- 21 Nov, 2018 1 commit
-
-
Peter W. Draper authored
Switch to only using ticks for repartition weights, avoid the problem of early repartitioning by not doing that, the memory balance initial partition is good enough to start with
-
- 19 Nov, 2018 1 commit
-
-
Matthieu Schaller authored
-
- 18 Nov, 2018 1 commit
-
-
Matthieu Schaller authored
When repartitioning, no need to verify that the multipoles were drifted. We are going to free them anyway.
-
- 17 Nov, 2018 3 commits
-
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
- 16 Nov, 2018 1 commit
-
-
Loic Hausammann authored
-
- 13 Nov, 2018 1 commit
-
-
Matthieu Schaller authored
-
- 10 Nov, 2018 6 commits
-
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
-
-
-
More uniform way of looping over pairs of top-level cells for the proxy construction, gravity pairs construction and hydro pairs construction.
-
- 09 Nov, 2018 2 commits
-
-
Peter W. Draper authored
-
Peter W. Draper authored
-
- 07 Nov, 2018 1 commit
-
-
Matthieu Schaller authored
-
- 06 Nov, 2018 2 commits
-
-
Matthieu Schaller authored
-
Loic Hausammann authored
-
- 04 Nov, 2018 3 commits
-
-
Matthieu Schaller authored
-
Matthieu Schaller authored
When resuming from a check-point file, we do not have the list of local top-level cells for the original drift all. Use all the cells instead.
-
Matthieu Schaller authored
Move the MPI type for multipole to a separate file. Create a bit-by-bit XOR reduction operation for multipoles. Utilise that reduction operation when exchanging the top-level multipoles.
-
- 02 Nov, 2018 5 commits
-
-
Matthieu Schaller authored
-
-
Pedro Gonnet authored
-
Pedro Gonnet authored
-
Pedro Gonnet authored
-
- 01 Nov, 2018 2 commits
-
-
Matthieu Schaller authored
-
Pedro Gonnet authored
-
- 31 Oct, 2018 11 commits
-
-
Loic Hausammann authored
-
Loic Hausammann authored
-
Loic Hausammann authored
-
Loic Hausammann authored
-
Loic Hausammann authored
-
-
-
-
-
-
-