Wolf, Dennis Leander ; Spang, Christoph ; Diener, Daniel ; Hochberger, Christian (2022)
Advantages of a Statistical Estimation Approach for Clock Frequency Estimation of Heterogeneous and Irregular CGRAs.
In: ACM Transactions on Reconfigurable Technology and Systems, 16 (1)
doi: 10.1145/3531062
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
Estimating the maximum clock frequency of homogeneous Coarse Grained Reconfigurable Arrays/ Architectures (CGRAs) with an arbitrary number of Processing Elements (PE) is difficult. Clock frequency estimation of highly heterogeneous CGRAs takes additional factors into account, thus is even more difficult. Main challenges are the heterogeneous set of operators for each Processing Element (PE) and the irregular interconnect (connecting a CGRA’s PEs). Multiple estimation approaches could be reasonable. We propose an optimized statistical estimator, which is based on our prior work. We demonstrate its superiority to state of the art neural networks in terms of accuracy and robustness, especially in situations with a sparse set of training data.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Wolf, Dennis Leander ; Spang, Christoph ; Diener, Daniel ; Hochberger, Christian |
| Art des Eintrags: | Bibliographie |
| Titel: | Advantages of a Statistical Estimation Approach for Clock Frequency Estimation of Heterogeneous and Irregular CGRAs |
| Sprache: | Englisch |
| Publikationsjahr: | 22 Dezember 2022 |
| Verlag: | ACM |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | ACM Transactions on Reconfigurable Technology and Systems |
| Jahrgang/Volume einer Zeitschrift: | 16 |
| (Heft-)Nummer: | 1 |
| DOI: | 10.1145/3531062 |
| Kurzbeschreibung (Abstract): | Estimating the maximum clock frequency of homogeneous Coarse Grained Reconfigurable Arrays/ Architectures (CGRAs) with an arbitrary number of Processing Elements (PE) is difficult. Clock frequency estimation of highly heterogeneous CGRAs takes additional factors into account, thus is even more difficult. Main challenges are the heterogeneous set of operators for each Processing Element (PE) and the irregular interconnect (connecting a CGRA’s PEs). Multiple estimation approaches could be reasonable. We propose an optimized statistical estimator, which is based on our prior work. We demonstrate its superiority to state of the art neural networks in terms of accuracy and robustness, especially in situations with a sparse set of training data. |
| Freie Schlagworte: | Design Space Exploration, Automation, Machine Learning, Coarse Grained Reconfigurable Architecture, Heterogeneity |
| ID-Nummer: | Artikel-ID: 7 |
| Fachbereich(e)/-gebiet(e): | 18 Fachbereich Elektrotechnik und Informationstechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Datentechnik 18 Fachbereich Elektrotechnik und Informationstechnik > Institut für Datentechnik > Rechnersysteme |
| Hinterlegungsdatum: | 26 Okt 2022 07:07 |
| Letzte Änderung: | 22 Jul 2024 13:20 |
| PPN: | 508920698 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum