15 articles for “GPU”

Set a search alert

Research ArticleOpen accessIn the abstractPerformance Analysis of Deep Learning Libraries: TensorFlow and PyTorchFelipe Florencio, Thiago Valenç, Edward David Moreno, Methanias Colaço JuniorThrough the increase in deep learning study and use, in the last years there was a development of specific libraries for Deep Neural Network (DNN). Each one of these libraries has different performance results and applies different techniques to optimize the implementation of algorithms. Therefore, even though implementing the same algorithm and using different libraries, the performance of their executions … …Journal of Computer Science, Vol. 15, Issue 6 · 11 Apr 2019 · 10,298 accessesView PDF Cite

Research ArticleOpen accessIn the abstractHYBRID IMPLEMENTATION AND PERFORMANCE ANALYSIS FOR HIGH PERFORMANCE COMPUTATION WORKLOADJoseph IssaGiven the need to achieve maximum performance possible, offloading intensive computation workload to GPU is a key to achieve this goal. Offloading most of the workload to GPU may not results in desired performance, so a middle approach is more suitable such as splitting the workload between the CPU and the GPU can be considered as an optimized approach. In … …Journal of Computer Science, Vol. 10, Issue 9 · 26 Apr 2014 · 6,520 accessesView PDF Cite

Research ArticleOpen accessIn the abstractAn Investigation of Thermal Characteristics of a Sintered-Wick Heat Pipe with Double Heat SourcesNattawut Tharawadee, Pradit Terdtoon, Niti Kammuang-lueHeat pipes have been used extensively in the electronic industry for decades especially in laptop computers. For cost-effectiveness, a single heat pipe is designed to simultaneously transfer heat from both the Central Processing Unit (CPU) and the Graphics Processing Unit (GPU) inside the main board to the heat sink. This causes the efficiency of the heat pipe to change without … …American Journal of Applied Sciences, Vol. 10, Issue 9 · 24 Aug 2013 · 7,232 accessesView PDF Cite

Research ArticleOpen accessIn the abstractPerformance Optimization of Physics Simulations Through Genetic AlgorithmsOksana Shadura, Federico Carminati, Anatoliy PetrenkoThe GeantV R&D approach is revisiting the standard particle transport simulation approach to be able to benefit from “Single Instruction, Multiple Data” (SIMD) computational architectures or extremely parallel systems like coprocessors and GPUs. The goal of this work is to develop a mechanism for optimizing the programs used for High-Energy Physics (HEP) particle transport simulations using a “black-box” optimization approach. … …Journal of Computer Science, Vol. 15, Issue 1 · 8 Jan 2019 · 8,096 accessesView PDF Cite

Research ArticleOpen accessIn the abstractEnhanced Preemptive Global Utility Accrual Real Time Scheduling Algorithms in Multicore EnvironmentIdawaty Ahmad, Mohamed Othman, Zuriati Ahmad ZulkarnainThis paper proposed an efficient real time scheduling algorithm using global scheduling paradigm running in multicore environment known as Global Preemptive Utility Accrual Scheduling (GPUAS) algorithm. The existing TUF/UA multiprocessor scheduling algorithms known as Greedy-Global Utility Accrual (G-GUA) and Non Greedy-Global Utility Accrual (NG-GUA) algorithms is seen to overlook the efficiency on its task scheduling algorithm. These algorithms have adapted … …Journal of Computer Science, Vol. 11, Issue 12 · 11 Feb 2016 · 6,395 accessesView PDF Cite