The CSV input data set can be obtained from: https://www.kaggle.com/datasets/rodolfofigueroa/spotify-12m-songs
Note: ./configure
only needs to be ran once.
The output will be placed in output/output.csv file.
./configure
make serial
./output/serial
./configure
make shared_cpu
./output/shared_cpu
For CHPC:
- module load cuda/12.1
Dependencies:
- cuda
./configure
make shared_gpu
./output/shared_gpu
On CHPC:
- module load intel-mpi
Dependencies:
- mpi
./configure
make distributed_cpu
mpiexec -n 2 ./output/distributed_cpu
On CHPC:
- module load cuda/12.1
- module load gcc/8.5
- module load intel-mpi
This requires having enough GPUs allocated.
./configure
make distributed_gpu
mpiexec -n 2 ./output/distributed_gpu
Dependencies:
- matplotlib
- pandas
- python
python main.py