Skip to content

Commit dbdd077

Browse files
Add CUDA and AMD build subchapters to docs
1 parent c670477 commit dbdd077

File tree

1 file changed

+10
-2
lines changed

1 file changed

+10
-2
lines changed

doc/quick_start_guide.rst

Lines changed: 10 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -144,7 +144,10 @@ installation layout of compatible version. The following plugins from CodePlay a
144144
Building ``dpnp`` also requires `building Data Parallel Control Library for custom SYCL targets.
145145
<https://intelpython.github.io/dpctl/latest/beginners_guides/installation.html#building-for-custom-sycl-targets>`_
146146

147-
``dpnp`` can be built for CUDA devices using the ``--target-cuda`` argument.
147+
CUDA build
148+
~~~~~~~~~~
149+
150+
To build for CUDA devices, use the ``--target-cuda`` argument.
148151

149152
To target a specific architecture (e.g., ``sm_80``):
150153

@@ -170,7 +173,10 @@ Compute Capabilities can be found in the official
170173
A full list of available SYCL alias targets is available in the
171174
`DPC++ Compiler User Manual <https://intel.github.io/llvm/UsersManual.html>`_.
172175

173-
To build for AMD devices, use:
176+
AMD build
177+
~~~~~~~~~
178+
179+
To build for AMD devices, use the ``--target-hip=<arch>`` argument:
174180

175181
.. code-block:: bash
176182
@@ -193,6 +199,8 @@ For example:
193199
.. code-block:: bash
194200
python scripts/build_locally.py --target-hip=gfx90a
195201
202+
Multi-target build
203+
~~~~~~~~~~~~~~~~~~
196204

197205
It is, however, possible to build for Intel devices, CUDA devices, and an AMD device
198206
architecture all at once:

0 commit comments

Comments
 (0)