View in EDS

Reference Histogram Image Convolution Bilateral Filtering

Saved in:
Bibliographic Details
Title: Reference Histogram Image Convolution Bilateral Filtering
Authors: Performance Analysis Of Histogram, Image Convolution
Contributors: The Pennsylvania State University CiteSeerX Archives
Source: http://datasys.cs.iit.edu/reports/2014_GCASR14_poster-apps-gpu.pdf.
Collection: CiteSeerX
Subject Terms: Aarhus • Performance comparison of application kernels. • Image Convolution, Histogram and Bilateral filtering • Multi-core CPU, many-core NVIDIA GPUs and GeMTC (GPU enabled Many Task Computing
Description: filtering. • These kernels have a large amount of data-level parallelism. • All these applications are executed in CPU, GPU and GeMTC. • GeMTC is an execution model and runtime system which enables NVIDIA GPUs to be programmed with many concurrent and independent tasks of potentially short or variable duration. • The target test bed for this implementation is GTX 670 GPU with AMD Phenom(tm) II X6 1100T Processor with 6GB RAM. • For GPU, the test are conducted with varying threads and varying problem size. • Throughput and FLOPS are taken as performance analysis factor. • Through this we better understand the behavior of different applications that belong to the Many-Task Computing paradigm. Conclusion & Future Work
Document Type: text
File Description: application/pdf
Language: English
Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.2920
Availability: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.2920
http://datasys.cs.iit.edu/reports/2014_GCASR14_poster-apps-gpu.pdf
Rights: Metadata may be used without restrictions as long as the oai identifier remains attached to it.
Accession Number: edsbas.911B16E2
Database: BASE
Description
Abstract:filtering. • These kernels have a large amount of data-level parallelism. • All these applications are executed in CPU, GPU and GeMTC. • GeMTC is an execution model and runtime system which enables NVIDIA GPUs to be programmed with many concurrent and independent tasks of potentially short or variable duration. • The target test bed for this implementation is GTX 670 GPU with AMD Phenom(tm) II X6 1100T Processor with 6GB RAM. • For GPU, the test are conducted with varying threads and varying problem size. • Throughput and FLOPS are taken as performance analysis factor. • Through this we better understand the behavior of different applications that belong to the Many-Task Computing paradigm. Conclusion & Future Work