RT Journal Article
T1 Enabling Easier Programming of Machine Learning Algorithms on Robots with oneAPI Toolkits.
A1 Constantinescu, Denisa-Andreea
A1 González-Navarro, María Ángeles
A1 Asenjo-Plaza, Rafael
A1 Fernández-Madrigal, Juan Antonio
A1 Cruz-Martín, Ana María
K1 Aprendizaje automático
K1 Aplicaciones informáticas - Desarrollo
AB This work shows that it is feasible to solve large-scale decision-making problems forrobot navigation in real-time onboard low-power heterogeneous CPU+iGPU platforms. We canachieve both performance and productivity by carefully selecting the scheduling strategy andprogramming model. In particular, we remark that the oneAPI programming model creates newopportunities to improve productivity, performance, and efficiency in low-power systems. Ourexperimental results show that the implementations based on the oneAPI programming modelare up to 5× easier to program than those based on OpenCL while incurring only 3 to 8%overhead for low-power systems.
PB SCV Chapter, IEEE Computer Society
YR 2022
FD 2022
LK https://hdl.handle.net/10630/38041
UL https://hdl.handle.net/10630/38041
LA eng
NO https://r6.ieee.org/scv-cs/wp-content/uploads/sites/81/2022/03/1-CS-Mag-Feedforward-Denisa-MyFinal.pdf
NO This work was supported in part by grants from TIN2016-80920-R, PID2019-105396RB-I00, UMA18-FEDERJA-108, UMA18-FEDERJA-113, and Intel.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026