-
Alex and Victoria have shown that there are performance benefits to be had by using asynchronous kernel launches, even if the kernels themselves have to be run in order. This is also bourne out by thi…
-
Andy and I have discussed ways in which we might migrate from existing NEMO code to something that is (arguably) more maintainable and supports OpenMP and OpenACC in a way that does not disturb the co…
-
I have 2 question :
1.`make install`
Makefile:133: recipe for target 'xmpf_coarray_wrap.o' failed
make[1]: *** [xmpf_coarray_wrap.o] Error 1
Makefile:23: recipe for target 'all' failed
make: …
-
As pointed out in kokkos/kokkos#5482, our minimum requirements are not properly documented https://kokkos.github.io/kokkos-core-wiki/requirements.html
OpenMP -> 3.X?
CUDA -> libraries 11.x?, comp…
-
Hi,
I downloaded DawnCC benchmarks zip file and compiled `auto_acc` directory files with PGI compiler (release 16.10-0) on Ubuntu 14.04.
This is the pgcc output during the compilation of `2DCon…
-
The current implementation of RESP charge fitting is slow. Although RESP charge fitting is intended to use for postprocessing and only for single configuration, I am interested in developing cuda/open…
-
Pragma should be allowed in top level
```fortran
module mod1
contains
function fct1(arg1)
integer, intent(in) :: arg1
integer :: fct1
end function fct1
!$acc routine (fc…
-
#76 is adding OpenACC versions of the tracer-advection benchmark. Currently these all use managed memory but psyclone/#310 is adding support for explicit control of data movement.
-
see #70
-
it should include:
- how to get things working on Tetralith (directories, modules, cloning repo, ...)
- how to use google colab