mbox series

[v1,0/3] Add support for 32 I/O per model

Message ID 20230423050814.825-1-syalavarthi@marvell.com (mailing list archive)
Headers
Series Add support for 32 I/O per model |

Message

Srikanth Yalavarthi April 23, 2023, 5:08 a.m. UTC 
  This patch series adds support for 32 inputs / outputs per each
model. Changes required to enable the required support include:

1. Splitiing model metadata fields into structures.
2. Update model metadata to v2301 which supports 32 I/O.
3. Update ML driver code to support metadata v2301 .


Srikanth Yalavarthi (3):
  ml/cnxk: split metadata fields into sections
  ml/cnxk: update model metadata to v2301
  ml/cnxk: add support for 32 I/O per model

 drivers/ml/cnxk/cn10k_ml_model.c | 401 +++++++++++++++++-------
 drivers/ml/cnxk/cn10k_ml_model.h | 512 +++++++++++++++++--------------
 drivers/ml/cnxk/cn10k_ml_ops.c   | 133 ++++++--
 3 files changed, 659 insertions(+), 387 deletions(-)

--
2.17.1

Comments

Thomas Monjalon June 12, 2023, 4:28 p.m. UTC | #1 
23/04/2023 07:08, Srikanth Yalavarthi:
> This patch series adds support for 32 inputs / outputs per each
> model. Changes required to enable the required support include:
> 
> 1. Splitiing model metadata fields into structures.
> 2. Update model metadata to v2301 which supports 32 I/O.
> 3. Update ML driver code to support metadata v2301 .
> 
> 
> Srikanth Yalavarthi (3):
>   ml/cnxk: split metadata fields into sections
>   ml/cnxk: update model metadata to v2301
>   ml/cnxk: add support for 32 I/O per model

Applied, thanks.