|
Neko 1.99.10
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 <device/cuda/buffer.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, cudaStream_t strm) |
| void | cuda_masked_copy_0 (void *a, void *b, void *mask, int *n, int *m, cudaStream_t strm) |
| void | cuda_masked_copy_aligned (void *a, void *b, void *mask, int *n, int *m, cudaStream_t strm) |
| void | cuda_masked_gather_copy (void *a, void *b, void *mask, int *n, int *m, cudaStream_t strm) |
| void | cuda_masked_gather_copy_aligned (void *a, void *b, void *mask, int *n, int *m, cudaStream_t strm) |
| void | cuda_face_masked_gather_copy (void *a, void *b, void *mask, void *facet, int *n1, int *n2, int *lx, int *ly, int *lz, int *m, cudaStream_t strm) |
| void | cuda_masked_atomic_reduction (void *a, void *b, void *mask, int *n, int *m, cudaStream_t strm) |
| void | cuda_masked_scatter_copy (void *a, void *b, void *mask, int *n, int *m, cudaStream_t strm) |
| void | cuda_masked_scatter_copy_aligned (void *a, void *b, void *mask, int *n, int *m, cudaStream_t strm) |
| void | cuda_cfill_mask (void *a, real *c, int *size, int *mask, int *mask_size, cudaStream_t strm) |
| void | cuda_rzero (void *a, int *n, cudaStream_t strm) |
| void | cuda_cmult (void *a, real *c, int *n, cudaStream_t strm) |
| void | cuda_cmult2 (void *a, void *b, real *c, int *n, cudaStream_t strm) |
| void | cuda_cdiv (void *a, real *c, int *n, cudaStream_t strm) |
| void | cuda_cdiv2 (void *a, void *b, real *c, int *n, cudaStream_t strm) |
| void | cuda_radd (void *a, real *c, int *n, cudaStream_t strm) |
| void | cuda_cadd2 (void *a, void *b, real *c, int *n, cudaStream_t strm) |
| void | cuda_cwrap (void *a, real *min_val, real *max_val, int *n, cudaStream_t strm) |
| void | cuda_sqrt_inplace (void *a, int *n, cudaStream_t strm) |
| void | cuda_power (void *ap, void *a, real *p, int *n, cudaStream_t strm) |
| void | cuda_cfill (void *a, real *c, int *n, cudaStream_t strm) |
| void | cuda_add2 (void *a, void *b, int *n, cudaStream_t strm) |
| void | cuda_add3 (void *a, void *b, void *c, int *n, cudaStream_t strm) |
| void | cuda_add4 (void *a, void *b, void *c, void *d, int *n, cudaStream_t strm) |
| void | cuda_add2s1 (void *a, void *b, real *c1, int *n, cudaStream_t strm) |
| void | cuda_add2s2 (void *a, void *b, real *c1, int *n, cudaStream_t strm) |
| void | cuda_add2s2_many (void *x, void **p, void *alpha, int *j, int *n, cudaStream_t strm) |
| void | cuda_addsqr2s2 (void *a, void *b, real *c1, int *n, cudaStream_t strm) |
| void | cuda_add3s2 (void *a, void *b, void *c, real *c1, real *c2, int *n, cudaStream_t strm) |
| void | cuda_add4s3 (void *a, void *b, void *c, void *d, real *c1, real *c2, real *c3, int *n, cudaStream_t strm) |
| void | cuda_add5s4 (void *a, void *b, void *c, void *d, void *e, real *c1, real *c2, real *c3, real *c4, int *n, cudaStream_t strm) |
| void | cuda_invcol1 (void *a, int *n, cudaStream_t strm) |
| void | cuda_invcol2 (void *a, void *b, int *n, cudaStream_t strm) |
| void | cuda_invcol3 (void *a, void *b, void *c, int *n, cudaStream_t strm) |
| void | cuda_col2 (void *a, void *b, int *n, cudaStream_t strm) |
| void | cuda_col3 (void *a, void *b, void *c, int *n, cudaStream_t strm) |
| void | cuda_subcol3 (void *a, void *b, void *c, int *n, cudaStream_t strm) |
| void | cuda_sub2 (void *a, void *b, int *n, cudaStream_t strm) |
| void | cuda_sub3 (void *a, void *b, void *c, int *n, cudaStream_t strm) |
| void | cuda_addcol3 (void *a, void *b, void *c, int *n, cudaStream_t strm) |
| void | cuda_addcol4 (void *a, void *b, void *c, void *d, int *n, cudaStream_t strm) |
| void | cuda_addcol3s2 (void *a, void *b, void *c, real *s, int *n, cudaStream_t strm) |
| void | cuda_vdot3 (void *dot, void *u1, void *u2, void *u3, void *v1, void *v2, void *v3, int *n, cudaStream_t strm) |
| void | cuda_vcross (void *u1, void *u2, void *u3, void *v1, void *v2, void *v3, void *w1, void *w2, void *w3, int *n, cudaStream_t strm) |
| void | cuda_redbuf_check_alloc (int nb) |
| void | cuda_redbuf_check_alloc_xp (int nb) |
| void | cuda_global_reduce_add (real *bufred, void *bufred_d, int n, const cudaStream_t stream) |
| void | cuda_global_reduce_add_xp (real_xp *bufred, void *bufred_d, int n, const cudaStream_t stream) |
| void | cuda_global_reduce_max (real *bufred, void *bufred_d, int n, const cudaStream_t stream) |
| void | cuda_global_reduce_min (real *bufred, void *bufred_d, int n, const cudaStream_t stream) |
| real | cuda_vlsc3 (void *u, void *v, void *w, int *n, cudaStream_t stream) |
| real_xp | cuda_glsc3 (void *a, void *b, void *c, int *n, cudaStream_t stream) |
| void | cuda_glsc3_many (real_xp *h, void *w, void *v, void *mult, int *j, int *n, cudaStream_t stream) |
| real_xp | cuda_glsc2 (void *a, void *b, int *n, cudaStream_t stream) |
| real_xp | cuda_glsubnorm2 (void *a, void *b, int *n, cudaStream_t stream) |
| real_xp | cuda_glsum (void *a, int *n, cudaStream_t stream) |
| real | cuda_glmax (void *a, real *ninf, int *n, cudaStream_t stream) |
| real | cuda_glmin (void *a, real *pinf, int *n, cudaStream_t stream) |
| real | cuda_glamax (void *a, int *n, cudaStream_t stream) |
| void | cuda_absval (void *a, int *n, cudaStream_t stream) |
| void | cuda_pwmax_vec2 (void *a, void *b, int *n, cudaStream_t stream) |
| void | cuda_pwmax_vec3 (void *a, void *b, void *c, int *n, cudaStream_t stream) |
| void | cuda_pwmax_sca2 (void *a, real *c, int *n, cudaStream_t stream) |
| void | cuda_pwmax_sca3 (void *a, void *b, real *c, int *n, cudaStream_t stream) |
| void | cuda_pwmin_vec2 (void *a, void *b, int *n, cudaStream_t stream) |
| void | cuda_pwmin_vec3 (void *a, void *b, void *c, int *n, cudaStream_t stream) |
| void | cuda_pwmin_sca2 (void *a, real *c, int *n, cudaStream_t stream) |
| void | cuda_pwmin_sca3 (void *a, void *b, real *c, int *n, cudaStream_t stream) |
| void | cuda_iadd (void *a, int *c, int *n, cudaStream_t stream) |
Variables | |
| cuda_buffer_t | redbuf = CUDA_BUFFER_INIT_SYMM |
| cuda_buffer_t | redbuf_xp = CUDA_BUFFER_INIT_SYMM |
| void cuda_absval | ( | void * | a, |
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_add2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_add2s1 | ( | void * | a, |
| void * | b, | ||
| real * | c1, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_add2s2 | ( | void * | a, |
| void * | b, | ||
| real * | c1, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_add2s2_many | ( | void * | x, |
| void ** | p, | ||
| void * | alpha, | ||
| int * | j, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_add3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_add4 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| void * | d, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_addcol3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_addcol3s2 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| real * | s, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_addcol4 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| void * | d, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_addsqr2s2 | ( | void * | a, |
| void * | b, | ||
| real * | c1, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_cadd2 | ( | void * | a, |
| void * | b, | ||
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_cdiv | ( | void * | a, |
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_cdiv2 | ( | void * | a, |
| void * | b, | ||
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_cfill | ( | void * | a, |
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_cfill_mask | ( | void * | a, |
| real * | c, | ||
| int * | size, | ||
| int * | mask, | ||
| int * | mask_size, | ||
| cudaStream_t | strm ) |
| void cuda_cmult | ( | void * | a, |
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_cmult2 | ( | void * | a, |
| void * | b, | ||
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_col2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_col3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_copy | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_face_masked_gather_copy | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| void * | facet, | ||
| int * | n1, | ||
| int * | n2, | ||
| int * | lx, | ||
| int * | ly, | ||
| int * | lz, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| real cuda_glamax | ( | void * | a, |
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_global_reduce_add | ( | real * | bufred, |
| void * | bufred_d, | ||
| int | n, | ||
| const cudaStream_t | stream ) |
| void cuda_global_reduce_add_xp | ( | real_xp * | bufred, |
| void * | bufred_d, | ||
| int | n, | ||
| const cudaStream_t | stream ) |
| void cuda_global_reduce_max | ( | real * | bufred, |
| void * | bufred_d, | ||
| int | n, | ||
| const cudaStream_t | stream ) |
| void cuda_global_reduce_min | ( | real * | bufred, |
| void * | bufred_d, | ||
| int | n, | ||
| const cudaStream_t | stream ) |
| real_xp cuda_glsc2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| real_xp cuda_glsc3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_glsc3_many | ( | real_xp * | h, |
| void * | w, | ||
| void * | v, | ||
| void * | mult, | ||
| int * | j, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| real_xp cuda_glsubnorm2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| real_xp cuda_glsum | ( | void * | a, |
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_iadd | ( | void * | a, |
| int * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_invcol1 | ( | void * | a, |
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_invcol2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_invcol3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_masked_atomic_reduction | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| int * | n, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| void cuda_masked_copy_0 | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| int * | n, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| void cuda_masked_copy_aligned | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| int * | n, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| void cuda_masked_gather_copy | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| int * | n, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| void cuda_masked_gather_copy_aligned | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| int * | n, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| void cuda_masked_scatter_copy | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| int * | n, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| void cuda_masked_scatter_copy_aligned | ( | void * | a, |
| void * | b, | ||
| void * | mask, | ||
| int * | n, | ||
| int * | m, | ||
| cudaStream_t | strm ) |
| void cuda_power | ( | void * | ap, |
| void * | a, | ||
| real * | p, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_pwmax_sca2 | ( | void * | a, |
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_pwmax_sca3 | ( | void * | a, |
| void * | b, | ||
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_pwmax_vec2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_pwmax_vec3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_pwmin_sca2 | ( | void * | a, |
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_pwmin_sca3 | ( | void * | a, |
| void * | b, | ||
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_pwmin_vec2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_pwmin_vec3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| void cuda_radd | ( | void * | a, |
| real * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_redbuf_check_alloc | ( | int | nb | ) |
| void cuda_redbuf_check_alloc_xp | ( | int | nb | ) |
| void cuda_rzero | ( | void * | a, |
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_sqrt_inplace | ( | void * | a, |
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_sub2 | ( | void * | a, |
| void * | b, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_sub3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_subcol3 | ( | void * | a, |
| void * | b, | ||
| void * | c, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_vcross | ( | void * | u1, |
| void * | u2, | ||
| void * | u3, | ||
| void * | v1, | ||
| void * | v2, | ||
| void * | v3, | ||
| void * | w1, | ||
| void * | w2, | ||
| void * | w3, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| void cuda_vdot3 | ( | void * | dot, |
| void * | u1, | ||
| void * | u2, | ||
| void * | u3, | ||
| void * | v1, | ||
| void * | v2, | ||
| void * | v3, | ||
| int * | n, | ||
| cudaStream_t | strm ) |
| real cuda_vlsc3 | ( | void * | u, |
| void * | v, | ||
| void * | w, | ||
| int * | n, | ||
| cudaStream_t | stream ) |
| cuda_buffer_t redbuf = CUDA_BUFFER_INIT_SYMM |
| cuda_buffer_t redbuf_xp = CUDA_BUFFER_INIT_SYMM |