Commit Graph

266 Commits

Author SHA1 Message Date
Rafael Ravedutti
911ba63336 Adjust ISA options and improve output
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-16 18:36:47 +02:00
Rafael Ravedutti
0caeea0494 Rename cuda.c to device.c
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-12 18:17:07 +02:00
Rafael Ravedutti
90609a2b5f Adjust file structure for CUDA
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-12 18:12:29 +02:00
Rafael Ravedutti
939197a785 Create separate structs DeviceAtom and DeviceNeighbor with device pointers
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-12 17:28:06 +02:00
Rafael Ravedutti
065b596074 Initial refactoring of CUDA code
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-12 04:19:38 +02:00
Rafael Ravedutti
959ff65126 Fix macro condition
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-12 01:29:40 +02:00
Rafael Ravedutti
87d006d418 Fix GPU version
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-11 16:42:41 +02:00
Rafael Ravedutti
3d95ec4b0a Small fixes
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-09 19:19:48 +02:00
Rafael Ravedutti
c18124b066 Integrate LAMMPS CUDA versions into master branch
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-08-09 18:53:53 +02:00
Rafael Ravedutti
eb77e1a3bd Fix DEM setup
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-19 04:13:06 +02:00
Rafael Ravedutti
2e77f6207b Avoid errors when compiling for AVX2 due to SIMD LJ implementation
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-19 02:30:26 +02:00
Rafael Ravedutti
577955dfb7 Apply first changes to DEM kernel
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-13 02:34:33 +02:00
Rafael Ravedutti
99237241fb Include domain box on DEM input file
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-08 23:15:30 +02:00
Rafael Ravedutti
3b85da83a7 Update timestep size for dem
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-08 02:56:56 +02:00
Rafael Ravedutti
814f561993 Allow PBC in just some directions
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-08 02:30:03 +02:00
Rafael Ravedutti
32836eebcb Setup first DEM example with input file from lecture
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-07 02:11:50 +02:00
Rafael Ravedutti
9ffc09f497 Add DEM kernel to parameter options
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-07 00:47:38 +02:00
Rafael Ravedutti
79483a446e Adjust code with DEM to be compilable
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-06 01:07:39 +02:00
Rafael Ravedutti
bb599c9ea8 Add first version of DEM kernel
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-07-05 15:33:31 +02:00
Rafael Ravedutti
e4d7faf91b Adjust cutforce and atom positions in stubbed version
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-05-14 01:02:08 +02:00
Rafael Ravedutti
bbdcaf2983 New stubbed version
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-05-14 00:55:33 +02:00
Rafael Ravedutti
14838389ff Fix stubbed variant for LAMMPS algorithm
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-04-30 04:08:18 +02:00
Rafael Ravedutti
ab2eb1ff50 Write LAMMPS kernel with SIMD intrinsics and implement AVX512 with double-precision functions
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-04-05 02:57:23 +02:00
Rafael Ravedutti
af1756bfe4 Fix skin for Argon simulation
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-04-04 22:22:35 +02:00
Rafael Ravedutti
4d11c5a3c2 Merge branch 'master' of github.com:RRZE-HPC/MD-Bench 2022-04-04 21:52:47 +02:00
Rafael Ravedutti
e48b3fb653 Add option to check if cj is local before applying reaction force
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-04-04 21:52:40 +02:00
Jan Eitzinger
7a0d6479a1 Merge branch 'master' of https://github.com/RRZE-HPC/MD-Bench 2022-04-01 15:58:05 +02:00
Jan Eitzinger
5585ebcf42 Add ONEAPI config. Remove omp simd for full neigh. 2022-04-01 15:57:54 +02:00
Rafael Ravedutti
fdbeed4368 Fix AVX2 versions with half neighbor lists
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-27 16:39:39 +02:00
Rafael Ravedutti
0e742766b7 Add working version of Simd4xn kernel with half neighbor lists
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-23 15:54:18 +01:00
Rafael Ravedutti
e72323ab6a Fix Simd2xnn Kernel with half neighbor lists and add AVX512 intrinsics with double
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-23 15:21:07 +01:00
Rafael Ravedutti
94521f03b3 Fix reference version with half neighbor lists
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-23 14:31:47 +01:00
Rafael Ravedutti
8709bc2a06 Add first version for half neighbor lists in GROMACS variant
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-22 23:47:05 +01:00
Rafael Ravedutti
2a555a7deb Add simd reduction pragma to vectorize innermost loop on half-neighbor variant
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-21 17:02:09 +01:00
Rafael Ravedutti
719330807b Change data layout for force arrays according to position
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-18 01:40:51 +01:00
Rafael Ravedutti
e7737e9151 Refactor half neighbor lists code
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-18 01:28:11 +01:00
Rafael Ravedutti
5df544637f Fix force calculation time in LAMMPS variant
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-17 02:53:58 +01:00
Rafael Ravedutti
887f41871c Add parameter reading for LAMMPS variant
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-17 02:44:34 +01:00
Rafael Ravedutti
d4b34e1fa4 Fix intrinsics for AVX2
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-17 00:35:21 +01:00
Rafael Ravedutti
4090f43095 Optimize partial forces reduction for compute_4xn kernel
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-16 17:54:52 +01:00
Rafael Ravedutti
f3263a2d48 Separate simd file into multiple files
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-16 14:52:55 +01:00
rafaelravedutti
459853dc25 Merge pull request #4 from RRZE-HPC/gromacs_sp
Gromacs sp
2022-03-15 20:31:42 +01:00
Rafael Ravedutti
d47173d7a2 Fix Simd2xNN kernel
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-15 19:59:10 +01:00
Rafael Ravedutti
d61576699d Add first compilable version of Gromacs with SP
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-15 02:40:56 +01:00
Rafael Ravedutti
8669f2f6d7 Fix LJ Simd4xN kernel
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-11 01:12:59 +01:00
Rafael Ravedutti
d79c3c2a1d Add first working version with 4x8 config (ref kernel)
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-10 22:33:41 +01:00
Jan Eitzinger
c2fcd50773 Initial version of lammps halfneighbor list 2022-03-10 17:06:45 +01:00
Jan Eitzinger
ba3a0524f6 Merge branch 'master' of github.com:RRZE-HPC/MD-Bench 2022-03-10 16:30:40 +01:00
Jan Eitzinger
6203cb12b6 Start to introduce halfneigh version 2022-03-10 16:30:37 +01:00
Rafael Ravedutti
22d0f0b958 Commit version that works for M=N
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2022-03-10 01:31:50 +01:00