mbox series

[0/3] add support for additional data types

Message ID 20240107152813.2668-1-syalavarthi@marvell.com (mailing list archive)
Headers
Series add support for additional data types |

Message

Srikanth Yalavarthi Jan. 7, 2024, 3:28 p.m. UTC 
  Added support for 64-bit integer data types for inference input and
output. Extended support for quantization of 32-bit and 64-bit integer
data types.

Srikanth Yalavarthi (3):
  mldev: add conversion routines for 32-bit integers
  mldev: add support for 64-integer data type
  ml/cnxk: add support for additional integer types

 drivers/ml/cnxk/cnxk_ml_io.c     |  24 ++
 drivers/ml/cnxk/mvtvm_ml_model.c |   4 +
 lib/mldev/mldev_utils.c          |   4 +
 lib/mldev/mldev_utils.h          | 184 ++++++++++
 lib/mldev/mldev_utils_neon.c     | 566 +++++++++++++++++++++++++++++++
 lib/mldev/mldev_utils_scalar.c   | 196 +++++++++++
 lib/mldev/rte_mldev.h            |   4 +
 lib/mldev/version.map            |   8 +
 8 files changed, 990 insertions(+)

Comments

Thomas Monjalon Feb. 18, 2024, 10:14 p.m. UTC | #1 
07/01/2024 16:28, Srikanth Yalavarthi:
> Added support for 64-bit integer data types for inference input and
> output. Extended support for quantization of 32-bit and 64-bit integer
> data types.
> 
> Srikanth Yalavarthi (3):
>   mldev: add conversion routines for 32-bit integers
>   mldev: add support for 64-integer data type
>   ml/cnxk: add support for additional integer types

Applied, thanks.