Wrote profile results to testing.py.lprof
Timer unit: 1e-06 s

Total time: 34.5321 s
File: /home/vetschn/src/python/qttools/src/qttools/datastructures/dbcsr.py
Function: from_coo at line 99

Line #      Hits         Time  Per Hit   % Time  Line Contents
==============================================================
    99                                               @profile
   100                                               @classmethod
   101                                               def from_coo(
   102                                                   cls,
   103                                                   coo: sps.coo_array,
   104                                                   block_sizes: np.ndarray,
   105                                                   stackshape: int | tuple,
   106                                               ) -> "DBCSR":
   107                                                   """Converts a coo matrix to a DBCSR matrix."""
   108                                                   # Sort the data by block-row and -column
   109         1        114.3    114.3      0.0          block_offsets = np.hstack(([0], np.cumsum(block_sizes)))
   110         1          0.6      0.6      0.0          num_blocks = len(block_sizes)
   111                                           
   112         1          0.2      0.2      0.0          rowptr_map = {}
   113                                           
   114         1          0.5      0.5      0.0          if isinstance(stackshape, int):
   115         1          0.2      0.2      0.0              stackshape = (stackshape,)
   116                                           
   117         1         20.3     20.3      0.0          data = np.zeros(stackshape + (coo.nnz,), dtype=coo.data.dtype)
   118         1          7.3      7.3      0.0          cols = np.zeros(coo.nnz, dtype=int)
   119                                           
   120         1          0.2      0.2      0.0          offset = 0
   121       401       2818.3      7.0      0.0          for i, j in np.ndindex(num_blocks, num_blocks):
   122       400      88299.0    220.7      0.3              inds = (
   123      1600    3474326.6   2171.5     10.1                  (block_offsets[i] <= coo.row)
   124       400    1751373.5   4378.4      5.1                  & (coo.row < block_offsets[i + 1])
   125       400    1479619.0   3699.0      4.3                  & (block_offsets[j] <= coo.col)
   126       400    1477859.1   3694.6      4.3                  & (coo.col < block_offsets[j + 1])
   127                                                       )
   128       400    2309967.2   5774.9      6.7              bnnz = np.sum(inds)
   129                                           
   130       400        657.4      1.6      0.0              if bnnz == 0:
   131                                                           continue
   132                                           
   133       400     677820.4   1694.6      2.0              data[..., offset : offset + bnnz] = coo.data[inds]
   134       400     537833.3   1344.6      1.6              cols[offset : offset + bnnz] = coo.col[inds]
   135                                           
   136       400       2443.4      6.1      0.0              rowptr = np.zeros(block_sizes[i] + 1, dtype=int)
   137  10000400    3166637.5      0.3      9.2              for row in coo.row[inds] - block_offsets[i]:
   138  10000000   19548554.5      2.0     56.6                  rowptr[row + 1] += 1
   139       400      12770.2     31.9      0.0              rowptr = np.cumsum(rowptr) + offset
   140       400        570.7      1.4      0.0              rowptr_map[(i, j)] = rowptr
   141                                           
   142       400        448.8      1.1      0.0              offset += bnnz
   143                                           
   144         1          5.4      5.4      0.0          return cls(data, cols, rowptr_map, block_sizes)

Total time: 48.8996 s
File: testing.py
Function: main at line 8

Line #      Hits         Time  Per Hit   % Time  Line Contents
==============================================================
     8                                           @profile
     9                                           def main():
    10                                           
    11         1    4131500.0    4e+06      8.4      coo = sps.random(10000, 10000, density=0.1, format="coo")
    12                                               # coo.data = np.arange(coo.nnz)
    13                                           
    14         1    3211805.7    3e+06      6.6      inds = np.lexsort((coo.col, coo.row))
    15         1     109128.4 109128.4      0.2      coo.row = coo.row[inds]
    16         1      98638.5  98638.5      0.2      coo.col = coo.col[inds]
    17                                           
    18         1   41348481.2    4e+07     84.6      dbcsr = DBCSR.from_coo(coo, [500] * 20, 10)
    19                                               # eye = DBCSR.from_coo(eye, [5]*200, 100)