diff mbox series

[v3,4/4] mldev: update release notes for 23.11

Message ID 20230927181159.9794-5-syalavarthi@marvell.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series Spec changes to support multi I/O models |

Checks

Context Check Description
ci/loongarch-compilation success Compilation OK
ci/checkpatch success coding style OK
ci/loongarch-unit-testing success Unit Testing PASS
ci/Intel-compilation success Compilation OK
ci/intel-Testing success Testing PASS
ci/github-robot: build success github build: passed
ci/intel-Functional success Functional PASS
ci/iol-mellanox-Performance success Performance Testing PASS
ci/iol-broadcom-Performance success Performance Testing PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-broadcom-Functional success Functional Testing PASS
ci/iol-compile-amd64-testing success Testing PASS
ci/iol-intel-Functional success Functional Testing PASS
ci/iol-unit-arm64-testing success Testing PASS
ci/iol-unit-amd64-testing success Testing PASS
ci/iol-compile-arm64-testing success Testing PASS
ci/iol-sample-apps-testing success Testing PASS

Commit Message

Srikanth Yalavarthi Sept. 27, 2023, 6:11 p.m. UTC 
  Updated 23.11 release notes for mldev spec.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
---
 doc/guides/rel_notes/release_23_11.rst | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

Comments

Jerin Jacob Sept. 29, 2023, 3:39 a.m. UTC | #1 
On Thu, Sep 28, 2023 at 3:01 PM Srikanth Yalavarthi
<syalavarthi@marvell.com> wrote:
>
> Updated 23.11 release notes for mldev spec.
>
> Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>


Squash the doc changes to relevant patches where respective source
code change has been made.
Srikanth Yalavarthi Oct. 2, 2023, 9:59 a.m. UTC | #2 
> -----Original Message-----
> From: Jerin Jacob <jerinjacobk@gmail.com>
> Sent: 29 September 2023 09:10
> To: Srikanth Yalavarthi <syalavarthi@marvell.com>
> Cc: dev@dpdk.org; Shivah Shankar Shankar Narayan Rao
> <sshankarnara@marvell.com>; Anup Prabhu <aprabhu@marvell.com>;
> Prince Takkar <ptakkar@marvell.com>; Srikanth Yalavarthi
> <syalavarthi@marvell.com>
> Subject: [EXT] Re: [PATCH v3 4/4] mldev: update release notes for 23.11
> 
> External Email
> 
> ----------------------------------------------------------------------
> On Thu, Sep 28, 2023 at 3:01 PM Srikanth Yalavarthi
> <syalavarthi@marvell.com> wrote:
> >
> > Updated 23.11 release notes for mldev spec.
> >
> > Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
> 
> 
> Squash the doc changes to relevant patches where respective source code
> change has been made.

Updated in v4.
diff mbox series

Patch

diff --git a/doc/guides/rel_notes/release_23_11.rst b/doc/guides/rel_notes/release_23_11.rst
index 9746809a66..ca31ac5985 100644
--- a/doc/guides/rel_notes/release_23_11.rst
+++ b/doc/guides/rel_notes/release_23_11.rst
@@ -41,6 +41,11 @@  DPDK Release 23.11
 New Features
 ------------
 
+   * **Added support for models with multiple I/O in mldev library.**
+
+     Added support in mldev library for models with multiple inputs and outputs.
+
+
 .. This section should contain new features added in this release.
    Sample format:
 
@@ -97,6 +102,8 @@  Removed Items
 
 * kni: Removed the Kernel Network Interface (KNI) library and driver.
 
+* mldev: Removed APIs ``rte_ml_io_input_size_get`` and ``rte_ml_io_output_size_get``.
+
 
 API Changes
 -----------
@@ -119,6 +126,14 @@  API Changes
   except ``rte_thread_setname()`` and ``rte_ctrl_thread_create()`` which are
   replaced with ``rte_thread_set_name()`` and ``rte_thread_create_control()``.
 
+* mldev: Updated mldev API to support models with multiple inputs and outputs.
+  Updated the structure ``rte_ml_model_info`` to support input and output with
+  arbitrary shapes. Introduced support for ``rte_ml_io_layout``. Two layout types
+  split and packed are supported by the specification, which enables higher
+  control in handling models with multiple inputs and outputs. Updated ``rte_ml_op``,
+  ``rte_ml_io_quantize`` and ``rte_ml_io_dequantize`` to support an array of
+  ``rte_ml_buff_seg`` for inputs and outputs and removed use of batches argument.
+
 
 ABI Changes
 -----------