Commit 9a8c0928 authored by Axel Kohlmeyer's avatar Axel Kohlmeyer
Browse files

use Hyper-Threading consistently

parent eca0487d
...@@ -93,12 +93,12 @@ The "t Nt" option specifies how many OpenMP threads per MPI task to ...@@ -93,12 +93,12 @@ The "t Nt" option specifies how many OpenMP threads per MPI task to
use with a node. The default is Nt = 1, which is MPI-only mode. Note use with a node. The default is Nt = 1, which is MPI-only mode. Note
that the product of MPI tasks * OpenMP threads/task should not exceed that the product of MPI tasks * OpenMP threads/task should not exceed
the physical number of cores (on a node), otherwise performance will the physical number of cores (on a node), otherwise performance will
suffer. If hyperthreading is enabled, then the product of MPI tasks * suffer. If Hyper-Threading (HT) is enabled, then the product of MPI
OpenMP threads/task should not exceed the physical number of cores * tasks * OpenMP threads/task should not exceed the physical number of
hardware threads. The "-k on" switch also issues a "package kokkos" cores * hardware threads. The "-k on" switch also issues a
command (with no additional arguments) which sets various KOKKOS "package kokkos" command (with no additional arguments) which sets
options to default values, as discussed on the "package"_package.html various KOKKOS options to default values, as discussed on the
command doc page. "package"_package.html command doc page.
The "-sf kk" "command-line switch"_Run_options.html will automatically The "-sf kk" "command-line switch"_Run_options.html will automatically
append the "/kk" suffix to styles that support it. In this manner no append the "/kk" suffix to styles that support it. In this manner no
...@@ -149,7 +149,7 @@ Intel Knight's Landing (KNL) Xeon Phi: ...@@ -149,7 +149,7 @@ Intel Knight's Landing (KNL) Xeon Phi:
KNL Intel Phi chips have 68 physical cores. Typically 1 to 4 cores are KNL Intel Phi chips have 68 physical cores. Typically 1 to 4 cores are
reserved for the OS, and only 64 or 66 cores are used. Each core has 4 reserved for the OS, and only 64 or 66 cores are used. Each core has 4
hyperthreads,so there are effectively N = 256 (4*64) or N = 264 (4*66) Hyper-Threads,so there are effectively N = 256 (4*64) or N = 264 (4*66)
cores to run on. The product of MPI tasks * OpenMP threads/task should cores to run on. The product of MPI tasks * OpenMP threads/task should
not exceed this limit, otherwise performance will suffer. Note that not exceed this limit, otherwise performance will suffer. Note that
with the KOKKOS package you do not need to specify how many KNLs there with the KOKKOS package you do not need to specify how many KNLs there
......
...@@ -363,7 +363,7 @@ specified with the OMP_NUM_THREADS environment variable or the {omp} ...@@ -363,7 +363,7 @@ specified with the OMP_NUM_THREADS environment variable or the {omp}
keyword). The extra thread is dedicated for performing part of the keyword). The extra thread is dedicated for performing part of the
"PPPM solver"_kspace_style.html computations and communications. This "PPPM solver"_kspace_style.html computations and communications. This
can improve parallel performance on processors supporting can improve parallel performance on processors supporting
Simultaneous Multithreading (SMT) such as Hyperthreading on Intel Simultaneous Multithreading (SMT) such as Hyper-Threading (HT) on Intel
processors. In this mode, one additional thread is generated per MPI processors. In this mode, one additional thread is generated per MPI
process. LAMMPS will generate a warning in the case that more threads process. LAMMPS will generate a warning in the case that more threads
are used than available in SMT hardware on a node. If the PPPM solver are used than available in SMT hardware on a node. If the PPPM solver
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment