Merge branch 'develop' into toolchain-202503-dev

Author: QuantumMisaka

.github/workflows/test.yml

@@ -17,11 +17,17 @@ jobs:
       volumes:
         - /tmp/ccache:/github/home/.ccache
     steps:
-      - name: Checkout
+      - name: Checkout repository
         uses: actions/checkout@v5
         with:
-          submodules: recursive
           fetch-depth: 0
+          # We will handle submodules manually after fixing ownership
+          submodules: 'false'
+
+      - name: Take ownership of the workspace and update submodules
+        run: |
+          sudo chown -R $(whoami) .
+          git submodule update --init --recursive
 
       - name: Install CI tools
         run: |

CMakeLists.txt

@@ -481,8 +481,12 @@ else()
   find_package(Lapack REQUIRED)
   include_directories(${FFTW3_INCLUDE_DIRS})
   list(APPEND math_libs FFTW3::FFTW3 LAPACK::LAPACK BLAS::BLAS)
+if(USE_DSP)
+  target_link_libraries(${ABACUS_BIN_NAME} ${SCALAPACK_LIBRARY_DIR})
+else()
   find_package(ScaLAPACK REQUIRED)
   list(APPEND math_libs ScaLAPACK::ScaLAPACK)
+endif()
   if(USE_OPENMP)
     list(APPEND math_libs FFTW3::FFTW3_OMP)
   endif()

docs/advanced/input_files/input-main.md

@@ -147,7 +147,6 @@
     - [out\_band](#out_band)
     - [out\_proj\_band](#out_proj_band)
     - [out\_stru](#out_stru)
-    - [out\_bandgap](#out_bandgap)
     - [out\_level](#out_level)
     - [out\_alllog](#out_alllog)
     - [out\_mat\_hs](#out_mat_hs)
@@ -256,6 +255,9 @@
     - [of\_ml\_chi\_pnl](#of_ml_chi_pnl)
     - [of\_ml\_chi\_qnl](#of_ml_chi_qnl)
     - [of\_ml\_local\_test](#of_ml_local_test)
+  - [TD-OFDFT: time dependent orbital free density functional theory](#tdofdft-time-dependent-orbital-free-density-functional-theory)
+    - [of\_cd](#of_cd)
+    - [of\_mcd\_alpha](#of_mcd_alpha)
   - [Electric Field and Dipole Correction](#electric-field-and-dipole-correction)
     - [efield\_flag](#efield_flag)
     - [dip\_cor\_flag](#dip_cor_flag)
@@ -528,6 +530,7 @@ These variables are used to control general system parameters.
 - **Description**: choose the energy solver.
   - ksdft: Kohn-Sham density functional theory
   - ofdft: orbital-free density functional theory
+  - tdofdft: time-dependent orbital-free density functional theory
   - sdft: [stochastic density functional theory](#electronic-structure-sdft)
   - tddft: real-time time-dependent density functional theory (TDDFT)
   - lj: Leonard Jones potential
@@ -1074,7 +1077,20 @@ calculations.
 
 - **Type**: String
 - **Description**: In our package, the XC functional can either be set explicitly using the `dft_functional` keyword in `INPUT` file. If `dft_functional` is not specified, ABACUS will use the xc functional indicated in the pseudopotential file.
-  On the other hand, if dft_functional is specified, it will overwrite the functional from pseudopotentials and performs calculation with whichever functional the user prefers. We further offer two ways of supplying exchange-correlation functional. The first is using 'short-hand' names such as 'LDA', 'PBE', 'SCAN'. A complete list of 'short-hand' expressions can be found in [the source code](../../../source/source_hamilt/module_xc/xc_functional.cpp). The other way is only available when ***compiling with LIBXC***, and it allows for supplying exchange-correlation functionals as combinations of LIBXC keywords for functional components, joined by a plus sign, for example, dft_functional='LDA_X_1D_EXPONENTIAL+LDA_C_1D_CSC'. The list of LIBXC keywords can be found on its [website](https://libxc.gitlab.io/functionals/). In this way, **we support all the LDA,GGA and mGGA functionals provided by LIBXC**.
+  On the other hand, if dft_functional is specified, it will overwrite the functional from pseudopotentials and performs calculation with whichever functional the user prefers. We further offer two ways of supplying exchange-correlation functional. The first is using 'short-hand' names. A complete list of 'short-hand' expressions can be found in [the source code](../../../source/source_hamilt/module_xc/xc_functional.cpp). Supported density functionals are:
+  - LDA functionals
+    - LDA (equivalent with PZ and SLAPZNOGXNOGC), PWLDA
+  - GGA functionals
+    - PBE (equivalent with SLAPWPBXPBC), PBESOL, REVPBE, WC, BLYP, BP(referred to BP86), PW91, HCTH, OLYP, BLYP_LR
+  - meta-GGA functionals
+    - SCAN (require LIBXC)
+  - Hybrid functionals
+    - PBE0, HF
+    - If LIBXC is avaliale, additional short-hand names of hybrid functionals are supported: HSE(referred to HSE06), B3LYP, LC_PBE, LC_WPBE, LRC_WPBE, LRC_WPBEH, CAM_PBEH, WP22, CWP22, MULLER (equivalent with POWER)
+  - Hybrid meta-GGA functionals
+    - SCAN0 (require LIBXC)
+
+   The other way is only available when ***compiling with LIBXC***, and it allows for supplying exchange-correlation functionals as combinations of LIBXC keywords for functional components, joined by a plus sign, for example, dft_functional='LDA_X_1D_EXPONENTIAL+LDA_C_1D_CSC'. The list of LIBXC keywords can be found on its [website](https://libxc.gitlab.io/functionals/). In this way, **we support all the LDA,GGA and mGGA functionals provided by LIBXC**. Some popular functionals and their usage are: RPBE of [Hammer et al.](https://journals.aps.org/prb/abstract/10.1103/PhysRevB.59.7413), set `dft_functional` to 'GGA_X_RPBE+GGA_C_PBE', and [r$^{2}$SCAN](https://pubs.acs.org/doi/10.1021/acs.jpclett.0c02405), set `dft_functional` to 'MGGA_X_R2SCAN+MGGA_C_R2SCAN'.
 
   Furthermore, the old INPUT parameter exx_hybrid_type for hybrid functionals has been absorbed into dft_functional. Options are `hf` (pure Hartree-Fock), `pbe0`(PBE0), `hse` (Note: in order to use HSE functional, LIBXC is required). Note also that HSE has been tested while PBE0 has NOT been fully tested yet, and the maximum CPU cores for running exx in parallel is $N(N+1)/2$, with N being the number of atoms.
 
@@ -1488,15 +1504,20 @@ These variables are used to control the geometry relaxation.
 
 ### relax_method
 
-- **Type**: String
+- **Type**: Vector of string
 - **Description**: The methods to do geometry optimization.
+  the first element:
   - cg: using the conjugate gradient (CG) algorithm. Note that there are two implementations of the conjugate gradient (CG) method, see [relax_new](#relax_new).
-  - bfgs: using the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm.
-  - bfgs_trad: using the traditional Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm.
+  - bfgs : using the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm.
+  - lbfgs: using the Limited-memory Broyden–Fletcher–Goldfarb–Shanno (LBFGS) algorithm.
   - cg_bfgs: using the CG method for the initial steps, and switching to BFGS method when the force convergence is smaller than [relax_cg_thr](#relax_cg_thr).
   - sd: using the steepest descent (SD) algorithm.
   - fire: the Fast Inertial Relaxation Engine method (FIRE), a kind of molecular-dynamics-based relaxation algorithm, is implemented in the molecular dynamics (MD) module. The algorithm can be used by setting [calculation](#calculation) to `md` and [md_type](#md_type) to `fire`. Also ionic velocities should be set in this case. See [fire](../md.md#fire) for more details.
-- **Default**: cg
+
+  the second element:
+  when the first element is bfgs, if the second parameter is 1, it indicates the use of the new BFGS algorithm; if the second parameter is not 1, it indicates the use of the old BFGS algorithm.
+- **Default**: cg 1
+- **Note**:In the 3.10-LTS version, the type of this parameter is std::string. It can be set to "cg","bfgs","cg_bfgs","bfgs_trad","lbfgs","sd","fire".
 
 ### relax_new
 
@@ -1823,14 +1844,6 @@ These variables are used to control the output of properties.
 - **Description**: Whether to output structure files per ionic step in geometry relaxation calculations into `OUT.${suffix}/STRU_ION${istep}_D`, where `${istep}` is the ionic step.
 - **Default**: False
 
-### out_bandgap
-
-- **Type**: Boolean
-- **Description**: Whether to print the bandgap per electronic iteration into `OUT.${suffix}/running_${calculation}.log`. The value of bandgaps can be obtained by searching for the keyword:
-  - [nupdown](#nupdown) > 0: `E_bandgap_up` and `E_bandgap_dw`
-  - [nupdown](#nupdown) = 0: `E_bandgap`
-- **Default**: False
-
 ### out_level
 
 - **Type**: String
@@ -2298,7 +2311,7 @@ Warning: this function is not robust enough for the current version. Please try
   - 0: Don't include bandgap label
   - 1: Include target bandgap label (see [deepks\_band\_range](#deepks_band_range) for more details)
   - 2: Include multiple bandgap label (see [deepks\_band\_range](#deepks_band_range) for more details)
-  - 3: For systems containing H atoms only, HOMO is defined as the max occupation expect H atoms and the bandgap label is the energy between HOMO and (HOMO + 1)
+  - 3: Used for systems containing H atoms. Here HOMO is defined as the max occupation except H atoms and the bandgap label is the energy between HOMO and (HOMO + 1)
 - **Default**: 0
 
 ### deepks_band_range
@@ -2730,6 +2743,25 @@ Warning: this function is not robust enough for the current version. Please try
 
 [back to top](#full-list-of-input-keywords)
 
+## TDOFDFT: time dependent orbital free density functional theory
+
+### of_cd
+
+- **Type**: Boolean
+- **Availability**: TDOFDFT
+- **Type**: Boolean
+- **Description**: Added the current dependent(CD) potential. (https://doi.org/10.1103/PhysRevB.98.144302)
+  - True: Added the CD potential.
+  - False: Not added the CD potential.
+- **Default**: False
+
+### of_mcd_alpha
+
+- **Type**: Real
+- **Availability**: TDOFDFT
+- **Description**: The value of the parameter alpha in modified CD potential method. mCDPotenial=alpha*CDPotenial(proposed in paper PhysRevB.98.144302)
+- **Default**: 1.0
+
 ## Electric field and dipole correction
 
 These variables are relevant to electric field and dipole correction

docs/advanced/interface/TB2J.md

@@ -66,7 +66,6 @@ out_mul                        1
 #Parameters (4.Relaxation)
 ks_solver                      genelpa
 scf_nmax                       200
-out_bandgap                    0
 
 #Parameters (5.LCAO)
 basis_type                     lcao

examples/03_spin_polarized/ATOM/INPUT

@@ -46,7 +46,6 @@ cal_force          1
 cal_stress         1
 out_stru           1  # print STRU in OUT
 out_chg            0  # print CHG or not
-out_bandgap        1  # if bandgap and mul out, chg will out
 out_mul            1  # print Mulliken charge and mag of atom in mulliken.txt
 # out_wfc_lcao       1
 # out_interval       1

examples/19_dftu/NiO/INPUT

@@ -28,7 +28,6 @@ dft_plus_u    1
 orbital_corr    2 2 -1
 hubbard_u    5.0 5.0 0.0
 
-out_bandgap 1
 out_chg 1
 out_mul 1
 

examples/relax/lcao_output/INPUT

@@ -40,4 +40,3 @@ out_band        0
 out_stru        0
 out_app_flag    0
 
-out_interval    1

examples/relax/pw_output/INPUT

@@ -37,7 +37,6 @@ out_dos         1  # dos.txt g
 out_elf         1  # elf.txt
 out_band        1  # eig.txt
 out_stru        1  # g
-out_bandgap     1
 
 out_app_flag    0
 

python/pyabacus/CONTRIBUTING.md

@@ -189,7 +189,7 @@ list(APPEND _diago
     ${HSOLVER_PATH}/diago_david.cpp
     ${HSOLVER_PATH}/diag_const_nums.cpp
     ${HSOLVER_PATH}/diago_iter_assist.cpp
-    ${HSOLVER_PATH}/kernels/dngvd_op.cpp
+    ${HSOLVER_PATH}/kernels/hegvd_op.cpp
     ${HSOLVER_PATH}/kernels/bpcg_kernel_op.cpp
     ${BASE_PATH}/kernels/math_kernel_op.cpp
     ${BASE_PATH}/kernels/math_kernel_op_vec.cpp

python/pyabacus/src/hsolver/py_diago_cg.hpp

@@ -145,7 +145,7 @@ class PyDiagoCG
             std::copy(hpsi_ptr, hpsi_ptr + nvec * ld_psi, hpsi_out.data<std::complex<double>>());
         };
 
-        auto subspace_func = [] (const ct::Tensor& psi_in, ct::Tensor& psi_out) { /*do nothing*/ };
+        auto subspace_func = [](const ct::Tensor& psi_in, ct::Tensor& psi_out, const bool S_orth) { /*do nothing*/ };
 
         auto spsi_func = [this] (const ct::Tensor& psi_in, ct::Tensor& spsi_out) {
             const auto ndim = psi_in.shape().ndim();