IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[DOC] cpu documentation fixes (#17815)

Browse Source
This commit is contained in:
Anton Voronov 2023-06-01 12:26:06 +04:00 committed by GitHub
parent 24cddecb57
commit 5e64a7c0c1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
docs/OV_Runtime_UG/supported_plugins/CPU.md
View File

@ -94,8 +94,7 @@ the `BFLOAT16 – Hardware Numerics Definition white paper <https://software.int
Using the ``bf16`` precision provides the following performance benefits:
- ``bfloat16`` data type allows using Intel® Advanced Matrix Extension (AMX), which provides dramatically faster computations on corresponding hardware in
comparison with AVX512 or AVX2 instructions in many DL operation implementations.
- ``bfloat16`` data type allows using Intel® Advanced Matrix Extension (AMX), which provides dramatically faster computations on corresponding hardware in comparison with AVX512 or AVX2 instructions in many DL operation implementations.
- Reduced memory consumption since ``bfloat16`` data half the size of 32-bit float.
To check if the CPU device can support the ``bfloat16`` data type, use the :doc:`query device properties interface <openvino_docs_OV_UG_query_api>`
@ -296,7 +295,7 @@ For more details, see the :doc:`model caching <openvino_docs_OV_UG_Model_caching
Extensibility
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
CPU plugin supports fallback on ``ov::Op`` reference implementation if the plugin do not have its own implementation for such operation.
CPU plugin supports fallback on ``ov::Op`` reference implementation if the plugin does not have its own implementation for such operation.
That means that :doc:`OpenVINO™ Extensibility Mechanism <openvino_docs_Extensibility_UG_Intro>` can be used for the plugin extension as well.
Enabling fallback on a custom operation implementation is possible by overriding the ``ov::Op::evaluate`` method in the derived operation
class (see :doc:`custom OpenVINO™ operations <openvino_docs_Extensibility_UG_add_openvino_ops>` for details).
@ -461,7 +460,7 @@ weights are loaded from DDR/L3 cache in the packed format this significantly dec
and as a consequence improve inference performance.
To use this feature, the user is provided with property ``sparse_weights_decompression_rate``, which can take
values from the interval \[0, 1\]. ``sparse_weights_decompression_rate`` defines sparse rate threshold: only operations
values from the interval \[0, 1\]. ``sparse_weights_decompression_rate`` defines sparse rate threshold: only operations
with higher sparse rate will be executed using ``sparse weights decompression feature``. The default value is ``1``,
which means the option is disabled.