This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
|
acelab:lammps [2015/09/01 15:37] mcawood created |
acelab:lammps [2021/12/09 16:42] (current) |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| - | ==General Info== | + | ===General Info=== |
| - | LAMMPS (" | + | LAMMPS (" |
| - | ==Useful Links== | + | ===Useful Links=== |
| - | Developer' | + | Developer' |
| - | HPCAC Best Practices [http:// | + | HPCAC Best Practices |
| - | ==Installation Guide== | + | ===Installation Guide=== |
| Setup environment: | Setup environment: | ||
| Line 30: | Line 30: | ||
| cd tar | cd tar | ||
| - | ===Building the benchmark=== | + | ==Building the benchmark== |
| - | Download the LAMMPS source (15 May 2015) here: http:// | + | Download the LAMMPS source (15 May 2015) here: [[http:// |
| tar -xf lammps.stable.tar.gz | tar -xf lammps.stable.tar.gz | ||
| Line 38: | Line 38: | ||
| cd ../ | cd ../ | ||
| - | ====Building x86 CPU Benchmark==== | + | =Building x86 CPU Benchmark= |
| To build the Intel compiled LAMMPS binary, first edit the Makefile: | To build the Intel compiled LAMMPS binary, first edit the Makefile: | ||
| Line 59: | Line 59: | ||
| cp lmp_intel_cpu ../bench | cp lmp_intel_cpu ../bench | ||
| - | ====Building CUDA GPU Benchmark==== | + | ==Building CUDA GPU Benchmark== |
| Build this binary using the python script: | Build this binary using the python script: | ||
| Line 103: | Line 103: | ||
| cp lmp_cuda ../ | cp lmp_cuda ../ | ||
| | | ||
| - | ==Benchmark== | + | ===Benchmark=== |
| The stock "3d Lennard-Jones melt" test problem is used as a benchmark for this code. | The stock "3d Lennard-Jones melt" test problem is used as a benchmark for this code. | ||
| Line 111: | Line 111: | ||
| cd ~/ | cd ~/ | ||
| - | ====x86 CPU Benchmark==== | + | A pre-configured input script is available here {{http:// |
| - | A pre-configured input script is available here [[File: | + | ==x86 CPU Benchmark== |
| - | For x86 CPU benchmarks, this is ''' | + | For x86 CPU benchmarks, this is **500K particles per core.** |
| Therefore, if you with to run the benchmark on 24 x86 cores, a total of 12,000K (500x24) particles is required. | Therefore, if you with to run the benchmark on 24 x86 cores, a total of 12,000K (500x24) particles is required. | ||
| Line 130: | Line 130: | ||
| Giving a total particle count of 500K * (6*4*4) = 48x10^6. | Giving a total particle count of 500K * (6*4*4) = 48x10^6. | ||
| - | ====CUDA GPU Benchmark==== | + | ==CUDA GPU Benchmark== |
| For the GPU benchmark, the same process is used as above, however with a larger number of particles per GPU. | For the GPU benchmark, the same process is used as above, however with a larger number of particles per GPU. | ||
| - | For GPU benchmarks, the particles per GPU are set as ''' | + | For GPU benchmarks, the particles per GPU are set as **8M particles per GPU.** |
| Download the pre-configured input file here | Download the pre-configured input file here | ||