Neko
0.9.99
A portable framework for high-order spectral element flow simulations
|
#include "math_kernel.h"
#include <device/device_config.h>
#include <device/cuda/check.h>
#include <stdio.h>
#include <stdlib.h>
#include <math/bcknd/device/device_mpi_reduce.h>
#include <math/bcknd/device/device_mpi_op.h>
Go to the source code of this file.
Functions | |
void | cuda_copy (void *a, void *b, int *n) |
void | cuda_masked_copy (void *a, void *b, void *mask, int *n, int *m) |
void | cuda_masked_red_copy (void *a, void *b, void *mask, int *n, int *m) |
void | cuda_cfill_mask (void *a, real *c, int *size, int *mask, int *mask_size) |
void | cuda_rzero (void *a, int *n) |
void | cuda_cmult (void *a, real *c, int *n) |
void | cuda_cmult2 (void *a, void *b, real *c, int *n) |
void | cuda_cadd (void *a, real *c, int *n) |
void | cuda_cadd2 (void *a, void *b, real *c, int *n) |
void | cuda_cfill (void *a, real *c, int *n) |
void | cuda_add2 (void *a, void *b, int *n) |
void | cuda_add3 (void *a, void *b, void *c, int *n) |
void | cuda_add4 (void *a, void *b, void *c, void *d, int *n) |
void | cuda_add2s1 (void *a, void *b, real *c1, int *n) |
void | cuda_add2s2 (void *a, void *b, real *c1, int *n) |
void | cuda_add2s2_many (void *x, void **p, void *alpha, int *j, int *n) |
void | cuda_addsqr2s2 (void *a, void *b, real *c1, int *n) |
void | cuda_add3s2 (void *a, void *b, void *c, real *c1, real *c2, int *n) |
void | cuda_invcol1 (void *a, int *n) |
void | cuda_invcol2 (void *a, void *b, int *n) |
void | cuda_col2 (void *a, void *b, int *n) |
void | cuda_col3 (void *a, void *b, void *c, int *n) |
void | cuda_subcol3 (void *a, void *b, void *c, int *n) |
void | cuda_sub2 (void *a, void *b, int *n) |
void | cuda_sub3 (void *a, void *b, void *c, int *n) |
void | cuda_addcol3 (void *a, void *b, void *c, int *n) |
void | cuda_addcol4 (void *a, void *b, void *c, void *d, int *n) |
void | cuda_vdot3 (void *dot, void *u1, void *u2, void *u3, void *v1, void *v2, void *v3, int *n) |
void | cuda_vcross (void *u1, void *u2, void *u3, void *v1, void *v2, void *v3, void *w1, void *w2, void *w3, int *n) |
real | cuda_vlsc3 (void *u, void *v, void *w, int *n) |
real | cuda_glsc3 (void *a, void *b, void *c, int *n) |
void | cuda_glsc3_many (real *h, void *w, void *v, void *mult, int *j, int *n) |
real | cuda_glsc2 (void *a, void *b, int *n) |
real | cuda_glsum (void *a, int *n) |
void | cuda_absval (void *a, int *n) |
void | cuda_pwmax_vec2 (void *a, void *b, int *n) |
void | cuda_pwmax_vec3 (void *a, void *b, void *c, int *n) |
void | cuda_pwmax_sca2 (void *a, real *c, int *n) |
void | cuda_pwmax_sca3 (void *a, void *b, real *c, int *n) |
void | cuda_pwmin_vec2 (void *a, void *b, int *n) |
void | cuda_pwmin_vec3 (void *a, void *b, void *c, int *n) |
void | cuda_pwmin_sca2 (void *a, real *c, int *n) |
void | cuda_pwmin_sca3 (void *a, void *b, real *c, int *n) |
Variables | |
int | red_s = 0 |
real * | bufred = NULL |
real * | bufred_d = NULL |
void cuda_absval | ( | void * | a, |
int * | n | ||
) |
void cuda_add2 | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
void cuda_add2s1 | ( | void * | a, |
void * | b, | ||
real * | c1, | ||
int * | n | ||
) |
void cuda_add2s2 | ( | void * | a, |
void * | b, | ||
real * | c1, | ||
int * | n | ||
) |
void cuda_add2s2_many | ( | void * | x, |
void ** | p, | ||
void * | alpha, | ||
int * | j, | ||
int * | n | ||
) |
void cuda_add3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_add4 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
void * | d, | ||
int * | n | ||
) |
void cuda_addcol3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_addcol4 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
void * | d, | ||
int * | n | ||
) |
void cuda_addsqr2s2 | ( | void * | a, |
void * | b, | ||
real * | c1, | ||
int * | n | ||
) |
void cuda_cadd | ( | void * | a, |
real * | c, | ||
int * | n | ||
) |
void cuda_cadd2 | ( | void * | a, |
void * | b, | ||
real * | c, | ||
int * | n | ||
) |
void cuda_cfill | ( | void * | a, |
real * | c, | ||
int * | n | ||
) |
void cuda_cfill_mask | ( | void * | a, |
real * | c, | ||
int * | size, | ||
int * | mask, | ||
int * | mask_size | ||
) |
void cuda_cmult | ( | void * | a, |
real * | c, | ||
int * | n | ||
) |
void cuda_cmult2 | ( | void * | a, |
void * | b, | ||
real * | c, | ||
int * | n | ||
) |
void cuda_col2 | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
void cuda_col3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_copy | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
real cuda_glsc2 | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
real cuda_glsc3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_glsc3_many | ( | real * | h, |
void * | w, | ||
void * | v, | ||
void * | mult, | ||
int * | j, | ||
int * | n | ||
) |
real cuda_glsum | ( | void * | a, |
int * | n | ||
) |
void cuda_invcol1 | ( | void * | a, |
int * | n | ||
) |
void cuda_invcol2 | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
void cuda_masked_copy | ( | void * | a, |
void * | b, | ||
void * | mask, | ||
int * | n, | ||
int * | m | ||
) |
void cuda_masked_red_copy | ( | void * | a, |
void * | b, | ||
void * | mask, | ||
int * | n, | ||
int * | m | ||
) |
void cuda_pwmax_sca2 | ( | void * | a, |
real * | c, | ||
int * | n | ||
) |
void cuda_pwmax_sca3 | ( | void * | a, |
void * | b, | ||
real * | c, | ||
int * | n | ||
) |
void cuda_pwmax_vec2 | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
void cuda_pwmax_vec3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_pwmin_sca2 | ( | void * | a, |
real * | c, | ||
int * | n | ||
) |
void cuda_pwmin_sca3 | ( | void * | a, |
void * | b, | ||
real * | c, | ||
int * | n | ||
) |
void cuda_pwmin_vec2 | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
void cuda_pwmin_vec3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_rzero | ( | void * | a, |
int * | n | ||
) |
void cuda_sub2 | ( | void * | a, |
void * | b, | ||
int * | n | ||
) |
void cuda_sub3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_subcol3 | ( | void * | a, |
void * | b, | ||
void * | c, | ||
int * | n | ||
) |
void cuda_vcross | ( | void * | u1, |
void * | u2, | ||
void * | u3, | ||
void * | v1, | ||
void * | v2, | ||
void * | v3, | ||
void * | w1, | ||
void * | w2, | ||
void * | w3, | ||
int * | n | ||
) |
void cuda_vdot3 | ( | void * | dot, |
void * | u1, | ||
void * | u2, | ||
void * | u3, | ||
void * | v1, | ||
void * | v2, | ||
void * | v3, | ||
int * | n | ||
) |
real cuda_vlsc3 | ( | void * | u, |
void * | v, | ||
void * | w, | ||
int * | n | ||
) |