Neko 1.99.2
A portable framework for high-order spectral element flow simulations
Loading...
Searching...
No Matches
euler_res_kernel.h
Go to the documentation of this file.
1/*
2 Copyright (c) 2025, The Neko Authors
3 All rights reserved.
4
5 Redistribution and use in source and binary forms, with or without
6 modification, are permitted provided that the following conditions
7 are met:
8
9 * Redistributions of source code must retain the above copyright
10 notice, this list of conditions and the following disclaimer.
11
12 * Redistributions in binary form must reproduce the above
13 copyright notice, this list of conditions and the following
14 disclaimer in the documentation and/or other materials provided
15 with the distribution.
16
17 * Neither the name of the authors nor the names of its
18 contributors may be used to endorse or promote products derived
19 from this software without specific prior written permission.
20
21 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
24 FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
25 COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
26 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
27 BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
28 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
29 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30 LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
31 ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
32 POSSIBILITY OF SUCH DAMAGE.
33*/
34#ifndef __FLUID_EULER_RES_KERNEL__
35#define __FLUID_EULER_RES_KERNEL__
36
37template< typename T >
38__global__ void euler_res_part_visc_kernel(T * __restrict__ rhs,
39 const T * __restrict__ Binv,
40 const T * __restrict__ lap_sol,
41 const T * __restrict__ effective_visc,
42 const int n) {
43
44 const int idx = blockIdx.x * blockDim.x + threadIdx.x;
45 const int str = blockDim.x * gridDim.x;
46
47 for (int i = idx; i < n; i += str) {
48 rhs[i] = -rhs[i] - effective_visc[i] * Binv[i] * lap_sol[i];
49 }
50}
51
52template< typename T >
53__global__ void euler_res_part_mx_flux_kernel(T * __restrict__ f_x,
54 T * __restrict__ f_y,
55 T * __restrict__ f_z,
56 const T * __restrict__ m_x,
57 const T * __restrict__ m_y,
58 const T * __restrict__ m_z,
59 const T * __restrict__ rho_field,
60 const T * __restrict__ p,
61 const int n) {
62
63 const int idx = blockIdx.x * blockDim.x + threadIdx.x;
64 const int str = blockDim.x * gridDim.x;
65
66 for (int i = idx; i < n; i += str) {
67 f_x[i] = m_x[i] * m_x[i] / rho_field[i] + p[i];
68 f_y[i] = m_x[i] * m_y[i] / rho_field[i];
69 f_z[i] = m_x[i] * m_z[i] / rho_field[i];
70 }
71}
72
73template< typename T >
74__global__ void euler_res_part_my_flux_kernel(T * __restrict__ f_x,
75 T * __restrict__ f_y,
76 T * __restrict__ f_z,
77 const T * __restrict__ m_x,
78 const T * __restrict__ m_y,
79 const T * __restrict__ m_z,
80 const T * __restrict__ rho_field,
81 const T * __restrict__ p,
82 const int n) {
83
84 const int idx = blockIdx.x * blockDim.x + threadIdx.x;
85 const int str = blockDim.x * gridDim.x;
86
87 for (int i = idx; i < n; i += str) {
88 f_x[i] = m_y[i] * m_x[i] / rho_field[i];
89 f_y[i] = m_y[i] * m_y[i] / rho_field[i] + p[i];
90 f_z[i] = m_y[i] * m_z[i] / rho_field[i];
91 }
92}
93
94template< typename T >
95__global__ void euler_res_part_mz_flux_kernel(T * __restrict__ f_x,
96 T * __restrict__ f_y,
97 T * __restrict__ f_z,
98 const T * __restrict__ m_x,
99 const T * __restrict__ m_y,
100 const T * __restrict__ m_z,
101 const T * __restrict__ rho_field,
102 const T * __restrict__ p,
103 const int n) {
104
105 const int idx = blockIdx.x * blockDim.x + threadIdx.x;
106 const int str = blockDim.x * gridDim.x;
107
108 for (int i = idx; i < n; i += str) {
109 f_x[i] = m_z[i] * m_x[i] / rho_field[i];
110 f_y[i] = m_z[i] * m_y[i] / rho_field[i];
111 f_z[i] = m_z[i] * m_z[i] / rho_field[i] + p[i];
112 }
113}
114
115template< typename T >
116__global__ void euler_res_part_E_flux_kernel(T * __restrict__ f_x,
117 T * __restrict__ f_y,
118 T * __restrict__ f_z,
119 const T * __restrict__ m_x,
120 const T * __restrict__ m_y,
121 const T * __restrict__ m_z,
122 const T * __restrict__ rho_field,
123 const T * __restrict__ p,
124 const T * __restrict__ E,
125 const int n) {
126
127 const int idx = blockIdx.x * blockDim.x + threadIdx.x;
128 const int str = blockDim.x * gridDim.x;
129
130 for (int i = idx; i < n; i += str) {
131 f_x[i] = (E[i] + p[i]) * m_x[i] / rho_field[i];
132 f_y[i] = (E[i] + p[i]) * m_y[i] / rho_field[i];
133 f_z[i] = (E[i] + p[i]) * m_z[i] / rho_field[i];
134 }
135}
136
137template< typename T >
138__global__ void euler_res_part_coef_mult_kernel(T * __restrict__ rhs_rho,
139 T * __restrict__ rhs_m_x,
140 T * __restrict__ rhs_m_y,
141 T * __restrict__ rhs_m_z,
142 T * __restrict__ rhs_E,
143 const T * __restrict__ mult,
144 const int n) {
145
146 const int idx = blockIdx.x * blockDim.x + threadIdx.x;
147 const int str = blockDim.x * gridDim.x;
148
149 for (int i = idx; i < n; i += str) {
150 rhs_rho[i] = rhs_rho[i] * mult[i];
151 rhs_m_x[i] = rhs_m_x[i] * mult[i];
152 rhs_m_y[i] = rhs_m_y[i] * mult[i];
153 rhs_m_z[i] = rhs_m_z[i] * mult[i];
154 rhs_E[i] = rhs_E[i] * mult[i];
155 }
156}
157
158template< typename T >
159__global__ void euler_res_part_rk_sum_kernel(T * __restrict__ rho,
160 T * __restrict__ m_x,
161 T * __restrict__ m_y,
162 T * __restrict__ m_z,
163 T * __restrict__ E,
164 const T * __restrict__ k_rho_i,
165 const T * __restrict__ k_m_x_i,
166 const T * __restrict__ k_m_y_i,
167 const T * __restrict__ k_m_z_i,
168 const T * __restrict__ k_E_i,
169 const T dt,
170 const T c,
171 const int n) {
172
173 const int idx = blockIdx.x * blockDim.x + threadIdx.x;
174 const int str = blockDim.x * gridDim.x;
175
176 for (int i = idx; i < n; i += str) {
177 rho[i] = rho[i] + dt * c * k_rho_i[i];
178 m_x[i] = m_x[i] + dt * c * k_m_x_i[i];
179 m_y[i] = m_y[i] + dt * c * k_m_y_i[i];
180 m_z[i] = m_z[i] + dt * c * k_m_z_i[i];
181 E[i] = E[i] + dt * c * k_E_i[i];
182 }
183}
184
185#endif // __FLUID_EULER_RES_KERNEL__
i
const int i
Definition ax_helm_full_kernel.h:95
dt
__global__ void const T *__restrict__ const T *__restrict__ const T *__restrict__ const T *__restrict__ dt
Definition cdtp_kernel.h:109
dirichlet_apply_scalar_kernel
__global__ void dirichlet_apply_scalar_kernel(const int *__restrict__ msk, T *__restrict__ x, const T g, const int m)
Definition dirichlet_kernel.h:42
euler_res_part_rk_sum_kernel
__global__ void euler_res_part_rk_sum_kernel(T *__restrict__ rho, T *__restrict__ m_x, T *__restrict__ m_y, T *__restrict__ m_z, T *__restrict__ E, const T *__restrict__ k_rho_i, const T *__restrict__ k_m_x_i, const T *__restrict__ k_m_y_i, const T *__restrict__ k_m_z_i, const T *__restrict__ k_E_i, const T dt, const T c, const int n)
Definition euler_res_kernel.h:159
euler_res_part_my_flux_kernel
__global__ void euler_res_part_my_flux_kernel(T *__restrict__ f_x, T *__restrict__ f_y, T *__restrict__ f_z, const T *__restrict__ m_x, const T *__restrict__ m_y, const T *__restrict__ m_z, const T *__restrict__ rho_field, const T *__restrict__ p, const int n)
Definition euler_res_kernel.h:74
euler_res_part_E_flux_kernel
__global__ void euler_res_part_E_flux_kernel(T *__restrict__ f_x, T *__restrict__ f_y, T *__restrict__ f_z, const T *__restrict__ m_x, const T *__restrict__ m_y, const T *__restrict__ m_z, const T *__restrict__ rho_field, const T *__restrict__ p, const T *__restrict__ E, const int n)
Definition euler_res_kernel.h:116
euler_res_part_visc_kernel
__global__ void euler_res_part_visc_kernel(T *__restrict__ rhs, const T *__restrict__ Binv, const T *__restrict__ lap_sol, const T *__restrict__ effective_visc, const int n)
Definition euler_res_kernel.h:38
euler_res_part_mz_flux_kernel
__global__ void euler_res_part_mz_flux_kernel(T *__restrict__ f_x, T *__restrict__ f_y, T *__restrict__ f_z, const T *__restrict__ m_x, const T *__restrict__ m_y, const T *__restrict__ m_z, const T *__restrict__ rho_field, const T *__restrict__ p, const int n)
Definition euler_res_kernel.h:95
euler_res_part_coef_mult_kernel
__global__ void euler_res_part_coef_mult_kernel(T *__restrict__ rhs_rho, T *__restrict__ rhs_m_x, T *__restrict__ rhs_m_y, T *__restrict__ rhs_m_z, T *__restrict__ rhs_E, const T *__restrict__ mult, const int n)
Definition euler_res_kernel.h:138
euler_res_part_mx_flux_kernel
__global__ void euler_res_part_mx_flux_kernel(T *__restrict__ f_x, T *__restrict__ f_y, T *__restrict__ f_z, const T *__restrict__ m_x, const T *__restrict__ m_y, const T *__restrict__ m_z, const T *__restrict__ rho_field, const T *__restrict__ p, const int n)
Definition euler_res_kernel.h:53