Work-in-Progress: Determining MPSoC Layout from Thermal Camera Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00353349" target="_blank" >RIV/68407700:21230/21:00353349 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/21:00353349

Výsledek na webu

<a href="https://doi.org/10.1145/3477244.3477619" target="_blank" >https://doi.org/10.1145/3477244.3477619</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3477244.3477619" target="_blank" >10.1145/3477244.3477619</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Work-in-Progress: Determining MPSoC Layout from Thermal Camera Images

Popis výsledku v původním jazyce

In many safety-critical applications, Multi-Processor Systems-on- Chip (MPSoC) must operate within a given thermal envelope under harsh environmental conditions. Meeting the thermal requirements often requires using advanced task allocation and scheduling techniques that are guided by detailed power models. This paper introduces a method that has the potential to simplify the creation of such models. It constructs so-called heat maps from thermal camera images. By comparing the heat maps of different workloads, we identify the locations of on-chip components and the amount of heat produced by them. We demonstrate our method on the i.MX8QuadMax chip from NXP, where we identify the locations of CPU clusters, bigger CPU cores, GPUs, and DRAM controllers.

Název v anglickém jazyce

Work-in-Progress: Determining MPSoC Layout from Thermal Camera Images

Popis výsledku anglicky

In many safety-critical applications, Multi-Processor Systems-on- Chip (MPSoC) must operate within a given thermal envelope under harsh environmental conditions. Meeting the thermal requirements often requires using advanced task allocation and scheduling techniques that are guided by detailed power models. This paper introduces a method that has the potential to simplify the creation of such models. It constructs so-called heat maps from thermal camera images. By comparing the heat maps of different workloads, we identify the locations of on-chip components and the amount of heat produced by them. We demonstrate our method on the i.MX8QuadMax chip from NXP, where we identify the locations of CPU clusters, bigger CPU cores, GPUs, and DRAM controllers.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

EMSOFT '21: Proceedings of the 2021 International Conference on Embedded Software

ISBN

978-1-4503-8712-5

ISSN

—

e-ISSN

—

Počet stran výsledku

2

Strana od-do

39-40

Název nakladatele

Association for Computing Machinery

Místo vydání

New York

Místo konání akce

Virtual

Datum konání akce

8. 10. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000724136100011