dc/d4f/hip_2prs__stress__res__kernel_8h_source.html

/*

 Copyright (c) 2024, The Neko Authors

 All rights reserved.


 Redistribution and use in source and binary forms, with or without

 modification, are permitted provided that the following conditions

 are met:


   * Redistributions of source code must retain the above copyright

     notice, this list of conditions and the following disclaimer.


   * Redistributions in binary form must reproduce the above

     copyright notice, this list of conditions and the following

     disclaimer in the documentation and/or other materials provided

     with the distribution.


   * Neither the name of the authors nor the names of its

     contributors may be used to endorse or promote products derived

     from this software without specific prior written permission.


 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT

 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS

 FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE

 COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,

 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,

 BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;

 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER

 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT

 LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN

 ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE

 POSSIBILITY OF SUCH DAMAGE.

*/


#ifndef __FLUID_PRS_STRESS_RES_KERNEL__

#define __FLUID_PRS_STRESS_RES_KERNEL__


template< typename T >


__global__ void prs_stress_res_part1_kernel(T * __restrict__ ta1,

                                            T * __restrict__ ta2,

                                            T * __restrict__ ta3,

                                            T * __restrict__ wa1,

                                            T * __restrict__ wa2,

                                            T * __restrict__ wa3,

                                            const T * __restrict__ s11,

                                            const T * __restrict__ s22,

                                            const T * __restrict__ s33,

                                            const T * __restrict__ s12,

                                            const T * __restrict__ s13,

                                            const T * __restrict__ s23,

                                            const T * __restrict__ f_u,

                                            const T * __restrict__ f_v,

                                            const T * __restrict__ f_w,

                                            const T * __restrict__ B,

                                            const T * __restrict__ rho,

                                            const int n) {


  const int idx = blockIdx.x * blockDim.x + threadIdx.x;

  const int str = blockDim.x * gridDim.x;


  for (int i = idx; i < n; i += str) {

    wa1[i] -= 2.0 * (ta1[i] * s11[i]

                   + ta2[i] * s12[i]

                   + ta3[i] * s13[i]);

    wa2[i] -= 2.0 * (ta1[i] * s12[i]

                   + ta2[i] * s22[i]

                   + ta3[i] * s23[i]);

    wa3[i] -= 2.0 * (ta1[i] * s13[i]

                   + ta2[i] * s23[i]

                   + ta3[i] * s33[i]);


    ta1[i] = (f_u[i] / rho[i]) - ((wa1[i] / rho[i]) * B[i]);

    ta2[i] = (f_v[i] / rho[i]) - ((wa2[i] / rho[i]) * B[i]);

    ta3[i] = (f_w[i] / rho[i]) - ((wa3[i] / rho[i]) * B[i]);

  }


}


template< typename T >


__global__ void prs_stress_res_part3_kernel(T * __restrict__ p_res,

                                            const T * __restrict__ ta1,

                                            const T * __restrict__ ta2,

                                            const T * __restrict__ ta3,

                                            const T * __restrict__ wa1,

                                            const T * __restrict__ wa2,

                                            const T * __restrict__ wa3,

                                            const T dtbd,

                                            const int n) {


  const int idx = blockIdx.x * blockDim.x + threadIdx.x;

  const int str = blockDim.x * gridDim.x;


  for (int i = idx; i < n; i += str) {

    p_res[i] = p_res[i] - (dtbd * (ta1[i] + ta2[i] + ta3[i]))

      - (wa1[i] + wa2[i] + wa3[i]);

  }

}


#endif // __FLUID_PRS_STRESS_RES_KERNEL__

ale_add_kinematics_kernel
__global__ void ale_add_kinematics_kernel(const int n, T *__restrict__ wx, T *__restrict__ wy, T *__restrict__ wz, const T *__restrict__ x_ref, const T *__restrict__ y_ref, const T *__restrict__ z_ref, const T *__restrict__ phi, const T *__restrict__ x, const T *__restrict__ y, const T *__restrict__ z, const kinematics_params_t kin_params)
Definition ale_kinematics_kernel.h:52

i
const int i
Definition ax_helm_full_kernel.h:95

prs_stress_res_part1_kernel
__global__ void prs_stress_res_part1_kernel(T *__restrict__ ta1, T *__restrict__ ta2, T *__restrict__ ta3, T *__restrict__ wa1, T *__restrict__ wa2, T *__restrict__ wa3, const T *__restrict__ s11, const T *__restrict__ s22, const T *__restrict__ s33, const T *__restrict__ s12, const T *__restrict__ s13, const T *__restrict__ s23, const T *__restrict__ f_u, const T *__restrict__ f_v, const T *__restrict__ f_w, const T *__restrict__ B, const T *__restrict__ rho, const int n)
Definition prs_stress_res_kernel.h:39

prs_stress_res_part3_kernel
__global__ void prs_stress_res_part3_kernel(T *__restrict__ p_res, const T *__restrict__ ta1, const T *__restrict__ ta2, const T *__restrict__ ta3, const T *__restrict__ wa1, const T *__restrict__ wa2, const T *__restrict__ wa3, const T dtbd, const int n)
Definition prs_stress_res_kernel.h:80