arXiv subjects

Vanderson Martins do Rosario

Publications and source records attributed to Vanderson Martins do Rosario.

3 recordsLinked to original sources

arXiv2020

Accelerating Multi-attribute Unsupervised Seismic Facies Analysis With RAPIDS

Classification of seismic facies is done by clustering seismic data samples based on their attributes. Year after year, 3D datasets used by exploration geophysics increase in size, complexity, and number of attributes, requiring a continuous rise in the classification performance. In this work, we explore the use of Graphics Processing Units (GPUs) to perform the classification of seismic surveys using the well-established Machine Learning (ML) method k-means. We show that the high-performance distributed implementation of the k-means algorithm available at the RAPIDS library can be used to classify facies in large seismic datasets much faster than a classical parallel CPU implementation (up to 258-fold faster in NVIDIA V100 GPUs), especially for large seismic blocks. We tested the algorithm with different real seismic volumes, including Netherlands, Parihaka, and Kahu (from 12GB to 66GB).

cs.DC↗

arXiv2020

Employing Simulation to Facilitate the Design of Dynamic Code Generators

Dynamic Translation (DT) is a sophisticated technique that allows the implementation of high-performance emulators and high-level-language virtual machines. In this technique, the guest code is compiled dynamically at runtime. Consequently, achieving good performance depends on several design decisions, including the shape of the regions of code being translated. Researchers and engineers explore these decisions to bring the best performance possible. However, a real DT engine is a very sophisticated piece of software, and modifying one is a hard and demanding task. Hence, we propose using simulation to evaluate the impact of design decisions on dynamic translators and present RAIn, an open-source DT simulator that facilitates the test of DT's design decisions, such as Region Formation Techniques (RFTs). RAIn outputs several statistics that support the analysis of how design decisions may affect the behavior and the performance of a real DT. We validated RAIn running a set of experiments with six well known RFTs (NET, MRET2, LEI, NETPlus, NET-R, and NETPlus-e-r) and showed that it can reproduce well-known results from the literature without the effort of implementing them on a real and complex dynamic translator engine.

cs.PL↗

arXiv2019

The Multi-Lane Capsule Network (MLCN)

We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and resource efficient organization of Capsule Networks (CapsNet) that allows parallel processing, while achieving high accuracy at reduced cost. A MLCN is composed of a number of (distinct) parallel lanes, each contributing to a dimension of the result, trained using the routing-by-agreement organization of CapsNet. Our results indicate similar accuracy with a much reduced cost in number of parameters for the Fashion-MNIST and Cifar10 datsets. They also indicate that the MLCN outperforms the original CapsNet when using a proposed novel configuration for the lanes. MLCN also has faster training and inference times, being more than two-fold faster than the original CapsNet in the same accelerator.

cs.CV↗