[Flang][OpenMP] Process reduction only once for parallel do (#70844)

Author: kiranchandramohan

flang/lib/Lower/OpenMP.cpp

@@ -2312,7 +2312,8 @@ genParallelOp(Fortran::lower::AbstractConverter &converter,
   cp.processProcBind(procBindKindAttr);
   cp.processDefault();
   cp.processAllocate(allocatorOperands, allocateOperands);
-  cp.processReduction(currentLocation, reductionVars, reductionDeclSymbols);
+  if (!outerCombined)
+    cp.processReduction(currentLocation, reductionVars, reductionDeclSymbols);
 
   return genOpWithBody<mlir::omp::ParallelOp>(
       converter, eval, currentLocation, outerCombined, &clauseList,

flang/test/Lower/OpenMP/parallel-wsloop-reduction.f90

@@ -0,0 +1,16 @@
+! Check that for parallel do, reduction is only processed for the loop
+
+! RUN: bbc -fopenmp -emit-hlfir %s -o - | FileCheck %s
+! RUN: flang-new -fc1 -fopenmp -emit-hlfir %s -o - | FileCheck %s
+
+! CHECK: omp.parallel {
+! CHECK: omp.wsloop reduction(@add_reduction_i_32
+subroutine sb
+  integer :: x
+  x = 0
+  !$omp parallel do reduction(+:x)
+  do i=1,100
+    x = x + 1
+  end do
+  !$omp end parallel do
+end subroutine