Efficient traversal of decision tree ensembles with FPGAs | ||
| dc.conicet.organizacion | Universidad Nacional de San Luis | |
| dc.conicet.organizacion | Università degli Studi di Trieste | |
| dc.conicet.organizacion | The Abdus Salam International Centre for Theoretical Physics | |
| dc.conicet.organizacion | Universidad Nacional de San Luis. Facultad de Ciencias Físico- Matemáticas y Naturales | |
| dc.conicet.organizacion | Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis | |
| dc.conicet.organizacion | Universidad Nacional de San Luis. Facultad de Ciencias Físico- Matemáticas y Naturales | |
| dc.conicet.organizacion | Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis | |
| dc.conicet.organizacion | Consiglio Nazionale delle Ricerche | |
| dc.conicet.organizacion | Consiglio Nazionale delle Ricerche | |
| dc.conicet.organizacion | Consiglio Nazionale delle Ricerche | |
| dc.contributor.author | Molina, Romina Soledad | |
| dc.contributor.author | Loor, Fernando | |
| dc.contributor.author | Gil Costa, Graciela Verónica | |
| dc.contributor.author | Nardini, Franco Maria | |
| dc.contributor.author | Perego, Raffaele | |
| dc.contributor.author | Trani, Salvatore | |
| dc.date.issued | 2021-09 | |
| dc.description.abstract | System-on-Chip (SoC) based Field Programmable Gate Arrays (FPGAs) provide a hardware acceleration technology that can be rapidly deployed and tuned, thus providing a flexible solution adaptable to specific design requirements and to changing demands. In this paper, we present three SoC architecture designs for speeding-up inference tasks based on machine learned ensembles of decision trees. We focus on QuickScorer, the state-of-the-art algorithm for the efficient traversal of tree ensembles and present the issues and the advantages related to its deployment on two SoC devices with different capacities. The results of the experiments conducted using publicly available datasets show that the solution proposed is very efficient and scalable. More importantly, it provides almost constant inference times, independently of the number of trees in the model and the number of instances to score. This allows the SoC solution deployed to be fine tuned on the basis of the accuracy and latency constraints of the application scenario considered. | es |
| dc.description.fil | Fil: Molina, Romina Soledad. Universidad Nacional de San Luis; Argentina. Università degli Studi di Trieste; Italia. The Abdus Salam International Centre for Theoretical Physics; Italia | |
| dc.description.fil | Fil: Loor, Fernando. Universidad Nacional de San Luis. Facultad de Ciencias Físico- Matemáticas y Naturales; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina | |
| dc.description.fil | Fil: Gil Costa, Graciela Verónica. Universidad Nacional de San Luis. Facultad de Ciencias Físico- Matemáticas y Naturales; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina | |
| dc.description.fil | Fil: Nardini, Franco Maria. Consiglio Nazionale delle Ricerche; Italia | |
| dc.description.fil | Fil: Perego, Raffaele. Consiglio Nazionale delle Ricerche; Italia | |
| dc.description.fil | Fil: Trani, Salvatore. Consiglio Nazionale delle Ricerche; Italia | |
| dc.format | application/pdf | es |
| dc.identifier.citation | Molina, Romina Soledad; Loor, Fernando; Gil Costa, Graciela Verónica; Nardini, Franco Maria; Perego, Raffaele; et al.; Efficient traversal of decision tree ensembles with FPGAs; Academic Press Inc Elsevier Science; Journal of Parallel and Distributed Computing; 155; 9-2021; 38-49 | es |
| dc.identifier.eissn | 1096-0848 | es |
| dc.identifier.institucional | CONICET | |
| dc.identifier.issn | 0743-7315 | es |
| dc.identifier.repo | CONICET Digital | |
| dc.identifier.uri | http://hdl.handle.net/11336/150230 | |
| dc.journal.pagination | 38-49 | es |
| dc.journal.pais | Estados Unidos | es |
| dc.journal.title | Journal of Parallel and Distributed Computing | es |
| dc.journal.volume | 155 | es |
| dc.language.iso | eng | es |
| dc.publisher | Academic Press Inc Elsevier Science | es |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S0743731521000915 | |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1016/j.jpdc.2021.04.008 | |
| dc.rights | info:eu-repo/semantics/restrictedAccess | * |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ | * |
| dc.subject | DECISION TREES | es |
| dc.subject | FPGA | es |
| dc.subject | MACHINE LEARNING | es |
| dc.subject | SYSTEM ON CHIP | es |
| dc.subject.classification | Ciencias de la Computación | es |
| dc.subject.classification | Ciencias de la Computación e Información | es |
| dc.subject.classification | CIENCIAS NATURALES Y EXACTAS | es |
| dc.title | Efficient traversal of decision tree ensembles with FPGAs | es |
| dc.type | info:eu-repo/semantics/article | |
| dc.type | info:ar-repo/semantics/artículo | |
| dc.type | info:eu-repo/semantics/publishedVersion | |
Archivos
Bloque original
Cargando...
- Nombre:
- CONICET_Digital_Nro.5edf6014-b0c8-4f5d-b836-91b81aadca0a_V.pdf
- Tamaño:
- 1.93 MB
- Formato:
- Adobe Portable Document Format
- Descripción: