High Performance Computing: 4th Latin American Conference, CARLA 2017, Buenos Aires, Argentina, and Colonia del Sacramento, Uruguay, September 20-22, 2017, Revised Selected PapersEsteban Mocskos, Sergio Nesmachnow This book constitutes the proceedings of the 4th Latin American Conference on High Performance Computing, CARLA 2017, held in Buenos Aires, Argentina, and Colonia del Sacramento, Uruguay, in September 2017. The 29 papers presented in this volume were carefully reviewed and selected from 50 submissions. They are organized in topical sections named: HPC infrastructures and datacenters; HPC industry and education; GPU, multicores, accelerators; HPC applications and tools; big data and data management; parallel and distributed algorithms; Grid, cloud and federations. |
Contents
| 3 | |
| 21 | |
Initial Experiences from TUPAC Supercomputer | 38 |
HPC Industry and Education | 53 |
A High Performance Training Platform for HPC GPU and DeepLearning | 54 |
GPU Multicores Accelerators | 68 |
Analysis and Characterization of GPU Benchmarks for Kernel Concurrency Efficiency | 69 |
Parallel Batch SelfOrganizing Map on Graphics Processing Unit Using CUDA | 87 |
Parallel and Distributed Algorithms | 233 |
Task Scheduling for Processing Big Graphs in Heterogeneous Commodity Clusters | 234 |
Exploring ApplicationLevel MessageLogging in Scalable HPC Programs | 250 |
Accelerated Numerical Optimization with Explicit Consideration of Model Constraints | 255 |
Parallel Processing of Intracranial Electroencephalogram Readings on Distributed Memory Systems | 262 |
Support Vector Machine Acceleration for Intel Xeon Phi Manycore Processors | 277 |
Performance Improvements of a Parallel Multithreading Selfgravity Algorithm | 291 |
A Fast GPU ConvolutionSuperposition Method for Radiotherapy Dose Calculation | 307 |
Performance Prediction of Acoustic Wave Numerical Kernel on Intel Xeon Phi Processor | 101 |
Evaluating the NVIDIA Tegra Processor as a LowPower Alternative for Sparse GPU Computations | 111 |
HPC Applications and Tools | 123 |
Influence of Task Location on Cluster Throughput | 125 |
A Framework Based on Finite Elements to Address Multi Scale and Multi Physics Problems | 139 |
The Prospect of Serverless Scientific Computing and HPC | 154 |
An HPC Simulator for Workload Management | 169 |
Finding Opportunities for MPI Applications in Fog and Edge Computing | 185 |
Big Data and Data Management | 200 |
IoT Workload Distribution Impact Between Edge and Cloud Computing in a Smart Grid Application | 203 |
A Framework for Scalable and Reproducible Ecological Niche Modeling | 218 |
Grid Cloud and Federations | 319 |
Choosing the Fault Tolerance Technique for my Cloud Workflow | 321 |
Energy Aware Multiobjective Scheduling in a Federation of Heterogeneous Datacenters | 337 |
Markov Decision Process to Dynamically Adapt Spots Instances Ratio on the Autoscaling of Scientific Workflows in the Cloud | 353 |
Experimental Analysis of Secret Sharing Schemes for Cloud Storage Based on RNS | 370 |
Biobjective Heterogeneous Consolidation in Cloud Computing | 384 |
Scaling the Deployment of Virtual Machines in UnaCloud | 399 |
Distributed Cosmic Ray Detection Using Cloud Computing | 414 |
| 430 | |
Other editions - View all
High Performance Computing: 4th Latin American Conference, CARLA 2017 ... Esteban Mocskos,Sergio Nesmachnow No preview available - 2017 |
Common terms and phrases
AccaSim algorithm analysis analyze applications architecture Argentina average behavior BitTorrent cache calculation cloud computing cluster computing resources configuration cores cosmic rays CUDA datacenter dataset deploy distributed Edge Computing edge nodes efficiency energy consumption environment evaluation execution experimental framework function graph grid Hadoop hardware heterogeneous heuristics host IEEE iEEG ILUPACK implementation improve infrastructure input Intel interface iteration Jetson kernels latency LIBSVM machine learning makespan mapping memory multi-core Nesmachnow NVIDIA OpenMP operations optimization parallel parameters particles platform policies power consumption preconditioner prediction presented problem processing processors programming proposed protocol Python Rodinia runtime scalability scenarios scheduling scientific workflows self-gravity server setup simulation specific speedup spot instances Springer storage strategy Table techniques tion UnaCloud Universidad usage users values vector virtual machines workflow workload