Skip to content

storeChunk: Workaround for bug with parallel flushing #5510

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.

Sign up for GitHub

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

Draft
wants to merge 2 commits into
base: dev
Choose a base branch
from
Draft

storeChunk: Workaround for bug with parallel flushing #5510

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
81a41f8
Little fix for parallel flushing
franzpoeschel Jun 30, 2025
6a4f325
Workaround for https://github.com/openPMD/openPMD-api/pull/1794
franzpoeschel Oct 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions include/picongpu/plugins/openPMD/writer/ParticleAttribute.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,21 @@ namespace picongpu
if(elements == 0)
{
// accumulateWrittenBytes += 0;

# if !OPENPMDAPI_VERSION_GE(0, 17, 0)
// Workaround for this bug: https://github.com/openPMD/openPMD-api/pull/1794
// In the affected versions of the openPMD-api, Span-based storeChunk must be
// treated as an MPI-collective call.
for(uint32_t d = 0; d < components; d++)
{
::openPMD::RecordComponent recordComponent
= components > 1 ? record[name_lookup[d]] : record[::openPMD::MeshRecordComponent::SCALAR];

recordComponent.storeChunk<ComponentType>(
::openPMD::Offset{globalOffset},
::openPMD::Extent{elements});
}
# endif
return;
}

Expand Down