QR factorization on a multicore node enhanced with multiple GPU accelerators

Emmanuel Agullo*, Cédric Augonnet, Jack Dongarra, Mathieu Faverge, Hatem Ltaief, Samuel Thibault, Stanimire Tomov

*Corresponding author for this work

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

68 Scopus citations

Abstract

One of the major trends in the design of exascale architectures is the use of multicore nodes enhanced with GPU accelerators. Exploiting all resources of a hybrid accelerators-based node at their maximum potential is thus a fundamental step towards exascale computing. In this article, we present the design of a highly efficient QR factorization for such a node. Our method is in three steps. The first step consists of expressing the QR factorization as a sequence of tasks of well chosen granularity that will aim at being executed on a CPU core or a GPU. We show that we can efficiently adapt high-level algorithms from the literature that were initially designed for homogeneous multicore architectures. The second step consists of designing the kernels that implement each individual task. We use CPU kernels from previous work and present new kernels for GPUs that complement kernels already available in the MAGMA library. We show the impact on performance of these GPU kernels. In particular, we present the benefits of new hybrid CPU/GPU kernels. The last step consists of scheduling these tasks on the computational units. We present two alternative approaches, respectively based on static and dynamic scheduling. In the case of static scheduling, we exploit the a priori knowledge of the schedule to perform successive optimizations leading to very high performance. We, however, highlight the lack of portability of this approach and its limitations to relatively simple algorithms on relatively homogeneous nodes. Alternatively, by relying on an efficient runtime system, Star PU, in charge of ensuring data availability and coherency, we can schedule more complex algorithms on complex heterogeneous nodes with much higher productivity. In this latter case, we show that we can achieve high performance in a portable way thanks to a fine interaction between the application and the runtime system. We demonstrate that the obtained performance is very close to the theoretical upper bounds that we obtained using Linear Programming.

Original languageEnglish (US)
Title of host publicationProceedings - 25th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2011
Pages932-943
Number of pages12
DOIs
StatePublished - Oct 3 2011
Event25th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2011 - Anchorage, AK, United States
Duration: May 16 2011May 20 2011

Publication series

NameProceedings - 25th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2011

Other

Other25th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2011
CountryUnited States
CityAnchorage, AK
Period05/16/1105/20/11

Keywords

  • Communication-Avoiding
  • Dense Linear Algebra
  • Heterogeneous Scheduling
  • High Performance Computing
  • Hybrid Architecture
  • Multicore
  • Multiple GPU Accelerators
  • QR Factorization
  • Runtime System
  • Tile Algorithm

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint Dive into the research topics of 'QR factorization on a multicore node enhanced with multiple GPU accelerators'. Together they form a unique fingerprint.

Cite this