Constants(3) · carta

Data types

Note that the Fortran types should only be used in Fortran programs, and the C types should only be used in C programs. For example, it is in error to use MPI_INT for a Fortran INTEGER. Datatypes are of type MPI_Datatype in C, type INTEGER in Fortran, and Type(MPI_Datatype) in Fortran08

C datatypes

MPI_CHAR: - char

MPI_SIGNED_CHAR: - signed char

MPI_UNSIGNED_CHAR: - unsigned char

MPI_BYTE: - See standard; like unsigned char

MPI_WCHAR: - wide character (wchar_t)

MPI_SHORT: - short

MPI_UNSIGNED_SHORT: - unsigned short

MPI_INT: - int

MPI_UNSIGNED: - unsigned int

MPI_LONG: - long

MPI_UNSIGNED_LONG: - unsigned long

MPI_LONG_LONG_INT: - long long

MPI_LONG_LONG: - synonyn for MPI_LONG_LONG_INT

MPI_UNSIGNED_LONG_LONG: - unsigned long long

MPI_FLOAT: - float

MPI_DOUBLE: - double

MPI_LONG_DOUBLE: - long double (some systems may not implement this)

MPI_INT8_T: - int8_t

MPI_INT16_T: - int16_t

MPI_INT32_T: - int32_t

MPI_INT64_T: - int64_t

MPI_UINT8_T: - uint8_t

MPI_UINT16_T: - uint16_t

MPI_UINT32_T: - uint32_t

MPI_UINT64_T: - uint64_t

MPI_C_BOOL: - _Bool

MPI_C_FLOAT_COMPLEX: - float _Complex

MPI_C_COMPLEX: - float _Complex

MPI_C_DOUBLE_COMPLEX: - double _Complex

MPI_C_LONG_DOUBLE_COMPLEX

- long double _Complex

The following are datatypes for the MPI functions MPI_MAXLOC and MPI_MINLOC .

MPI_FLOAT_INT: - struct { float, int }

MPI_LONG_INT: - struct { long, int }

MPI_DOUBLE_INT: - struct { double, int }

MPI_SHORT_INT: - struct { short, int }

MPI_2INT: - struct { int, int }

MPI_LONG_DOUBLE_INT

- struct { long double, int } ; this is an optional type, and may be set to MPI_DATATYPE_NULL

Special datatypes for C and Fortran

MPI_PACKED: - For MPI_Pack and MPI_Unpack

MPI_UB: - For MPI_Type_struct ; an upper-bound indicator. Removed in MPI 3

MPI_LB: - For MPI_Type_struct ; a lower-bound indicator. Removed in MPI 3

Fortran datatypes

MPI_REAL: - REAL

MPI_INTEGER: - INTEGER

MPI_LOGICAL: - LOGICAL

MPI_DOUBLE_PRECISION: - DOUBLE PRECISION

MPI_COMPLEX: - COMPLEX

MPI_DOUBLE_COMPLEX

- complex*16 (or complex*32 ) where supported.

The following datatypes are optional

MPI_INTEGER1: - integer*1 if supported

MPI_INTEGER2: - integer*2 if supported

MPI_INTEGER4: - integer*4 if supported

MPI_INTEGER8: - integer*8 if supported

MPI_INTEGER16: - integer*16 if supported

MPI_REAL4: - real*4 if supported

MPI_REAL8: - real*8 if supported

MPI_REAL16: - real*16 if supported

MPI_COMPLEX8: - complex*8 if supported

MPI_COMPLEX16: - complex*16 if supported

MPI_COMPLEX32

- complex*32 if supported

The following are datatypes for the MPI functions MPI_MAXLOC and MPI_MINLOC . In Fortran, these datatype always consist of two elements of the same Fortran type.

MPI_2INTEGER: - INTEGER,INTEGER

MPI_2REAL: - REAL, REAL

MPI_2DOUBLE_PRECISION

- DOUBLE PRECISION, DOUBLE PRECISION

MPI Datatypes for MPI Types

MPI_AINT: - Datatype for an MPI_Aint

MPI_OFFSET: - Datatype for an MPI_Offset

MPI_COUNT: - Datatype for an MPI_Count

Mpi datatype combiner names

`MPI_COMBINER_NAMED`	- a named predefined datatype
`MPI_COMBINER_DUP`	- MPI_TYPE_DUP
`MPI_COMBINER_CONTIGUOUS`	- MPI_TYPE_CONTIGUOUS
`MPI_COMBINER_VECTOR`	- MPI_TYPE_VECTOR
`MPI_COMBINER_HVECTOR_INTEGER`	- Removed in MPI-3
`MPI_COMBINER_HVECTOR`	- MPI_TYPE_CREATE_HVECTOR
`MPI_COMBINER_INDEXED`	- MPI_TYPE_INDEXED
`MPI_COMBINER_HINDEXED_INTEGER`	- Removed in MPI-3
`MPI_COMBINER_HINDEXED`	- MPI_TYPE_CREATE_HINDEXED
`MPI_COMBINER_INDEXED_BLOCK`	- MPI_TYPE_CREATE_INDEXED_BLOCK
`MPI_COMBINER_STRUCT_INTEGER`	- Removed in MPI-3
`MPI_COMBINER_STRUCT`	- MPI_TYPE_CREATE_STRUCT
`MPI_COMBINER_SUBARRAY`	- MPI_TYPE_CREATE_SUBARRAY
`MPI_COMBINER_DARRAY`	- MPI_TYPE_CREATE_DARRAY
`MPI_COMBINER_F90_REAL`	- MPI_TYPE_CREATE_F90_REAL
`MPI_COMBINER_F90_COMPLEX`	- MPI_TYPE_CREATE_F90_COMPLEX
`MPI_COMBINER_F90_INTEGER`	- MPI_TYPE_CREATE_F90_INTEGER
`MPI_COMBINER_RESIZED`	- MPI_TYPE_CREATE_RESIZED
`MPI_COMBINER_HINDEXED_BLOCK`	- MPI_TYPE_CREATE_HINDEXED_BLOCK

Mpi datatype type classes

MPI Type classes used with routines to return Fortran types with defined precision and range

`MPI_TYPECLASS_REAL`	- REAL
`MPI_TYPECLASS_INTEGER`	- INTEGER
`MPI_TYPECLASS_COMPLEX`	- COMPLEX

Mpi darray and subarray values

These values are used to create a datatype with the DARRAY and SUBARRAY constructors.

`MPI_ORDER_C`	- Row-major order (as used by C)
`MPI_ORDER_FORTRAN`	- Column-major order (as used by Fortran)
`MPI_DISTRIBUTE_BLOCK`	- Block distribution
`MPI_DISTRIBUTE_CYCLIC`	- Cyclic distribution
`MPI_DISTRIBUTE_NONE`	- This dimension is not distributed
`MPI_DISTRIBUTE_DFLT_DARG`	- Use the default distribution

Communicators

Communicators are of type MPI_Comm in C, INTEGER in Fortran, and Type(MPI_Comm) in Fortran08

`MPI_COMM_WORLD`	- Contains all of the processes
`MPI_COMM_SELF`	- Contains only the calling process

Kind of communicator for 'mpi_comm_split_type'

MPI_COMM_TYPE_SHARED: - All processes that can share memory are grouped into the same communicator.

Groups

Groups are of type MPI_Group in C, INTEGER in Fortran, and Type(MPI_Group) in Fortran08

MPI_GROUP_EMPTY: - A group containing no members.

Results of the compare operations on groups and communicators

`MPI_IDENT`	- Identical
`MPI_CONGRUENT`	- (only for MPI_COMM_COMPARE ) The groups are identical
`MPI_SIMILAR`	- Same members, but in a different order
`MPI_UNEQUAL`	- Different

Collective operations

The collective combination operations (e.g., MPI_REDUCE , MPI_ALLREDUCE , MPI_REDUCE_SCATTER , and MPI_SCAN ) take a combination operation. This operation is of type MPI_Op in C and of type INTEGER in Fortran. The predefined operations are

MPI_MAX: - return the maximum

MPI_MIN: - return the minimum

MPI_SUM: - return the sum

MPI_PROD: - return the product

MPI_LAND: - return the logical and

MPI_BAND: - return the bitwise and

MPI_LOR: - return the logical or

MPI_BOR: - return the bitwise of

MPI_LXOR: - return the logical exclusive or

MPI_BXOR: - return the bitwise exclusive or

MPI_MINLOC: - return the minimum and the location (actually, the value of the second element of the structure where the minimum of the first is found)

MPI_MAXLOC: - return the maximum and the location

MPI_REPLACE: - replace b with a

MPI_NO_OP: - perform no operation

Notes on collective operations

The reduction functions ( MPI_Op ) do not return an error value. As a result, if the functions detect an error, all they can do is either call MPI_Abort or silently skip the problem. Thus, if you change the error handler from MPI_ERRORS_ARE_FATAL to something else, for example, MPI_ERRORS_RETURN , then no error may be indicated.

The reason for this is the performance problems in ensuring that all collective routines return the same error value.

Note that not all datatypes are valid for these functions. For example, MPI_COMPLEX is not valid for MPI_MAX and MPI_MIN . In addition, the MPI 1.1 standard did not include the C types MPI_CHAR and MPI_UNSIGNED_CHAR among the lists of arithmetic types for operations like MPI_SUM . However, since the C type char is an integer type (like short ), it should have been included. The MPI Forum will probably include char and unsigned char as a clarification to MPI 1.1; until then, users are advised that MPI implementations may not accept MPI_CHAR and MPI_UNSIGNED_CHAR as valid datatypes for MPI_SUM , MPI_PROD , etc. MPICH does allow these datatypes.

Permanent key values

These are the same in C and Fortran

MPI_TAG_UB: - Largest tag value

MPI_HOST: - Rank of process that is host, if any

MPI_IO: - Rank of process that can do I/O

MPI_WTIME_IS_GLOBAL: - Has value 1 if MPI_WTIME is globally synchronized.

MPI_UNIVERSE_SIZE: - Number of available processes. See the standard for a description of limitations on this value

MPI_LASTUSEDCODE: - Last used MPI error code (check - code or class?)

MPI_APPNUM: - Application number, starting from 0. See the standard for MPI_COMM_SPAWN_MULTIPLE and mpiexec for details

Null objects

`MPI_COMM_NULL`	- Null communicator
`MPI_OP_NULL`	- Null operation
`MPI_GROUP_NULL`	- Null group
`MPI_DATATYPE_NULL`	- Null datatype
`MPI_REQUEST_NULL`	- Null request
`MPI_ERRHANDLER_NULL`	- Null error handler
`MPI_WIN_NULL`	- Null window handle
`MPI_FILE_NULL`	- Null file handle
`MPI_INFO_NULL`	- Null info handle
`MPI_MESSAGE_NULL`	- Null message handle
`MPI_ARGV_NULL`	- Empty ARGV value for spawn commands
`MPI_ARGVS_NULL`	- Empty ARGV array for spawn-multiple command
`MPI_T_ENUM_NULL`	- Null MPI_T enum
`MPI_T_CVAR_HANDLE_NULL`	- Null MPI_T control variable handle
`MPI_T_PVAR_HANDLE_NULL`	- Null MPI_T performance variable handle
`MPI_T_PVAR_SESSION_NULL`	- Null MPI_T performance variable session handle

Predefined constants

`MPI_MAX_PROCESSOR_NAME`	- Maximum length of name returned by MPI_GET_PROCESSOR_NAME
`MPI_MAX_ERROR_STRING`	- Maximum length of string return by MPI_ERROR_STRING
`MPI_MAX_LIBRARY_VERSION_STRING`	- Maximum length of string returned by MPI_GET_LIBRARY_VERSION_STRING ???
`MPI_MAX_PORT_NAME`	- Maximum length of a port
`MPI_MAX_OBJECT_NAME`	- Maximum length of an object (?)
`MPI_MAX_INFO_KEY`	- Maximum length of an info key
`MPI_MAX_INFO_VAL`	- Maximum length of an info value
`MPI_UNDEFINED`	- Used by many routines to indicated undefined or unknown integer value
`MPI_UNDEFINED_RANK`	- Unknown rank
`MPI_KEYVAL_INVALID`	- Special keyval that may be used to detect uninitialized keyvals.
`MPI_BSEND_OVERHEAD`	- Add this to the size of a MPI_BSEND buffer for each outstanding message
`MPI_PROC_NULL`	- This rank may be used to send or receive from no-one.
`MPI_ANY_SOURCE`	- In a receive, accept a message from anyone.
`MPI_ANY_TAG`	- In a receive, accept a message with any tag value.
`MPI_BOTTOM`	- May be used to indicate the bottom of the address space
`MPI_IN_PLACE`	- Special location for buffer in some collective communication routines
`MPI_VERSION`	- Numeric value of MPI version (e.g., 3)
`MPI_SUBVERSION`	- Numeric value of MPI subversion (e.g., 1)

Topology types

`MPI_CART`	- Cartesian grid
`MPI_GRAPH`	- General graph
`MPI_DIST_GRAPH`	- General distributed graph

Special values for distributed graph

`MPI_UNWEIGHTED`	- Indicates that the edges are unweighted
`MPI_WEIGHTS_EMPTY`	- Special address that indicates no array of weights information

File modes

`MPI_MODE_RDONLY`	- Read only
`MPI_MODE_RDWR`	- Read and write
`MPI_MODE_WRONLY`	- Write only
`MPI_MODE_CREATE`	- Create the file if it does not exist
`MPI_MODE_EXCL`	- It is an error if creating a file that already exists
`MPI_MODE_DELETE_ON_CLOSE`	- Delete the file on close
`MPI_MODE_UNIQUE_OPEN`	- The file will not be concurrently opened elsewhere
`MPI_MODE_APPEND`	- The initial position of all file pointers is at the end of the file
`MPI_MODE_SEQUENTIAL`	- File will only be accessed sequentially

File displacement

MPI_DISPLACEMENT_CURRENT: - Use with files opened with mode MPI_MODE_SEQUENTIAL in calls to MPI_FILE_SET_VIEW

File positioning

`MPI_SEEK_SET`	- Set the pointer to offset
`MPI_SEEK_CUR`	- Set the pointer to the current position plus offset
`MPI_SEEK_END`	- Set the pointer to the end of the file plus offset

Window attributes

`MPI_WIN_BASE`	- window base address.
`MPI_WIN_SIZE`	- window size, in bytes
`MPI_WIN_DISP_UNIT`	- displacement unit associated with the window
`MPI_WIN_CREATE_FLAVOR`	- how the window was created
`MPI_WIN_MODEL`	- memory model for window

Window flavors

`MPI_WIN_FLAVOR_CREATE`	- Window was created with MPI_WIN_CREATE.
`MPI_WIN_FLAVOR_ALLOCATE`	- Window was created with MPI_WIN_ALLOCATE.
`MPI_WIN_FLAVOR_DYNAMIC`	- Window was created with MPI_WIN_CREATE_DYNAMIC.
`MPI_WIN_FLAVOR_SHARED`	- Window was created with MPI_WIN_ALLOCATE_SHARED.

Window memory model

MPI_WIN_SEPARATE: - Separate public and private copies of window memory

MPI_WIN_UNIFIED: - The public and private copies are identical (by which we mean that updates are eventually observed without additional RMA operations)

Window lock types

`MPI_LOCK_EXCLUSIVE`	- Only one process at a time will execute accesses within the lock
`MPI_LOCK_SHARED`	- Not exclusive; multiple processes may execute accesses within the lock

Window assertions

See section 11.5 in MPI 3.1 for a detailed description of each of these assertion values.

MPI_MODE_NOCHECK: - The matching calls to MPI_WIN_POST or MPI_WIN_START have already completed, or no process holds or will attempt to acquire, a conflicting lock.

MPI_MODE_NOSTORE: - The local window has not been updated by stores since the last synchronization

MPI_MODE_NOPUT: - The local window will not be updated by put or accumulate until the next synchronization

MPI_MODE_NOPRECEDE: - The fence does not complete any locally issued RMA calls

MPI_MODE_NOSUCCEED: - The fence does not start any locally issued RMA calls

Predefined info object

MPI_INFO_ENV: - Contains the execution environment

Mpi status

The MPI_Status datatype is a structure in C. The three elements for use by programmers are

MPI_SOURCE: - Who sent the message

MPI_TAG: - What tag the message was sent with

MPI_ERROR: - Any error return (only when the error returned by the routine has error class MPI_ERR_IN_STATUS )

MPI_STATUS_IGNORE: - Ignore a single MPI_Status argument

MPI_STATUSES_IGNORE: - Ignore an array of MPI_Status

Special value for error codes array

MPI_ERRCODES_IGNORE: - Ignore an array of error codes

Mpi_t constants

MPI_T_VERBOSITY_USER_BASIC: - Basic information of interest to users

MPI_T_VERBOSITY_USER_DETAIL: - Detailed information of interest to users

MPI_T_VERBOSITY_USER_ALL: - All remaining information of interest to users

MPI_T_VERBOSITY_TUNER_BASIC: - Basic information required for tuning

MPI_T_VERBOSITY_TUNER_DETAIL: - Detailed information required for tuning

MPI_T_VERBOSITY_TUNER_ALL: - All remaining information required for tuning

MPI_T_VERBOSITY_MPIDEV_BASIC: - Basic information for MPI implementors

MPI_T_VERBOSITY_MPIDEV_DETAIL: - Detailed information for MPI implementors

MPI_T_VERBOSITY_MPIDEV_ALL: - All remaining information for MPI implementors

MPI_T_BIND_NO_OBJECT: - Applies globally to entire MPI process

MPI_T_BIND_MPI_COMM: - MPI communicators

MPI_T_BIND_MPI_DATATYPE: - MPI datatypes

MPI_T_BIND_MPI_ERRHANDLER: - MPI error handlers

MPI_T_BIND_MPI_FILE: - MPI file handles

MPI_T_BIND_MPI_GROUP: - MPI groups

MPI_T_BIND_MPI_OP: - MPI reduction operators

MPI_T_BIND_MPI_REQUEST: - MPI requests

MPI_T_BIND_MPI_WIN: - MPI windows for one-sided communication

MPI_T_BIND_MPI_MESSAGE: - MPI message object

MPI_T_BIND_MPI_INFO: - MPI info object

MPI_T_SCOPE_CONSTANT: - read-only, value is constant

MPI_T_SCOPE_READONLY: - read-only, cannot be written, but can change

MPI_T_SCOPE_LOCAL: - may be writeable, writing is a local operation

MPI_T_SCOPE_GROUP: - may be writeable, must be done to a group of processes, all processes in a group must be set to consistent values

MPI_T_SCOPE_GROUP_EQ: - may be writeable, must be done to a group of processes, all processes in a group must be set to the same value

MPI_T_SCOPE_ALL: - may be writeable, must be done to all processes, all connected processes must be set to consistent values

MPI_T_SCOPE_ALL_EQ: - may be writeable, must be done to all processes, all connected processes must be set to the same value

MPI_T_PVAR_CLASS_STATE: - set of discrete states (MPI_INT)

MPI_T_PVAR_CLASS_LEVEL: - utilization level of a resource

MPI_T_PVAR_CLASS_SIZE: - size of a resource

MPI_T_PVAR_CLASS_PERCENTAGE: - percentage utilization of a resource

MPI_T_PVAR_CLASS_HIGHWATERMARK: - high watermark of a resource

MPI_T_PVAR_CLASS_LOWWATERMARK: - low watermark of a resource

MPI_T_PVAR_CLASS_COUNTER: - number of occurrences of an event

MPI_T_PVAR_CLASS_AGGREGATE: - aggregate value over an event (e.g., sum of all memory allocations)

MPI_T_PVAR_CLASS_TIMER: - aggretate time spent executing event

MPI_T_PVAR_CLASS_GENERIC: - used for any other time of performance variable

Thread levels

`MPI_THREAD_SINGLE`	- Only one thread executes
`MPI_THREAD_FUNNELED`	- Only the main thread makes MPI calls
`MPI_THREAD_SERIALIZED`	- Only one thread at a time makes MPI calls
`MPI_THREAD_MULTIPLE`	- Multiple threads may make MPI calls

Special mpi types and functions

MPI_Aint: - C type that holds any valid address.

MPI_Count: - C type that holds any valid count.

MPI_Offset: - C type that holds any valid file offset.

MPI_Handler_function: - C function for handling errors (see MPI_Errhandler_create ) .

MPI_User_function: - C function to combine values (see collective operations and MPI_Op_create )

MPI_Copy_function: - Function to copy attributes (see MPI_Keyval_create )

MPI_Delete_function: - Function to delete attributes (see MPI_Keyval_create )

MPI_ERRORS_ARE_FATAL: - Error handler that forces exit on error

MPI_ERRORS_RETURN: - Error handler that returns error codes (as value of MPI routine in C and through last argument in Fortran)

MPI_ERRORS_ABORT: - Error handler that forces exit on error (only aborts local process if the error handler is invoked on a session)

Mpi attribute default functions

`MPI_COMM_NULL_COPY_FN`	- Predefined attribute copy function for communicators
`MPI_COMM_NULL_DELETE_FN`	- Predefined attribute delete function for communicators
`MPI_COMM_DUP_FN`	- Predefined attribute duplicate function for communicators
`MPI_WIN_NULL_COPY_FN`	- Predefined attribute copy function for windows
`MPI_WIN_NULL_DELETE_FN`	- Predefined attribute delete function for windows
`MPI_WIN_DUP_FN`	- Predefined attribute duplicate function for windows
`MPI_TYPE_NULL_COPY_FN`	- Predefined attribute copy function for datatypes
`MPI_TYPE_NULL_DELETE_FN`	- Predefined attribute delete function for datatypes
`MPI_TYPE_DUP_FN`	- Predefined attribute duplicate function for datatypes

Mpi-1 attribute default functions

`MPI_NULL_COPY_FN`	- Predefined copy function
`MPI_NULL_DELETE_FN`	- Predefined delete function
`MPI_DUP_FN`	- Predefined duplication function

Mpi error classes

MPI_SUCCESS: - Successful return code

MPI_ERR_BUFFER: - Invalid buffer pointer

MPI_ERR_COUNT: - Invalid count argument

MPI_ERR_TYPE: - Invalid datatype argument

MPI_ERR_TAG: - Invalid tag argument

MPI_ERR_COMM: - Invalid communicator

MPI_ERR_RANK: - Invalid rank

MPI_ERR_ROOT: - Invalid root

MPI_ERR_GROUP: - Null group passed to function

MPI_ERR_OP: - Invalid operation

MPI_ERR_TOPOLOGY: - Invalid topology

MPI_ERR_DIMS: - Illegal dimension argument

MPI_ERR_ARG: - Invalid argument

MPI_ERR_UNKNOWN: - Unknown error

MPI_ERR_TRUNCATE: - Message truncated on receive

MPI_ERR_OTHER: - Other error; use Error_string

MPI_ERR_INTERN: - Internal error code

MPI_ERR_IN_STATUS: - Look in status for error value

MPI_ERR_PENDING: - Pending request

MPI_ERR_REQUEST: - Invalid mpi_request handle

MPI_ERR_ACCESS: - Permission denied

MPI_ERR_AMODE: - Error related to the amode passed to MPI_FILE_OPEN

MPI_ERR_BAD_FILE: - Invalid file name (e.g., path name too long)

MPI_ERR_CONVERSION: - An error occurred in a user supplied data conversion function

MPI_ERR_DUP_DATAREP: - Conversion functions could not be registered because a data representation identifier that was already defined was passed to MPI_REGISTER_DATAREP

MPI_ERR_FILE_EXISTS: - File exists

MPI_ERR_FILE_IN_USE: - File operation could not be completed, as the file is currently open by some process

MPI_ERR_FILE: - Invalid file handle

MPI_ERR_IO: - Other I/O error

MPI_ERR_NO_SPACE: - Not enough space

MPI_ERR_NO_SUCH_FILE: - File does not exist

MPI_ERR_READ_ONLY: - Read-only file or file system

MPI_ERR_UNSUPPORTED_DATAREP: - Unsupported datarep passed to MPI_FILE_SET_VIEW

MPI_ERR_INFO: - Invalid info argument

MPI_ERR_INFO_KEY: - Key longer than MPI_MAX_INFO_KEY

MPI_ERR_INFO_VALUE: - Value longer than MPI_MAX_INFO_VAL

MPI_ERR_INFO_NOKEY: - Invalid key passed to MPI_INFO_DELETE

MPI_ERR_NAME: - Invalid service name passed to MPI_LOOKUP_NAME

MPI_ERR_NO_MEM: - Alloc_mem could not allocate memory

MPI_ERR_NOT_SAME: - Collective argument not identical on all processes, or collective routines called in a different order by different processes

MPI_ERR_PORT: - Invalid port name passed to MPI_COMM_CONNECT

MPI_ERR_QUOTA: - Quota exceeded

MPI_ERR_SERVICE: - Invalid service name passed to MPI_UNPUBLISH_NAME

MPI_ERR_SPAWN: - Error in spawning processes

MPI_ERR_UNSUPPORTED_OPERATION: - Unsupported operation, such as seeking on a file which supports sequential access only

MPI_ERR_WIN: - Invalid win argument

MPI_ERR_BASE: - Invalid base passed to MPI_FREE_MEM

MPI_ERR_LOCKTYPE: - Invalid locktype argument

MPI_ERR_KEYVAL: - Erroneous attribute key

MPI_ERR_RMA_CONFLICT: - Conflicting accesses to window

MPI_ERR_RMA_SYNC: - Wrong synchronization of RMA calls

MPI_ERR_SIZE: - Invalid size argument

MPI_ERR_DISP: - Invalid disp argument

MPI_ERR_ASSERT: - Invalid assert argument

MPI_ERR_RMA_RANGE: - Target memory is not part of the window (in the case of a window created with MPI_WIN_CREATE_DYNAMIC, target memory is not attached)

MPI_ERR_RMA_ATTACH: - Memory cannot be attached (e.g., because of resource exhaustion)

MPI_ERR_RMA_SHARED: - Memory cannot be shared (e.g., some process in the group of the specified communicator cannot expose shared memory)

MPI_ERR_RMA_FLAVOR: - Passed window has the wrong flavor for the called function

MPI_ERR_LASTCODE: - Last error code -- always at end

Error codes for mpi_t

`MPI_T_ERR_MEMORY`	- Out of memory
`MPI_T_ERR_NOT_INITIALIZED`	- Interface not initialized
`MPI_T_ERR_CANNOT_INIT`	- Interface not in the state to be initialized
`MPI_T_ERR_INVALID_INDEX`	- The index is invalid or has been deleted
`MPI_T_ERR_INVALID_HANDLE`	- The handle is invalid
`MPI_T_ERR_OUT_OF_HANDLES`	- No more handles available
`MPI_T_ERR_OUT_OF_SESSIONS`	- No more sessions available
`MPI_T_ERR_INVALID_SESSION`	- Session argument is not valid
`MPI_T_ERR_CVAR_SET_NOT_NOW`	- Cvar cannot be set at this moment
`MPI_T_ERR_CVAR_SET_NEVER`	- Cvar cannot be set until end of execution
`MPI_T_ERR_PVAR_NO_STARTSTOP`	- Pvar can't be started or stopped
`MPI_T_ERR_PVAR_NO_WRITE`	- Pvar can't be written or reset
`MPI_T_ERR_PVAR_NO_ATOMIC`	- Pvar can't be R/W atomically
`MPI_T_ERR_INVALID_NAME`	- Name doesn't match
`MPI_T_ERR_INVALID`	- Invalid use of the interface or bad parameter values(s)

Releases

9 releases since Debian 2.0 (Hamm); the text changed 5 times.