Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2509.18295 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916961774993408 |
|---|---|
| author | Boston, Allen Seyoum, Biruk Carloni, Luca Gaillardon, Pierre-Emmanuel |
| author_facet | Boston, Allen Seyoum, Biruk Carloni, Luca Gaillardon, Pierre-Emmanuel |
| contents | Field-Programmable Gate Arrays (FPGAs) have evolved from uniform logic arrays into heterogeneous fabrics integrating digital signal processors (DSPs), memories, and specialized accelerators to support emerging workloads such as machine learning. While these enhancements improve power, performance, and area (PPA), they complicate design space exploration and application optimization due to complex resource interactions.
To address these challenges, we propose a lightweight profiling methodology inspired by the Roofline model. It introduces three congruence scores that quickly identify bottlenecks related to heterogeneous resources, fabric, and application logic. Evaluated on the Koios and VPR benchmark suites using a Stratix 10 like FPGA, this approach enables efficient FPGA architecture co-design to improve heterogeneous FPGA performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18295 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lightweight Congruence Profiling for Early Design Exploration of Heterogeneous FPGAs Boston, Allen Seyoum, Biruk Carloni, Luca Gaillardon, Pierre-Emmanuel Hardware Architecture Field-Programmable Gate Arrays (FPGAs) have evolved from uniform logic arrays into heterogeneous fabrics integrating digital signal processors (DSPs), memories, and specialized accelerators to support emerging workloads such as machine learning. While these enhancements improve power, performance, and area (PPA), they complicate design space exploration and application optimization due to complex resource interactions. To address these challenges, we propose a lightweight profiling methodology inspired by the Roofline model. It introduces three congruence scores that quickly identify bottlenecks related to heterogeneous resources, fabric, and application logic. Evaluated on the Koios and VPR benchmark suites using a Stratix 10 like FPGA, this approach enables efficient FPGA architecture co-design to improve heterogeneous FPGA performance. |
| title | Lightweight Congruence Profiling for Early Design Exploration of Heterogeneous FPGAs |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2509.18295 |