skip to main content
Idioma:

The Design and Performance of Batched BLAS on Modern High-Performance Computing Systems

Dongarra, Jack ; Hammarling, Sven ; Higham, Nicholas J ; Relton, Samuel D ; Valero-Lara, Pedro ; Zounon, Mawussi

Elsevier 2017

Texto completo disponível

Citações Citado por
  • Título:
    The Design and Performance of Batched BLAS on Modern High-Performance Computing Systems
  • Autor: Dongarra, Jack ; Hammarling, Sven ; Higham, Nicholas J ; Relton, Samuel D ; Valero-Lara, Pedro ; Zounon, Mawussi
  • Assuntos: Batched BLAS ; BLAS ; Dispositius de memòria ; Enginyeria elèctrica ; Gestió de memòria (Informàtica) ; High performance computing ; Memory management ; Memory management (Computer science) ; Ordinadors ; Parallel processing ; Scientific computing ; Supercomputadors ; Àrees temàtiques de la UPC
  • Descrição: A current trend in high-performance computing is to decompose a large linear algebra problem into batches containing thousands of smaller problems, that can be solved independently, before collating the results. To standardize the interface to these routines, the community is developing an extension to the BLAS standard (the batched BLAS), enabling users to perform thousands of small BLAS operations in parallel whilst making efficient use of their hardware. We discuss the benefits and drawbacks of the current batched BLAS proposals and perform a number of experiments, focusing on a general matrix-matrix multiplication (GEMM), to explore their affect on the performance. In particular we analyze the effect of novel data layouts which, for example, interleave the matrices in memory to aid vectorization and prefetching of data. Utilizing these modifications our code outperforms both MKL1 CuBLAS2 by up to 6 times on the self-hosted Intel KNL (codenamed Knights Landing) and Kepler GPU architectures, for large numbers of double precision GEMM operations using matrices of size 2 × 2 to 20 × 20. The authors would like to thank The University of Tennessee for the use of their computational resources. This research was funded in part from the European Union’s Horizon 2020 research and innovation programme under the NLAFET grant agreement No. 671633. Peer Reviewed
  • Editor: Elsevier
  • Data de criação/publicação: 2017
  • Idioma: Inglês
Links
Voltar para lista de resultados
Resultado  1 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.