MPI maintains exactly one shared file pointer per collective MPI_FILE_OPEN (shared among processes in the communicator group). The current value of this pointer implicitly specifies the offset in the data access routines described in this section. These routines only use and update the shared file pointer maintained by MPI. The individual file pointers are not used nor updated.
The shared file pointer routines have the same semantics as the data access with explicit offset routines described in Section Data Access with Explicit Offsets , page Data Access with Explicit Offsets , with the following modifications:
After a shared file pointer operation is initiated, the shared file pointer is updated to point to the next etype after the last one that will be accessed. The file pointer is updated relative to the current view of the file.
| MPI_FILE_READ_SHARED(fh, buf, count, datatype, status) | |
| INOUT fh | file handle (handle) |
| OUT buf | initial address of buffer (choice) |
| IN count | number of elements in buffer (integer) |
| IN datatype | datatype of each buffer element (handle) |
| OUT status | status object (Status) |
int MPI_File_read_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
MPI_FILE_READ_SHARED reads a file
using the shared file pointer.
int MPI_File_write_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
MPI_FILE_WRITE_SHARED writes a file
using the shared file pointer.
int MPI_File_iread_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Request *request)
MPI_FILE_IREAD_SHARED is a nonblocking version
of the MPI_FILE_READ_SHARED interface.
int MPI_File_iwrite_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Request *request)
MPI_FILE_IWRITE_SHARED is a nonblocking version
of the MPI_FILE_WRITE_SHARED interface.
The semantics of a collective access using a shared file pointer is
that the accesses to the file will be
in the order determined by the ranks of the processes
within the group.
For each process, the location in the file at which data is accessed is the
position at which the shared file pointer would be after all processes whose
ranks within the group less than that of this process had accessed their data.
In addition, in order to prevent subsequent
shared offset accesses by the same processes from interfering
with this collective
access, the call might return only after all the processes
within the group have initiated their
accesses.
When the call returns, the shared file pointer points
to the next etype accessible,
according to the file view used by all processes,
after the last etype requested.
There may be some programs in which all processes in the
group
need to access the
file using the shared file pointer, but the program may not require
that data be accessed in order of process rank.
In such programs, using the shared ordered routines
(e.g., MPI_FILE_WRITE_ORDERED
rather than MPI_FILE_WRITE_SHARED)
may enable an implementation to optimize access, improving performance.
( End of advice to users.)
Accesses to the data requested by all processes do not have to be serialized.
Once all processes have issued their requests, locations within the file for
all accesses can be computed, and accesses can proceed independently from each
other, possibly in parallel.
( End of advice to implementors.)
int MPI_File_read_ordered(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
MPI_FILE_READ_ORDERED is a collective version of the
MPI_FILE_READ_SHARED interface.
int MPI_File_write_ordered(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
MPI_FILE_WRITE_ORDERED is a collective version of the
MPI_FILE_WRITE_SHARED interface.
If MPI_MODE_SEQUENTIAL mode was specified when the file was opened,
it is erroneous to call the following two routines
( MPI_FILE_SEEK_SHARED and MPI_FILE_GET_POSITION_SHARED).
int MPI_File_seek_shared(MPI_File fh, MPI_Offset offset, int whence)
MPI_FILE_SEEK_SHARED updates the shared file pointer according to
whence,
which has
the following possible values:
The offset can be negative, which allows seeking backwards.
It is erroneous to seek to a negative position in the view.
int MPI_File_get_position_shared(MPI_File fh, MPI_Offset *offset)
MPI_FILE_GET_POSITION_SHARED returns, in offset,
the current position of the shared file pointer in etype units
relative to the current
view.
The offset can be used in a future call
to MPI_FILE_SEEK_SHARED
using whence = MPI_SEEK_SET to return to the current position.
To set the displacement to the current file pointer position,
first convert offset into an absolute byte position using
MPI_FILE_GET_BYTE_OFFSET,
then call MPI_FILE_SET_VIEW with the resulting
displacement.
( End of advice to users.)
MPI_FILE_READ_SHARED(FH, BUF, COUNT, DATATYPE, STATUS, IERROR)
<type> BUF(*)
INTEGER FH, COUNT, DATATYPE, STATUS(MPI_STATUS_SIZE), IERROR
{ void MPI::File::Read_shared(void* buf, int count, const MPI::Datatype& datatype, MPI::Status& status) (binding deprecated, see Section Deprecated since MPI-2.2
) }
{ void MPI::File::Read_shared(void* buf, int count, const MPI::Datatype& datatype) (binding deprecated, see Section Deprecated since MPI-2.2
) }
MPI_FILE_WRITE_SHARED(fh, buf, count, datatype, status) INOUT fh file handle (handle) IN buf initial address of buffer (choice) IN count number of elements in buffer (integer) IN datatype datatype of each buffer element (handle) OUT status status object (Status)
MPI_FILE_WRITE_SHARED(FH, BUF, COUNT, DATATYPE, STATUS, IERROR)
<type> BUF(*)
INTEGER FH, COUNT, DATATYPE, STATUS(MPI_STATUS_SIZE), IERROR
{ void MPI::File::Write_shared(const void* buf, int count, const MPI::Datatype& datatype, MPI::Status& status) (binding deprecated, see Section Deprecated since MPI-2.2
) }
{ void MPI::File::Write_shared(const void* buf, int count, const MPI::Datatype& datatype) (binding deprecated, see Section Deprecated since MPI-2.2
) }
MPI_FILE_IREAD_SHARED(fh, buf, count, datatype, request) INOUT fh file handle (handle) OUT buf initial address of buffer (choice) IN count number of elements in buffer (integer) IN datatype datatype of each buffer element (handle) OUT request request object (handle)
MPI_FILE_IREAD_SHARED(FH, BUF, COUNT, DATATYPE, REQUEST, IERROR)
<type> BUF(*)
INTEGER FH, COUNT, DATATYPE, REQUEST, IERROR
{ MPI::Request MPI::File::Iread_shared(void* buf, int count, const MPI::Datatype& datatype) (binding deprecated, see Section Deprecated since MPI-2.2
) }
MPI_FILE_IWRITE_SHARED(fh, buf, count, datatype, request) INOUT fh file handle (handle) IN buf initial address of buffer (choice) IN count number of elements in buffer (integer) IN datatype datatype of each buffer element (handle) OUT request request object (handle)
MPI_FILE_IWRITE_SHARED(FH, BUF, COUNT, DATATYPE, REQUEST, IERROR)
<type> BUF(*)
INTEGER FH, COUNT, DATATYPE, REQUEST, IERROR
{ MPI::Request MPI::File::Iwrite_shared(const void* buf, int count, const MPI::Datatype& datatype) (binding deprecated, see Section Deprecated since MPI-2.2
) }
Up: Data Access with Shared File Pointers
Next: Collective Operations
Previous: Data Access with Shared File Pointers
263.2. Collective Operations
Up: Data Access with Shared File Pointers
Next: Seek
Previous: Noncollective Operations
Advice to users.
Advice
to implementors.
MPI_FILE_READ_ORDERED(fh, buf, count, datatype, status) INOUT fh file handle (handle) OUT buf initial address of buffer (choice) IN count number of elements in buffer (integer) IN datatype datatype of each buffer element (handle) OUT status status object (Status)
MPI_FILE_READ_ORDERED(FH, BUF, COUNT, DATATYPE, STATUS, IERROR)
<type> BUF(*)
INTEGER FH, COUNT, DATATYPE, STATUS(MPI_STATUS_SIZE), IERROR
{ void MPI::File::Read_ordered(void* buf, int count, const MPI::Datatype& datatype, MPI::Status& status) (binding deprecated, see Section Deprecated since MPI-2.2
) }
{ void MPI::File::Read_ordered(void* buf, int count, const MPI::Datatype& datatype) (binding deprecated, see Section Deprecated since MPI-2.2
) }
MPI_FILE_WRITE_ORDERED(fh, buf, count, datatype, status) INOUT fh file handle (handle) IN buf initial address of buffer (choice) IN count number of elements in buffer (integer) IN datatype datatype of each buffer element (handle) OUT status status object (Status)
MPI_FILE_WRITE_ORDERED(FH, BUF, COUNT, DATATYPE, STATUS, IERROR)
<type> BUF(*)
INTEGER FH, COUNT, DATATYPE, STATUS(MPI_STATUS_SIZE), IERROR
{ void MPI::File::Write_ordered(const void* buf, int count, const MPI::Datatype& datatype, MPI::Status& status) (binding deprecated, see Section Deprecated since MPI-2.2
) }
{ void MPI::File::Write_ordered(const void* buf, int count, const MPI::Datatype& datatype) (binding deprecated, see Section Deprecated since MPI-2.2
) }
Up: Data Access with Shared File Pointers
Next: Seek
Previous: Noncollective Operations
263.3. Seek
Up: Data Access with Shared File Pointers
Next: Split Collective Data Access Routines
Previous: Collective Operations
MPI_FILE_SEEK_SHARED(fh, offset, whence) INOUT fh file handle (handle) IN offset file offset (integer) IN whence update mode (state)
MPI_FILE_SEEK_SHARED(FH, OFFSET, WHENCE, IERROR)
INTEGER FH, WHENCE, IERROR
INTEGER(KIND=MPI_OFFSET_KIND) OFFSET
{ void MPI::File::Seek_shared(MPI::Offset offset, int whence) (binding deprecated, see Section Deprecated since MPI-2.2
) }
MPI_FILE_SEEK_SHARED is collective;
all the processes in the communicator group associated with the file
handle fh must call MPI_FILE_SEEK_SHARED with the same
values for
offset and whence.
MPI_FILE_GET_POSITION_SHARED(fh, offset) IN fh file handle (handle) OUT offset offset of shared pointer (integer)
MPI_FILE_GET_POSITION_SHARED(FH, OFFSET, IERROR)
INTEGER FH, IERROR
INTEGER(KIND=MPI_OFFSET_KIND) OFFSET
{ MPI::Offset MPI::File::Get_position_shared() const (binding deprecated, see Section Deprecated since MPI-2.2
) }
Advice to users.
Up: Data Access with Shared File Pointers
Next: Split Collective Data Access Routines
Previous: Collective Operations
Return to MPI-2.2 Standard Index
Return to MPI Forum Home Page
(Unofficial) MPI-2.2 of September 4, 2009
HTML Generated on September 10, 2009