Skip to content
GitLab
Projects
Groups
Snippets
/
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
SWIFT
SWIFTsim
Commits
6a4da17a
Commit
6a4da17a
authored
Aug 30, 2018
by
Matthieu Schaller
Browse files
Added comments to highlight a possible superior strategy to the mesh assignment.
parent
dc602245
Changes
1
Hide whitespace changes
Inline
Side-by-side
src/mesh_gravity.c
View file @
6a4da17a
...
...
@@ -224,6 +224,11 @@ void cell_gpart_to_mesh_CIC_mapper(void *map_data, int num, void* extra) {
/* Pointer to the chunk to be processed */
int
*
local_cells
=
(
int
*
)
map_data
;
//MATTHIEU: This could in principle be improved by creating a local mesh
// with just the extent required for the cell. Assignment can
// then be done without atomics. That local mesh is then added
// atomically to the global one.
/* Loop over the elements assigned to this thread */
for
(
int
i
=
0
;
i
<
num
;
++
i
)
{
...
...
@@ -349,6 +354,7 @@ void mesh_to_gparts_CIC(struct gpart* gp, const double* pot, int N, double fac,
*
* @param mesh The #pm_mesh used to store the potential.
* @param s The #space containing the particles.
* @param tp The #threadpool object used for parallelisation.
* @param verbose Are we talkative?
*/
void
pm_mesh_compute_potential
(
struct
pm_mesh
*
mesh
,
const
struct
space
*
s
,
...
...
Write
Preview
Supports
Markdown
0%
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment