HPCE/gitea-pages
0
0
Fork 0
Code Issues 3 Pull Requests 1 Actions Packages Projects Activity

ADD: build steps for cp2k
All checks were successful
Build and Deploy Documentation / build-and-deploy (push) Successful in 6s
Details

Browse Source
This commit is contained in:
germann_e
2025-11-07 16:08:52 +01:00
parent 62b25a11a5
commit 9f66244987
1 changed files with 77 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
pages/merlin7/05-Software-Support/cp2k.md
View File

@@ -28,6 +28,11 @@ module load gcc/12.3 openmpi/5.0.8-hgej cp2k/2025.2-yb6g-omp
module use unstable Spack
module load gcc/12.3 openmpi/5.0.8-5tb3-A100-gpu cp2k/2025.2-osvk-A100-gpu-omp
```
### GH nodes
```bash
module use unstable Spack
module load gcc/12.3 openmpi/5.0.8-v4cd-GH200-gpu cp2k/2025.2-vvak-GH200-gpu-omp
```
### SBATCH CPU, 4 MPI ranks, 16 OMP threads
```bash
@@ -76,3 +81,75 @@ export OMP_NUM_THREADS=$((SLURM_CPUS_PER_TASK - 1))
srun cp2k.psmp -i <CP2K_INPUT> -o <CP2K_OUTPUT>
```
### SBATCH GH, 2 GPU, 18 OMP threads, 2 MPI ranks
```bash
#!/bin/bash
#SBATCH --time=00:10:00 # maximum execution time of 10 minutes
#SBATCH --output=_scheduler-stdout.txt
#SBATCH --error=_scheduler-stderr.txt
#SBATCH --nodes=1 # number of GH200 nodes with each node having 4 CPU+GPU
#SBATCH --ntasks-per-node=2 # 2 MPI ranks per node
#SBATCH --cpus-per-task=18 # 18 OMP threads per MPI rank
#SBATCH --cluster=gmerlin7
#SBATCH --hint=nomultithread
#SBATCH --partition=gh-hourly
#SBATCH --gpus=2
unset PMODULES_ENV
module purge
module use unstable Spack
module load gcc/12.3 openmpi/5.0.8-v4cd-GH200-gpu cp2k/2025.2-vvak-GH200-gpu-omp
export FI_CXI_RX_MATCH_MODE=software
export OMP_NUM_THREADS=$((SLURM_CPUS_PER_TASK - 1))
srun cp2k.psmp -i <CP2K_INPUT> -o <CP2K_OUTPUT>
```
## Developing your own CPU code
[![Pipeline](https://gitea.psi.ch/HPCE/spack-psi/actions/workflows/cp2k_cpu_merlin7.yml/badge.svg?branch=main)](https://gitea.psi.ch/HPCE/spack-psi
```bash
module purge
module use Spack unstable
module load gcc/12.3 openmpi/5.0.8-hgej dbcsr/2.8.0-4yld-omp openblas/0.3.30-gye6-omp netlib-scalapack/2.2.2-2trj libxsmm/1.17-hwwi libxc/7.0.0-mibp libint/2.11.1-nxhl hdf5/1.14.6-tgzo fftw/3.3.10-t7bo-omp py-fypp/3.1-bteo sirius/7.8.0-uh3i-omp cmake/3.31.6-2ajs ninja/1.12.1-afxy
git clone https://github.com/cp2k/cp2k.git
cd cp2k
mkdir build && cd build
CC=mpicc CXX=mpic++ FC=mpifort cmake -GNinja -DCMAKE_CUDA_HOST_COMPILER=mpicc -DCP2K_USE_LIBXC=ON -DCP2K_USE_LIBINT2=ON -DCP2K_USE_SIRIUS=ON -DCP2K_USE_SPLA=ON -DCP2K_USE_SPGLIB=ON -DCP2K_USE_HDF5=ON -DCP2K_USE_FFTW3=ON ..
ninja -j 16
```
## Developing your own GPU code
#### A100
[![Pipeline](https://gitea.psi.ch/HPCE/spack-psi/actions/workflows/cp2k_gpu_merlin7.yml/badge.svg?branch=main)](https://gitea.psi.ch/HPCE/spack-psi
```bash
module purge
module use Spack unstable
module load gcc/12.3 openmpi/5.0.8-5tb3-A100-gpu dbcsr/2.8.0-xcn2-A100-gpu-omp fftw/3.3.10-v4mq-omp libint/2.11.1-3lxv libxc/7.0.0-u556 netlib-scalapack/2.2.2-enjp openblas/0.3.30-ynou-omp py-fypp/3.1-z25p py-numpy/2.3.2-45ay python/3.13.5-qivs cmake/3.31.6-2ajs ninja/1.12.1-afxy
git clone https://github.com/cp2k/cp2k.git
cd cp2k
mkdir build && cd build
CC=mpicc CXX=mpic++ FC=mpifort cmake -GNinja -DCMAKE_CUDA_HOST_COMPILER=mpicc -DCP2K_USE_LIBXC=ON -DCP2K_USE_LIBINT2=ON -DCP2K_USE_ACCEL=CUDA -DCMAKE_CUDA_ARCHITECTURES=80 -DCP2K_USE_FFTW3=ON ..
ninja -j 16
```
#### GH200
[![Pipeline](https://gitea.psi.ch/HPCE/spack-psi/actions/workflows/cp2k_gh_merlin7.yml/badge.svg?branch=main)](https://gitea.psi.ch/HPCE/spack-psi
```bash
module purge
module use Spack unstable
module load gcc/12.3 openmpi/5.0.8-v4cd-GH200-gpu dbcsr/2.8.0-lzj6-GH200-gpu-omp fftw/3.3.10-ajlu-omp hdf5/1.14.6-62wt libint/2.11.1-dpqq libxc/7.0.0-ojgl netlib-scalapack/2.2.2-k7uz openblas/0.3.30-rv46-omp py-fypp/3.1-j4yw py-numpy/2.3.2-yoqr python/3.13.5-xbg5 cmake/3.31.8-2jne ninja/1.13.0-xn4a
git clone https://github.com/cp2k/cp2k.git
cd cp2k
mkdir build && cd build
CC=mpicc CXX=mpic++ FC=mpifort cmake -GNinja -DCMAKE_CUDA_HOST_COMPILER=mpicc -DCP2K_USE_LIBXC=ON -DCP2K_USE_LIBINT2=ON -DCP2K_USE_ACCEL=CUDA -DCMAKE_CUDA_ARCHITECTURES=90 ..
ninja -j 16
```