Your browser doesn't support javascript.
loading
Application Performance Analysis and Efficient Execution on Systems with multi-core CPUs, GPUs and MICs: A Case Study with Microscopy Image Analysis.
Teodoro, George; Kurc, Tahsin; Andrade, Guilherme; Kong, Jun; Ferreira, Renato; Saltz, Joel.
Afiliação
  • Teodoro G; Department of Computer Science, University of Brasília, Brasília, DF, Brazil.
  • Kurc T; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA; Scientific Data Group, Oak Ridge National Laboratory, Oak Ridge, TN, USA.
  • Andrade G; Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte, MG, Brazil.
  • Kong J; Department of Biomedical Informatics, Emory University, Atlanta, GA, USA.
  • Ferreira R; Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte, MG, Brazil.
  • Saltz J; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA; Scientific Data Group, Oak Ridge National Laboratory, Oak Ridge, TN, USA.
Int J High Perform Comput Appl ; 31(1): 32-51, 2017 Jan.
Article em En | MEDLINE | ID: mdl-28239253
We carry out a comparative performance study of multi-core CPUs, GPUs and Intel Xeon Phi (Many Integrated Core-MIC) with a microscopy image analysis application. We experimentally evaluate the performance of computing devices on core operations of the application. We correlate the observed performance with the characteristics of computing devices and data access patterns, computation complexities, and parallelization forms of the operations. The results show a significant variability in the performance of operations with respect to the device used. The performances of operations with regular data access are comparable or sometimes better on a MIC than that on a GPU. GPUs are more efficient than MICs for operations that access data irregularly, because of the lower bandwidth of the MIC for random data accesses. We propose new performance-aware scheduling strategies that consider variabilities in operation speedups. Our scheduling strategies significantly improve application performance compared to classic strategies in hybrid configurations.
Palavras-chave
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Revista: Int J High Perform Comput Appl Ano de publicação: 2017 Tipo de documento: Article País de afiliação: Brasil País de publicação: Estados Unidos
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Revista: Int J High Perform Comput Appl Ano de publicação: 2017 Tipo de documento: Article País de afiliação: Brasil País de publicação: Estados Unidos