Field of study: Electrical engineering. ; Dr. Michela Becchi, Thesis Supervisor. ; "December 2017." ; Floating-point computations produce approximate results, possibly leading to inaccuracy and reproducibility problems. Existing work addresses two issues: first, the design of high precision floating-point representations, and second, the study of methods to support a trade-off between accuracy and performance of central processing unit (CPU) applications. However, a comprehensive study of trade-offs between accuracy and performance on modern graphic processing units (GPUs) is missing. This thesis covers the use of different floating-point precisions (i.e., single and double floating-point precision) in the IEEE 754 standard, the GNU Multiple Precision Arithmetic Library (GMP), and composite floating-point precision on a GPU using a variety of synthetic and real-world benchmark applications. First, we analyze the support for a single and double precision floating-point arithmetic on the considered GPU architectures, and we characterize the latencies of all floating-point instructions on GPU. Second, a study is presented on the performance/accuracy tradeoffs related to the use of different arithmetic precisions on addition, multiplication, division, and natural exponential function. Third, an analysis is given on the combined use of different arithmetic operations on three benchmark applications characterized by different instruction mixes and arithmetic intensities. As a result of this analysis, a novel auto tuner was designed in order to select the arithmetic precision of a GPU program leading to a better performance and accuracy tradeoff depending on the arithmetic operations and math functions used in the program and the degree of multithreading of the code. ; Includes bibliographical references (pages 76-81).


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Performance/accuracy trade-offs of floating-point arithmetic on NVidia GPUs : from a characterization to an auto-tuner



    Erscheinungsdatum :

    2017-01-01


    Anmerkungen:

    1099281561
    Submited to University of Missouri--Columbia Graduate School.



    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt , Englisch


    Klassifikation :

    DDC:    629



    Accelerating Unstructured-grid CFD Algorithms on NVIDIA and AMD GPUs

    Christopher P Stone / Aaron Walden / Eric Nielsen et al. | NTRS


    UCAV Configuration & Performance Trade-Offs

    Woolvin, Stuart | AIAA | 2006


    Accuracy vs Efficiency Trade-offs in Optical Flow Algorithms

    Liu, H. / Hong, T.-H. / Herman, M. et al. | British Library Online Contents | 1998



    An Asynchronous IEEE Floating-Point Arithmetic Unit

    Noche, Joel R. / Araneta, Jose C. | BASE | 2008

    Freier Zugriff