-
Right now, `c_interface_test` is fully compiled and linked as part of the compile workflow. Since the only purpose of this test is to confirm that `quda.h` contains only "legal `C` code", there's no p…
-
It seems the `copyExtendedColorSpinor` functions in `lib/extended_color_spinor_utilities.cu` does not recognize the extra 5th dimension for domain-wall/mobius fermions. I don't know if this is somethi…
-
Currently, the `t_boundary` member of the `GaugeField` class is serving double-duty.
* In the case of applying/removing staggered phases, it keeps track of what boundary conditions the field had _…
-
A major optimization that can be explored is to see if amortizing the gauge field loads by acting on multiple spinors simultaneously will lead a large speed up. This is much more important for the st…
-
Code to compute the staggered quark-field outer product needed for the fermion force has been added to QUDA. However, the code still requires substantial polishing. Before the next release, we need to…
-
The clover construction in lib/clover_quda.cpp does not presently support anisotropic clover construction. To do this Fmunu should be constructed with an isotropic gauge field, and the anisotropy tak…
-
Once PR #776 is in, the relevant comment is on line 47 of `include/kernels/gauge_stout.cuh`. A good way to address this might be similar to how Coulomb vs Landau gauge fixing is handled---pass in a di…
-
There is symmetry in the clover them that is not exploited that could reduce the memory footprint and reduce the memory traffic in the kernels that use the clover term.
Specifically, if we consider t…
-
This crash was produced on Frontier (HPE Cray EX supercomputer) with Clang 17.0.0 and ROCm 5.7.0. The crash occurs when compiling with -O3 -Ofast, but not with -O3 alone. I have also tested with Clang…
-
QUDA applications relies on non-blocking behavior of MPI_Test. However, current MPICH implementation of MPI_Test is blocking. When tracing I see that MPI_Test only returns when communication is comple…