功能不支持函数
针对本小节内所述函数，Hyper IO库暂未做功能支持，若文件使用Hyper IO库创建后，使用该文件句柄调用以下函数，将会返回错误码或者做特殊处理。若以下函数入参中的文件句柄为原MPI-IO打开，则函数将桥接至原函数调用，参数范围及错误码等将与原MPI-IO保持一致。
函数定义
- int PMPI_File_iwrite_shared(MPI_File fh, const void *buf, int count, MPI_Datatype datatype, MPIO_Request *request)
- int PMPI_File_write_ordered(MPI_File fh, const void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int PMPI_File_write_ordered_begin(MPI_File fh, const void *buf, int count, MPI_Datatype datatype)
- int PMPI_File_write_ordered_end(MPI_File fh, const void *buf, MPI_Status *status)
- int PMPI_File_write_shared(MPI_File fh, const void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int PMPI_File_read_ordered(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int PMPI_File_read_ordered_begin(MPI_File fh, void *buf, int count, MPI_Datatype datatype)
- int PMPI_File_read_ordered_end(MPI_File fh, void *buf, MPI_Status *status)
- int PMPI_File_read_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int PMPI_File_iread_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Request *request)
- int PMPI_File_get_atomicity(MPI_File fh, int *flag)
- int PMPI_File_get_size(MPI_File fh, MPI_Offset *size)
- int PMPI_File_preallocate(MPI_File fh, MPI_Offset size)
- int PMPI_File_set_atomicity(MPI_File fh, int flag)
- int PMPI_File_set_size(MPI_File fh, MPI_Offset size)
为达成性能加速目的，Hyper IO库不支持预分配文件大小功能，若文件使用Hyper IO库创建后调用此接口，将恒返回MPI_SUCCESS，但文件大小不会改变。
- int MPI_File_iwrite_shared(MPI_File fh, const void *buf, int count, MPI_Datatype datatype, MPIO_Request *request)
- int MPI_File_write_ordered(MPI_File fh, const void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int MPI_File_write_ordered_begin(MPI_File fh, const void *buf, int count, MPI_Datatype datatype)
- int MPI_File_write_ordered_end(MPI_File fh, const void *buf, MPI_Status *status)
- int MPI_File_write_shared(MPI_File fh, const void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int MPI_File_read_ordered(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int MPI_File_read_ordered_begin(MPI_File fh, void *buf, int count, MPI_Datatype datatype)
- int MPI_File_read_ordered_end(MPI_File fh, void *buf, MPI_Status *status)
- int MPI_File_read_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Status *status)
- int MPI_File_iread_shared(MPI_File fh, void *buf, int count, MPI_Datatype datatype, MPI_Request *request)
- int MPI_File_get_atomicity(MPI_File fh, int *flag)
- int MPI_File_get_size(MPI_File fh, MPI_Offset *size)
- int MPI_File_preallocate(MPI_File fh, MPI_Offset size)
- int MPI_File_set_atomicity(MPI_File fh, int flag)
- int MPI_File_set_size(MPI_File fh, MPI_Offset size)
为达成性能加速目的，Hyper IO库不支持预分配文件大小功能，若文件使用Hyper IO库创建后调用此接口，将恒返回MPI_SUCCESS，但文件大小不会改变。
父主题： MPI-IO桥接函数