Merge pull request #8708 from awlauria/ppc_atomics_v4.1.x

v4.1.x: Powerpc atomics: Force usage of powerpc assembly.

Author: rajachan

config/opal_config_asm.m4

@@ -1136,6 +1136,18 @@ AC_DEFUN([OPAL_CONFIG_ASM],[
                 AC_MSG_ERROR([Could not determine PowerPC word size: $ac_cv_sizeof_long])
             fi
             OPAL_GCC_INLINE_ASSIGN='"1: li %0,0" : "=&r"(ret)'
+
+            # See the following github PR and some performance numbers/discussion:
+            # https://github.com/open-mpi/ompi/pull/8649
+            AC_MSG_CHECKING([$opal_cv_asm_arch: Checking if force gcc atomics requested])
+            if test $force_gcc_atomics_ppc = 0 ; then
+                AC_MSG_RESULT([no])
+                opal_cv_asm_builtin="BUILTIN_NO"
+            else
+                AC_MSG_RESULT([Yes])
+                AC_MSG_WARN([$opal_cv_asm_arch: gcc atomics have been known to perform poorly on powerpc.])
+            fi
+
             ;;
         # There is no current difference between s390 and s390x
         # But use two different defines in case some come later

config/opal_configure_options.m4

@@ -84,6 +84,13 @@ else
     WANT_BRANCH_PROBABILITIES=0
 fi
 
+AC_ARG_ENABLE([builtin-atomics-for-ppc],[AS_HELP_STRING([--enable-builtin-atomics-for-ppc],
+                  [POWER architectures only: Force use of builtin atomics if available. This could either be gcc builtins or C11 atomics, depending on what is available on your system. Enabling this is known to cause poor performance in atomic operations on Power machines. (default: disabled)])])
+if test "x$enable_builtin_atomics_for_ppc" = "xyes" ; then
+force_gcc_atomics_ppc=1
+else
+force_gcc_atomics_ppc=0
+fi
 
 #
 # Memory debugging