Merge branch 'develop' into threads_view

deepmodeling · Oct 22, 2024 · 952dd6b · 952dd6b
2 parents 4de541a + efb83c8
commit 952dd6b
Show file tree

Hide file tree

Showing 25 changed files with 48 additions and 143 deletions.
diff --git a/docs/advanced/input_files/kpt.md b/docs/advanced/input_files/kpt.md
@@ -8,7 +8,7 @@ ABACUS uses periodic boundary conditions for both crystals and finite systems. F
 
 ## Gamma-only Calculations
 
-In ABACUS, we offer th option of running gamma-only calculations for LCAO basis by setting [gamma_only](./input-main.md#gamma_only) to be 1. Due to details of implementation, gamma-only calculation will be slightly faster than running a non gamma-only calculation and explicitly setting gamma point to be the only the k-point, but the results should be consistent.
+In ABACUS, we offer the option of running gamma-only calculations for LCAO basis by setting [gamma_only](./input-main.md#gamma_only) to be 1. Due to details of implementation, gamma-only calculation will be slightly faster than running a non gamma-only calculation and explicitly setting gamma point to be the only the k-point, but the results should be consistent.
 
 > If gamma_only is set to 1, the KPT file will be overwritten. So make sure to turn off gamma_only for multi-k calculations.
 
@@ -23,7 +23,7 @@ method to generate k-mesh, and the following is an example input k-point (`KPT`)
 K_POINTS //keyword for start
 0 //total number of k-point, `0' means generate automatically
 Gamma //which kind of Monkhorst-Pack method, `Gamma' or `MP'
-2 2 2 0 0 0 //first three number: subdivisions along recpri. vectors
+2 2 2 0 0 0 //first three number: subdivisions along reciprocal vectors
             //last three number: shift of the mesh
 ```
 
@@ -63,8 +63,8 @@ Direct //`Direct' or `Cartesian' coordinate
 ## Band structure calculations
 
 ABACUS uses specified high-symmetry directions of the Brillouin zone for band structure
-calculations. The third line of k-point file should start with ‘Line’ or ‘Line_Cartesian’ for
-line mode. ‘Line’ means the positions below are in Direct coordinates, while ‘Line_Cartesian’
+calculations. The third line of k-point file should start with 'Line' or 'Line_Cartesian' for
+line mode. 'Line' means the positions below are in Direct coordinates, while 'Line_Cartesian'
 means in Cartesian coordinates:
 
 ```

diff --git a/source/Makefile.Objects b/source/Makefile.Objects
@@ -484,7 +484,6 @@ OBJS_IO=input_conv.o\
     output.o\
     print_info.o\
     read_cube.o\
-    read_rho.o\
     rhog_io.o\
     read_exit_file.o\
     read_wfc_pw.o\

diff --git a/source/module_elecstate/module_charge/charge_init.cpp b/source/module_elecstate/module_charge/charge_init.cpp
@@ -14,7 +14,7 @@
 #include "module_elecstate/magnetism.h"
 #include "module_hamilt_pw/hamilt_pwdft/global.h"
 #include "module_hamilt_pw/hamilt_pwdft/parallel_grid.h"
-#include "module_io/rho_io.h"
+#include "module_io/cube_io.h"
 #include "module_io/rhog_io.h"
 #include "module_io/read_wfc_to_rho.h"
 #ifdef USE_PAW
@@ -54,24 +54,22 @@ void Charge::init_rho(elecstate::efermi& eferm_iout,
                 std::stringstream ssc;
                 ssc << PARAM.globalv.global_readin_dir << "SPIN" << is + 1 << "_CHG.cube";
                 double& ef_tmp = eferm_iout.get_ef(is);
-                if (ModuleIO::read_rho(
+                if (ModuleIO::read_cube(
 #ifdef __MPI
-                        &(GlobalC::Pgrid),
+                    & (GlobalC::Pgrid),
 #endif
-                        GlobalV::MY_RANK,
-                        PARAM.inp.esolver_type,
-                        GlobalV::RANK_IN_STOGROUP,
-                        is,
-                        GlobalV::ofs_running,
-                        PARAM.inp.nspin,
-                        ssc.str(),
-                        this->rho[is],
-                        this->rhopw->nx,
-                        this->rhopw->ny,
-                        this->rhopw->nz,
-                        ef_tmp,
-                        &(GlobalC::ucell),
-                        this->prenspin))
+                    (PARAM.inp.esolver_type == "sdft" ? GlobalV::RANK_IN_STOGROUP : GlobalV::MY_RANK),
+                    is,
+                    GlobalV::ofs_running,
+                    PARAM.inp.nspin,
+                    ssc.str(),
+                    this->rho[is],
+                    this->rhopw->nx,
+                    this->rhopw->ny,
+                    this->rhopw->nz,
+                    ef_tmp,
+                    & (GlobalC::ucell),
+                    this->prenspin))
                 {
                     GlobalV::ofs_running << " Read in the charge density: " << ssc.str() << std::endl;
                 }
@@ -129,24 +127,22 @@ void Charge::init_rho(elecstate::efermi& eferm_iout,
                     GlobalV::ofs_running << " try to read kinetic energy density from file : " << ssc.str()
                                          << std::endl;
                     // mohan update 2012-02-10, sunliang update 2023-03-09
-                    if (ModuleIO::read_rho(
+                    if (ModuleIO::read_cube(
 #ifdef __MPI
-                            &(GlobalC::Pgrid),
+                        & (GlobalC::Pgrid),
 #endif
-                            GlobalV::MY_RANK,
-                            PARAM.inp.esolver_type,
-                            GlobalV::RANK_IN_STOGROUP,
-                            is,
-                            GlobalV::ofs_running,
-                            PARAM.inp.nspin,
-                            ssc.str(),
-                            this->kin_r[is],
-                            this->rhopw->nx,
-                            this->rhopw->ny,
-                            this->rhopw->nz,
-                            eferm_iout.ef,
-                            &(GlobalC::ucell),
-                            this->prenspin))
+                        (PARAM.inp.esolver_type == "sdft" ? GlobalV::RANK_IN_STOGROUP : GlobalV::MY_RANK),
+                        is,
+                        GlobalV::ofs_running,
+                        PARAM.inp.nspin,
+                        ssc.str(),
+                        this->kin_r[is],
+                        this->rhopw->nx,
+                        this->rhopw->ny,
+                        this->rhopw->nz,
+                        eferm_iout.ef,
+                        & (GlobalC::ucell),
+                        this->prenspin))
                     {
                         GlobalV::ofs_running << " Read in the kinetic energy density: " << ssc.str() << std::endl;
                     }

diff --git a/source/module_esolver/cal_edm_tddft.cpp b/source/module_esolver/cal_edm_tddft.cpp
@@ -2,7 +2,6 @@
 
 #include "module_io/cal_r_overlap_R.h"
 #include "module_io/dipole_io.h"
-#include "module_io/rho_io.h"
 #include "module_io/td_current_io.h"
 #include "module_io/write_HS.h"
 #include "module_io/write_HS_R.h"

diff --git a/source/module_esolver/esolver_ks_lcao_tddft.cpp b/source/module_esolver/esolver_ks_lcao_tddft.cpp
@@ -2,7 +2,6 @@
 
 #include "module_io/cal_r_overlap_R.h"
 #include "module_io/dipole_io.h"
-#include "module_io/rho_io.h"
 #include "module_io/td_current_io.h"
 #include "module_io/write_HS.h"
 #include "module_io/write_HS_R.h"

diff --git a/source/module_esolver/esolver_ks_lcaopw.cpp b/source/module_esolver/esolver_ks_lcaopw.cpp
@@ -32,7 +32,6 @@
 #include "module_io/berryphase.h"
 #include "module_io/numerical_basis.h"
 #include "module_io/numerical_descriptor.h"
-#include "module_io/rho_io.h"
 #include "module_io/to_wannier90_pw.h"
 #include "module_io/winput.h"
 #include "module_io/write_elecstat_pot.h"

diff --git a/source/module_esolver/lcao_gets.cpp b/source/module_esolver/lcao_gets.cpp
@@ -22,7 +22,6 @@
 #include "module_hamilt_lcao/hamilt_lcaodft/operator_lcao/operator_lcao.h"
 #include "module_hamilt_lcao/module_deltaspin/spin_constrain.h"
 #include "module_io/read_wfc_nao.h"
-#include "module_io/rho_io.h"
 #include "module_io/write_elecstat_pot.h"
 #include "module_io/write_wfc_nao.h"
 #ifdef __EXX

diff --git a/source/module_esolver/lcao_nscf.cpp b/source/module_esolver/lcao_nscf.cpp
@@ -29,7 +29,6 @@
 #include "module_hamilt_lcao/hamilt_lcaodft/operator_lcao/operator_lcao.h"
 #include "module_hamilt_lcao/module_deltaspin/spin_constrain.h"
 #include "module_io/read_wfc_nao.h"
-#include "module_io/rho_io.h"
 #include "module_io/write_elecstat_pot.h"
 #include "module_io/write_wfc_nao.h"
 #ifdef __EXX

diff --git a/source/module_esolver/lcao_others.cpp b/source/module_esolver/lcao_others.cpp
@@ -27,7 +27,6 @@
 #include "module_hamilt_lcao/hamilt_lcaodft/operator_lcao/operator_lcao.h"
 #include "module_hamilt_lcao/module_deltaspin/spin_constrain.h"
 #include "module_io/read_wfc_nao.h"
-#include "module_io/rho_io.h"
 #include "module_io/write_elecstat_pot.h"
 #include "module_io/write_wfc_nao.h"
 #ifdef __EXX

diff --git a/source/module_esolver/pw_fun.cpp b/source/module_esolver/pw_fun.cpp
@@ -34,7 +34,6 @@
 #include "module_io/berryphase.h"
 #include "module_io/numerical_basis.h"
 #include "module_io/numerical_descriptor.h"
-#include "module_io/rho_io.h"
 #include "module_io/to_wannier90_pw.h"
 #include "module_io/winput.h"
 #include "module_io/write_elecstat_pot.h"

diff --git a/source/module_esolver/pw_init_after_vc.cpp b/source/module_esolver/pw_init_after_vc.cpp
@@ -34,7 +34,6 @@
 #include "module_io/berryphase.h"
 #include "module_io/numerical_basis.h"
 #include "module_io/numerical_descriptor.h"
-#include "module_io/rho_io.h"
 #include "module_io/to_wannier90_pw.h"
 #include "module_io/winput.h"
 #include "module_io/write_elecstat_pot.h"

diff --git a/source/module_esolver/pw_init_globalc.cpp b/source/module_esolver/pw_init_globalc.cpp
@@ -34,7 +34,6 @@
 #include "module_io/berryphase.h"
 #include "module_io/numerical_basis.h"
 #include "module_io/numerical_descriptor.h"
-#include "module_io/rho_io.h"
 #include "module_io/to_wannier90_pw.h"
 #include "module_io/winput.h"
 #include "module_io/write_elecstat_pot.h"

diff --git a/source/module_esolver/pw_nscf.cpp b/source/module_esolver/pw_nscf.cpp
@@ -34,7 +34,6 @@
 #include "module_io/berryphase.h"
 #include "module_io/numerical_basis.h"
 #include "module_io/numerical_descriptor.h"
-#include "module_io/rho_io.h"
 #include "module_io/to_wannier90_pw.h"
 #include "module_io/winput.h"
 #include "module_io/write_elecstat_pot.h"

diff --git a/source/module_esolver/pw_others.cpp b/source/module_esolver/pw_others.cpp
@@ -34,7 +34,6 @@
 #include "module_io/berryphase.h"
 #include "module_io/numerical_basis.h"
 #include "module_io/numerical_descriptor.h"
-#include "module_io/rho_io.h"
 #include "module_io/to_wannier90_pw.h"
 #include "module_io/winput.h"
 #include "module_io/write_elecstat_pot.h"

diff --git a/source/module_esolver/set_matrix_grid.cpp b/source/module_esolver/set_matrix_grid.cpp
@@ -12,7 +12,6 @@
 #include "module_hamilt_lcao/hamilt_lcaodft/operator_lcao/operator_lcao.h"
 #include "module_hamilt_pw/hamilt_pwdft/global.h"
 #include "module_io/read_wfc_nao.h"
-#include "module_io/rho_io.h"
 #include "module_io/write_elecstat_pot.h"
 #include "module_io/write_wfc_nao.h"
 #include "module_parameter/parameter.h"

diff --git a/source/module_hamilt_lcao/module_gint/gint_vl_gpu.cu b/source/module_hamilt_lcao/module_gint/gint_vl_gpu.cu
@@ -47,7 +47,8 @@ void gint_vl_gpu(hamilt::HContainer<double>* hRGint,
         checkCuda(cudaStreamCreate(&streams[i]));
     }
 
-    Cuda_Mem_Wrapper<double> grid_vlocal_g(hRGint->get_nnr(), 1, false);
+    const int nnrg = is_gamma_only ? hRGint->get_nnr() : gridt.nnrg;
+    Cuda_Mem_Wrapper<double> grid_vlocal_g(nnrg, 1, false);
     grid_vlocal_g.memset_device_sync();
 
     Cuda_Mem_Wrapper<double> dr_part(max_atom_per_z * 3, num_streams, true);
@@ -189,15 +190,15 @@ void gint_vl_gpu(hamilt::HContainer<double>* hRGint,
         checkCuda(cudaMemcpy(
             hRGint->get_wrapper(),
             grid_vlocal_g.get_device_pointer(),
-            hRGint->get_nnr() * sizeof(double),
+            nnrg * sizeof(double),
             cudaMemcpyDeviceToHost));
     }
     else
     {
         checkCuda(cudaMemcpy(
             pvpR,
             grid_vlocal_g.get_device_pointer(),
-            hRGint->get_nnr() * sizeof(double),
+            nnrg * sizeof(double),
             cudaMemcpyDeviceToHost));
     }
     for (int i = 0; i < num_streams; i++)

diff --git a/source/module_hsolver/diago_elpa_native.cpp b/source/module_hsolver/diago_elpa_native.cpp
@@ -81,7 +81,11 @@ void DiagoElpaNative<T>::diag_pool(hamilt::MatrixBlock<T>& h_mat,
     // elpa_init(20210430);
     int success;
     elpa_t handle = elpa_allocate(&success);
+#ifdef _OPENMP
     int num_threads = omp_get_max_threads();
+#else
+    int num_threads = 1;
+#endif
     elpa_set(handle, "omp_threads", num_threads, &success);
     elpa_set(handle, "na", (int)nFull, &success);
     elpa_set(handle, "nev", (int)nev, &success);

diff --git a/source/module_io/CMakeLists.txt b/source/module_io/CMakeLists.txt
@@ -13,7 +13,6 @@ list(APPEND objects
     output.cpp
     print_info.cpp
     read_cube.cpp
-    read_rho.cpp
     rhog_io.cpp
     read_exit_file.cpp
     read_wfc_pw.cpp

diff --git a/source/module_io/cube_io.h b/source/module_io/cube_io.h
@@ -13,8 +13,6 @@ bool read_cube(
     const Parallel_Grid*const Pgrid,
 #endif
     const int my_rank,
-    const std::string esolver_type,
-    const int rank_in_stogroup,
     const int is,
     std::ofstream& ofs_running,
     const int nspin,

diff --git a/source/module_io/read_cube.cpp b/source/module_io/read_cube.cpp
@@ -6,8 +6,6 @@ bool ModuleIO::read_cube(
     const Parallel_Grid*const Pgrid,
 #endif
     const int my_rank,
-    const std::string esolver_type,
-    const int rank_in_stogroup,
     const int is,
     std::ofstream& ofs_running,
     const int nspin,
@@ -112,12 +110,11 @@ bool ModuleIO::read_cube(
         }
     }
 
-    const bool flag_read_rank = (my_rank == 0 || (esolver_type == "sdft" && rank_in_stogroup == 0));
 #ifdef __MPI
     if(nx == nx_read && ny == ny_read && nz == nz_read)
-        ModuleIO::read_cube_core_match(ifs, Pgrid, flag_read_rank, data, nx*ny, nz);
+        ModuleIO::read_cube_core_match(ifs, Pgrid, (my_rank == 0), data, nx * ny, nz);
     else
-        ModuleIO::read_cube_core_mismatch(ifs, Pgrid, flag_read_rank, data, nx, ny, nz, nx_read, ny_read, nz_read);
+        ModuleIO::read_cube_core_mismatch(ifs, Pgrid, (my_rank == 0), data, nx, ny, nz, nx_read, ny_read, nz_read);
 #else
     ofs_running << " Read SPIN = " << is + 1 << " charge now." << std::endl;
     if(nx == nx_read && ny == ny_read && nz == nz_read)

diff --git a/source/module_io/read_rho.cpp b/source/module_io/read_rho.cpp
diff --git a/source/module_io/rho_io.h b/source/module_io/rho_io.h
diff --git a/source/module_io/test_serial/CMakeLists.txt b/source/module_io/test_serial/CMakeLists.txt
@@ -46,7 +46,7 @@ AddTest(
 AddTest(
   TARGET io_rho_io
   LIBS parameter ${math_libs} base device cell_info 
-  SOURCES rho_io_test.cpp ../read_cube.cpp ../write_cube.cpp ../read_rho.cpp ../output.cpp
+  SOURCES rho_io_test.cpp ../read_cube.cpp ../write_cube.cpp ../output.cpp
 )
 
 AddTest(