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

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

89 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationProcedia Computer Science
Number of pages10
Publication statusPublished - 2017


  • BLAS
  • Batched BLAS
  • Scientific computing
  • High-performance computing
  • memory management
  • Parallel processing


Dive into the research topics of 'The Design and Performance of Batched BLAS on Modern High-Performance Computing Systems'. Together they form a unique fingerprint.

Cite this