To guarantee the timing constraints of real-time IoT devices, engineers need to estimate the Worst-Case Execution Time. Such estimation is always very pessimistic and represents a condition that almost never occurs in practice. In this poster, we present a novel compiler-based approach that instruments the tasks to inform, at run-time, the operating system when non-worst-case branches are taken. The generated slack is then used to take better scheduling decisions.
Poster Abstract: Run-time Dynamic WCET Estimation
Lia Cagnizi;Federico Reghenzani;William Fornaciari
2023-01-01
Abstract
To guarantee the timing constraints of real-time IoT devices, engineers need to estimate the Worst-Case Execution Time. Such estimation is always very pessimistic and represents a condition that almost never occurs in practice. In this poster, we present a novel compiler-based approach that instruments the tasks to inform, at run-time, the operating system when non-worst-case branches are taken. The generated slack is then used to take better scheduling decisions.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
2023_IOTDI_AAM.pdf
Open Access dal 11/05/2023
Descrizione: Paper
:
Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione
470.67 kB
Formato
Adobe PDF
|
470.67 kB | Adobe PDF | Visualizza/Apri |
3576842.3589168_poster_lia.pdf
Accesso riservato
Descrizione: camera ready
:
Publisher’s version
Dimensione
511.65 kB
Formato
Adobe PDF
|
511.65 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.