Merge branch 'TDDFT_GPU_phase_1' of github.com:AsTonyshment/abacus-develop into TDDFT_GPU_phase_1

Author: AsTonyshment

docs/quick_start/input.md

@@ -8,17 +8,17 @@ The `INPUT` file contains parameters that control the type of calculation as wel
 
 Below is an example `INPUT` file with some of the most important parameters that need to be set:
 
-```
+```plaintext
 INPUT_PARAMETERS
 suffix                  MgO
 ntype                   2
 pseudo_dir              ./
-orbital_dir		./
-ecutwfc                 100             # Rydberg
-scf_thr                 1e-4		# Rydberg
-basis_type              lcao            
-calculation             scf		# this is the key parameter telling abacus to do a scf calculation
-out_chg			True
+orbital_dir             ./
+ecutwfc                 100  # in Rydberg
+scf_thr                 1e-4 # Rydberg
+basis_type              lcao
+calculation             scf  # this is the key parameter telling abacus to do a scf calculation
+out_chg                 True
 ```
 
 The parameter list always starts with key word `INPUT_PARAMETERS`. Any content before `INPUT_PARAMETERS` will be ignored.
@@ -40,22 +40,23 @@ In the above example, the meanings of the parameters are:
 - `ntype` : how many types of elements in the unit cell
 - `pseudo_dir` : the directory where pseudopotential files are provided
 - `orbital_dir` : the directory where orbital files are provided
-- `ecutwfc` : the plane-wave energy cutoff for the wave function expansion (UNIT: Rydberg)    
-- `scf_thr` : the threshold for the convergence of charge density (UNIT: Rydberg)    
+- `ecutwfc` : the plane-wave energy cutoff for the wave function expansion (UNIT: Rydberg)
+- `scf_thr` : the threshold for the convergence of charge density (UNIT: Rydberg)
 - `basis_type` : the type of basis set for expanding the electronic wave functions
 - `calculation` : the type of calculation to be performed by ABACUS
-- `out_chg` : if true, output thee charge density oon real space grid
+- `out_chg` : if true, output the charge density on real space grid
 
 For a complete list of input parameters, please consult this [instruction](../advanced/input_files/input-main.md).
 
-> **Note:** Users cannot change the filename “INPUT” to other names. Boolean paramerters such as `out_chg` can be set by using `True` and `False`, `1` and `0`, or `T` and `F`. It is case insensitive so that other preferences such as `true` and `false`, `TRUE` and `FALSE`, and `t` and `f` for setting boolean values are also supported.
+> **Note:** Users cannot change the filename “INPUT” to other names. Boolean paramerters such as `out_chg` can be set by using `True` and `False`, `1` and `0`, or `T` and `F`. It is case insensitive so that other preferences such as `true` and `false`, `TRUE` and `FALSE`, and `t` and `f` for setting boolean values are also supported. Specifically for the `out_chg`, `-1` option is also available, which means turn off the checkpoint of charge density in binary (always dumped in `OUT.{suffix}`, whose name ends with `CHARGE-DENSITY.restart`). Some parameters controlling the output also support a second option to control the output precision, e.g., `out_chg True 8` will output the charge density on realspace grid with 8 digits after the decimal point.
 
 ## *STRU*
 
-The structure file contains structural information about the system, e.g., lattice constant, lattice vectors, and positions of the atoms within a unit cell. The positions can be given either in direct or Cartesian coordinates. 
+The structure file contains structural information about the system, e.g., lattice constant, lattice vectors, and positions of the atoms within a unit cell. The positions can be given either in direct or Cartesian coordinates.
 
 An example of the `STRU` file is given as follows :
-```
+
+```plaintext
 #This is the atom file containing all the information
 #about the lattice structure.
 
@@ -68,7 +69,7 @@ Mg_gga_8au_100Ry_4s2p1d.orb
 O_gga_8au_100Ry_2s2p1d.orb
 
 LATTICE_CONSTANT
-1.8897259886 		# 1.8897259886 Bohr =  1.0 Angstrom
+1.8897259886 # 1.8897259886 Bohr =  1.0 Angstrom
 
 LATTICE_VECTORS
 4.25648 0.00000 0.00000  
@@ -100,9 +101,10 @@ For a more detailed description of STRU file, please consult [here](../advanced/
 ## *KPT*
 
 This file contains information of the kpoint grid setting for the Brillouin zone sampling.
-    
+
 An example of the `KPT` file is given below:
-```
+
+```plaintext
 K_POINTS
 0 
 Gamma
@@ -111,7 +113,6 @@ Gamma
 
 > **Note:** users may choose a different name for their k-point file using keyword `kpoint_file`
 
-
 For a more detailed description, please consult [here](../advanced/input_files/kpt.md).
 
 - The pseudopotential files

source/module_base/intarray.h

@@ -141,9 +141,14 @@ class IntArray
     }
 
   private:
-    int size;
-    int dim;
-    int bound1, bound2, bound3, bound4, bound5, bound6;
+    int size=0;
+    int dim=0;
+    int bound1=0;
+    int bound2=0; 
+    int bound3=0;
+    int bound4=0; 
+    int bound5=0; 
+    int bound6=0;
     static int arrayCount;
     void freemem();
 };

source/module_base/inverse_matrix.h

@@ -20,13 +20,13 @@ class Inverse_Matrix_Complex
 	void init( const int &dim_in);
 
 	private:
-	int dim;
-	double *e;
-	int lwork;
-	std::complex<double> *work2;
-	double* rwork;
-	int info;
-	bool allocate; //mohan add 2012-04-02
+	int dim=0;
+	double *e=nullptr;
+	int lwork=0;
+	std::complex<double> *work2=nullptr;
+	double* rwork=nullptr;
+	int info=0;
+	bool allocate=false; //mohan add 2012-04-02
 
 	ModuleBase::ComplexMatrix EA;
 };

source/module_base/memory.cpp

@@ -436,6 +436,7 @@ void Memory::print_all(std::ofstream &ofs)
 #if defined(__CUDA) || defined(__ROCM)
 	if(!init_flag_gpu) 
 	{
+		delete[] print_flag;
 		return;
 	}
 

source/module_base/parallel_2d.cpp

@@ -12,20 +12,24 @@ bool Parallel_2D::in_this_processor(const int iw1_all, const int iw2_all) const
 
 int Parallel_2D::get_global_row_size() const
 {
+    if (!is_serial)
+    {
 #ifdef __MPI
-    return desc[2];
-#else
-    return nrow;
+        return desc[2];
 #endif
+    }
+    return nrow;
 }
 
 int Parallel_2D::get_global_col_size() const
 {
+    if (!is_serial)
+    {
 #ifdef __MPI
-    return desc[3];
-#else
-    return ncol;
+        return desc[3];
 #endif
+    }
+    return ncol;
 }
 
 #ifdef __MPI
@@ -133,6 +137,7 @@ void Parallel_2D::set_serial(const int mg, const int ng)
     std::iota(local2global_col_.begin(), local2global_col_.end(), 0);
     global2local_row_ = local2global_row_;
     global2local_col_ = local2global_col_;
+    is_serial = true;
 #ifdef __MPI
     blacs_ctxt = -1;
 #endif

source/module_base/parallel_2d.h

@@ -129,6 +129,9 @@ class Parallel_2D
     /// process coordinate in the BLACS grid
     int coord[2] = {-1, -1};
 
+    /// whether to use the serial mode
+    bool is_serial = false;
+
   protected:
     /// map from global index to local index
     std::vector<int> global2local_row_;

source/module_basis/module_ao/ORB_nonlocal.cpp

@@ -7,6 +7,7 @@ Numerical_Nonlocal::Numerical_Nonlocal()
 	//question remains
 	this->type = 0;
 	this->lmax = 0;
+	this->rcut_max = 0.0;
 	this->Proj = new Numerical_Nonlocal_Lm[1];
 	this->nproj = -1;
 	//zhengdy-soc, for optimize nonlocal part
@@ -49,6 +50,7 @@ void Numerical_Nonlocal::set_type_info
 //----------------------------------------------------------
 	//only store radial function
 	delete[] Proj;
+	this->Proj = nullptr;
 	this->Proj = new Numerical_Nonlocal_Lm[this->nproj];
 
 	for (int p1=0; p1<nproj; p1++)

source/module_basis/module_ao/ORB_nonlocal.h

@@ -44,20 +44,20 @@ class Numerical_Nonlocal
 
 	Numerical_Nonlocal_Lm* Proj; ///< length: nproj(only store radial function )
 
-	const double& get_rcut_max(void) const { return rcut_max; }
+	const double& get_rcut_max() const { return rcut_max; }
     const int& get_nproj() const { return nproj; }
 
 	private:
 
-	std::string label; /// <element label
+	std::string label=""; /// <element label
 
 	int type; ///< element index
 
 	int lmax; ///< max value of L angular momentum
 
-	double rcut_max;
+	double rcut_max=0.0;
 
-	std::string type_ps; ///<local or nonlocal
+	std::string type_ps=""; ///<local or nonlocal
 
 	int nproj;
 

source/module_basis/module_ao/ORB_nonlocal_lm.cpp

@@ -16,6 +16,7 @@ Numerical_Nonlocal_Lm::Numerical_Nonlocal_Lm()
 	label = "";
 	index_atom_type = 0;
 	angular_momentum_l = 0;
+	index_proj = 0;
 
 	nr = 1;
 	nk = 1;
@@ -34,7 +35,7 @@ Numerical_Nonlocal_Lm::~Numerical_Nonlocal_Lm()
 	this->freemem();
 }
 
-void Numerical_Nonlocal_Lm::renew(void)
+void Numerical_Nonlocal_Lm::renew()
 {
 	assert(nr_uniform>0);
 	assert(nr>0);
@@ -55,7 +56,7 @@ void Numerical_Nonlocal_Lm::renew(void)
 	ModuleBase::GlobalFunc::ZEROS(beta_k, nk);
 }
 
-void Numerical_Nonlocal_Lm::freemem(void)
+void Numerical_Nonlocal_Lm::freemem()
 {
 	delete[] this->r_radial;
 	delete[] this->rab;
@@ -246,7 +247,7 @@ void Numerical_Nonlocal_Lm::extra_uniform(const double &dr_uniform_in)
 }
 */
 
-void Numerical_Nonlocal_Lm::get_kradial(void)
+void Numerical_Nonlocal_Lm::get_kradial()
 {
     //ModuleBase::TITLE("Numerical_Nonlocal_Lm","get_kradial");
     double *jl = new double[nr];

source/module_basis/module_ao/parallel_orbitals.cpp

@@ -6,12 +6,20 @@
 
 Parallel_Orbitals::Parallel_Orbitals()
 {
-    loc_sizes = nullptr;
-
+    this->loc_sizes = nullptr;
     // in multi-k, 2D-block-division variables for FT (R<->k)
-    nnr = 1;
-    nlocdim = nullptr;
-    nlocstart = nullptr;
+    this->nlocdim = nullptr;
+    this->nlocstart = nullptr;
+    this->nnr = 1;
+    this->ncol_bands = 0;
+    this->nrow_bands=0;
+    this->nloc_wfc=0;
+    this->nloc_Eij=0;
+    this->lastband_in_proc=0;
+    this->lastband_number=0;
+    this->loc_size=0;
+    this->nbands = 0;
+
 }
 
 Parallel_Orbitals::~Parallel_Orbitals()