Stan Moore
067119f6c6
Adding missing friend statement to pair_lj_class2_coul_cut_kokkos
2017-02-02 15:21:30 -07:00
Stan Moore
1834a5e46c
Fixing more Kokkos per-atom and fdotr issues
2017-02-02 15:21:21 -07:00
Stan Moore
6a4918b39a
Fixing typo in pair_buck_coul_cut_kokkos
2017-02-02 15:21:05 -07:00
Stan Moore
5da0d39392
Fixing fdotr in pair_buck_coul_cut_kokkos
2017-02-02 13:35:51 -07:00
Stan Moore
6f92429602
Fixing per-atom ev issue
2017-02-02 13:34:27 -07:00
Stan Moore
38e0e4bb69
Add missing typedef in Kokkos pair styles
2017-02-02 13:24:05 -07:00
Stan Moore
daf9f95381
Fixing Kokkos per-atom e/v issue
2017-02-02 13:09:52 -07:00
sjplimp
997142a4c1
Merge pull request #364 from stanmoore1/kk_triclinic_neighlist
...
Add triclinic neighbor list support to Kokkos
2017-01-30 07:27:02 -07:00
sjplimp
033b07fdb7
Merge pull request #363 from ibaned/obey-datamask
...
Fix GPU sync bugs
2017-01-30 07:26:49 -07:00
Stan Moore
59f4a77dd5
Whitespace change to npair_kokkos
2017-01-27 15:17:39 -07:00
Stan Moore
579cc6d7aa
More tweaks to npair_kokkos for triclinic
2017-01-27 15:13:37 -07:00
Stan Moore
5afd3e995b
Adding support to npair_kokkos for triclinic-newton-on neighborlists
2017-01-27 14:18:01 -07:00
Dan Ibanez
2a6f5e651c
more preference of datamask over custom sync
...
see commit 09fc8b0
for details on why
2017-01-27 09:35:55 -07:00
Dan Ibanez
09fc8b0bd7
kspace & dihedral can't do their own sync/modify
...
because the verlet_kokkos system has
a "clever" optimization which will
alter the datamasks before calling sync/modify,
so the datamask framework must be
strictly obeyed for GPU correctness.
(the optimization is to concurrently
compute forces on the host and GPU,
and add them up at the end of an iteration.
calling your own sync will overwrite
the partial GPU forces with the
partial host forces).
2017-01-27 08:39:55 -07:00
Steve Plimpton
f8506fee23
sync GHub with SVN
2017-01-26 14:06:43 -07:00
sjplimp
18e5584311
Merge pull request #354 from stanmoore1/kokkos_bugfixes
...
Kokkos bugfixes
2017-01-26 13:51:47 -07:00
sjplimp
851f80464f
Merge pull request #361 from akohlmey/user-omp-fix-per-atom-data
...
fix USER-OMP bug on per-atom data with hybrid styles
2017-01-26 13:50:13 -07:00
sjplimp
5971d4c994
Merge pull request #358 from ibaned/warnings
...
warning fixes (Kokkos+CUDA)
2017-01-26 13:49:56 -07:00
sjplimp
868d95f0a5
Merge pull request #352 from akohlmey/fix-skip-with-ghost-issue
...
Fix skip with ghost issue
2017-01-26 13:47:12 -07:00
sjplimp
a5ff35435a
Merge pull request #351 from timattox/USER-DPD_pair_exp6_bugfix
...
USER-DPD: Possible uninitialized variable in pair_exp6_rx.cpp bugfix.
2017-01-26 13:45:45 -07:00
Axel Kohlmeyer
8b7bd9d88e
fix bug where per atom data for USER-OMP was reducing the wrong arrays with hybrid styles
2017-01-26 14:59:10 -05:00
Dan Ibanez
672bbbe494
add more missing KOKKOS_INLINE_FUNCTION attributes
2017-01-25 16:03:11 -07:00
Dan Ibanez
03c9c46533
add missing KOKKOS_INLINE_FUNCTION attributes
2017-01-25 15:49:05 -07:00
Dan Ibanez
e992bfe510
remove unused variable
2017-01-25 15:40:52 -07:00
Dan Ibanez
053ee54a27
remove unused variable
2017-01-25 15:38:41 -07:00
Dan Ibanez
1074c6734b
add missing return keywords
2017-01-25 15:37:27 -07:00
Dan Ibanez
60b48c9d66
add missing KOKKOS_INLINE_FUNCTION attributes
...
this structure gets put inside a DualView,
so these members need to be able to execute
on the GPU
2017-01-25 15:36:24 -07:00
Dan Ibanez
3d40b51708
remove unused variable
2017-01-25 15:24:52 -07:00
Dan Ibanez
effbe18c46
fix domain boundary indexing
...
the compiler pointed out that
boundary[2][2] doesn't exist.
If I understand this correctly,
those checks should be against
boundary[*][0].
2017-01-25 15:24:01 -07:00
Dan Ibanez
6328beb7d7
fix double-return warning
...
this #ifdef adds a return statement
for little endian machines, but leaves
the old one, which the compiler comlains
is unreachable. this commit combines
the conditionals so we can use #else
2017-01-25 15:22:42 -07:00
Stan Moore
26c8d3d98f
Fixing GPU memory issue in fix_langevin_kokkos
2017-01-25 12:53:55 -07:00
Stan Moore
73177d650d
Fixing GPU memory issue in domain_kokkos
2017-01-25 11:18:03 -07:00
Axel Kohlmeyer
b5cb74bd33
skip list build is compatible with NP_GHOST
2017-01-23 19:21:48 -05:00
Axel Kohlmeyer
31976d1dee
skip list definition was missing NP_HALFFULL flag
2017-01-23 19:20:05 -05:00
Christopher Stone
c8260af37c
Possible uninitialized variable in USER-DPD/pair_exp6_rx.cpp bugfix.
...
Added explicit initialization (to zero) for several variables inside the
inner j-loop to avoid using them uninitialized or from prior iterations
within rmOldij_12 == 0.
2017-01-23 13:34:51 -05:00
Steve Plimpton
caea8973a3
add neighbor list kind output to screen
2017-01-20 13:24:09 -07:00
sjplimp
aa0ad9b483
Merge pull request #349 from akohlmey/collected-small-fixes
...
collected fixes and improvements
2017-01-20 13:19:43 -07:00
sjplimp
5d0e4e1ba9
Merge pull request #346 from stanmoore1/kokkos_fixes
...
Kokkos fixes
2017-01-20 13:15:16 -07:00
sjplimp
f8d3c4c740
Merge pull request #345 from timattox/USER-DPD_another_zero_compute
...
USER-DPD another zero compute optimization
2017-01-20 13:14:59 -07:00
Axel Kohlmeyer
e6996121d1
remove dead code
2017-01-20 14:30:46 -05:00
Axel Kohlmeyer
fbfb1df5eb
fix typo causing wrong neighbor list copy selections
2017-01-19 20:47:10 -05:00
Steve Plimpton
9a299875da
simplified neighbor list copying to avoid possible same-timestep re-build issues
2017-01-19 17:01:15 -07:00
Stan Moore
fc94f1bd18
Fixing GPU memory issues in Kokkos
2017-01-19 12:14:25 -07:00
Stan Moore
5ce8e2fbae
Fixing GPU memory issue in modify_kokkos, need to cherry pick back to Master
2017-01-19 12:13:48 -07:00
Tim Mattox
f6cd98636b
USER-DPD: Also apply "check if a0 is zero" optimization to pair_dpd_fdt
...
This relates to commit 4eb08a5822
that was applied to pair_dpd_fdt_energy
2017-01-18 16:17:11 -05:00
Tim Mattox
05cafb716f
USER-DPD: cleanup initialization of splitFDT_flag in pair_dpd_fdt.cpp
2017-01-18 15:51:50 -05:00
sjplimp
3af4b3c28c
Merge pull request #337 from ohenrich/user-cgdna
...
Added source code and documentation for USER-CGDNA
2017-01-18 11:31:35 -07:00
sjplimp
7fc0970587
Merge pull request #344 from timattox/USER-DPD_zero_compute
...
USER-DPD: Skip a0*stuff computations, if a0 was set to zero in pair_coeff
2017-01-18 11:31:14 -07:00
sjplimp
93262b52b4
Merge pull request #343 from timattox/USER-DPD_bugfix_molecule
...
USER-DPD: bugfix for a segfault when using MOLECULE and DPD together.
2017-01-18 11:30:58 -07:00
Tim Mattox
4eb08a5822
USER-DPD: Skip a0*stuff computations, if a0 was set to zero in pair_coeff.
...
This saves around 10% of the runtime for many of our tests using SSA.
2017-01-17 15:55:39 -05:00