Loading doc/src/Section_howto.txt +1 −1 Original line number Diff line number Diff line "Previous Section"_Section_accelerate.html - "LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc - "Next Section"_Examples.html :c "Previous Section"_Speed.html - "LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc - "Next Section"_Examples.html :c :link(lws,http://lammps.sandia.gov) :link(ld,Manual.html) Loading doc/src/Speed.txt +0 −5 Original line number Diff line number Diff line Loading @@ -42,11 +42,6 @@ hardware platforms. .. toctree:: Speed_packages Speed_gpu Speed_intel Speed_kokkos Speed_omp Speed_opt Speed_compare END_RST --> Loading doc/src/Speed_intel.txt +4 −4 Original line number Diff line number Diff line Loading @@ -186,8 +186,8 @@ can start running so that the CPU pipeline is still being used efficiently. Although benefits can be seen by launching a MPI task for every hardware thread, for multinode simulations, we recommend that OpenMP threads are used for SMT instead, either with the USER-INTEL package, "USER-OMP package"_accelerate_omp.html, or "KOKKOS package"_accelerate_kokkos.html. In the example above, up USER-INTEL package, "USER-OMP package"_Speed_omp.html, or "KOKKOS package"_Speed_kokkos.html. In the example above, up to 36X speedups can be observed by using all 36 physical cores with LAMMPS. By using all 72 hardware threads, an additional 10-30% performance gain can be achieved. Loading Loading @@ -389,8 +389,8 @@ performance and/or scalability for simple 2-body potentials such as lj/cut or when using LRT mode on processors supporting AVX-512. Not all styles are supported in the USER-INTEL package. You can mix the USER-INTEL package with styles from the "OPT"_accelerate_opt.html package or the "USER-OMP package"_accelerate_omp.html. Of course, the USER-INTEL package with styles from the "OPT"_Speed_opt.html package or the "USER-OMP package"_Speed_omp.html. Of course, this requires that these packages were installed at build time. This can performed automatically by using "-sf hybrid intel opt" or "-sf hybrid intel omp" command-line options. Alternatively, the "opt" Loading doc/src/Speed_omp.txt +1 −1 Original line number Diff line number Diff line Loading @@ -99,7 +99,7 @@ task, versus running standard LAMMPS with its standard un-accelerated styles (in serial or all-MPI parallelization with 1 task/core). This is because many of the USER-OMP styles contain similar optimizations to those used in the OPT package, described in "Section 5.3.5"_accelerate_opt.html. 5.3.5"_Speed_opt.html. With multiple threads/task, the optimal choice of number of MPI tasks/node and OpenMP threads/task can vary a lot and should always be Loading doc/src/Speed_packages.txt +13 −13 Original line number Diff line number Diff line Loading @@ -23,11 +23,11 @@ pages. These are the accelerator packages currently in LAMMPS, either as standard or user packages: "GPU Package"_accelerate_gpu.html : for NVIDIA GPUs as well as OpenCL support "USER-INTEL Package"_accelerate_intel.html : for Intel CPUs and Intel Xeon Phi "KOKKOS Package"_accelerate_kokkos.html : for Nvidia GPUs, Intel Xeon Phi, and OpenMP threading "USER-OMP Package"_accelerate_omp.html : for OpenMP threading and generic CPU optimizations "OPT Package"_accelerate_opt.html : generic CPU optimizations :tb(s=:) "GPU Package"_Speed_gpu.html : for NVIDIA GPUs as well as OpenCL support "USER-INTEL Package"_Speed_intel.html : for Intel CPUs and Intel Xeon Phi "KOKKOS Package"_Speed_kokkos.html : for Nvidia GPUs, Intel Xeon Phi, and OpenMP threading "USER-OMP Package"_Speed_omp.html : for OpenMP threading and generic CPU optimizations "OPT Package"_Speed_opt.html : generic CPU optimizations :tb(s=:) <!-- RST Loading @@ -35,20 +35,20 @@ standard or user packages: :maxdepth: 1 :hidden: accelerate_gpu accelerate_intel accelerate_kokkos accelerate_omp accelerate_opt Speed_gpu Speed_intel Speed_kokkos Speed_omp Speed_opt END_RST --> Inverting this list, LAMMPS currently has acceleration support for three kinds of hardware, via the listed packages: Many-core CPUs : "USER-INTEL"_accelerate_intel.html, "KOKKOS"_accelerate_kokkos.html, "USER-OMP"_accelerate_omp.html, "OPT"_accelerate_opt.html packages NVIDIA GPUs : "GPU"_accelerate_gpu.html, "KOKKOS"_accelerate_kokkos.html packages Intel Phi : "USER-INTEL"_accelerate_intel.html, "KOKKOS"_accelerate_kokkos.html packages :tb(s=:) Many-core CPUs : "USER-INTEL"_Speed_intel.html, "KOKKOS"_Speed_kokkos.html, "USER-OMP"_Speed_omp.html, "OPT"_Speed_opt.html packages NVIDIA GPUs : "GPU"_Speed_gpu.html, "KOKKOS"_Speed_kokkos.html packages Intel Phi : "USER-INTEL"_Speed_intel.html, "KOKKOS"_Speed_kokkos.html packages :tb(s=:) Which package is fastest for your hardware may depend on the size problem you are running and what commands (accelerated and Loading Loading
doc/src/Section_howto.txt +1 −1 Original line number Diff line number Diff line "Previous Section"_Section_accelerate.html - "LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc - "Next Section"_Examples.html :c "Previous Section"_Speed.html - "LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc - "Next Section"_Examples.html :c :link(lws,http://lammps.sandia.gov) :link(ld,Manual.html) Loading
doc/src/Speed.txt +0 −5 Original line number Diff line number Diff line Loading @@ -42,11 +42,6 @@ hardware platforms. .. toctree:: Speed_packages Speed_gpu Speed_intel Speed_kokkos Speed_omp Speed_opt Speed_compare END_RST --> Loading
doc/src/Speed_intel.txt +4 −4 Original line number Diff line number Diff line Loading @@ -186,8 +186,8 @@ can start running so that the CPU pipeline is still being used efficiently. Although benefits can be seen by launching a MPI task for every hardware thread, for multinode simulations, we recommend that OpenMP threads are used for SMT instead, either with the USER-INTEL package, "USER-OMP package"_accelerate_omp.html, or "KOKKOS package"_accelerate_kokkos.html. In the example above, up USER-INTEL package, "USER-OMP package"_Speed_omp.html, or "KOKKOS package"_Speed_kokkos.html. In the example above, up to 36X speedups can be observed by using all 36 physical cores with LAMMPS. By using all 72 hardware threads, an additional 10-30% performance gain can be achieved. Loading Loading @@ -389,8 +389,8 @@ performance and/or scalability for simple 2-body potentials such as lj/cut or when using LRT mode on processors supporting AVX-512. Not all styles are supported in the USER-INTEL package. You can mix the USER-INTEL package with styles from the "OPT"_accelerate_opt.html package or the "USER-OMP package"_accelerate_omp.html. Of course, the USER-INTEL package with styles from the "OPT"_Speed_opt.html package or the "USER-OMP package"_Speed_omp.html. Of course, this requires that these packages were installed at build time. This can performed automatically by using "-sf hybrid intel opt" or "-sf hybrid intel omp" command-line options. Alternatively, the "opt" Loading
doc/src/Speed_omp.txt +1 −1 Original line number Diff line number Diff line Loading @@ -99,7 +99,7 @@ task, versus running standard LAMMPS with its standard un-accelerated styles (in serial or all-MPI parallelization with 1 task/core). This is because many of the USER-OMP styles contain similar optimizations to those used in the OPT package, described in "Section 5.3.5"_accelerate_opt.html. 5.3.5"_Speed_opt.html. With multiple threads/task, the optimal choice of number of MPI tasks/node and OpenMP threads/task can vary a lot and should always be Loading
doc/src/Speed_packages.txt +13 −13 Original line number Diff line number Diff line Loading @@ -23,11 +23,11 @@ pages. These are the accelerator packages currently in LAMMPS, either as standard or user packages: "GPU Package"_accelerate_gpu.html : for NVIDIA GPUs as well as OpenCL support "USER-INTEL Package"_accelerate_intel.html : for Intel CPUs and Intel Xeon Phi "KOKKOS Package"_accelerate_kokkos.html : for Nvidia GPUs, Intel Xeon Phi, and OpenMP threading "USER-OMP Package"_accelerate_omp.html : for OpenMP threading and generic CPU optimizations "OPT Package"_accelerate_opt.html : generic CPU optimizations :tb(s=:) "GPU Package"_Speed_gpu.html : for NVIDIA GPUs as well as OpenCL support "USER-INTEL Package"_Speed_intel.html : for Intel CPUs and Intel Xeon Phi "KOKKOS Package"_Speed_kokkos.html : for Nvidia GPUs, Intel Xeon Phi, and OpenMP threading "USER-OMP Package"_Speed_omp.html : for OpenMP threading and generic CPU optimizations "OPT Package"_Speed_opt.html : generic CPU optimizations :tb(s=:) <!-- RST Loading @@ -35,20 +35,20 @@ standard or user packages: :maxdepth: 1 :hidden: accelerate_gpu accelerate_intel accelerate_kokkos accelerate_omp accelerate_opt Speed_gpu Speed_intel Speed_kokkos Speed_omp Speed_opt END_RST --> Inverting this list, LAMMPS currently has acceleration support for three kinds of hardware, via the listed packages: Many-core CPUs : "USER-INTEL"_accelerate_intel.html, "KOKKOS"_accelerate_kokkos.html, "USER-OMP"_accelerate_omp.html, "OPT"_accelerate_opt.html packages NVIDIA GPUs : "GPU"_accelerate_gpu.html, "KOKKOS"_accelerate_kokkos.html packages Intel Phi : "USER-INTEL"_accelerate_intel.html, "KOKKOS"_accelerate_kokkos.html packages :tb(s=:) Many-core CPUs : "USER-INTEL"_Speed_intel.html, "KOKKOS"_Speed_kokkos.html, "USER-OMP"_Speed_omp.html, "OPT"_Speed_opt.html packages NVIDIA GPUs : "GPU"_Speed_gpu.html, "KOKKOS"_Speed_kokkos.html packages Intel Phi : "USER-INTEL"_Speed_intel.html, "KOKKOS"_Speed_kokkos.html packages :tb(s=:) Which package is fastest for your hardware may depend on the size problem you are running and what commands (accelerated and Loading
