Domain-specific languages assessment in heterogeneous architectures: from low-power to high-performance platforms
The evolution of computer architecture faces new challenges encompassing energy efficiency, reliability, and performance, marking a departure from the traditional Moore's Law and Dennard's scaling paradigms. This transition towards hardware specialization and heterogeneous systems necessit...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis doctoral |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | inglés |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/117665 |
| Acceso en línea: | https://hdl.handle.net/20.500.14352/117665 |
| Access Level: | acceso abierto |
| Palabra clave: | 004.3(043.2) Arquitectura de ordenadores Informática (Informática) 1203.17 Informática |
| Sumario: | The evolution of computer architecture faces new challenges encompassing energy efficiency, reliability, and performance, marking a departure from the traditional Moore's Law and Dennard's scaling paradigms. This transition towards hardware specialization and heterogeneous systems necessitates novel programming models to fully exploit their ccapabilities. Domain-specific architectures have emerged as a solution to these challenges, offering specialized hardware for specific tasks, such as machine learning, signal processing, and cryuptography. In response, domain-specific languages have emerged as a soluiton to the complexity of programming these architectures, providing high-level abstractions that allow developers to focus on the algorithmic aspects of their applications. However, many of these languages are not protable or vendro-dependent. Languages like VHDL or CUDA serve as examples... |
|---|