1: #pragma once

  3: /* MANSEC = Vec */
  4: /* SUBMANSEC = IS */

  6: /*S
  7:    IS - Abstract PETSc object used for efficient indexing into vector and matrices

  9:    Level: beginner

 11: .seealso: `ISType`, `ISCreateGeneral()`, `ISCreateBlock()`, `ISCreateStride()`, `ISGetIndices()`, `ISDestroy()`
 12: S*/
 13: typedef struct _p_IS *IS;

 15: /*S
 16:    ISLocalToGlobalMapping - mappings from a
 17:    local ordering (on individual MPI processes) of 0 to n-1 to a global PETSc ordering (across collections of MPI processes)
 18:    used by a vector or matrix.

 20:    Level: intermediate

 22:    Note:
 23:    Mapping from local to global is scalable; but global
 24:    to local may not be if the range of global values represented locally
 25:    is very large. `ISLocalToGlobalMappingType` provides alternative ways of efficiently applying `ISGlobalToLocalMappingApply()

 27:    Developer Note:
 28:    `ISLocalToGlobalMapping` is actually a private object; it is included
 29:    here for the inline function `ISLocalToGlobalMappingApply()` to allow it to be inlined since
 30:    it is used so often.

 32: .seealso: `ISLocalToGlobalMappingCreate()`, `ISLocalToGlobalMappingApply()`, `ISLocalToGlobalMappingDestroy()`, `ISGlobalToLocalMappingApply()`
 33: S*/
 34: typedef struct _p_ISLocalToGlobalMapping *ISLocalToGlobalMapping;

 36: /*S
 37:    ISColoring - sets of `IS`s that define a coloring of something, such as a graph defined by a sparse matrix

 39:    Level: intermediate

 41:    Notes:
 42:    One should not access the *is records below directly because they may not yet
 43:    have been created. One should use `ISColoringGetIS()` to make sure they are
 44:    created when needed.

 46:    When the coloring type is `IS_COLORING_LOCAL` the coloring is in the local ordering of the unknowns.
 47:    That is the matching the local (ghosted) vector; a local to global mapping must be applied to map
 48:    them to the global ordering.

 50:    Developer Note:
 51:    This is not a `PetscObject`

 53: .seealso: `IS`, `MatColoringCreate()`, `MatColoring`, `ISColoringCreate()`, `ISColoringGetIS()`, `ISColoringView()`
 54: S*/
 55: typedef struct _n_ISColoring *ISColoring;

 57: /*S
 58:    PetscLayout - defines layout of vectors and matrices (that is the "global" numbering of vector and matrix entries) across MPI processes (which rows are owned by which processes)

 60:    Level: developer

 62:    Notes:
 63:    PETSc vectors (`Vec`) have a global number associated with each vector entry. The first MPI process that shares the vector owns the first `n0` entries of the vector,
 64:    the second MPI process the next `n1` entries, etc. A `PetscLayout` is a way of managing this information, for example the number of locally owned entries is provided
 65:    by `PetscLayoutGetLocalSize()` and the range of indices for a given MPI process is provided by `PetscLayoutGetRange()`.

 67:    Each PETSc `Vec` contains a `PetscLayout` object which can be obtained with `VecGetLayout()`. For convenience `Vec` provides an API to access the layout information directly,
 68:    for example with `VecGetLocalSize()` and `VecGetOwnershipRange()`.

 70:    Similarly PETSc matrices have layouts, these are discussed in [](ch_matrices).

 72: .seealso: `PetscLayoutCreate()`, `PetscLayoutDestroy()`, `PetscLayoutGetRange()`, `PetscLayoutGetLocalSize()`, `PetscLayoutGetSize()`,
 73:           `PetscLayoutGetBlockSize()`, `PetscLayoutGetRanges()`, `PetscLayoutFindOwner()`,  `PetscLayoutFindOwnerIndex()`,
 74:           `VecGetLayout()`, `VecGetLocalSize()`, `VecGetOwnershipRange()`
 75: S*/
 76: typedef struct _n_PetscLayout *PetscLayout;