ICODE-ADC/lammps
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Kokkos threaded reverse comm option

Browse Source
This commit is contained in:
Stan Moore
2017-10-03 10:14:24 -06:00
parent 529eeb6039
commit ca032f21fb
17 changed files with 748 additions and 1850 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
doc/src/package.txt
View File

@ -62,7 +62,7 @@ args = arguments specific to the style :l
{no_affinity} values = none
{kokkos} args = keyword value ...
zero or more keyword/value pairs may be appended
keywords = {neigh} or {neigh/qeq} or {newton} or {binsize} or {comm} or {comm/exchange} or {comm/forward}
keywords = {neigh} or {neigh/qeq} or {newton} or {binsize} or {comm} or {comm/exchange} or {comm/forward} or {comm/reverse}
{neigh} value = {full} or {half}
full = full neighbor list
half = half neighbor list built in thread-safe manner
@ -75,9 +75,10 @@ args = arguments specific to the style :l
{binsize} value = size
size = bin size for neighbor list construction (distance units)
{comm} value = {no} or {host} or {device}
use value for both comm/exchange and comm/forward
use value for comm/exchange and comm/forward and comm/reverse
{comm/exchange} value = {no} or {host} or {device}
{comm/forward} value = {no} or {host} or {device}
{comm/reverse} value = {no} or {host} or {device}
no = perform communication pack/unpack in non-KOKKOS mode
host = perform pack/unpack on host (e.g. with OpenMP threading)
device = perform pack/unpack on device (e.g. on GPU)
@ -429,17 +430,18 @@ Coulombic solver"_kspace_style.html because the GPU is faster at
performing pairwise interactions, then this rule of thumb may give too
large a binsize.
The {comm} and {comm/exchange} and {comm/forward} keywords determine
The {comm} and {comm/exchange} and {comm/forward} and {comm/reverse} keywords determine
whether the host or device performs the packing and unpacking of data
when communicating per-atom data between processors. "Exchange"
communication happens only on timesteps that neighbor lists are
rebuilt. The data is only for atoms that migrate to new processors.
"Forward" communication happens every timestep. The data is for atom
"Forward" communication happens every timestep. "Reverse" communication
happens every timestep if the {newton} option is on. The data is for atom
coordinates and any other atom properties that needs to be updated for
ghost atoms owned by each processor.
The {comm} keyword is simply a short-cut to set the same value
for both the {comm/exchange} and {comm/forward} keywords.
for both the {comm/exchange} and {comm/forward} and {comm/reverse} keywords.
The value options for all 3 keywords are {no} or {host} or {device}.
A value of {no} means to use the standard non-KOKKOS method of