diff options
Diffstat (limited to 'doxygen/dox')
| -rw-r--r-- | doxygen/dox/GettingStarted.dox | 4 | ||||
| -rw-r--r-- | doxygen/dox/IntroParExamples.dox | 569 | ||||
| -rw-r--r-- | doxygen/dox/IntroParHDF5.dox | 271 | ||||
| -rw-r--r-- | doxygen/dox/LearnBasics1.dox | 2 |
4 files changed, 843 insertions, 3 deletions
diff --git a/doxygen/dox/GettingStarted.dox b/doxygen/dox/GettingStarted.dox index 29c5033..87f3566 100644 --- a/doxygen/dox/GettingStarted.dox +++ b/doxygen/dox/GettingStarted.dox @@ -50,10 +50,10 @@ Parallel HDF5, and the HDF5-1.10 VDS and SWMR new features: </tr> <tr> <td style="background-color:#F5F5F5"> -<a href="https://portal.hdfgroup.org/display/HDF5/Introduction+to+Parallel+HDF5">Introduction to Parallel HDF5</a> +\ref IntroParHDF5 </td> <td> -A brief introduction to Parallel HDF5. If you are new to HDF5 please see the @ref LearnBasics topic first. +A brief introduction to Parallel HDF5. If you are new to HDF5 please see the @ref LearnBasics topic first. </td> </tr> <tr> diff --git a/doxygen/dox/IntroParExamples.dox b/doxygen/dox/IntroParExamples.dox new file mode 100644 index 0000000..ba96fed --- /dev/null +++ b/doxygen/dox/IntroParExamples.dox @@ -0,0 +1,569 @@ +/** @page IntroParContHyperslab Writing by Contiguous Hyperslab + +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 +<hr> + +This example shows how to write a contiguous buffer in memory to a contiguous hyperslab in a file. In this case, +each parallel process writes a contiguous hyperslab to the file. + +In the C example (figure a), each hyperslab in memory consists of an equal number of consecutive rows. In the FORTRAN +90 example (figure b), each hyperslab in memory consists of +an equal number of consecutive columns. This reflects the difference in the storage order for C and FORTRAN 90. +<table> +<tr> +<th><strong>Figure a</strong> C Example</th> +<th><strong>Figure b</strong> Fortran Example</th> +</tr><tr> +<td> +\image html pcont_hy_figa.gif +</td> +<td> +\image html pcont_hy_figb.gif +</td> +</tr> +</table> + +\section secIntroParContHyperslabC Writing a Contiguous Hyperslab in C +In this example, you have a dataset of 8 (rows) x 5 (columns) and each process writes an equal number +of rows to the dataset. The dataset hyperslab is defined as follows: +\code + count [0] = dimsf [0] / number_processes + count [1] = dimsf [1] +\endcode +where, +\code + dimsf [0] is the number of rows in the dataset + dimsf [1] is the number of columns in the dataset +\endcode +The offset for the hyperslab is different for each process: +\code + offset [0] = k * count[0] + offset [1] = 0 +\endcode +where, +\code + "k" is the process id number + count [0] is the number of rows written in each hyperslab + offset [1] = 0 indicates to start at the beginning of the row +\endcode + +The number of processes that you could use would be 1, 2, 4, or 8. The number of rows that would be written by each slab is as follows: +<table> +<tr> +<th><strong>Processes</strong></th> +<th><strong>Size of count[0](\# of rows) </strong></th> +</tr><tr> +<td>1</td><td>8</td> +</tr><tr> +<td>2</td><td>4</td> +</tr><tr> +<td>4</td><td>2</td> +</tr><tr> +<td>8</td><td>1</td> +</tr> +</table> + +If using 4 processes, then process 1 would look like: +<table> +<tr> +<td> +\image html pcont_hy_figc.gif +</td> +</tr> +</table> + +The code would look like the following: +\code + 71 /* + 72 * Each process defines dataset in memory and writes it to the hyperslab + 73 * in the file. + 74 */ + 75 count[0] = dimsf[0]/mpi_size; + 76 count[1] = dimsf[1]; + 77 offset[0] = mpi_rank * count[0]; + 78 offset[1] = 0; + 79 memspace = H5Screate_simple(RANK, count, NULL); + 80 + 81 /* + 82 * Select hyperslab in the file. + 83 */ + 84 filespace = H5Dget_space(dset_id); + 85 H5Sselect_hyperslab(filespace, H5S_SELECT_SET, offset, NULL, count, NULL); +\endcode + +Below is the example program: +<table> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/C/H5Parallel/ph5_hyperslab_by_row.c">hyperslab_by_row.c</a> +</td> +</tr> +</table> + +If using this example with 4 processes, then, +\li Process 0 writes "10"s to the file. +\li Process 1 writes "11"s. +\li Process 2 writes "12"s. +\li Process 3 writes "13"s. + +The following is the output from h5dump for the HDF5 file created by this example using 4 processes: +\code +HDF5 "SDS_row.h5" { +GROUP "/" { + DATASET "IntArray" { + DATATYPE H5T_STD_I32BE + DATASPACE SIMPLE { ( 8, 5 ) / ( 8, 5 ) } + DATA { + 10, 10, 10, 10, 10, + 10, 10, 10, 10, 10, + 11, 11, 11, 11, 11, + 11, 11, 11, 11, 11, + 12, 12, 12, 12, 12, + 12, 12, 12, 12, 12, + 13, 13, 13, 13, 13, + 13, 13, 13, 13, 13 + } + } +} +} +\endcode + + +\section secIntroParContHyperslabFort Writing a Contiguous Hyperslab in Fortran +In this example you have a dataset of 5 (rows) x 8 (columns). Since a contiguous hyperslab in Fortran 90 +consists of consecutive columns, each process will be writing an equal number of columns to the dataset. + +You would define the size of the hyperslab to write to the dataset as follows: +\code + count(1) = dimsf(1) + count(2) = dimsf(2) / number_of_processes +\endcode + +where, +\code + dimsf(1) is the number of rows in the dataset + dimsf(2) is the number of columns +\endcode + +The offset for the hyperslab dimension would be different for each process: +\code + offset (1) = 0 + offset (2) = k * count (2) +\endcode + +where, +\code + offset (1) = 0 indicates to start at the beginning of the column + "k" is the process id number + "count(2) is the number of columns to be written by each hyperslab +\endcode + +The number of processes that could be used in this example are 1, 2, 4, or 8. The number of +columns that could be written by each slab is as follows: +<table> +<tr> +<th><strong>Processes</strong></th> +<th><strong>Size of count (2)(\# of columns) </strong></th> +</tr><tr> +<td>1</td><td>8</td> +</tr><tr> +<td>2</td><td>4</td> +</tr><tr> +<td>4</td><td>2</td> +</tr><tr> +<td>8</td><td>1</td> +</tr> +</table> + +If using 4 processes, the offset and count parameters for Process 1 would look like: +<table> +<tr> +<td> +\image html pcont_hy_figd.gif +</td> +</tr> +</table> + +The code would look like the following: +\code + 69 ! Each process defines dataset in memory and writes it to the hyperslab + 70 ! in the file. + 71 ! + 72 count(1) = dimsf(1) + 73 count(2) = dimsf(2)/mpi_size + 74 offset(1) = 0 + 75 offset(2) = mpi_rank * count(2) + 76 CALL h5screate_simple_f(rank, count, memspace, error) + 77 ! + 78 ! Select hyperslab in the file. + 79 ! + 80 CALL h5dget_space_f(dset_id, filespace, error) + 81 CALL h5sselect_hyperslab_f (filespace, H5S_SELECT_SET_F, offset, count, error) +\endcode + +Below is the F90 example program which illustrates how to write contiguous hyperslabs by column in Parallel HDF5: +<table> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/Fortran/H5Parallel/ph5_f90_hyperslab_by_col.f90">hyperslab_by_col.f90</a> +</td> +</tr> +</table> + +If you run this program with 4 processes and look at the output with h5dump you will notice that the output is +much like the output shown above for the C example. This is because h5dump is written in C. The data would be +displayed in columns if it was printed using Fortran 90 code. + +<hr> +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 + +@page IntroParRegularSpaced Writing by Regularly Spaced Data + +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 +<hr> + +In this case, each process writes data from a contiguous buffer into disconnected locations in the file, using a regular pattern. + +In C it is done by selecting a hyperslab in a file that consists of regularly spaced columns. In F90, it is done by selecting a +hyperslab in a file that consists of regularly spaced rows. +<table> +<tr> +<th><strong>Figure a</strong> C Example</th> +<th><strong>Figure b</strong> Fortran Example</th> +</tr><tr> +<td> +\image html preg_figa.gif +</td> +<td> +\image html preg_figb.gif +</td> +</tr> +</table> + +\section secIntroParRegularSpacedC Writing Regularly Spaced Columns in C +In this example, you have two processes that write to the same dataset, each writing to +every other column in the dataset. For each process the hyperslab in the file is set up as follows: +\code + 89 count[0] = 1; + 90 count[1] = dimsm[1]; + 91 offset[0] = 0; + 92 offset[1] = mpi_rank; + 93 stride[0] = 1; + 94 stride[1] = 2; + 95 block[0] = dimsf[0]; + 96 block[1] = 1; +\endcode + +The stride is 2 for dimension 1 to indicate that every other position along this +dimension will be written to. A stride of 1 indicates that every position along a dimension will be written to. + +For two processes, the mpi_rank will be either 0 or 1. Therefore: +\li Process 0 writes to even columns (0, 2, 4...) +\li Process 1 writes to odd columns (1, 3, 5...) + +The block size allows each process to write a column of data to every other position in the dataset. + +<table> +<tr> +<td> +\image html preg_figc.gif +</td> +</tr> +</table> + +Below is an example program for writing hyperslabs by column in Parallel HDF5: +<table> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/C/H5Parallel/ph5_hyperslab_by_col.c">hyperslab_by_col.c</a> +</td> +</tr> +</table> + +The following is the output from h5dump for the HDF5 file created by this example: +\code +HDF5 "SDS_col.h5" { +GROUP "/" { + DATASET "IntArray" { + DATATYPE H5T_STD_I32BE + DATASPACE SIMPLE { ( 8, 6 ) / ( 8, 6 ) } + DATA { + 1, 2, 10, 20, 100, 200, + 1, 2, 10, 20, 100, 200, + 1, 2, 10, 20, 100, 200, + 1, 2, 10, 20, 100, 200, + 1, 2, 10, 20, 100, 200, + 1, 2, 10, 20, 100, 200, + 1, 2, 10, 20, 100, 200, + 1, 2, 10, 20, 100, 200 + } + } +} +} +\endcode + + +\section secIntroParRegularSpacedFort Writing Regularly Spaced Rows in Fortran +In this example, you have two processes that write to the same dataset, each writing to every +other row in the dataset. For each process the hyperslab in the file is set up as follows: + + +You would define the size of the hyperslab to write to the dataset as follows: +\code + 83 ! Each process defines dataset in memory and writes it to + 84 ! the hyperslab in the file. + 85 ! + 86 count(1) = dimsm(1) + 87 count(2) = 1 + 88 offset(1) = mpi_rank + 89 offset(2) = 0 + 90 stride(1) = 2 + 91 stride(2) = 1 + 92 block(1) = 1 + 93 block(2) = dimsf(2) +\endcode + +The stride is 2 for dimension 1 to indicate that every other position along this dimension will +be written to. A stride of 1 indicates that every position along a dimension will be written to. + +For two process, the mpi_rank will be either 0 or 1. Therefore: +\li Process 0 writes to even rows (0, 2, 4 ...) +\li Process 1 writes to odd rows (1, 3, 5 ...) + +The block size allows each process to write a row of data to every other position in the dataset, +rather than just a point of data. + +The following shows the data written by Process 1 to the file: +<table> +<tr> +<td> +\image html preg_figd.gif +</td> +</tr> +</table> + +Below is the example program for writing hyperslabs by column in Parallel HDF5: +<table> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/Fortran/H5Parallel/ph5_f90_hyperslab_by_row.f90">hyperslab_by_row.f90</a> +</td> +</tr> +</table> + +The output for h5dump on the file created by this program will look like the output as shown above for the C example. This is +because h5dump is written in C. The data would be displayed in rows if it were printed using Fortran 90 code. + +<hr> +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 + +@page IntroParPattern Writing by Pattern + +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 +<hr> + +This is another example of writing data into disconnected locations in a file. Each process writes data from the contiguous +buffer into regularly scattered locations in the file. + +Each process defines a hyperslab in the file as described below and writes data to it. The C and Fortran 90 examples below +result in the same data layout in the file. + +<table> +<tr> +<th><strong>Figure a</strong> C Example</th> +<th><strong>Figure b</strong> Fortran Example</th> +</tr><tr> +<td> +\image html ppatt_figa.gif +</td> +<td> +\image html ppatt_figb.gif +</td> +</tr> +</table> + +The C and Fortran 90 examples use four processes to write the pattern shown above. Each process defines a hyperslab by: +\li Specifying a stride of 2 for each dimension, which indicates that you wish to write to every other position along a dimension. +\li Specifying a different offset for each process: +<table> +<tr> +<th rowspan="3"><strong>C</strong></th><th>Process 0</th><th>Process 1</th><th>Process 2</th><th>Process 3</th> +</tr><tr> +<td>offset[0] = 0</td><td>offset[0] = 1</td><td>offset[0] = 0</td><td>offset[0] = 1</td> +</tr><tr> +<td>offset[1] = 0</td><td>offset[1] = 0</td><td>offset[1] = 1</td><td>offset[1] = 1</td> +</tr><tr> +<th rowspan="3"><strong>Fortran</strong></th><th>Process 0</th><th>Process 1</th><th>Process 2</th><th>Process 3</th> +</tr><tr> +<td>offset(1) = 0</td><td>offset(1) = 0</td><td>offset(1) = 1</td><td>offset(1) = 1</td> +</tr><tr> +<td>offset(2) = 0</td><td>offset(2) = 1</td><td>offset(2) = 0</td><td>offset(2) = 1</td> +</tr> +</table> +\li Specifying the size of the slab to write. The count is the number of positions along a dimension to write to. If writing a 4 x 2 slab, +then the count would be: +<table> +<tr> +<th><strong>C</strong></th><th>Fortran</th> +</tr><tr> +<td>count[0] = 4</td><td>count(1) = 2</td> +</tr><tr> +<td>count[1] = 2</td><td>count(2) = 4</td> +</tr> +</table> + +For example, the offset, count, and stride parameters for Process 2 would look like: +<table> +<tr> +<th><strong>Figure a</strong> C Example</th> +<th><strong>Figure b</strong> Fortran Example</th> +</tr><tr> +<td> +\image html ppatt_figc.gif +</td> +<td> +\image html ppatt_figd.gif +</td> +</tr> +</table> + +Below are example programs for writing hyperslabs by pattern in Parallel HDF5: +<table> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/C/H5Parallel/ph5_hyperslab_by_pattern.c">hyperslab_by_pattern.c</a> +</td> +</tr> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/Fortran/H5Parallel/ph5_f90_hyperslab_by_pattern.f90">hyperslab_by_pattern.f90</a> +</td> +</tr> +</table> + +The following is the output from h5dump for the HDF5 file created in this example: +\code +HDF5 "SDS_pat.h5" { +GROUP "/" { + DATASET "IntArray" { + DATATYPE H5T_STD_I32BE + DATASPACE SIMPLE { ( 8, 4 ) / ( 8, 4 ) } + DATA { + 1, 3, 1, 3, + 2, 4, 2, 4, + 1, 3, 1, 3, + 2, 4, 2, 4, + 1, 3, 1, 3, + 2, 4, 2, 4, + 1, 3, 1, 3, + 2, 4, 2, 4 + } + } +} +} +\endcode +The h5dump utility is written in C so the output is in C order. + + +<hr> +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 + +@page IntroParChunk Writing by Chunk + +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 +<hr> + +In this example each process writes a "chunk" of data to a dataset. The C and Fortran 90 +examples result in the same data layout in the file. + +<table> +<tr> +<th><strong>Figure a</strong> C Example</th> +<th><strong>Figure b</strong> Fortran Example</th> +</tr><tr> +<td> +\image html pchunk_figa.gif +</td> +<td> +\image html pchunk_figb.gif +</td> +</tr> +</table> + +For this example, four processes are used, and a 4 x 2 chunk is written to the dataset by each process. + +To do this, you would: +\li Use the block parameter to specify a chunk of size 4 x 2 (or 2 x 4 for Fortran). +\li Use a different offset (start) for each process, based on the chunk size: +<table> +<tr> +<th rowspan="3"><strong>C</strong></th><th>Process 0</th><th>Process 1</th><th>Process 2</th><th>Process 3</th> +</tr><tr> +<td>offset[0] = 0</td><td>offset[0] = 0</td><td>offset[0] = 4</td><td>offset[0] = 4</td> +</tr><tr> +<td>offset[1] = 0</td><td>offset[1] = 2</td><td>offset[1] = 0</td><td>offset[1] = 2</td> +</tr><tr> +<th rowspan="3"><strong>Fortran</strong></th><th>Process 0</th><th>Process 1</th><th>Process 2</th><th>Process 3</th> +</tr><tr> +<td>offset(1) = 0</td><td>offset(1) = 2</td><td>offset(1) = 0</td><td>offset(1) = 2</td> +</tr><tr> +<td>offset(2) = 0</td><td>offset(2) = 0</td><td>offset(2) = 4</td><td>offset(2) = 4</td> +</tr> +</table> + +For example, the offset and block parameters for Process 2 would look like: +<table> +<tr> +<th><strong>Figure a</strong> C Example</th> +<th><strong>Figure b</strong> Fortran Example</th> +</tr><tr> +<td> +\image html pchunk_figc.gif +</td> +<td> +\image html pchunk_figd.gif +</td> +</tr> +</table> + +Below are example programs for writing hyperslabs by pattern in Parallel HDF5: +<table> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/C/H5Parallel/ph5_hyperslab_by_chunk.c">hyperslab_by_chunk.c</a> +</td> +</tr> +<tr> +<td> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/Fortran/H5Parallel/ph5_f90_hyperslab_by_chunk.f90">hyperslab_by_chunk.f90</a> +</td> +</tr> +</table> + +The following is the output from h5dump for the HDF5 file created in this example: +\code +HDF5 "SDS_chnk.h5" { +GROUP "/" { + DATASET "IntArray" { + DATATYPE H5T_STD_I32BE + DATASPACE SIMPLE { ( 8, 4 ) / ( 8, 4 ) } + DATA { + 1, 1, 2, 2, + 1, 1, 2, 2, + 1, 1, 2, 2, + 1, 1, 2, 2, + 3, 3, 4, 4, + 3, 3, 4, 4, + 3, 3, 4, 4, + 3, 3, 4, 4 + } + } +} +} +\endcode +The h5dump utility is written in C so the output is in C order. + +<hr> +Navigate back: \ref index "Main" / \ref GettingStarted / \ref IntroParHDF5 + +*/ diff --git a/doxygen/dox/IntroParHDF5.dox b/doxygen/dox/IntroParHDF5.dox new file mode 100644 index 0000000..9e9aaa0 --- /dev/null +++ b/doxygen/dox/IntroParHDF5.dox @@ -0,0 +1,271 @@ +/** @page IntroParHDF5 A Brief Introduction to Parallel HDF5 + +Navigate back: \ref index "Main" / \ref GettingStarted +<hr> + +If you are new to HDF5 please see the @ref LearnBasics topic first. + +\section sec_pintro_overview Overview of Parallel HDF5 (PHDF5) Design +There were several requirements that we had for Parallel HDF5 (PHDF5). These were: +\li Parallel HDF5 files had to be compatible with serial HDF5 files and sharable +between different serial and parallel platforms. +\li Parallel HDF5 had to be designed to have a single file image to all processes, +rather than having one file per process. Having one file per process can cause expensive +post processing, and the files are not usable by different processes. +\li A standard parallel I/O interface had to be portable to different platforms. + +With these requirements of HDF5 our initial target was to support MPI programming, but not +for shared memory programming. We had done some experimentation with thread-safe support +for Pthreads and for OpenMP, and decided to use these. + +Implementation requirements were to: +\li Not use Threads, since they were not commonly supported in 1998 when we were looking at this. +\li Not have a reserved process, as this might interfere with parallel algorithms. +\li Not spawn any processes, as this is not even commonly supported now. + +The following shows the Parallel HDF5 implementation layers. + + +\subsection subsec_pintro_prog Parallel Programming with HDF5 +This tutorial assumes that you are somewhat familiar with parallel programming with MPI (Message Passing Interface). + +If you are not familiar with parallel programming, here is a tutorial that may be of interest: +<a href="http://www.nersc.gov/users/training/online-tutorials/introduction-to-scientific-i-o/?show_all=1">Tutorial on HDF5 I/O tuning at NERSC</a> + +Some of the terms that you must understand in this tutorial are: +<ul> +<li> +<strong>MPI Communicator</strong> +Allows a group of processes to communicate with each other. + +Following are the MPI routines for initializing MPI and the communicator and finalizing a session with MPI: +<table> +<tr> +<th>C</th> +<th>Fortran</th> +<th>Description</th> +</tr> +<tr> +<td>MPI_Init</td> +<td>MPI_INIT</td> +<td>Initialize MPI (MPI_COMM_WORLD usually)</td> +</tr> +<tr> +<td>MPI_Comm_size</td> +<td>MPI_COMM_SIZE</td> +<td>Define how many processes are contained in the communicator</td> +</tr> +<tr> +<td>MPI_Comm_rank</td> +<td>MPI_COMM_RANK</td> +<td>Define the process ID number within the communicator (from 0 to n-1)</td> +</tr> +<tr> +<td>MPI_Finalize</td> +<td>MPI_FINALIZE</td> +<td>Exiting MPI</td> +</tr> +</table> +</li> +<li> +<strong>Collective</strong> +MPI defines this to mean all processes of the communicator must participate in the right order. +</li> +</ul> + +Parallel HDF5 opens a parallel file with a communicator. It returns a file handle to be used for future access to the file. + +All processes are required to participate in the collective Parallel HDF5 API. Different files can be opened using different communicators. + +Examples of what you can do with the Parallel HDF5 collective API: +\li File Operation: Create, open and close a file +\li Object Creation: Create, open, and close a dataset +\li Object Structure: Extend a dataset (increase dimension sizes) +\li Dataset Operations: Write to or read from a dataset +(Array data transfer can be collective or independent.) + +Once a file is opened by the processes of a communicator: +\li All parts of the file are accessible by all processes. +\li All objects in the file are accessible by all processes. +\li Multiple processes write to the same dataset. +\li Each process writes to an individual dataset. + +Please refer to the Supported Configuration Features Summary in the release notes for the current release +of HDF5 for an up-to-date list of the platforms that we support Parallel HDF5 on. + + +\subsection subsec_pintro_create_file Creating and Accessing a File with PHDF5 +The programming model for creating and accessing a file is as follows: +<ol> +<li>Set up an access template object to control the file access mechanism.</li> +<li>Open the file.</li> +<li>Close the file.</li> +</ol> + +Each process of the MPI communicator creates an access template and sets it up with MPI parallel +access information. This is done with the #H5Pcreate call to obtain the file access property list +and the #H5Pset_fapl_mpio call to set up parallel I/O access. + +Following is example code for creating an access template in HDF5: +<em>C</em> +\code + 23 MPI_Comm comm = MPI_COMM_WORLD; + 24 MPI_Info info = MPI_INFO_NULL; + 25 + 26 /* + 27 * Initialize MPI + 28 */ + 29 MPI_Init(&argc, &argv); + 30 MPI_Comm_size(comm, &mpi_size); + 31 MPI_Comm_rank(comm, &mpi_rank); + 32 + 33 /* + 34 * Set up file access property list with parallel I/O access + 35 */ + 36 plist_id = H5Pcreate(H5P_FILE_ACCESS); 37 H5Pset_fapl_mpio(plist_id, comm, info); +\endcode + +<em>Fortran</em> +\code + 23 comm = MPI_COMM_WORLD + 24 info = MPI_INFO_NULL + 25 + 26 CALL MPI_INIT(mpierror) + 27 CALL MPI_COMM_SIZE(comm, mpi_size, mpierror) + 28 CALL MPI_COMM_RANK(comm, mpi_rank, mpierror) + 29 ! + 30 ! Initialize FORTRAN interface + 31 ! + 32 CALL h5open_f(error) + 33 + 34 ! + 35 ! Setup file access property list with parallel I/O access. + 36 ! + 37 CALL h5pcreate_f(H5P_FILE_ACCESS_F, plist_id, error) 38 CALL h5pset_fapl_mpio_f(plist_id, comm, info, error) +\endcode + +The following example programs create an HDF5 file using Parallel HDF5: +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/C/H5Parallel/ph5_file_create.c">C: file_create.c</a> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/Fortran/H5Parallel/ph5_f90_file_create.f90">F90: file_create.f90</a> + + +\subsection subsec_pintro_create_dset Creating and Accessing a Dataset with PHDF5 +The programming model for creating and accessing a dataset is as follows: +<ol> +<li> +Create or open a Parallel HDF5 file with a collective call to: +#H5Dcreate +#H5Dopen +</li> +<li> +Obtain a copy of the file transfer property list and set it to use collective or independent I/O. +<ul> +<li> +Do this by first passing a data transfer property list class type to: #H5Pcreate +</li> +<li> +Then set the data transfer mode to either use independent I/O access or to use collective I/O, with a call to: #H5Pset_dxpl_mpio + +Following are the parameters required by this call: +<em>C</em> +\code + herr_t H5Pset_dxpl_mpio (hid_t dxpl_id, H5FD_mpio_xfer_t xfer_mode ) + dxpl_id IN: Data transfer property list identifier + xfer_mode IN: Transfer mode: + H5FD_MPIO_INDEPENDENT - use independent I/O access + (default) + H5FD_MPIO_COLLECTIVE - use collective I/O access +\endcode + +<em>Fortran</em> +\code + h5pset_dxpl_mpi_f (prp_id, data_xfer_mode, hdferr) + prp_id IN: Property List Identifier (INTEGER (HID_T)) + data_xfer_mode IN: Data transfer mode (INTEGER) + H5FD_MPIO_INDEPENDENT_F (0) + H5FD_MPIO_COLLECTIVE_F (1) + hdferr IN: Error code (INTEGER) +\endcode +</li> +<li> +Access the dataset with the defined transfer property list. +All processes that have opened a dataset may do collective I/O. Each process may do an independent +and arbitrary number of data I/O access calls, using: +#H5Dwrite +#H5Dread + +If a dataset is unlimited, you can extend it with a collective call to: #H5Dextend +</li> +</ul> +</li> +</ol> + +The following code demonstrates a collective write using Parallel HDF5: +<em>C</em> +\code + 95 /* + 96 * Create property list for collective dataset write. + 97 */ + 98 plist_id = H5Pcreate (H5P_DATASET_XFER); 99 H5Pset_dxpl_mpio (plist_id, H5FD_MPIO_COLLECTIVE); + 100 + 101 status = H5Dwrite (dset_id, H5T_NATIVE_INT, memspace, filespace, + 102 plist_id, data); +\endcode + +<em>Fortran</em> +\code + 108 ! Create property list for collective dataset write + 109 ! + 110 CALL h5pcreate_f (H5P_DATASET_XFER_F, plist_id, error) 111 CALL h5pset_dxpl_mpio_f (plist_id, H5FD_MPIO_COLLECTIVE_F, error) + 112 + 113 ! + 114 ! Write the dataset collectively. + 115 ! + 116 CALL h5dwrite_f (dset_id, H5T_NATIVE_INTEGER, data, dimsfi, error, & + 117 file_space_id = filespace, mem_space_id = memspace, xfer_prp = plist_id) +\endcode + +The following example programs create an HDF5 dataset using Parallel HDF5: +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/C/H5Parallel/ph5_dataset.c">C: dataset.c</a> +<a href="https://github.com/HDFGroup/hdf5-examples/blob/master/Fortran/H5Parallel/ph5_f90_dataset.f90">F90: dataset.f90</a> + + +\subsubsection subsec_pintro_hyperslabs Hyperslabs +The programming model for writing and reading hyperslabs is: +/li Each process defines the memory and file hyperslabs. +/li Each process executes a partial write/read call which is either collective or independent. + +The memory and file hyperslabs in the first step are defined with the #H5Sselect_hyperslab. + +The start (or offset), count, stride, and block parameters define the portion of the dataset +to write to. By changing the values of these parameters you can write hyperslabs with Parallel +HDF5 by contiguous hyperslab, by regularly spaced data in a column/row, by patterns, and by chunks: + +<table> +<tr> +<td> +\li @subpage IntroParContHyperslab +</td> +</tr> +<tr> +<td> +\li @subpage IntroParRegularSpaced +</td> +</tr> +<tr> +<td> +\li @subpage IntroParPattern +</td> +</tr> +<tr> +<td> +\li @subpage IntroParChunk +</td> +</tr> +</table> + + +<hr> +Navigate back: \ref index "Main" / \ref GettingStarted + +*/ diff --git a/doxygen/dox/LearnBasics1.dox b/doxygen/dox/LearnBasics1.dox index a9b6d0e..53c8e0a 100644 --- a/doxygen/dox/LearnBasics1.dox +++ b/doxygen/dox/LearnBasics1.dox @@ -642,7 +642,7 @@ See the programming example for an illustration of the use of these calls. \subsection subsecLBDsetCreateContent File Contents The contents of the file dset.h5 (dsetf.h5 for FORTRAN) are shown below: <table> -<caption>Contents of dset.h5 ( dsetf.h5)</caption> +<caption>Contents of dset.h5 (dsetf.h5)</caption> <tr> <td> \image html imgLBDsetCreate.gif |