44 void *wa1,
void *wa2,
void *wa3,
45 void *f_u,
void *f_v,
void *f_w,
46 void *B,
void *
h1,
real *mu,
49 const dim3 nthrds(1024, 1, 1);
50 const dim3 nblcks(((*n) + 1024 - 1) / 1024, 1, 1);
53 prs_res_part1_kernel<real>
54 <<<nblcks, nthrds, 0, stream>>>((
real *) ta1, (
real *) ta2,
59 (
real *)
h1, *mu, *rho, *n);
66 const dim3 nthrds(1024, 1, 1);
67 const dim3 nblcks(((*n) + 1024 - 1) / 1024, 1, 1);
70 prs_res_part2_kernel<real>
71 <<<nblcks, nthrds, 0, stream>>>((
real *) p_res, (
real *) wa1,
78 void *ta3,
real *dtbd,
int *n) {
80 const dim3 nthrds(1024, 1, 1);
81 const dim3 nblcks(((*n) + 1024 - 1) / 1024, 1, 1);
84 prs_res_part3_kernel<real>
85 <<<nblcks, nthrds, 0, stream>>>((
real *) p_res, (
real *) ta1,
93 void *ta1,
void *ta2,
void *ta3,
94 void *f_u,
void *f_v,
void *f_w,
int *n) {
96 const dim3 nthrds(1024, 1, 1);
97 const dim3 nblcks(((*n) + 1024 - 1) / 1024, 1, 1);
100 vel_res_update_kernel<real>
101 <<<nblcks, nthrds, 0, stream>>>((
real *) u_res, (
real *) v_res,
__global__ void T *__restrict__ T *__restrict__ const T *__restrict__ const T *__restrict__ const T *__restrict__ const T *__restrict__ const T *__restrict__ const T *__restrict__ const T *__restrict__ h1
void pnpn_prs_res_part2_cuda(void *p_res, void *wa1, void *wa2, void *wa3, int *n)
void pnpn_prs_res_part3_cuda(void *p_res, void *ta1, void *ta2, void *ta3, real *dtbd, int *n)
void pnpn_vel_res_update_cuda(void *u_res, void *v_res, void *w_res, void *ta1, void *ta2, void *ta3, void *f_u, void *f_v, void *f_w, int *n)
void pnpn_prs_res_part1_cuda(void *ta1, void *ta2, void *ta3, void *wa1, void *wa2, void *wa3, void *f_u, void *f_v, void *f_w, void *B, void *h1, real *mu, real *rho, int *n)