- 21 Jun, 2016 1 commit
-
-
Pedro Gonnet authored
Conflicts: src/engine.c src/scheduler.c src/space.c src/task.c
-
- 17 Jun, 2016 4 commits
-
-
Pedro Gonnet authored
-
Pedro Gonnet authored
-
Peter W. Draper authored
Remove the part<->gpart link checks. These can be un-commented back in when debugging. As discussed during the meeting, here are some tests that are non-necessary in serious runs. See merge request !185
-
Matthieu Schaller authored
-
- 16 Jun, 2016 4 commits
-
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Peter W. Draper authored
Coding style Sorry Peter here is another big annoying one. - Improved the code quality in `runner_doiact.h` to match the coding standard used elsewhere: declare variable only where they are needed and use constants where possible. - Modified many headers to avoid long unnecessary inclusion lists. Should speed up compilation. Thanks ! See merge request !182
-
Peter W. Draper authored
Moved some more hydro parameters as optional Some more parameters flagged as optional. See merge request !184
-
- 15 Jun, 2016 5 commits
-
-
Peter W. Draper authored
Typo in sub_subset that leads to a crash in the isothermal sphere case. This bug has been there forever. @jregan uncovered it today by running the isothermal sphere case which has a rather deep tree. Re-assign to me if happy. See merge request !183
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
- 14 Jun, 2016 17 commits
-
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Peter W. Draper authored
Task sub split This implements #175 While at it I also removed some dead code (including #174) and cleaned up the linking of libraries in the Makefile. For some reasons we had still blas in lapack in there. Finally I have also removed some commented-out old gravity stuff. That should make the diff for the gravity branch much easier to read when it becomes time to merge that in. See merge request !180
-
Peter W. Draper authored
-
Peter W. Draper authored
-
Peter W. Draper authored
Unified the atomic calls everywhere using the defined macros Some more code clean-up. I have modified all the calls to __sync_* to use the defined atomic macros. Makes the code easier to read. Note that in the case of the timer function, moving to the defined macros changed the return value (++i instead of i++). But we don't use the return value anyway. Re-assign to me if you are happy to have this merged in. See merge request !181
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
Matthieu Schaller authored
-
- 13 Jun, 2016 3 commits
-
-
Pedro Gonnet authored
-
Pedro Gonnet authored
-
Pedro Gonnet authored
make engine_make_extra_hydroloop_tasks and engine_count_and_link_tasks serial again, keeping the mapper versions in for now, still need to check if this was the source of the negative waits.
-
- 12 Jun, 2016 1 commit
-
-
Matthieu Schaller authored
-
- 11 Jun, 2016 1 commit
-
-
Matthieu Schaller authored
-
- 10 Jun, 2016 3 commits
-
-
Peter W. Draper authored
-
Matthieu Schaller authored
-
Peter W. Draper authored
Queue fix Separate adding and getting a task. Uses a double-ended queue to buffer incoming tasks. The buffer is then added to the actual queue whenever queue_gettask is called. Peter, can you check if this doesn't break anything? Thanks! See merge request !178
-
- 09 Jun, 2016 1 commit
-
-
Pedro Gonnet authored
use chunked mappers in the threadpool, make sure that the map function actually waits for all the threads to have started.
-