Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

tutorial update: hdf5_parallel, fix #16 #20

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

jmorice91
Copy link

No description provided.

@jmorice91 jmorice91 linked an issue Nov 21, 2024 that may be closed by this pull request
To see your `h5` file in readable file format, you can check the section [Comparison with the `h5dump` command](#h5comparison).

\warning
If you relaunch the executable, remember to delete your old `ex9.h5` file before, otherwise the data will not be changed correctly.

![graphical representation of the parallel I/O](PDI_hdf5_parallel.jpg)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

jpg not exist

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The images of the tutorial are in pdi/doc/images.
For solving this issue, we need to change the generation of website to avoid duplicate images.
I propose to add a new issue to solve this aftre the validation of all the tutorials.

Comment on lines +347 to 348
In this exercise you will write one single file `ex9.h5`(see `ex9.yml`) with parallel HDF5 whose content
should be independent from the number of processes used.
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Keep maximum code line length to 80.

Suggested change
In this exercise you will write one single file `ex9.h5`(see `ex9.yml`) with parallel HDF5 whose content
should be independent from the number of processes used.
In this exercise you will write one single file `ex9.h5`(see `ex9.yml`) with
parallel HDF5 whose content should be independent from the number of
processes used.

Once again, you only need to modify the YAML file in this exercise, no need to
touch the C file.

\attention You need to do this exercise with a parallel version of HDF5 and the \ref Decl_HDF5_plugin "Decl'HDF5 plugin" compiled in parallel.
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
\attention You need to do this exercise with a parallel version of HDF5 and the \ref Decl_HDF5_plugin "Decl'HDF5 plugin" compiled in parallel.
\attention You need to do this exercise with a parallel version of HDF5 and the
\ref Decl_HDF5_plugin "Decl'HDF5 plugin" compiled in parallel.


* Set the size of the dataset to take the global (parallel) array size into
account.
\note we have added the directive `collision_policy: write_into` of the \ref Decl_HDF5_plugin "Decl'HDF5 plugin" (see section COLLISION_POLICY). This parameter is used to define what to do when writing to a file or dataset that already exists.
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
\note we have added the directive `collision_policy: write_into` of the \ref Decl_HDF5_plugin "Decl'HDF5 plugin" (see section COLLISION_POLICY). This parameter is used to define what to do when writing to a file or dataset that already exists.
\note We have added the directive `collision_policy: write_into` of the
\ref Decl_HDF5_plugin "Decl'HDF5 plugin" (see section COLLISION_POLICY).
This parameter is used to define what to do when writing to a file or dataset
that already exists.

You will need to multiply the local size by the number of processes in each
dimension (use `psize`).

* Ensure the dataset selection of each process does not overlap with the others.
You will need to make a selection in the dataset that depends on the global
coordinate of the local data block (use `pcoord`).

Match the output from `ex9.h5dump`, that should be independent from the number
of processes used. You can easily check if the files are the same by running:
You should be able to match the expected output described in `ex9.h5dump`. You can easily check if the files are the same by running:
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
You should be able to match the expected output described in `ex9.h5dump`. You can easily check if the files are the same by running:
You should be able to match the expected output described in `ex9.h5dump`.
You can easily check if the files are the same by running:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

tutorial update: hdf5 parallel (ex9)
3 participants