Fourier Transform Based GPU Acceleration

2013 ◽  
Vol 347-350 ◽  
pp. 2926-2929
Author(s):  
Jing Shen Li
Keyword(s):  
Fourier Transform ◽  
Parallel Computing ◽  
Large Scale ◽  
Gpu Acceleration ◽  
Image Transformation ◽  
Gpu Parallel Computing ◽  
Large Scale Data ◽  
Relationship Of ◽  
The Relationship ◽  
Scale Data

In digital image processing, Fourier transform is an important algorithm of image transformation. In order to improve the speed of Fourier transform, the paper proposes to deal with the image with GPU parallel computing through the method of GPU accelerating MATLB. The relationship of data scale and calculation speed is analyzed through the traditional CPU serial operation and GPU parallel computing. Computer simulations verify that the calculation speed can be improved by GPU about large scale data.

GPU enhanced parallel computing for large scale data clustering

2013 ◽  
Vol 29 (7) ◽  
pp. 1736-1741 ◽  
Author(s):  
Xiaohui Cui ◽  
Jesse St. Charles ◽  
Thomas Potok
Keyword(s):  
Parallel Computing ◽  
Data Clustering ◽  
Large Scale ◽  
Large Scale Data ◽  
Scale Data

The Research of MapReduce on the Cloud Computing

2012 ◽  
Vol 182-183 ◽  
pp. 2127-2130
Author(s):  
Tie Liang Gao ◽  
Jiao Li ◽  
Jun Peng Zhang ◽  
Bing Jie Shi
Keyword(s):  
Cloud Computing ◽  
Parallel Computing ◽  
Large Scale ◽  
Parallel Program ◽  
Large Scale Data ◽  
Distribute System ◽  
Scale Data

MapReduce is a kind of model of program that is use in the parallel computing about large scale data muster in the Cloud Computing[1] , it mainly consist of map and reduce . MapReduce is tremendously convenient for the programmer who can’t familiar with the parallel program .These people use the MapReduce to run their program on the distribute system. This paper mainly research the model and process and theory of MapReduce .

scholarly journals An Evaluation Model and Benchmark for Parallel Computing Frameworks

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Weibei Fan ◽  
Zhijie Han ◽  
Ruchuan Wang
Keyword(s):  
Support Vector Machine ◽  
Parallel Computing ◽  
Comparative Evaluation ◽  
Large Scale ◽  
Evaluation Model ◽  
Performance Model ◽  
Support Vector ◽  
Large Scale Data ◽  
Performance Evaluation Model ◽  
Scale Data

MARS and Spark are two popular parallel computing frameworks and widely used for large-scale data analysis. In this paper, we first propose a performance evaluation model based on support vector machine (SVM), which is used to analyze the performance of parallel computing frameworks. Furthermore, we give representative results of a set of analysis with the proposed analytical performance model and then perform a comparative evaluation of MARS and Spark by using representative workloads and considering factors, such as performance and scalability. The experiments show that our evaluation model has higher accuracy than multifactor line regression (MLR) in predicting execution time, and it also provides a resource consumption requirement. Finally, we study benchmark experiments between MARS and Spark. MARS has better performance than Spark in both throughput and speedup in the executions of logistic regression and Bayesian classification because MARS has a large number of GPU threads that can handle higher parallelism. It also shows that Spark has lower latency than MARS in the execution of the four benchmarks.

Networks of Contemporary Popular Musicians

Leonardo ◽  
2012 ◽  
Vol 45 (1) ◽  
pp. 78-79 ◽  
Author(s):  
Juyong Park
Keyword(s):  
High Throughput ◽  
Large Scale ◽  
Human Perception ◽  
The Internet ◽  
Network Data ◽  
Storage And Retrieval ◽  
Music Production ◽  
Large Scale Data ◽  
The Relationship ◽  
Scale Data

The Internet has enabled easy storage and retrieval of various network data, including data showing the relationship between music professionals. “High-Throughput Humanities” is a new way of thought that aims to bring analysis of such large-scale data to the study of traditional humanities subjects including music. Here we present how networks of musical professionals can help us understand the process of collective music production and the human perception of musical similarity.

Models and computational strategies linking physiological response to molecular networks from large-scale data

2008 ◽  
Vol 366 (1878) ◽  
pp. 3067-3089 ◽  
Author(s):  
Fernando Ortega ◽  
Katrin Sameith ◽  
Nil Turan ◽  
Russell Compton ◽  
Victor Trevino ◽  
...  
Keyword(s):  
Physiological Response ◽  
Large Scale ◽  
Molecular Network ◽  
Molecular Networks ◽  
Organizational Complexity ◽  
Large Scale Data ◽  
Genome Wide ◽  
Modelling Techniques ◽  
The Relationship ◽  
Scale Data

An important area of research in systems biology involves the analysis and integration of genome-wide functional datasets. In this context, a major goal is the identification of a putative molecular network controlling physiological response from experimental data. With very fragmentary mechanistic information, this is a challenging task. A number of methods have been developed, each one with the potential to address an aspect of the problem. Here, we review some of the most widely used methodologies and report new results in support of the usefulness of modularization and other modelling techniques in identifying components of the molecular networks that are predictive of physiological response. We also discuss how system identification in biology could be approached, using a combination of methodologies that aim to reconstruct the relationship between molecular pathways and physiology at different levels of the organizational complexity of the molecular network.

Sign in / Sign up

Export Citation Format

Share Document