Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
O
openfpm_pdata
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
argupta
openfpm_pdata
Commits
369e7277
Commit
369e7277
authored
9 years ago
by
Pietro Incardona
Browse files
Options
Downloads
Patches
Plain Diff
Fixing comment in dec optimizer
parent
76417828
No related branches found
Branches containing commit
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
src/Decomposition/CartDecomposition.hpp
+1
-1
1 addition, 1 deletion
src/Decomposition/CartDecomposition.hpp
src/dec_optimizer.hpp
+10
-15
10 additions, 15 deletions
src/dec_optimizer.hpp
with
11 additions
and
16 deletions
src/Decomposition/CartDecomposition.hpp
+
1
−
1
View file @
369e7277
...
...
@@ -156,7 +156,7 @@ private:
// Create a cartesian grid graph
CartesianGraphFactory
<
dim
,
Graph_CSR
<
nm_part_v
,
nm_part_e
>>
g_factory_part
;
//
Processor
graph
//
sub-sub-domain
graph
Graph_CSR
<
nm_part_v
,
nm_part_e
>
gp
=
g_factory_part
.
template
construct
<
NO_EDGE
,
T
,
dim
-
1
>(
gr
.
getSize
(),
domain
);
// Get the number of processing units
...
...
This diff is collapsed.
Click to expand it.
src/dec_optimizer.hpp
+
10
−
15
View file @
369e7277
...
...
@@ -550,19 +550,17 @@ public:
/*! \brief optimize the graph
*
* Starting from a domain (hyper-cubic), it create wavefront at the boundary and expand
* the boundary until the wavefronts cannot expand any more.
* To the domains inside the hyper-cube one sub-id is assigned. This procedure continue until
* all the domain of one p_id has a sub-id
* Starting from a sub-sub-domain, it create wavefronts at the boundary and expand
* the boundary until the wavefronts cannot expand any more, creating a sub-domain covering more sub-sub-domain.
* This procedure continue until all the domain is covered by a sub-domains
*
* \tparam j property containing the decomposition
* \tparam i property to fill with the sub-decomposition
* \tparam j property containing the
processor
decomposition
* \tparam i property to fill with the sub-
domain-
decomposition
id
*
* \param start_p seed point
* \param graph we are processing
*
*/
template
<
unsigned
int
p_sub
,
unsigned
int
p_id
>
void
optimize
(
grid_key_dx
<
dim
>
&
start_p
,
Graph
&
graph
)
{
// temporal vector
...
...
@@ -577,20 +575,18 @@ public:
/*! \brief optimize the graph
*
* Starting from a domain (hyper-cubic), it create wavefront at the boundary and expand
* the boundary until the wavefronts cannot expand any more.
* To the domains inside the hyper-cube one sub-id is assigned. This procedure continue until
* all the domain of one p_id has a sub-id
* Starting from a sub-sub-domain, it create wavefronts at the boundary and expand
* the boundary until the wavefronts cannot expand any more, creating a sub-domain covering more sub-sub-domain.
* This procedure continue until all the sub-domain of the processor p_id are covered by a sub-domains
*
* \tparam j property containing the decomposition
* \tparam i property to fill with the sub-decomposition
* \tparam i property to fill with the sub-
domain-
decomposition
id
*
* \param graph we are processing
* \param p_id Processor id (if p_id == -1 the optimization is done for all the processors)
* \param list of sub-domain boxes
*
*/
template
<
unsigned
int
p_sub
,
unsigned
int
p_id
>
void
optimize
(
Graph
&
graph
,
long
int
pr_id
,
openfpm
::
vector
<
Box
<
dim
,
size_t
>>
&
lb
,
openfpm
::
vector
<
openfpm
::
vector
<
size_t
>
>
&
box_nn_processor
)
{
// search for the first seed
...
...
@@ -613,11 +609,10 @@ public:
* \param start_p seed point
* \param graph we are processing
* \param p_id Processor id (if p_id == -1 the optimization is done for all the processors)
* \param list of sub-domain boxes
* \param list of sub-domain boxes
produced by the algorithm
* \param box_nn_processor for each box it list all the neighborhood processor
*
*/
template
<
unsigned
int
p_sub
,
unsigned
int
p_id
>
void
optimize
(
grid_key_dx
<
dim
>
&
start_p
,
Graph
&
graph
,
long
int
pr_id
,
openfpm
::
vector
<
Box
<
dim
,
size_t
>>
&
lb
,
openfpm
::
vector
<
openfpm
::
vector
<
size_t
>
>
&
box_nn_processor
)
{
// sub-domain id
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
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!
Save comment
Cancel
Please
register
or
sign in
to comment