Neko 1.99.9
A portable framework for high-order spectral element flow simulations
Loading...
Searching...
No Matches
dynamic_smagorinsky_nut.c
Go to the documentation of this file.
1/*
2 Copyright (c) 2026, 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
35#ifdef __APPLE__
36#include <OpenCL/cl.h>
37#else
38#include <CL/cl.h>
39#endif
40
42#include <device/opencl/check.h>
43#include <device/opencl/jit.h>
45
46#include "dynamic_smagorinsky_nut_kernel.cl.h"
47
55
57static void dynamic_smagorinsky_run(cl_kernel kernel, const int n) {
58 if (n > 0) {
59 const int nb = (n + 256 - 1) / 256;
60 const size_t global_item_size = 256 * nb;
61 const size_t local_item_size = 256;
62
66 }
67
69}
70
72void opencl_s_abs_compute(void *s_abs, void *s11, void *s22, void *s33,
73 void *s12, void *s13, void *s23, int *n) {
74 cl_int err;
75
77
79 "s_abs_compute_kernel", &err);
81
82 CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *) &s_abs));
83 CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *) &s11));
84 CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *) &s22));
85 CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_mem), (void *) &s33));
86 CL_CHECK(clSetKernelArg(kernel, 4, sizeof(cl_mem), (void *) &s12));
87 CL_CHECK(clSetKernelArg(kernel, 5, sizeof(cl_mem), (void *) &s13));
88 CL_CHECK(clSetKernelArg(kernel, 6, sizeof(cl_mem), (void *) &s23));
89 CL_CHECK(clSetKernelArg(kernel, 7, sizeof(int), n));
90
92}
93
95void opencl_lij_compute_part1(void *l11, void *l22, void *l33,
96 void *l12, void *l13, void *l23,
97 void *u, void *v, void *w,
98 void *fu, void *fv, void *fw,
99 void *fuu, void *fvv, void *fww,
100 void *fuv, void *fuw, void *fvw, int *n) {
101 cl_int err;
102
104
106 "lij_compute_part1_kernel", &err);
107 CL_CHECK(err);
108
109 CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *) &l11));
110 CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *) &l22));
111 CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *) &l33));
112 CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_mem), (void *) &l12));
113 CL_CHECK(clSetKernelArg(kernel, 4, sizeof(cl_mem), (void *) &l13));
114 CL_CHECK(clSetKernelArg(kernel, 5, sizeof(cl_mem), (void *) &l23));
115 CL_CHECK(clSetKernelArg(kernel, 6, sizeof(cl_mem), (void *) &u));
116 CL_CHECK(clSetKernelArg(kernel, 7, sizeof(cl_mem), (void *) &v));
117 CL_CHECK(clSetKernelArg(kernel, 8, sizeof(cl_mem), (void *) &w));
118 CL_CHECK(clSetKernelArg(kernel, 9, sizeof(cl_mem), (void *) &fu));
119 CL_CHECK(clSetKernelArg(kernel, 10, sizeof(cl_mem), (void *) &fv));
120 CL_CHECK(clSetKernelArg(kernel, 11, sizeof(cl_mem), (void *) &fw));
121 CL_CHECK(clSetKernelArg(kernel, 12, sizeof(cl_mem), (void *) &fuu));
122 CL_CHECK(clSetKernelArg(kernel, 13, sizeof(cl_mem), (void *) &fvv));
123 CL_CHECK(clSetKernelArg(kernel, 14, sizeof(cl_mem), (void *) &fww));
124 CL_CHECK(clSetKernelArg(kernel, 15, sizeof(cl_mem), (void *) &fuv));
125 CL_CHECK(clSetKernelArg(kernel, 16, sizeof(cl_mem), (void *) &fuw));
126 CL_CHECK(clSetKernelArg(kernel, 17, sizeof(cl_mem), (void *) &fvw));
127 CL_CHECK(clSetKernelArg(kernel, 18, sizeof(int), n));
128
130}
131
133void opencl_lij_compute_part2(void *l11, void *l22, void *l33,
134 void *l12, void *l13, void *l23,
135 void *fuu, void *fvv, void *fww,
136 void *fuv, void *fuw, void *fvw, int *n) {
137 cl_int err;
138
140
142 "lij_compute_part2_kernel", &err);
143 CL_CHECK(err);
144
145 CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *) &l11));
146 CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *) &l22));
147 CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *) &l33));
148 CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_mem), (void *) &l12));
149 CL_CHECK(clSetKernelArg(kernel, 4, sizeof(cl_mem), (void *) &l13));
150 CL_CHECK(clSetKernelArg(kernel, 5, sizeof(cl_mem), (void *) &l23));
151 CL_CHECK(clSetKernelArg(kernel, 6, sizeof(cl_mem), (void *) &fuu));
152 CL_CHECK(clSetKernelArg(kernel, 7, sizeof(cl_mem), (void *) &fvv));
153 CL_CHECK(clSetKernelArg(kernel, 8, sizeof(cl_mem), (void *) &fww));
154 CL_CHECK(clSetKernelArg(kernel, 9, sizeof(cl_mem), (void *) &fuv));
155 CL_CHECK(clSetKernelArg(kernel, 10, sizeof(cl_mem), (void *) &fuw));
156 CL_CHECK(clSetKernelArg(kernel, 11, sizeof(cl_mem), (void *) &fvw));
157 CL_CHECK(clSetKernelArg(kernel, 12, sizeof(int), n));
158
160}
161
163void opencl_mij_compute_part1(void *m11, void *m22, void *m33,
164 void *m12, void *m13, void *m23,
165 void *s_abs, void *s11, void *s22, void *s33,
166 void *s12, void *s13, void *s23,
167 void *fs_abs, void *fs11, void *fs22, void *fs33,
168 void *fs12, void *fs13, void *fs23,
169 void *fsabss11, void *fsabss22, void *fsabss33,
170 void *fsabss12, void *fsabss13, void *fsabss23,
171 real *delta_ratio2, int *n) {
172 cl_int err;
173
175
177 "mij_compute_part1_kernel", &err);
178 CL_CHECK(err);
179
180 CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *) &m11));
181 CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *) &m22));
182 CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *) &m33));
183 CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_mem), (void *) &m12));
184 CL_CHECK(clSetKernelArg(kernel, 4, sizeof(cl_mem), (void *) &m13));
185 CL_CHECK(clSetKernelArg(kernel, 5, sizeof(cl_mem), (void *) &m23));
186 CL_CHECK(clSetKernelArg(kernel, 6, sizeof(cl_mem), (void *) &s_abs));
187 CL_CHECK(clSetKernelArg(kernel, 7, sizeof(cl_mem), (void *) &s11));
188 CL_CHECK(clSetKernelArg(kernel, 8, sizeof(cl_mem), (void *) &s22));
189 CL_CHECK(clSetKernelArg(kernel, 9, sizeof(cl_mem), (void *) &s33));
190 CL_CHECK(clSetKernelArg(kernel, 10, sizeof(cl_mem), (void *) &s12));
191 CL_CHECK(clSetKernelArg(kernel, 11, sizeof(cl_mem), (void *) &s13));
192 CL_CHECK(clSetKernelArg(kernel, 12, sizeof(cl_mem), (void *) &s23));
193 CL_CHECK(clSetKernelArg(kernel, 13, sizeof(cl_mem), (void *) &fs_abs));
194 CL_CHECK(clSetKernelArg(kernel, 14, sizeof(cl_mem), (void *) &fs11));
195 CL_CHECK(clSetKernelArg(kernel, 15, sizeof(cl_mem), (void *) &fs22));
196 CL_CHECK(clSetKernelArg(kernel, 16, sizeof(cl_mem), (void *) &fs33));
197 CL_CHECK(clSetKernelArg(kernel, 17, sizeof(cl_mem), (void *) &fs12));
198 CL_CHECK(clSetKernelArg(kernel, 18, sizeof(cl_mem), (void *) &fs13));
199 CL_CHECK(clSetKernelArg(kernel, 19, sizeof(cl_mem), (void *) &fs23));
200 CL_CHECK(clSetKernelArg(kernel, 20, sizeof(cl_mem), (void *) &fsabss11));
201 CL_CHECK(clSetKernelArg(kernel, 21, sizeof(cl_mem), (void *) &fsabss22));
202 CL_CHECK(clSetKernelArg(kernel, 22, sizeof(cl_mem), (void *) &fsabss33));
203 CL_CHECK(clSetKernelArg(kernel, 23, sizeof(cl_mem), (void *) &fsabss12));
204 CL_CHECK(clSetKernelArg(kernel, 24, sizeof(cl_mem), (void *) &fsabss13));
205 CL_CHECK(clSetKernelArg(kernel, 25, sizeof(cl_mem), (void *) &fsabss23));
207 CL_CHECK(clSetKernelArg(kernel, 27, sizeof(int), n));
208
210}
211
213void opencl_mij_nut_compute_part2(void *m11, void *m22, void *m33,
214 void *m12, void *m13, void *m23,
215 void *l11, void *l22, void *l33,
216 void *l12, void *l13, void *l23,
217 void *fsabss11, void *fsabss22,
218 void *fsabss33, void *fsabss12,
219 void *fsabss13, void *fsabss23,
220 void *num, void *den, void *c_dyn,
221 void *delta, void *s_abs, void *nut,
222 real *alpha, int *n) {
223 cl_int err;
224
226
228 "mij_nut_compute_part2_kernel", &err);
229 CL_CHECK(err);
230
231 CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *) &m11));
232 CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *) &m22));
233 CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *) &m33));
234 CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_mem), (void *) &m12));
235 CL_CHECK(clSetKernelArg(kernel, 4, sizeof(cl_mem), (void *) &m13));
236 CL_CHECK(clSetKernelArg(kernel, 5, sizeof(cl_mem), (void *) &m23));
237 CL_CHECK(clSetKernelArg(kernel, 6, sizeof(cl_mem), (void *) &l11));
238 CL_CHECK(clSetKernelArg(kernel, 7, sizeof(cl_mem), (void *) &l22));
239 CL_CHECK(clSetKernelArg(kernel, 8, sizeof(cl_mem), (void *) &l33));
240 CL_CHECK(clSetKernelArg(kernel, 9, sizeof(cl_mem), (void *) &l12));
241 CL_CHECK(clSetKernelArg(kernel, 10, sizeof(cl_mem), (void *) &l13));
242 CL_CHECK(clSetKernelArg(kernel, 11, sizeof(cl_mem), (void *) &l23));
243 CL_CHECK(clSetKernelArg(kernel, 12, sizeof(cl_mem), (void *) &fsabss11));
244 CL_CHECK(clSetKernelArg(kernel, 13, sizeof(cl_mem), (void *) &fsabss22));
245 CL_CHECK(clSetKernelArg(kernel, 14, sizeof(cl_mem), (void *) &fsabss33));
246 CL_CHECK(clSetKernelArg(kernel, 15, sizeof(cl_mem), (void *) &fsabss12));
247 CL_CHECK(clSetKernelArg(kernel, 16, sizeof(cl_mem), (void *) &fsabss13));
248 CL_CHECK(clSetKernelArg(kernel, 17, sizeof(cl_mem), (void *) &fsabss23));
249 CL_CHECK(clSetKernelArg(kernel, 18, sizeof(cl_mem), (void *) &num));
250 CL_CHECK(clSetKernelArg(kernel, 19, sizeof(cl_mem), (void *) &den));
251 CL_CHECK(clSetKernelArg(kernel, 20, sizeof(cl_mem), (void *) &c_dyn));
252 CL_CHECK(clSetKernelArg(kernel, 21, sizeof(cl_mem), (void *) &delta));
253 CL_CHECK(clSetKernelArg(kernel, 22, sizeof(cl_mem), (void *) &s_abs));
254 CL_CHECK(clSetKernelArg(kernel, 23, sizeof(cl_mem), (void *) &nut));
255 CL_CHECK(clSetKernelArg(kernel, 24, sizeof(real), alpha));
256 CL_CHECK(clSetKernelArg(kernel, 25, sizeof(int), n));
257
259}
__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)
__global__ void T *__restrict__ T *__restrict__ const T *__restrict__ const T *__restrict__ const T *__restrict__ w
__global__ void T *__restrict__ T *__restrict__ const T *__restrict__ u
__global__ void T *__restrict__ T *__restrict__ const T *__restrict__ const T *__restrict__ v
double real
void opencl_lij_compute_part1(void *l11, void *l22, void *l33, void *l12, void *l13, void *l23, void *u, void *v, void *w, void *fu, void *fv, void *fw, void *fuu, void *fvv, void *fww, void *fuv, void *fuw, void *fvw, int *n)
static void dynamic_smagorinsky_jit()
void opencl_s_abs_compute(void *s_abs, void *s11, void *s22, void *s33, void *s12, void *s13, void *s23, int *n)
void opencl_mij_nut_compute_part2(void *m11, void *m22, void *m33, void *m12, void *m13, void *m23, void *l11, void *l22, void *l33, void *l12, void *l13, void *l23, void *fsabss11, void *fsabss22, void *fsabss33, void *fsabss12, void *fsabss13, void *fsabss23, void *num, void *den, void *c_dyn, void *delta, void *s_abs, void *nut, real *alpha, int *n)
void opencl_mij_compute_part1(void *m11, void *m22, void *m33, void *m12, void *m13, void *m23, void *s_abs, void *s11, void *s22, void *s33, void *s12, void *s13, void *s23, void *fs_abs, void *fs11, void *fs22, void *fs33, void *fs12, void *fs13, void *fs23, void *fsabss11, void *fsabss22, void *fsabss33, void *fsabss12, void *fsabss13, void *fsabss23, real *delta_ratio2, int *n)
void opencl_lij_compute_part2(void *l11, void *l22, void *l33, void *l12, void *l13, void *l23, void *fuu, void *fvv, void *fww, void *fuv, void *fuw, void *fvw, int *n)
static void dynamic_smagorinsky_run(cl_kernel kernel, const int n)
void opencl_kernel_jit(const char *kernel, cl_program *program)
Definition jit.c:50
#define CL_CHECK(err)
Definition check.h:12
void * dynamic_smagorinsky_nut_program