Research
Our research group is particularly concerned about “productivity” in the context of high performance computing, or in other words, to achieve “performance without pain”. From the computer architecture point of view we are in heterogeneous era where computing systems are composed of multicore or manycore CPUs along with accelerators like GPUs or FPGAs. To fully exploit these architectures is a challenge from the software point of view, because, to fully exploit them more development time and knowledge is required in comparison with the plain old sequential architectures. Our research goals are to find new tools and programming models to alleviate these new difficulties and challenges.
Research Interests
Parallel programming models, Scheduling for heterogeneous architectures, Parallel libraries (oneTBB), Parallel languages (DPC++, SYCL, oneAPI, Chapel, X10, UPC), Parallelizing/optimizing compilers, multiprocessor and heterogeneous (CPU+GPU+FPGA) architectures.
Selected publications
CPU and GPU oriented optimizations for LiDAR data processing
[doi]
Felipe Muñoz, Rafael Asenjo, Angeles Navarro, J. Carlos Cabaleiro
Journal of Computational Science,
Vol 79, July 2024
Impact Factor: 3.3; Category: Computer Science, Theory and Methods; 37/111, Q2 (JCR 2022)
SkyFlow: Heterogeneous Streaming for Skyline computation using FlowGraph and SYCL
[doi]
J.C. Romero, A. Navarro, A. Rodriguez, R. Asenjo
Future Generation Computer Systems,
Vol 141, pages 269-283, April 2023
Impact Factor: 7.5; Category: Computer Science, Theory and Methods; 10/111, Q1 (JCR 2022)
Lightweight asynchronous scheduling in heterogeneous reconfigurable systems
[doi]
A. Rodríguez, A. Navarro, K. Nikov, J. Nunez-Yanez, R. Gran, D. Suárez Gracia, R. Asenjo
Journal of Systems Architecture,
Vol 124, March 2022
Impact Factor: 4.5; Category: Computer Science, Hardware & Architecture; 11/54, Q1 (JCR 2022)
Efficient Heterogeneous Matrix Profile on a CPU + High Performance FPGA with Integrated HBM
[doi]
J.C. Romero, A. Navarro, A. Vilches, A. Rodriguez, F. Corbera, R. Asenjo
Future Generation Computer Systems,
Vol. 125, December 2021, pp. 10-23
Impact Factor: 7.307; Category: Computer Science, Theory and Methods; 10/109, Q1 (JCR 2021)
Efficiency and productivity for decision making on low-power heterogeneous CPU+GPU SoCs
[doi]
Denisa-Andreea Constantinescu, Angeles Navarro, Francisco Corbera, Juan-Antonio Fernández-Madrigal, Rafael Asenjo
The Journal of Supercomputing,
Vol 77, pp. 44-65, January 2021
Impact Factor: 2.557; Category: Computer Science, Theory and Methods; 43/110, Q2 (JCR 2021)
ScrimpCo: Scalable Matrix Profile on Commodity Heterogeneous Processors
[doi]
Jose Carlos Romero, Antonio Vilches, Andrés Rodríguez, Angeles Navarro, Rafael Asenjo
The Journal of Supercomputing,
March 2020
Impact Factor: 2.474; Category: Computer Science, Theory and Methods; 33/110, Q2 (JCR 2020)
Performance evaluation of decision making under uncertainty for low power heterogeneous platforms
[doi]
Denisa-Andreea Constantinescu, Angeles Navarro, Juan-Antonio Fernández Madrigal, Rafael Asenjo
Journal of Parallel and Distributed Computing, JPDC,
Vol. 137 pp. 119-133, March 2020
Impact Factor: 3.734; Category: Computer Science, Theory and Methods; 19/110, Q1 (JCR 2020)
News
New Paper Published - May 6, 2024
New Paper Published - November 18, 2022
Postdoc Position Open - November 14, 2022