Set amrex.omp_threads = "nosmt"

Improve the performance on Intel and AMD CPUs by default:
Avoid oversubscribing the physical number of CPU threads, as is
default in OpenMP.

Docs/source/usage/parameters.rst

@@ -167,6 +167,12 @@ Overall simulation parameters
     For all regular WarpX operations, we therefore do explicit memory transfers without the need for managed memory and thus changed the AMReX default to false.
     `Please also see the documentation in AMReX <https://amrex-codes.github.io/amrex/docs_html/GPU.html#inputs-parameters>`__.
 
+* ``amrex.omp_threads``  (``system``, ``nosmt`` or positive integer; default is ``nosmt``)
+    An integer number can be set in lieu of the ``OMP_NUM_THREADS`` environment variable to control the number of OpenMP threads to use for the ``OMP`` compute backend on CPUs.
+    By default, we use the ``nosmt`` option, which overwrites the OpenMP default of spawning one thread per logical CPU core, and instead only spawns a number of threads equal to the number of physical CPU cores on the machine.
+    If set, the environment variable ``OMP_NUM_THREADS`` takes precedence over ``system`` and ``nosmt``, but not over integer numbers set in this option.
+
+
 Signal Handling
 ^^^^^^^^^^^^^^^
 

Source/Initialization/WarpXAMReXInit.cpp

@@ -29,6 +29,10 @@ namespace {
         bool the_arena_is_managed = false; // AMReX' default: true
         pp_amrex.queryAdd("the_arena_is_managed", the_arena_is_managed);
 
+        // link ...
+        std::string omp_threads = "nosmt"; // AMReX' default: system
+        pp_amrex.queryAdd("omp_threads", omp_threads);
+
         // Work-around:
         // If warpx.numprocs is used for the domain decomposition, we will not use blocking factor
         // to generate grids. Nonetheless, AMReX has asserts in place that validate that the