lijiext
/
lammps
mirror of https://github.com/lammps/lammps.git
1
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@8722 f3b2605a-c512-4ea7-a41b-209d697bcdaa

This commit is contained in:
sjplimp 2012-08-27 21:24:47 +00:00
parent a64ffc0be3
commit 8972165b3a
1 changed files with 3 additions and 3 deletions
bench/GPU
README

6
bench/GPU/README
View File

@ -50,11 +50,11 @@ the USER-CUDA package. For example:
mpirun -np 1 ../lmp_linux_single -sf cuda -v g 1 -v x 16 -v y 16 -v z 16 -v t 100 < in.lj.cuda mpirun -np 1 ../lmp_linux_single -sf cuda -v g 1 -v x 16 -v y 16 -v z 16 -v t 100 < in.lj.cuda
mpirun -np 1 ../lmp_linux_double -sf cuda -v g 1 -v x 32 -v y 64 -v z 64 -v t 100 < in.eam.cuda mpirun -np 2 ../lmp_linux_double -sf cuda -v g 2 -v x 32 -v y 64 -v z 64 -v t 100 < in.eam.cuda
The "xyz" settings determine the problem size. The "t" setting The "xyz" settings determine the problem size. The "t" setting
determines the number of timesteps. The "np" setting determines how determines the number of timesteps. The "np" setting determines how
many CPUs the problem will be run on, and the "g" setting determines many CPUs the problem will be run on, and the "g" setting determines
how many GPUs the problem will run on, i.e. 1 or 2 in this case. You how many GPUs the problem will run on, i.e. 1 or 2 in this case. You
can use more CPUs than GPUs with the GPU package. You should make the should make the number of CPUs and number of GPUs equal for the
number of CPUs and number of GPUs equal for the USER-CUDA package. USER-CUDA package.