Ginkgo: A high performance numerical linear algebra library

Anzt, Hartwig; Cojean, Terry; Chen, Yen‐Chen; Flegar, Goran; Göbel, Fritz; Grützmacher, Thomas; Nayak, Pratik; Ribizel, Tobias; Tsai, Yu‐Hsiang

doi:10.21105/joss.02260

Cited by 28 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fortunately, most iterative solvers and preconditioners are memory bound, and the conversion can be hidden behind the memory transfers (Flegar et al, 2021). A production-ready implementation of an adaptive-precision block-Jacobi preconditioner decoupling memory precision from arithmetic precision is available in the Ginkgo library (Anzt et al, 2020).…”

Section: Sparse Linear Algebramentioning

confidence: 99%

A survey of numerical linear algebra methods utilizing mixed-precision arithmetic

Abdelfattah

Anzt

Boman

et al. 2021

The International Journal of High Performance Computing Applica

Self Cite

106

View full text Add to dashboard Cite

The efficient utilization of mixed-precision numerical linear algebra algorithms can offer attractive acceleration to scientific computing applications. Especially with the hardware integration of low-precision special-function units designed for machine learning applications, the traditional numerical algorithms community urgently needs to reconsider the floating point formats used in the distinct operations to efficiently leverage the available compute power. In this work, we provide a comprehensive survey of mixed-precision numerical linear algebra routines, including the underlying concepts, theoretical background, and experimental results for both dense and sparse linear algebra problems.

show abstract

Section: Sparse Linear Algebramentioning

confidence: 99%

A survey of numerical linear algebra methods utilizing mixed-precision arithmetic

Abdelfattah

Anzt

Boman

et al. 2021

The International Journal of High Performance Computing Applica

Self Cite

106

View full text Add to dashboard Cite

show abstract

“…Using the Ginkgo [9] Solver Benchmark module (as described in Section 5.2), the solver performances vector p can be obtained for every matrix in the dataset (cf. Section 5.1).…”

Section: Solver Performances On Datamentioning

confidence: 99%

Prediction of Optimal Solvers for Sparse Linear Systems Using Deep Learning

Funk¹,

Götz²,

Anzt³

2022

Proceedings of the 2022 SIAM Conference on Parallel Processing for Scientific Computing (PP)

Self Cite

View full text Add to dashboard Cite

Solving sparse linear systems is a key task in a number of computational problems, such as data analysis and simulations, and majorly determines overall execution time. Choosing a suitable iterative solver algorithm, however, can significantly improve time-to-completion. We present a deep learning approach designed to predict the optimal iterative solver for a given sparse linear problem. For this, we detail useful linear system features to drive the prediction process, the metrics we use to quantify the iterative solvers' timeto-approximation performance and a comprehensive experimental evaluation of the prediction quality of the neural network. Using a hyperparameter optimization and an ablation study on the SuiteSparse matrix collection we have inferred the importance of distinct features, achieving a top-1 classification accuracy of 60%.

show abstract

“…GINKGO is a GPU-focused cross-platform linear operator library focusing on sparse linear algebra [3,2]. The library design is guided by combining ecosystem extensibility with heavy, architecture-specific kernel optimization using the platform-native languages CUDA (NVIDIA GPUs), HIP (AMD GPUs), or OpenMP (Intel/AMD/ARM multicore) [4].…”

Section: Ginkgo Designmentioning

confidence: 99%

“…https://spec.oneApi.com/versions/latest/index.html2 Both extensions are now also part of the SYCL 2020 Provisional Specification: https://www.khronos.org/news/press/ khronos-releases-sycl-2020-provisional-specification 3 https://intel.github.io/llvm-docs/PluginInterface.html 4 https://spec.oneApi.com/level-zero/latest/core/INTRO.html…”

mentioning

confidence: 99%

Porting a sparse linear algebra math library to Intel GPUs

Tsai,

Cojean,

Anzt

2021

Preprint

Self Cite

View full text Add to dashboard Cite

With the announcement that the Aurora Supercomputer will be composed of general purpose Intel CPUs complemented by discrete high performance Intel GPUs, and the deployment of the oneAPI ecosystem, Intel has committed to enter the arena of discrete high performance GPUs. A central requirement for the scientific computing community is the availability of production-ready software stacks and a glimpse of the performance they can expect to see on Intel high performance GPUs. In this paper, we present the first platform-portable open source math library supporting Intel GPUs via the DPC++ programming environment. We also benchmark some of the developed sparse linear algebra functionality on different Intel GPUs to assess the efficiency of the DPC++ programming ecosystem to translate raw performance into application performance. Aside from quantifying the efficiency within the hardware-specific roofline model, we also compare against routines providing the same functionality that ship with Intel's oneMKL vendor library.

show abstract

Ginkgo: A high performance numerical linear algebra library

Abstract: Ginkgo is a production-ready sparse linear algebra library for high performance computing on GPU-centric architectures with a high level of performance portability and focuses on software sustainability.

Cited by 28 publications

References 13 publications

A survey of numerical linear algebra methods utilizing mixed-precision arithmetic

A survey of numerical linear algebra methods utilizing mixed-precision arithmetic

Prediction of Optimal Solvers for Sparse Linear Systems Using Deep Learning

Porting a sparse linear algebra math library to Intel GPUs

Contact Info

Product

Resources

About