fc8d9207c6
update Makefile.lammps, too.
2022-10-17 12:22:28 -04:00
a981843686
forgot updated Makefile
2022-10-17 11:51:50 -04:00
9f20347375
update PACE library for conventional build
2022-10-15 15:10:01 -04:00
c113253e2d
Merge branch 'develop' of https://github.com/lammps/lammps into kk_update_3.7
2022-10-10 13:44:02 -07:00
1fb07387b9
Merge pull request #3479 from yury-lysogorskiy/feature/pace-al
...
BUGFIX: address issue with compilation KOKKOS + pace/extrapolation
2022-10-10 14:57:13 -04:00
341bb57555
Update Install.py
2022-10-10 08:45:33 -07:00
7c9666798e
whitespace
2022-10-08 09:34:20 -04:00
7551c0a3ca
GPU Package: Documenting some additional preprocessor flags, updating oneapi Makefile.
2022-10-07 22:44:21 -07:00
5a98a38e24
GPU Package: Switching to parallel GPU initialization / JIT compilation.
2022-10-07 13:25:14 -07:00
f715f174bb
GPU Package: Print OCL platform name to screen when multiple platforms
2022-10-06 21:40:42 -07:00
a6a39d47e1
Fixing potential issues with automatic splitting of accelerators for NUMA.
2022-10-06 20:48:02 -07:00
e9f39f85d2
Fixing issue where shared main memory property only set for NVIDIA devices.
2022-10-06 20:05:33 -07:00
7157643fdd
Merge pull request #3315 from yury-lysogorskiy/feature/pace-al
...
ML_PACE with extrapolation grade / active learning
2022-10-05 20:16:13 -04:00
e51be5d6e0
Need desul library
2022-10-04 15:00:14 -06:00
f9f9e44f2d
Update Kokkos library in LAMMPS to v3.7.0
2022-10-04 14:04:40 -06:00
fb675028b9
whitespace
2022-09-29 02:42:11 -04:00
71464d8314
GPU Package: Fixing logic in OpenCL backend that could result in unnecessary device allocations.
2022-09-28 22:30:09 -07:00
6e34d21b24
GPU Package: Switching back to timer disabling with multiple MPI tasks per GPU. Logic added to prevent mem leak.
2022-09-28 21:02:16 -07:00
de28c9b19c
propagate new pace lib version tage and hash to lib/pace/Install.py
2022-09-27 15:27:43 -04:00
2e3fc4c054
Merge branch 'develop' into feature/pace-al
2022-09-25 16:01:48 -04:00
8d6629cb80
update MDI library to version 1.4.12 which plugs memory leaks on initialization
2022-09-18 11:04:57 -04:00
797a45232c
Merge branch 'fix-pair-dump-skip' into feature/pace-al
...
# Conflicts:
# src/fix_pair.cpp
2022-09-15 11:07:24 +02:00
1abfec066c
update MDI library version to 1.4.11
2022-09-12 12:30:34 -04:00
1364033055
Merge pull request #3432 from benmenadue/develop
...
Use primary context in CUDA GPU code.
2022-09-09 16:24:46 -04:00
d1fb2244e2
make downloaded version consistent
2022-09-09 15:21:42 -04:00
167abe9ce0
add preprocessor flags to select between the changed and the old code variant
2022-09-09 12:41:24 -04:00
ffb8b8ba97
Merge branch 'develop' into mdi-tweak
2022-09-09 00:03:39 -04:00
1cd47b762b
Update MDI plugin code
2022-09-09 02:28:06 +00:00
5c73befc66
upgrade to MDI 1.4.9
2022-09-07 13:57:20 -06:00
0d2db984eb
Merge branch 'develop' into benmenadue/develop
2022-09-06 19:25:21 -04:00
294a1c2168
Use primary context in CUDA GPU code.
...
Since LAMMPS uses the low-level driver API of CUDA, it needs to ensure
that it is in the correct context when invoking such functions. At the
moment it creates and switches to its own context inside `UCL_Device::set`
but then assumes that the driver is still in that context for subsequent
calls into CUDA; if another part of the program uses a different context
(such as the CUDA runtime using the "primary" context) this will cause
failures inside LAMMPS.
This patch changes the context creation to instead use the primary
context for the requested device. While it's not perfect, in that it
still doesn't ensure that it's in the correct context before making
driver API calls, it at least allows it to work with libraries that use
the runtime API.
2022-09-06 09:28:51 +10:00
51a4819bfc
Fixed an illegal preprocessor issue.
2022-09-02 11:42:30 -04:00
70ad53f125
newest version of MDI
2022-08-30 09:56:22 -06:00
4e5604daef
Merge remote-tracking branch 'official/fix-pair-dump-skip' into feature/pace-al
2022-08-30 16:07:10 +02:00
8d77c1daee
Merge remote-tracking branch 'origin/develop' into tip4p_cornercase
2022-08-25 17:58:17 +03:00
ab7ae9324f
update version of MDI library
2022-08-22 13:15:48 -06:00
baf3e614fb
Add comments for tip4p GPU kernels
2022-08-07 22:26:11 +03:00
691004509a
standarize use of static methods with MDI, also plugin args
2022-08-05 16:05:36 -06:00
ade64c586e
move to 1.4.2 version of MDI lib
2022-08-05 14:04:16 -06:00
b395d41eb6
fix index copy-n-paste error
2022-08-05 07:40:36 -04:00
fe0cbf1a68
enable to pass string constants
2022-08-05 07:22:11 -04:00
2ce33c14b7
Merge pull request #3365 from pvelesko/chip_spv
...
Add CMake and GNU make support for HIP via CHIP-SPV
2022-07-29 06:33:55 -04:00
5fee276348
add some GNU Make magic(tm) to Makefile.hip to adapt itself to OpenMPI and MPICH
2022-07-28 07:03:58 -04:00
e7ffa7fae3
Add Makefile support for CHIP-SPV
2022-07-27 08:34:35 +00:00
e973a4b31c
workaround for CHIP-SPV different textrure func
2022-07-26 16:19:11 +00:00
b2cdc40919
Enable CHIP-SPV support
2022-07-26 16:00:43 +00:00
c8cc2b1b24
update to LAPACK version 3.10.1
2022-07-21 08:41:44 -04:00
bf65b4720f
add more BLAS/LAPACK functions to support LATTE package
2022-07-21 05:20:11 -04:00
0ac8dce7b4
strip off -pendantic-errors flag when compiling with nvcc_wrapper to fix error compiling ML-PACE
2022-07-18 14:01:32 -04:00
6e34856c77
Merge branch 'develop' into feature_pace-al
2022-07-09 15:14:20 -04:00
