Merge branch 'develop' into rdmft-egrad, still with conflicts in blas/lapack

Author: Kai Luo

.github/workflows/pytest.yml

@@ -13,7 +13,7 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v5
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
             python-version: 3.8
       - name: Build Pyabacus

.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: |
@@ -126,12 +132,12 @@ jobs:
         run: |
           cmake --build build --target test ARGS="-V --timeout 1700 -R 03_NAO_multik"
 
-      - name: 04_LJ_DP Test
+      - name: 04_FF Test
         env:
           GTEST_COLOR: 'yes'
           OMP_NUM_THREADS: '2'
         run: |
-          cmake --build build --target test ARGS="-V --timeout 1700 -R 04_LJ_DP"
+          cmake --build build --target test ARGS="-V --timeout 1700 -R 04_FF"
 
       - name: 05_rtTDDFT Test
         env:
@@ -180,4 +186,4 @@ jobs:
           GTEST_COLOR: 'yes'
           OMP_NUM_THREADS: '2'
         run: |
-          cmake --build build --target test ARGS="-V --timeout 1700 -E 'integrate_test|01_PW|02_NAO_Gamma|03_NAO_multik|04_LJ_DP|05_rtTDDFT|06_SDFT|07_OFDFT|08_EXX|09_DeePKS|10_others|11_PW_GPU|12_NAO_Gamma_GPU|13_NAO_multik_GPU|15_rtTDDFT_GPU|16_SDFT_GPU|MODULE_BASE|MODULE_IO|MODULE_HSOLVER|MODULE_CELL|MODULE_MD|source_psi|MODULE_RI'"
+          cmake --build build --target test ARGS="-V --timeout 1700 -E 'integrate_test|01_PW|02_NAO_Gamma|03_NAO_multik|04_FF|05_rtTDDFT|06_SDFT|07_OFDFT|08_EXX|09_DeePKS|10_others|11_PW_GPU|12_NAO_Gamma_GPU|13_NAO_multik_GPU|15_rtTDDFT_GPU|16_SDFT_GPU|MODULE_BASE|MODULE_IO|MODULE_HSOLVER|MODULE_CELL|MODULE_MD|source_psi|MODULE_RI'"

CMakeLists.txt

@@ -290,7 +290,7 @@ if (USE_SW)
   set(SW ON)
   include_directories(${SW_MATH}/include)
   include_directories(${SW_FFT}/include)
-  
+
   target_link_libraries(${ABACUS_BIN_NAME} ${SW_FFT}/lib/libfftw3.a)
   target_link_libraries(${ABACUS_BIN_NAME} ${SW_MATH}/libswfft.a)
   target_link_libraries(${ABACUS_BIN_NAME} ${SW_MATH}/libswscalapack.a)
@@ -376,6 +376,7 @@ if(USE_CUDA)
   if(USE_CUDA)
     add_compile_definitions(__CUDA)
     add_compile_definitions(__UT_USE_CUDA)
+    target_compile_definitions(${ABACUS_BIN_NAME} PRIVATE __USE_NVTX)
     if (CMAKE_BUILD_TYPE STREQUAL "Debug")
       set(CMAKE_CUDA_FLAGS_DEBUG "${CMAKE_CUDA_FLAGS_DEBUG} -g -G" CACHE STRING "CUDA flags for debug build" FORCE)
     endif()
@@ -482,9 +483,13 @@ else()
   find_package(FFTW3 REQUIRED)
   find_package(Lapack REQUIRED)
   include_directories(${FFTW3_INCLUDE_DIRS})
-  list(APPEND math_libs FFTW3::FFTW3 LAPACKE::LAPACKE LAPACK::LAPACK BLAS::BLAS)
+  list(APPEND math_libs FFTW3::FFTW3 LAPACK::LAPACK BLAS::BLAS)
+if(USE_DSP)
+  target_link_libraries(${ABACUS_BIN_NAME} ${SCALAPACK_LIBRARY_DIR})
+else()
   find_package(ScaLAPACK REQUIRED)
   list(APPEND math_libs ScaLAPACK::ScaLAPACK)
+endif()
   if(USE_OPENMP)
     list(APPEND math_libs FFTW3::FFTW3_OMP)
   endif()
@@ -523,7 +528,7 @@ if(ENABLE_MLALGO)
     include_directories(${libnpy_INCLUDE_DIR})
   endif()
   include_directories(${libnpy_SOURCE_DIR}/include)
-  
+
   add_compile_definitions(__MLALGO)
 endif()
 
@@ -563,7 +568,7 @@ if (ENABLE_CNPY)
     include_directories(${cnpy_INCLUDE_DIR})
   endif()
   include_directories(${cnpy_SOURCE_DIR})
-  
+
   # find ZLIB and link
   find_package(ZLIB REQUIRED)
   target_link_libraries(${ABACUS_BIN_NAME} cnpy ZLIB::ZLIB)
@@ -652,6 +657,15 @@ if(DEFINED DeePMD_DIR)
   endif()
 endif()
 
+if(DEFINED NEP_DIR)
+  find_package(NEP REQUIRED)
+
+  if(NEP_FOUND)
+    add_compile_definitions(__NEP)
+    target_link_libraries(${ABACUS_BIN_NAME} NEP::nep)
+  endif()
+endif()
+
 if(DEFINED TensorFlow_DIR)
   find_package(TensorFlow REQUIRED)
   include_directories(${TensorFlow_DIR}/include)

cmake/FindNEP.cmake

@@ -0,0 +1,49 @@
+###############################################################################
+# - Find NEP
+# Finds the NEP header and library.
+#
+# This module will search for the NEP library, looking for a hint
+# from the NEP_DIR environment variable or CMake variable.
+#
+# This module defines the following variables:
+#
+#  NEP_FOUND        - True if the NEP library and headers were found.
+#  NEP_INCLUDE_DIR  - The directory where nep.h is located.
+#  NEP_LIBRARY      - The full path to the NEP library.
+#
+# It also defines the following imported target:
+#
+#  NEP::nep     - The NEP library target.
+#
+###############################################################################
+# Note: Currently only CPU version is supported, Since the NEP interface with GPU support is not available yet.
+#       In feature, if available, we can use USE_CUDA to switch between CPU and GPU version.
+
+find_path(NEP_INCLUDE_DIR nep.h
+    HINTS ${NEP_DIR}
+    PATH_SUFFIXES "include"
+    )
+
+find_library(NEP_LIBRARY
+    NAMES nep
+    HINTS ${NEP_DIR}
+    PATH_SUFFIXES "lib"
+    )
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(NEP
+    DEFAULT_MSG
+    NEP_LIBRARY NEP_INCLUDE_DIR)
+
+if(NEP_FOUND)
+    if(NOT TARGET NEP::nep)
+        add_library(NEP::nep UNKNOWN IMPORTED)
+        set_target_properties(NEP::nep PROPERTIES
+            IMPORTED_LINK_INTERFACE_LANGUAGES "C"
+            IMPORTED_LOCATION "${NEP_LIBRARY}"
+            INTERFACE_INCLUDE_DIRECTORIES "${NEP_INCLUDE_DIR}"
+        )
+    endif()
+endif()
+
+mark_as_advanced(NEP_INCLUDE_DIR NEP_LIBRARY)

docs/advanced/elec_properties/Mulliken.md

@@ -1,7 +1,7 @@
 # Mulliken Charge Analysis
 
 From version 2.1.0, ABACUS has the function of Mulliken population analysis. The example can be found in [examples/mulliken](https://github.com/deepmodeling/abacus-develop/tree/develop/examples/mulliken). \
-To use this function, set [out_mul](./input-main.md#out_mul) to `1` in the INPUT file. After calculation, there will be an output file named `mulliken.txt` in the output directory. In MD calculations, the output interval is controlled by the keyword [out_interval](./input-main.md#out_interval). In the file, there are contents like (`nspin 1`):
+To use this function, set [out_mul](./input-main.md#out_mul) to `1` in the INPUT file. After calculation, there will be an output file named `mulliken.txt` in the output directory. In MD calculations, the output interval is controlled by the keyword [out_freq_ion](./input-main.md#out_freq_ion). In the file, there are contents like (`nspin 1`):
 
 ```
 STEP: 0

docs/advanced/elec_properties/hs_matrix.md

@@ -45,7 +45,7 @@ The CSR format stores a sparse m × n matrix M in row form using three (one-dime
   - The arrays V and COL_INDEX are of length NNZ, and contain the non-zero values and the column indices of those values respectively.
   - The array ROW_INDEX is of length m + 1 and encodes the index in V and COL_INDEX where the given row starts. This is equivalent to ROW_INDEX[j] encoding the total number of nonzeros above row j. The last element is NNZ , i.e., the fictitious index in V immediately after the last valid index NNZ - 1.
 
-For calculations involving ionic movements, the output frequency of the matrix is controlled by [out_interval](../input_files/input-main.md#out_interval) and [out_app_flag](../input_files/input-main.md#out_app_flag). 
+For calculations involving ionic movements, the output frequency of the matrix is controlled by [out_freq_ion](../input_files/input-main.md#out_freq_ion) and [out_app_flag](../input_files/input-main.md#out_app_flag). 
 
 ## get_s
 We also offer the option of only calculating the overlap matrix without running SCF. For that purpose, in `INPUT` file we need to set the value keyword [calculation](../input_files/input-main.md#calculation) to be `get_s`.

docs/advanced/elec_properties/position_matrix.md

@@ -18,7 +18,7 @@ Each file or each section of the appended file starts with "STEP: " followed by
 
 Each block here contains the matrix for the corresponding cell. There are three columns in each block, giving the matrix elements in x, y, z directions, respectively. There are altogether nbasis * nbasis lines in each block, which emulates the matrix elements.
 
-In molecular dynamics (MD) calculations, if [out_app_flag](../input_files/input-main.md#out_app_flag) is set to true, then `data-rR-tr` is written in an append manner. Otherwise, output files will be put in a separate directory, `matrix`, and named as `$x`_data-rR-tr, where `$x` is the number of MD step. In addition, the output frequency is controlled by [out_interval](../input_files/input-main.md#out_interval). For example, if we are running a 10-step MD with out_interval = 3, then `$x` will be 0, 3, 6, and 9.
+In molecular dynamics (MD) calculations, if [out_app_flag](../input_files/input-main.md#out_app_flag) is set to true, then `data-rR-tr` is written in an append manner. Otherwise, output files will be put in a separate directory, `matrix`, and named as `$x`_data-rR-tr, where `$x` is the number of MD step. In addition, the output frequency is controlled by [out_freq_ion](../input_files/input-main.md#out_freq_ion). For example, if we are running a 10-step MD with out_freq_ion = 3, then `$x` will be 0, 3, 6, and 9.
 
 ## get_s
 We also offer the option of only calculating the position matrix without running SCF. For that purpose, in `INPUT` file we need to set the keyword [calculation](../input_files/input-main.md#calculation) to `get_s`, and [out_mat_r](../input_files/input-main.md#out_mat_r) to `true`.