Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add brain graph generator. #50

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Add brain graph generator. #50

wants to merge 4 commits into from

Conversation

niklas-uhl
Copy link
Collaborator

No description provided.

@@ -428,6 +429,18 @@ This is mostly useful for experimental graph generators or when using KaGen to l
cmd->add_option("--cols-per-pe", config.image_mesh.cols_per_pe, "Number of columns assigned to the same PE");
cmd->add_option("--rows-per-pe", config.image_mesh.rows_per_pe, "Number of rows assigned to the same PE");
}
{ // BRAIN
auto* cmd = app.add_subcommand("brain", "R-MAT Graph");
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

R-MAT?

#include <algorithm/AlgorithmEnum.h>
#include <mpi.h>

#include "algorithm/BarnesHutInternal/BarnesHutCell.h"
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

use <> instead of "" since these are not project files

#include "sim/Simulation.h"
#include "sim/random/SubdomainFromNeuronPerRank.h"
#include "structure/Partition.h"
#include <memory>
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

\n

break;
case BrainSynapseCreationModel::BARNES_HUT_INVERTED:
algorithm = AlgorithmEnum::BarnesHutInverted;
break;
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

default unreachable?

: _sim(std::make_unique<Essentials>(), std::shared_ptr<Partition>(nullptr)),
_config(config.brain),
_rank(rank) {
MPIWrapper::init(1, nullptr);
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

does this call MPI_Init? wouldn't that crash?

the "KaGen" way would be to use Finalize() for everything that requires communication (the communicator is only passed to Finalize()), but obviously, this is stroingly biased by the communication free nature of KaGen.

Should we generate the entire graph there or keep it as it? Personally I don't have a strong opinion on whether we should stick to this model or not

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants