mldev: add scale and zero point to I/O info struct

Added scale and zero point to I/O information structure.
This would provision sharing the recommended scale factor
and zero point to the user for q

mldev: add scale and zero point to I/O info struct

Added scale and zero point to I/O information structure.
This would provision sharing the recommended scale factor
and zero point to the user for quantization process.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...

mldev: introduce data type conversion functions

Introduced data type conversion functions with support for
user defined scale factor and zero-point. Updated library
functions to support asymmetric /

mldev: introduce data type conversion functions

Introduced data type conversion functions with support for
user defined scale factor and zero-point. Updated library
functions to support asymmetric / affine conversion for
integer types.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...

mldev: add queue pair count

Added API to get ML device queue-pair count.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

lib: move alignment attribute on types for MSVC

The current location used for __rte_aligned(a) for alignment of types
is not compatible with MSVC. There is only a single location accepted
by both to

lib: move alignment attribute on types for MSVC

The current location used for __rte_aligned(a) for alignment of types
is not compatible with MSVC. There is only a single location accepted
by both toolchains.

The standard offers no alignment facility that compatibly interoperates
with C and C++ but it may be achieved by relocating the placement of
__rte_aligned(a) to the aforementioned location accepted by all currently
supported toolchains.

To allow alignment for both compilers, do the following:

* Expand __rte_aligned(a) to __declspec(align(a)) when building
with MSVC.

* Move __rte_aligned from the end of {struct,union} definitions to
be between {struct,union} and tag.

The placement between {struct,union} and the tag allows the desired
alignment to be imparted on the type regardless of the toolchain being
used for all of GCC, LLVM, MSVC compilers building both C and C++.

Note: this move has an additional benefit as Doxygen is not confused
anymore like for the rte_event_vector struct definition.

Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
Acked-by: Chengwen Feng <fengchengwen@huawei.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>

show more ...

lib: use log helper with prefix

Use RTE_LOG_LINE_PREFIX instead of RTE_LOG_LINE in macro expansions
which allows a prefix and arguments to be inserted into the log line
without the need to use the #

lib: use log helper with prefix

Use RTE_LOG_LINE_PREFIX instead of RTE_LOG_LINE in macro expansions
which allows a prefix and arguments to be inserted into the log line
without the need to use the ## args variadic argument pack extension.

Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>

show more ...

mldev: add 64-bit integers

Added support in mldev spec for 64-bit integer types. Added
routines to convert data from 64-bit integer type to float32_t
and vice-versa.

Signed-off-by: Srikanth Yalavar

mldev: add 64-bit integers

Added support in mldev spec for 64-bit integer types. Added
routines to convert data from 64-bit integer type to float32_t
and vice-versa.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...

lib: use per line logging in helpers

Use RTE_LOG_LINE in existing macros that append a \n.
This will help catching unwanted newline character or multilines
in log messages.

Signed-off-by: David Mar

lib: use per line logging in helpers

Use RTE_LOG_LINE in existing macros that append a \n.
This will help catching unwanted newline character or multilines
in log messages.

Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Chengwen Feng <fengchengwen@huawei.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>

show more ...

mldev: drop input and output size queries

Drop support and use of ML input and output size get functions,
rte_ml_io_input_size_get and rte_ml_io_output_size_get.

These functions are not required, a

mldev: drop input and output size queries

Drop support and use of ML input and output size get functions,
rte_ml_io_input_size_get and rte_ml_io_output_size_get.

These functions are not required, as the model buffer size can
be computed from the fields of updated rte_ml_io_info structure.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
Acked-by: Anup Prabhu <aprabhu@marvell.com>
Acked-by: Shivah Shankar S <sshankarnara@marvell.com>

show more ...

mldev: introduce IO layout

Introduce IO layout in ML device specification.
IO layout defines the expected arrangement of model input and output
buffers in the memory.
Packed and Split layout support

mldev: introduce IO layout

Introduce IO layout in ML device specification.
IO layout defines the expected arrangement of model input and output
buffers in the memory.
Packed and Split layout support is added in the specification.

Updated rte_ml_op to support array of rte_ml_buff_seg
pointers to support packed and split I/O layouts.
Updated ML quantize and dequantize APIs to support rte_ml_buff_seg
pointer arrays.
Replaced batch_size with min_batches and max_batches in rte_ml_model_info.

Implement support for model IO layout in ml/cnxk driver.
Updated the ML test application to support IO layout and
dropped support for '--batches' in test application.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
Acked-by: Shivah Shankar S <sshankarnara@marvell.com>

show more ...

mldev: support arbitrary shape dimensions

Updated rte_ml_io_info to support shape of arbitrary number of dimensions.
Dropped use of rte_ml_io_shape and rte_ml_io_format.
Introduced new fields nb_ele

mldev: support arbitrary shape dimensions

Updated rte_ml_io_info to support shape of arbitrary number of dimensions.
Dropped use of rte_ml_io_shape and rte_ml_io_format.
Introduced new fields nb_elements and size in rte_ml_io_info.

Updated drivers and app/mldev to support the changes.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
Acked-by: Anup Prabhu <aprabhu@marvell.com>
Acked-by: Shivah Shankar S <sshankarnara@marvell.com>

show more ...

remove C11 compatibility macro

C11 conformant compiler is documented as a minimum requirement to build
and consume DPDK.
Remove use of RTE_STD_C11 macro marking use of C11 features with
__extension_

remove C11 compatibility macro

C11 conformant compiler is documented as a minimum requirement to build
and consume DPDK.
Remove use of RTE_STD_C11 macro marking use of C11 features with
__extension__ since it is no longer necessary and then remove definition
of RTE_STD_C11 macro.

Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Morten Brørup <mb@smartsharesystems.com>

show more ...

mldev: introduce revised xstats

Introduce revised xstats APIs to support reporting device and
per-model xstats. Stat type is selected through mode parameter.
Support modes include device and model.

mldev: introduce revised xstats

Introduce revised xstats APIs to support reporting device and
per-model xstats. Stat type is selected through mode parameter.
Support modes include device and model.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...

mldev: remove xstats

This change is a preparatory step for revised xstats APIs.
Revised xstats APIs support reporting device and per model
stats, which is based on eventdev xstats.

Removed xstats A

mldev: remove xstats

This change is a preparatory step for revised xstats APIs.
Revised xstats APIs support reporting device and per model
stats, which is based on eventdev xstats.

Removed xstats APIs from spec and library implementation.
Disabled reporting xstats in test application and disabled
xstats functions in drivers. Renamed stats_get function to
throughput_get.

This change is needed as the revised APIs are not backward
compatible with the current xstats.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...

mldev: introduce machine learning device API

Add mldev API specification to standardize and use the machine learning
device and inference operations in vendor neutral way.

Following operations are

mldev: introduce machine learning device API

Add mldev API specification to standardize and use the machine learning
device and inference operations in vendor neutral way.

Following operations are abstracted through APIs

- ML device capability probe
- ML device configuration
- ML device queue pair configuration
- ML device state management
- ML device stat/xstat operations
- ML model load/unload/start/stop operations
- ML model information probe
- ML IO operations to find size for input and output buffers
- ML quantize and dequantize operations
- ML ops pool creation and free operations
- ML device enqueue/dequeue fastpath interference operations

Also added programming guide.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...