Roger Kowalewski
Roger Kowalewski
Unfortunately, we cannot implement the following example: ~~~cpp struct Parent { int x; }; struct Child : public Parent { int y; }; static_assert(dash::is_container_compatible_v:, "FAILS"); //The reason is... static_assert(std::is_standard_layout_v, "FAILS");...
Our `AtomicTest.cc` test suite has two confusing unit tests: - [AtomicTest.PunnedType](https://github.com/dash-project/dash/blob/development/dash/test/types/AtomicTest.cc#L139) - [AtomicTest.PunnedFetchOp](https://github.com/dash-project/dash/blob/development/dash/test/types/AtomicTest.cc#L212) The thing is that the used `elem_t` for `dash::Atomic` is a container with two value members. This...
I recently stumbled upon another test framework, called [Catch2](https://github.com/catchorg/Catch2). It looks very interesting for us and is already used in couple of big [open source projects](https://github.com/catchorg/Catch2/blob/master/docs/opensource-users.md#top). The biggest advantage is...
We need more parallelism to exploit the power of many-core nodes. The underlying algorithm itself will be rewritten to eliminate barriers. This includes the following major changes: - Algorithmic improvements:...
All DART API calls validate the unitId arguments (source and destination) to be in the range `0
The implementation of `dash::sort` now heavily relies on threading and asynchronous tasks, especially in the end while we merge all our sorted sequences. In order to test that we had...
The logging mechanism in our header library suffers from several issues: 1. Our Logging macros log always complete objects which can be both of simple datatypes and classes. Either way...
While looking at the debug output on circle ci I noticed a problem with the gnu_openmpi3 environment. HDF5 shows some errors, however, the [unit test](https://circleci.com/gh/dash-project/dash/4868) of development passes. Is it...
DART should provide operations to support both blocking and nonblocking all-to-all operations. - blocking: `MPI_Alltoall` and `MPI_Alltoallv` - nonblocking: `MPI_Ialltoall` and `MPI_Ialltoallv` Currently the only way to transpose an (N-)Array...