Drop redundant __MPI guards around internally-guarded wrappers

Remove #ifdef __MPI/#endif around 12 Parallel_Reduce::reduce_all and
Parallel_Common::bcast_bool calls in module_wannier: these wrappers
are declared unconditionally and behave as no-op serially, so calling
them without preprocessor guards is safe and consistent with the
governance rule of using guarded wrappers instead of direct MPI.
Guards around MPI_Barrier, ScalapackConnector::gemm and the pool
partition logic in out_unk are kept.
- Verified: incremental build passes with no errors; 5 guards remain
  in the module, all wrapping MPI/ScaLAPACK-specific symbols or logic

Author: abacus_fixer

source/source_io/module_wannier/to_w90.cpp

@@ -69,9 +69,7 @@ void toW90::read_nnkp(const UnitCell& ucell, const K_Vectors& kv)
         read_success = try_read_nnkp(ucell,kv);
     }
 
-#ifdef __MPI
     Parallel_Common::bcast_bool(read_success);
-#endif
 
     if (GlobalV::MY_RANK != 0 && read_success)
     {

source/source_io/module_wannier/to_w90_lcao_overlap.cpp

@@ -479,9 +479,7 @@ void toW90_LCAO::unkdotA(const K_Vectors& kv,
         }
     }
 
-#ifdef __MPI
     Parallel_Reduce::reduce_all(Amn.c, Amn.size);
-#endif
 }
 
 #endif

source/source_io/module_wannier/to_w90_lcao_pw.cpp

@@ -165,9 +165,7 @@ std::unique_ptr<psi::Psi<std::complex<double>>> toW90_LCAO_IN_PW::get_unk_from_l
                     anorm = anorm + conj((*unk_inLcao)(ik, ib, ig)) * (*unk_inLcao)(ik, ib, ig);
                 }
 
-#ifdef __MPI
                 Parallel_Reduce::reduce_all(anorm);
-#endif
 
                 for (int ig = 0; ig < npw; ig++)
                 {
@@ -179,14 +177,6 @@ std::unique_ptr<psi::Psi<std::complex<double>>> toW90_LCAO_IN_PW::get_unk_from_l
         {
             for (int ib = 0; ib < num_bands; ib++)
             {
-                // for (int ig = 0; ig < npwx*npol_; ig++)
-                // {
-                //     for (int iw = 0; iw < PARAM.globalv.nlocal; iw++)
-                //     {
-                //         (*unk_inLcao)(ik, ib, ig) +=  lcao_wfc_global(ib, iw) * orbital_in_G(iw, ig);
-                //     }
-                // }
-
                 for (int ig = 0; ig < npw; ig++)
                 {
                     int basis_num = PARAM.globalv.nlocal / 2;
@@ -204,9 +194,7 @@ std::unique_ptr<psi::Psi<std::complex<double>>> toW90_LCAO_IN_PW::get_unk_from_l
                             + conj((*unk_inLcao)(ik, ib, ig+npwx)) * (*unk_inLcao)(ik, ib, ig+npwx);
                 }
 
-#ifdef __MPI
                 Parallel_Reduce::reduce_all(anorm);
-#endif
 
                 for (int ig = 0; ig < npw; ig++)
                 {
@@ -274,9 +262,7 @@ void toW90_LCAO_IN_PW::get_lcao_wfc_global_ik(
         }
     }
 
-#ifdef __MPI
     Parallel_Reduce::reduce_all(lcao_wfc_global.c, lcao_wfc_global.size);
-#endif
 
 }
 #endif

source/source_io/module_wannier/to_w90_lcao_setup.cpp

@@ -243,9 +243,7 @@ void toW90_LCAO::unkdotkb(const UnitCell& ucell,
         }
     }
 
-#ifdef __MPI
     Parallel_Reduce::reduce_all(Mmn.c, num_bands * num_bands);
-#endif
 }
 
 void toW90_LCAO::produce_basis_orb()

source/source_io/module_wannier/to_w90_pw_overlap.cpp

@@ -71,9 +71,7 @@ void toW90_PW::unkdotkb(
                         result_tem = result_tem + conj(psir_up[ig]) * psi_pw(cal_ikb, in, ig)
                                                    + conj(psir_dn[ig]) * psi_pw(cal_ikb, in, ig+pwNumberMax);
                     }
-#ifdef __MPI
                     Parallel_Reduce::reduce_all(result_tem);
-#endif
                     Mmn(m, n) = result_tem;
                 }
                 else
@@ -112,9 +110,7 @@ void toW90_PW::unkdotkb(
                         result_tem = result_tem + conj(psir[ig]) * psi_pw(cal_ikb, in, ig);
                     }
 
-#ifdef __MPI
                     Parallel_Reduce::reduce_all(result_tem);
-#endif
                     Mmn(m, n) = result_tem;
                 }
                 else
@@ -169,8 +165,6 @@ void toW90_PW::unkdotW_A(
         }
     }
 
-#ifdef __MPI
     Parallel_Reduce::reduce_all(Amn.c, Amn.size);
-#endif
 
 }

source/source_io/module_wannier/to_w90_pw_setup.cpp

@@ -418,9 +418,7 @@ void toW90_PW::produce_trial_in_pw(
             anorm += conj(trial_orbitals_k(wannier_index, ig)) * trial_orbitals_k(wannier_index, ig);
         }
 
-#ifdef __MPI
         Parallel_Reduce::reduce_all(anorm);
-#endif
         for (int ig = 0; ig < npw; ig++)
         {
             trial_orbitals_k(wannier_index, ig) = trial_orbitals_k(wannier_index, ig) / sqrt(anorm);