Record Date: 18, Oct, 2021