Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/129250
Título: A Hardware/Software Design Space Exploration for Efficient Video Compression on ESA missions
Autores/as: Machado, Felipe
Barrios,Yubal 
Sarmiento, Roberto 
Sanjuan, Francisco
Fiengo, Aniello
Clasificación UNESCO: 3307 Tecnología electrónica
Palabras clave: Design Space Exploration
High-Level Synthesis
Software Profiling
Video Compression
Fecha de publicación: 2023
Publicación seriada: Proceedings Of The 2023 European Data Handling And Data Processing Conference For Space, Edhpc 2023
Conferencia: 2023 European Data Handling and Data Processing Conference for Space, EDHPC 2023 
Resumen: Electronics design of complex systems is not trivial when it is directly addressed at RTL. Under highly timing-constrained projects, such as space missions, it is useful to quickly develop a system model with a higher level of abstraction than RTL to identify critical processing stages that could prevent from achieving design goals in terms of performance, hardware occupancy and/or power consumption. At the same time, the development time at RTL could be reduced, since some of the main issues are already detected and solved in the high-level model. This work presents a mixed DSE strategy, combining software profiling with HLS models. While software profiling allows to quickly identify the critical stages of the system functionality from a computational point of view, the HLS design methodology permits to evaluate those critical system stages but considering their implications when the design is implemented on hardware. The use case is the development of a video compression IP core for future ESA missions, compliant with the H.264 standard, which is a highly-parameterized algorithm with several features. Therefore, at early stages it is important to restrict the options of the standard to those that will keep the project performance goals while limiting the hardware occupancy.
URI: http://hdl.handle.net/10553/129250
ISBN: 9789090379241
DOI: 10.23919/EDHPC59100.2023.10396095
Fuente: Proceedings of the 2023 European Data Handling and Data Processing Conference for Space, EDHPC 2023[EISSN ], (Enero 2023)
Colección:Actas de congresos
Vista completa

Visitas

41
actualizado el 13-ene-2024

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.