Luca Bertagna

Handling of real kind in chunk_cache routines in pio_nf.F90

6

There are several instances in the Scorpio Fortran interface source code where Fortran types without kind specifications are passed directly to the C interface functions. The types of the arguments...

Add interfaces accepting scorpio data structures rather than a list of builtin types

5

I was wondering if there is a plan to add a set of interfaces accepting scorpio data structures instead of a bunch of raw types (int, double, pointers,...). For instance,...

Do not make EKAT enable FPEs during initialize_ekat_session

4

I marked it as a bug, but it's more like a conceptual change. EKAT should not take care of enabling any FPEs when the ekat session is started. There are...

Now that HIP support has been added (#225), and SYCL is going in soon (#230), we should probably start testing them as part of our PR testing. The problem is...

PR #218 added the ability to dispatch a kernel on host when CudaUVM is used, by creating a team policy on host. However, CudaUVM is still a device memory space,...

It is possible that the user tries to stress test some functionalities for very large arrays. In this case, we _might_ need 64 bits for their size. Note: I don't...

Allow user to specify a PATH for finding MPI

3

Currently, EKAT calls `find_package(MPI REQUIRED)`, without allowing the user to specify a suggestion for a path where to look for mpi. Ideally, the user should be able to specify a...

It would be nice to allow users to provide YAML files that can directly be parsed into some structs. E.g., it would be nice to parse ``` My Complex: 1.0...

Having different storage for values and sequences when it comes to bool is annoying, also from the code complexity point of view. As of today, our YAML parser stores arrays...

This is related to #151 : when calling `EkatCreateUnitTest(foo ...)`, the names of the tests are of the form `foo_ut_npX_ompY`, with X and Y being the number of MPI ranks...