-
See ```dslash_body()``` in code generator. Fix should be easy enough by encapsulation with ```if(tbc[dim])```.
-
Throughout QUDA we presently use the triple chevron syntax for launching kernels, e.g.
``` c++
kernel (arg);
```
However, there exists a lower-latency API call for launching kernels `cudaLaunchKerne…
-
In the tmLQCD interface we currently see that the solver for Wilson works, for Wilson twisted mass it does not converge. We assumed that all the QPhiX code had been properly tested against QDP++. On f…
-
I have now added support for Travis CI on `devel`. This is already enabled on [my fork](https://travis-ci.org/martin-ueding/qphix), so every commit I push will be automatically built and tested.
Fo…
-
QDP++ is only supposed to be needed to build the unit test codes which test correctness. I need to clean out the build system so code and the timers build without QDP++. Need to make sure all the COMM…
-
QPhiX and also QDP++ use a lot of `#warning` directives to signal which compile time branches were taken. This is handy for debugging compile flags, but it makes working with the actual code harder. T…
-
I just tried to merge the `etmc/master` into `plabus/qphix_devel` since they have diverged quite far already. There are a lot of merge conflicts in `config.h.in` which should not be versioned anyway. …
-
For tmLQCD we want to have twisted boundary conditions. This will be a global phase that is multiplied to the gauge field at every lattice site.
The 12-parameter gauge compression is likely to remo…
-
In some of the tests, I found double include guards. In the file `tests/testMInvCG.cc`, there is the following:
```c++
#ifndef DSLASH_M_W_H
#include "dslashm_w.h"
#endif
```
The included fil…
-
The file `blas_c.h` does not get installed with `make install`. It seems that it is not really used by any of the other files, though.
Should that file be deleted, then?