MPI_TYPE_LB(3)

📦
version 5.0.11 · 17 versions
, in arch rolling

💅 MPI_TYPE_LB(3) — Open MPI, bestie edition 🎀

Okay so real talk: this is the MPI_Type_lb page from the Open MPI manual, section 3. And it does exactly one thing — hands you the lower bound of a datatype — but it's been deprecated since MPI-2, so consider this your ✨vintage✨ era. Let's get into it.

🌸 NAME 🌸

MPI_Type_lb — returns the lower bound of a datatype. And listen, bestie: this routine is deprecated in favor of MPI_Type_get_extent. Like, it still works, but it's giving "using the aux cord in 2026." iykyk.

✨ SYNTAX ✨

💖 C Syntax

#include <mpi.h>

int MPI_Type_lb(MPI_Datatype datatype, MPI_Aint *displacement)

🦋 Fortran Syntax

USE MPI
! or the older form: INCLUDE 'mpif.h'

MPI_TYPE_LB(DATATYPE, DISPLACEMENT, IERROR)
     INTEGER DATATYPE, DISPLACEMENT, IERROR

🍓 INPUT PARAMETER 🍓

  • datatype — the datatype handle. That's it, that's the whole input. Slay.

🎀 OUTPUT PARAMETERS 🎀

  • displacement — how far the lower bound sits from the origin, in bytes (an integer, no cap).
  • ierror — Fortran only: the error status (integer).

👑 DESCRIPTION 👑

🚨 PSA time: using this routine is deprecated as of MPI-2. Please use MPI_Type_get_extent instead. I'm not mad, I'm just disappointed. 💀

So MPI_Type_lb returns the lower bound of a datatype. It might not be zero — it'll differ from zero if the type was constructed using MPI_LB. Not a typo, not a glitch, it's the vibe.

The "pseudo-datatypes," MPI_LB and MPI_UB, can be used, respectively, to mark the lower bound (or the upper bound) of a datatype. These pseudo-datatypes occupy no space — extent (MPI_LB) = extent (MPI_UB) =0. (Yes, that's how the original writes it, and yes I'm keeping it exactly like that, bestie. ✍️) They don't affect the size or count of a datatype, and they don't affect the context of a message created with this datatype. But — and this is the plot twist — they do affect the definition of the extent of a datatype, and therefore they affect the outcome of a replication of this datatype by a datatype constructor. Main character behavior, honestly.

In general, if

Typemap = {(type0, disp0), ..., (type(n-1), disp(n-1)}

then the lower bound of Typemap is defined to be

                  (min(j) disp(j)                          if no entry has
    lb(Typemap) = (                                        basic type lb
                  (min(j) {disp(j) such that type(j) = lb} otherwise

Similarly, the upper bound of Typemap is defined to be

                      (max(j) disp(j) + sizeof((type(j)) + e   if no entry has
        ub(Typemap) = (                                        basic type ub
                      (max(j) {disp(j) such that type(j) = ub} otherwise

Then

    extent(Typemap) = ub(Typemap) - lb(Typemap)

If type(i) requires alignment to a byte address that is a multiple of k(i), then e is the least nonnegative increment needed to round extent(Typemap) to the next multiple of max(i) k(i). Math ate, no crumbs. 🔥

😭 ERRORS 😭

Almost all MPI routines return an error value — C routines as the return result of the function, and Fortran routines in the last argument. (Fortran girlies, check that last slot. 🫶)

Before the error value is returned, the current MPI error handler associated with the communication object (e.g., communicator, window, file) is called. If no communication object is associated with the MPI call, then the call is considered attached to MPI_COMM_SELF and will call the associated MPI error handler. When MPI_COMM_SELF is not initialized (i.e., before MPI_Init/MPI_Init_thread, after MPI_Finalize, or when using the Sessions Model exclusively) the error raises the initial error handler. The initial error handler can be changed by calling MPI_Comm_set_errhandler on MPI_COMM_SELF when using the World model, or the mpi_initial_errhandler CLI argument to mpiexec or info key to MPI_Comm_spawn/MPI_Comm_spawn_multiple. If no other appropriate error handler has been set, then the MPI_ERRORS_RETURN error handler is called for MPI I/O functions and the MPI_ERRORS_ABORT error handler is called for all other MPI functions.

Open MPI includes three predefined error handlers that can be used:

  • MPI_ERRORS_ARE_FATAL — causes the program to abort all connected MPI processes. Not a drill. 💀
  • MPI_ERRORS_ABORT — an error handler that can be invoked on a communicator, window, file, or session. When called on a communicator, it acts as if MPI_Abort was called on that communicator. If called on a window or file, it acts as if MPI_Abort was called on a communicator containing the group of processes in the corresponding window or file. If called on a session, it aborts only the local process.
  • MPI_ERRORS_RETURN — returns an error code to the application. The chill one.

MPI applications can also implement their own error handlers by calling:

  • MPI_Comm_create_errhandler then MPI_Comm_set_errhandler
  • MPI_File_create_errhandler then MPI_File_set_errhandler
  • MPI_Session_create_errhandler then MPI_Session_set_errhandler or at MPI_Session_init
  • MPI_Win_create_errhandler then MPI_Win_set_errhandler
⚠️ Note that MPI does not guarantee that an MPI program can continue past an error. So like… don't bet on it. 🙈

See the MPI man page for a full list of MPI error codes.

See the Error Handling section of the MPI-3.1 standard for more information.

🔍 SEE ALSO 🔍

  • MPI_Type_get_extent — the glow-up replacement. Go use this one, bestie. 💖

2003-2026, The Open MPI Community

And that's the whole page, bestie! ✨ Signing off from Open MPI, dated Sep 11, 2026 — MPI_TYPE_LB(3), out. 💅🎀🦋

📦 where this page comes from