Browsing by Author "Navaux, Philippe O.A."
Now showing items 1-8 of 8
-
Adaptive request scheduling for the I/O forwarding layer using reinforcement learning
Bez, Jean Luca; Zanon Boito, Francieli; Nou Castell, Ramon; Miranda Bueno, Alberto; Cortés, Toni; Navaux, Philippe O.A. (Elsevier, 2020-11)
Article
Open AccessIn this paper, we propose an approach to adapt the I/O forwarding layer of HPC systems to applications’ access patterns. I/O optimization techniques can improve performance for the access patterns they were designed to ... -
Arbitration policies for on-demand user-level I/O forwarding on HPC platforms
Bez, Jean Luca; Miranda, Alberto; Nou Castell, Ramon; Zanon Boito, Francieli; Cortés, Toni; Navaux, Philippe O.A. (Institute of Electrical and Electronics Engineers (IEEE), 2021)
Conference report
Open AccessI/O forwarding is a well-established and widely-adopted technique in HPC to reduce contention in the access to storage servers and transparently improve I/O performance. Rather than having applications directly accessing ... -
Enhancing Energy Production with Exascale HPC Methods
Camata, José J.; Cela, José M.; Costa, Danilo; Coutinho, Alvaro LGA; Fernández-Galisteo, Daniel; Jiménez, Carmen; Kourdioumov, Vadim; Mattoso, Marta; Mayo-García, Rafael; Miras, Thomas; Moríñigo, José A.; Navarro, Jorge; Navaux, Philippe O.A.; Oliveira, Daniel de; Rodríguez-Pascual, Manuel; Silva, Vítor; Souza, Renan; Valduriez, Patrick (2016)
Conference lecture
Open AccessHigh Performance Computing (HPC) resources have become the key actor for achieving more ambitious challenges in many disciplines. In this step beyond, an explosion on the available parallelism and the use of special ... -
Fostering Collaboration in Energy Research and Technological Developments applying new exascale HPC techniques
Cela, Jose M.; Coutinho, Alvaro L.G.A.; Navaux, Philippe O.A.; Mayo-García, Rafael (Institute of Electrical and Electronics Engineers (IEEE), 2016-05)
Conference report
Open AccessDuring the last years, High Performance Computing (HPC) resources have undergone a dramatic transformation, with an explosion on the available parallelism and the use of special purpose processors. There ... -
Hardware-Assisted Thread and Data Mapping in Hierarchical Multicore Architectures
Cruz, Eduardo H.M.; Diener, Matthias; Pilla, Laércio L.; Navaux, Philippe O.A. (Association for Computing Machinery (ACM), 2016-09-06)
Article
Open AccessThe performance and energy efficiency of modern architectures depend on memory locality, which can be improved by thread and data mappings considering the memory access behavior of parallel applications. In this article, ... -
Leveraging Cloud Heterogeneity for Cost-Efficient Execution of Parallel Applications
Roloff, Eduardo; Diener, Matthias; Diaz Carreño, Emmanuell; Gaspary, Luciano Paschoal; Navaux, Philippe O.A. (Springer, 2017-08-01)
Conference lecture
Open AccessPublic cloud providers offer a wide range of instance types, with different processing and interconnection speeds, as well as varying prices. Furthermore, the tasks of many parallel applications show different computational ... -
Strategies to Improve the Performance of a Geophysics Model for Different Manycore Systems
Serpa, Matheus S.; Cruz, Eduardo H.M.; Diener, Matthias; Krause, Arthur M.; Navaux, Philippe O.A.; Farrés, Albert; Rosas, Claudia; Hanzich, Mauricio; Panetta, Jairo (IEEE, 2017-11-16)
Conference lecture
Open AccessMany software mechanisms for geophysics exploration in Oil & Gas industries are based on wave propagation simulation. To perform such simulations, state-of-art HPC architectures are employed, generating results faster and ... -
Towards on-demand I/O forwarding in HPC platforms
Bez, Jean Luca; Zanon Boito, Francieli; Miranda Bueno, Alberto; Nou Castell, Ramon; Cortés, Toni; Navaux, Philippe O.A. (Institute of Electrical and Electronics Engineers (IEEE), 2020)
Conference report
Open AccessI/O forwarding is an established and widely-adopted technique in HPC to reduce contention and improve I/O performance in the access to shared storage infrastructure. On such machines, this layer is often physically deployed ...