The method that enables a Simulink model to execute parallel computation by using GPGPU technology is introduced.The GPGPU, General-purpose computing on graphics processing units, is a technology to accelerate program by using graphic card instead of CPU computation.This method was developed to reduce the time to detect failure mode of automatic transmission’s valve body.The valve body is the major part of automatic transmission. It is extremely important to confirm the functional safety of automatic transmission in the case that any parts of valve body failed. We have developed Simulink-based valve body failure mode simulator, and made a considerable contribution for this work.However, the number of failure mode is increasing recently. Therefore, we made the simulator to compute at a high-speed using GPGPU technology.We have sharply reduced the computation time and strengthened the computing ability to support the detection for an increasing amount of failure modes. In addition, we have automated almost a whole detection process and have made the simulator easier to use and scalable from now.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    GPGPU-Based High Performance Parallel Computation Method for Valve Body Failure Mode


    Additional title:

    Sae International Journal of Passenger Cars. Mechanical Systems
    Sae Int. J. Passeng. Cars - Mech. Syst


    Contributors:

    Conference:

    SAE 2016 World Congress and Exhibition ; 2016



    Publication date :

    2016-04-05


    Size :

    9 pages




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    GPGPU-based high performance parallel computation method for body failure mode

    Suzuki,T. / Mani,T. / Tsuchida,K. et al. | Automotive engineering | 2016


    GPGPU parallel algorithms for structured-grid CFD codes

    Stone, Christopher / Duque, Earl / Zhang, Yao et al. | AIAA | 2011


    Accelerating CSRN Based Face Recognition on an NVIDIA GPGPU

    Rice, K. / Taha, T. / Miller, R. et al. | British Library Conference Proceedings | 2011


    Accelerating CSRN based face recognition on an NVIDIA GPGPU

    Taha, Tarek / Rice, Kenneth / Miller, Ronald et al. | AIAA | 2011


    GPGPU Implementation and Benchmarking of the Unsteady Vortex Lattice Method

    Chabalko, C. / Fitzgerald, T. / Balachandran, B. et al. | British Library Conference Proceedings | 2013