FOGLIA P., GIORGI R., PRETE C. A. · Use Siena air (University of Siena) · 2001
In this work, by using dynamic analysis techniques, we analyze how a workload can be accelerated in the case of a shared-bus shared-memory multiprocessor. It is well known that, in this kind of systems, the bus is the critical element that can limit the scalability of the machine. Nevertheless, many factors that influence bus utilization have not been yet investigated for this kind of workload, in particular the effects of thread migration. The operating system effects are also considered in our evaluation. We analyzed a basic four-processor and a high-end sixteen-processor machine, implementing three different coherence protocols (including MESI and another solution from the literature). We show that even in the four-processor case, the overhead induced by the sharing of private data, as a consequence of process migration, namely passive sharing, cannot be neglected. Indeed, the analysis shows that a protocol based on a selective strategy for dealing with private and shared data has a better performance than protocols either relying on the detection of migratory access-pattern or purely using a Write-Invalidate strategy, like MESI. We varied the architectural parameters to show how passive sharing and other coherence overhead are influenced by different cache choices. Then, we considered the sixteen-processor case, where the effects on performance are more evident. We also end up that performance can take advantage of large caches and cache affinity scheduling. However, even with affinity scheduling, a selective protocol delivers better performance.
Cited by 0
Ranjan Jha · HAL (Le Centre pour la Communication Scientifique Directe) · 2016
Cited by 3Open access
Sangram Nayak, Sarojananda Mishra, Manoranjan Dash et al. · International Journal of Recent Technology and Engineering (IJRTE) · 2019
SCTP is a connection oriented general purpose transport protocol and applications presented in the transport layer for concept of streams. Different streams provide multiple end to end connections that enables independent send and receiver buffer at two end points. In this paper we performed performance measurement for simultaneous parallel streams. Performance of SCTP is closely examined for two parallel streams and considerable improvement of bandwidth utilization observed as compared to single stream
Cited by 0Open access
Alain Pétrowski, Gérard Dreyfus, Claude Girault · IEEE Transactions on Neural Networks · 1993
The supervised training of feedforward neural networks is often based on the error backpropagation algorithm. The authors consider the successive layers of a feedforward neural network as the stages of a pipeline which is used to improve the efficiency of the parallel algorithm. A simple placement rule is used to take advantage of simultaneous executions of the calculations on each layer of the network. The analytic expressions show that the parallelization is efficient. Moreover, they indicate that the performance of this implementation is almost independent of the neural network architecture. Their simplicity assures easy prediction of learning performance on a parallel machine for any neural network architecture. The experimental results are in agreement with analytical estimates.
Cited by 62
Wei Shi, Qi Deng, Boyong Liang · 2003
The pre-computation of data cubes is critical to improving the response time of On-Line Analytical Processing (OLAP) systems and can be instrumental in accelerating data mining tasks in large data warehouses. In order to meet the need for improved performance created by growing data sizes, parallel solutions for generating the data cube are becoming increasingly important. This Project Report reports the test result of building and querying data cube between large parallel database: DB2 and Panda sys-tem. We have investigated two large parallel database: DB2 and Oracle 9i. Under the default setup of DB2 and Panda system, we tested the performance of building a cube in both Panda system and DB2 and also some data cube queries. We mainly studied the Partition difference between Panda system and DB2, then analyze the reason of the test result after the serious study of these two systems. 1
Cited by 0
Wolf, F. · JuSER (Forschungszentrum Jülich) · 2006
Cited by 0
Iris Aguilar · 2024
Plant-parasitic nematodes (PPN) are an understudied threat in sugarcane production. Previous survey work showed that Tylenchorhynchus (stunt nematode), Pratylenchus (lesion nematode), Mesocriconema (ring nematode), and Helicotylenchus (spiral nematode) are the primary PPN genera found in sugarcane fields in Louisiana. This study evaluated the impact of nematodes on sugarcane growth and the effect of nematicides on nematode population densities. Greenhouse studies were conducted using soil collected from multiple sugarcane fields with moderate PPN infestation levels to determine the nematode impact on sugarcane growth and nematicide efficacy. Field soil collected from each site was subjected to four treatments: an untreated and sterilized control, ethoprop (Mocap 15G), and fluensulfone (Nimitz). After three months in a greenhouse, PPNs were extracted from soil and roots to quantify nematode population densities. Plant growth was evaluated by measuring shoot height, number of tillers, and total biomass. Sterilized soil significantly increased sugarcane growth suggesting that PPNs likely negatively influenced sugarcane production in Louisiana. Both nematicides showed the potential to suppress PPNs on sugarcane. A field experiment evaluated the efficacy of nematicide formulation and application frequency on nematode population development and sugar yield in a newly planted sugarcane field. The trial consisted of six treatments: (1) untreated control, (2) ethoprop applied once, (3) fluensulfone applied once, (4) fluensulfone applied twice, (5) cyclobutrifluram once, and (6) cyclobutrifluram twice. During the cropping cycle, PPN soil population densities increased with crop age. Cyclobutrifluram reduced lesion nematode densities in soil and roots regardless of application frequency, while stunt nematode populations were reduced only with two applications of fluensulfone or cyclobutrifluram. No differences were observed in sugar yield and cane tonnage. Additional greenhouse experiments were designed to evaluate the efficacy of the three nematicides under more controlled environmental vii conditions. The greenhouse experiment did not show the potential effectiveness of fluensulfone and cyclobutrifluram observed in the field trial. In conclusion, the efficacy of nematicides in this study varied depending on nematode genera and application frequency. No significant yield differences were observed during the plant-cane year however, differences may become apparent in the following years as nematode population densities increase in untreated soil over time.
Cited by 0Open access
Yicong Hao · Highlights in Science Engineering and Technology · 2023
The use of parallel computing can speed up the training of deep learning models. The traditional neural network model ResNet is chosen for testing in this paper on the effectiveness of data parallelism in image classification, and test data is provided in a 6-GPU environment. In this paper, it is suggested that various factors should be considered when building affordable hardware configurations to expedite model training in practical application scenarios. The communication costs are not insignificant because today's large computing clusters are primarily offered via cloud computing. Another crucial point to remember is that the number of CUDA cores is the primary hardware foundation for GPU acceleration technology. Therefore, acceleration may not be affected by more incredible video memory or fewer CUDA cores for some particular graphics cards. In addition, the issue of beyond-model performance in parallel computing is another issue that must be disregarded. Due to the parallel strategy's limitations, it is essential to tweak the super parameters while speeding up model training. The model's performance is more likely to be ensured by the lower learning rate and Batch size. This paper's experimental conclusion can support building an appropriate hardware configuration scheme.
Cited by 0Open access
Sayantan Singha Roy, Chandan Garai, Ranjan Dasgupta · 2015
Clustering of data set is a very contemporary problem for handling big data and parallelizing the process of clustering helps in improving efficiency for applications which involve frequent searching. Various clustering techniques are used for grouping of data set and CBAR is one such very frequently used technique used for different applications. Parallelization of CBAR is very necessary for handling Bigdata and Hadoop MapReduce platform provides a suitable environment to improve efficiency for any problem dealing with huge volume of data by using appropriate segmentation technique. In this work, we designed and developed a few algorithms for implementing CBAR using MapReduce technique and tested the results in different clusters of up to 4 nodes. Significant improvement has been observed and analysis and explanation on these results have also been presented in our work with suitable example.
Cited by 1
Kaveh Mahdavi · 2022
Clustering analysis is widely used to stratify data in the same cluster when they are similar according to the specific metrics. We can use the cluster analysis to group the CPU burst of a parallel application, and the regions on each process in-between communication calls or calls to the parallel runtime. The resulting clusters obtained are the different computational trends or phases that appear in the application. These clusters are useful to understand the behavior of the computation part of the application and focus the analyses on those that present performance issues. Although density-based clustering algorithms are a powerful and efficient tool to summarize this type of information, their traditional user-guided clustering methodology has many shortcomings and deficiencies in dealing with the complexity of data, the diversity of data structures, high-dimensionality of data, and the dramatic increase in the amount of data. Consequently, the majority of DBSCAN-like algorithms have weaknesses to handle high-dimensionality and/or Multi-density data, and they are sensitive to their hyper-parameter configuration. Furthermore, extracting insight from the obtained clusters is an intuitive and manual task. To mitigate these weaknesses, we have proposed a new unified approach to replace the user-guided clustering with an automated clustering analysis pipeline, called Enhanced Cluster Identification and Interpretation (ECII) pipeline. To build the pipeline, we propose novel techniques including Robust Independent Feature Selection, Feature Space Curvature Map, Organization Component Analysis, and hyper-parameters tuning to feature selection, density homogenization, cluster interpretation, and model selection which are the main components of our machine learning pipeline. This thesis contributes four new techniques to the Machine Learning field with a particular use case in Performance Analytics field. The first contribution is a novel unsupervised approach for feature selection on noisy data, called Robust Independent Feature Selection (RIFS). Specifically, we choose a feature subset that contains most of the underlying information, using the same criteria as the Independent component analysis. Simultaneously, the noise is separated as an independent component. The second contribution of the thesis is a parametric multilinear transformation method to homogenize cluster densities while preserving the topological structure of the dataset, called Feature Space Curvature Map (FSCM). We present a new Gravitational Self-organizing Map to model the feature space curvature by plugging the concepts of gravity and fabric of space into the Self-organizing Map algorithm to mathematically describe the density structure of the data. To homogenize the cluster density, we introduce a novel mapping mechanism to project the data from the non-Euclidean curved space to a new Euclidean flat space. The third contribution is a novel topological-based method to study potentially complex high-dimensional categorized data by quantifying their shapes and extracting fine-grain insights from them to interpret the clustering result. We introduce our Organization Component Analysis (OCA) method for the automatic arbitrary cluster-shape study without an assumption about the data distribution. Finally, to tune the DBSCAN hyper-parameters, we propose a new tuning mechanism by combining techniques from machine learning and optimization domains, and we embed it in the ECII pipeline. Using this cluster analysis pipeline with the CPU burst data of a parallel application, we provide the developer/analyst with a high-quality SPMD computation structure detection with the added value that reflects the fine grain of the computation regions. El análisis de conglomerados se usa ampliamente para estratificar datos en el mismo conglomerado cuando son similares según las métricas específicas. Nosotros puede usar el análisis de clúster para agrupar la ráfaga de CPU de una aplicación paralela y las regiones en cada proceso intermedio llamadas de comunicación o llamadas al tiempo de ejecución paralelo. Los clusters resultantes obtenidos son las diferentes tendencias computacionales o fases que aparecen en la solicitud. Estos clusters son útiles para entender el comportamiento de la parte de computación del aplicación y centrar los análisis en aquellos que presenten problemas de rendimiento. Aunque los algoritmos de agrupamiento basados en la densidad son una herramienta poderosa y eficiente para resumir este tipo de información, su La metodología tradicional de agrupación en clústeres guiada por el usuario tiene muchas deficiencias y deficiencias al tratar con la complejidad de los datos, la diversidad de estructuras de datos, la alta dimensionalidad de los datos y el aumento dramático en la cantidad de datos. En consecuencia, el La mayoría de los algoritmos similares a DBSCAN tienen debilidades para manejar datos de alta dimensionalidad y/o densidad múltiple, y son sensibles a su configuración de hiperparámetros. Además, extraer información de los clústeres obtenidos es una forma intuitiva y tarea manual Para mitigar estas debilidades, hemos propuesto un nuevo enfoque unificado para reemplazar el agrupamiento guiado por el usuario con un canalización de análisis de agrupamiento automatizado, llamada canalización de identificación e interpretación de clúster mejorada (ECII). para construir el tubería, proponemos técnicas novedosas que incluyen la selección robusta de características independientes, el mapa de curvatura del espacio de características, Análisis de componentes de la organización y ajuste de hiperparámetros para la selección de características, homogeneización de densidad, agrupación interpretación y selección de modelos, que son los componentes principales de nuestra canalización de aprendizaje automático. Esta tesis aporta cuatro nuevas técnicas al campo de Machine Learning con un caso de uso particular en el campo de Performance Analytics. La primera contribución es un enfoque novedoso no supervisado para la selección de características en datos ruidosos, llamado Robust Independent Feature. Selección (RIFS).Específicamente, elegimos un subconjunto de funciones que contiene la mayor parte de la información subyacente, utilizando el mismo criterios como el análisis de componentes independientes. Simultáneamente, el ruido se separa como un componente independiente. La segunda contribución de la tesis es un método de transformación multilineal paramétrica para homogeneizar densidades de clústeres mientras preservando la estructura topológica del conjunto de datos, llamado Mapa de Curvatura del Espacio de Características (FSCM). Presentamos un nuevo Gravitacional Mapa autoorganizado para modelar la curvatura del espacio característico conectando los conceptos de gravedad y estructura del espacio en el Algoritmo de mapa autoorganizado para describir matemáticamente la estructura de densidad de los datos. Para homogeneizar la densidad del racimo, introducimos un mecanismo de mapeo novedoso para proyectar los datos del espacio curvo no euclidiano a un nuevo plano euclidiano espacio. La tercera contribución es un nuevo método basado en topología para estudiar datos categorizados de alta dimensión potencialmente complejos mediante cuantificando sus formas y extrayendo información detallada de ellas para interpretar el resultado de la agrupación. presentamos nuestro Método de análisis de componentes de organización (OCA) para el estudio automático de forma arbitraria de conglomerados sin una suposición sobre el distribución de datos.
Cited by 2Open access
Poonam Kumari, Mona Aggarwal · International Journal of Engineering Research and · 2016
Cited by 0Open access
Fuqin Chang · Chinese Journal of Mechanical Engineering · 2004
Cited by 2
Keith Arnett Shields · 1994
cooking me those really yummy dinners, her friendship, and the Dells. Chris "Elfman" Elford deserves special thanks for all his help with the adaptive control mechanism, fixing whatever tools happen to be broken each week, and coming up with unique solutions to all my programming needs. He truly is the MacGyver of the Picasso Group. I'd like to thank Brian Totty for teaching me new ways to look at problems, sharing his insights in computer science, life, politics, and religion, showing me that homebrew can be both yummy and painless, and for our various military operations in and around IMPE. I'd like to thank Phil Roth for developing the sliding window average code used in our studies, allowing me to witness him bowl a 200+ game, and showing me that some marriages will last forever. I'd like to thank Ruth Aydt and Roger Noe for their roles in the Pablo project, their iii friendship and help in numerous areas, keeping our machines running, and being patient with some of my mo
Cited by 0
J. Jorba, T. Margalef, E. Luque et al. · 2006
Permission to make digital or hard copies of portions of this work for personal or classroom use is granted provided that the copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise requires prior specific permission by the publisher mentioned above.
Cited by 0
Guang Zeng · Journal of Physics Conference Series · 2023
Abstract As multicore processors become more common in today’s computing systems and parallel programming models are enriched, programmers must consider how to choose the appropriate and parallel programming model when writing parallel code. The purpose of this paper is to compare and analyze the performance gap between different C++ parallel programming models, such as C++ standard library threads, OpenMP and Pthreads, in terms of matrix operations. The experiments use different libraries to implement matrix multiplication separately and then analyze their performance. The experimental data show that the data size has a significant impact on the performance of the different models. For very small matrices of size magnitude less than or close to the number of threads, the performance of parallel implementations is much lower than that of serial implementations. For small matrices with magnitudes larger than the number of threads, the C++ standard library threads outperforms Pthreads and OpenMP due to its lightweight thread performance on relatively small matrices. pthreads shows the best performance on very large matrices due to its fine-grained control over thread management, communication, and synchronization operations. openMP’s is not as stable as the other two libraries, especially for smaller matrices. This paper provides a comparative analysis that can help programmers choose the most appropriate library for their specific computational needs.
Cited by 1Open access
Susumu Yamada · Medical Entomology and Zoology · 2000
Cited by 2
Vijay An, Gul Agha · 2010
Energy consumption by computer systems has emerged as an important concern, both at the level of individual devices (limited battery capacity in mobile systems) and at the societal level (the production of Green House Gases). In multicore architectures, applications may be executed on a variable number of cores and these cores may operate at different frequencies. The performance and energy cost of a parallel algorithm executing on a multicore architecture have different trade-offs, depending on how many cores the algorithm uses, at what frequencies these cores operate, and the structure of the algorithm. We show how algorithm designers and software developers can analyze the energy-performance trade-off in parallel algorithms. We believe that such analyses should be applied to parallel algorithms to facilitate energy conservation. 1
Cited by 0
Biao Yan, XU Zong-ze · 2004
A parallel quadrature Amplitude modulation data transmission system can allow a total signaling rate very close to the Nyquist rate of bandlimited channels through the use of a number of overlapping subchannels.In this paper a description of the parallel data transmission system is given.Then,the performance of the system is analyzed in the presence of phase offset and delay distortion.Analysis results show that system distortion is inversely proportional to the square of the number of subchannels and therefore this illustrates the effectiveness of a parallel system in combating delay distortion.In addition, the performance of the parallel system can be substantially improved by altering the demodulating phase.
Cited by 0
Wei-Ming Lin · Parallel Computing · 2008
Cited by 5
Warn, Seth · Journal of the Arkansas Academy of Science · 2011
Geographic information systems (GIS) are performing increasingly sophisticated analyses on growing data sets. These analyses demand high performance. At the same time, modern computing platforms increasingly derive their performance from several forms of parallelism. This dissertation explores the available parallelism in several GIS-applied algorithms: viewshed calculation, image feature transform, and feature analysis. It presents implementations of these algorithms that exploit parallel processing to reduce execution time, and analyzes the effectiveness of the implementations in their use of parallel processing.
Cited by 1Open access