RE: [EXTERNAL] [PATCH] mldev: enable to be compiled with msvc

> Now that the issues preventing this lib from being compiled with MSVC > are solved, it can be enabled. > > Signed-off-by: Andre Muezerie <mailto:andre...@linux.microsoft.com> Acked-by: Srikanth Yalavarthi

[PATCH v1 1/1] ml/cnxk: updates to cn10k error handling

Renamed cnxk error codes as cn10k error codes. Added support for model specific op_error_get routines. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.c | 8 drivers/ml/cnxk/cn10k_ml_dev.h | 16 drivers/ml/cnxk/cn10k_ml_ops.c | 20

[PATCH v1 1/1] 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 --- drivers/ml/cnxk/cnxk_ml_io.c| 134 +++ lib/mldev

[PATCH v1 1/1] 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 sclae factor and zero point to the user for quantization process. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_model.c | 4 drivers/ml/cnxk/cnxk_ml_io.h | 3

[PATCH v1 1/1] mldev: support get queue pair count

Added API to get ML device queue-pair count. Signed-off-by: Srikanth Yalavarthi --- lib/mldev/rte_mldev.c | 15 +++ lib/mldev/rte_mldev.h | 13 + lib/mldev/version.map | 1 + 3 files changed, 29 insertions(+) diff --git a/lib/mldev/rte_mldev.c b/lib/mldev/rte_mldev.c

[PATCH v1 1/1] ml/cnxk: fix incorrect handling of TVM model I/O

uctures for TVM model type") Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cnxk_ml_ops.c| 12 drivers/ml/cnxk/mvtvm_ml_model.c | 2 +- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/ml/cnxk/cnxk_ml_ops.c b/drivers/ml/cnxk/cnxk_ml_ops

[PATCH 1/1] ml/cnxk: enable data caching for all MRVL layers

From: Anup Prabhu Enabled data caching for all MRVL layers in TVM models Signed-off-by: Anup Prabhu --- drivers/ml/cnxk/cn10k_ml_ops.c | 9 ++--- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/ml/cnxk/cn10k_ml_ops.c b/drivers/ml/cnxk/cn10k_ml_ops.c index 834e55e88e9.

[PATCH v1 1/1] ml/cnxk: fix incorrect handling of TVM model I/O

uctures for TVM model type") Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cnxk_ml_ops.c| 12 drivers/ml/cnxk/mvtvm_ml_model.c | 2 +- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/ml/cnxk/cnxk_ml_ops.c b/drivers/ml/cnxk/cnxk_ml_ops

RE: [EXT] [PATCH] ml/cnxk: remove unused memory barrier macros

> -Original Message- > From: Honnappa Nagarahalli > Sent: Wednesday, February 7, 2024 9:06 AM > To: dev@dpdk.org; Srikanth Yalavarthi > Cc: Jerin Jacob ; n...@arm.com; Honnappa Nagarahalli > > Subject: [EXT] [PATCH] ml/cnxk: remove unused memory barrier macros >

[PATCH 1/1] buildtools: remove absolute paths from pc file

When linking with non-versioned libraries, absolute paths of the libraries are added to libdpdk.pc. This patch replaces the absolute path with correct linker flags, -l. https://github.com/mesonbuild/meson/issues/7766 Signed-off-by: Srikanth Yalavarthi --- buildtools/pkg-config/set-static

[PATCH 4/4] ml/cnxk: add adapter dequeue function

Implemented ML adapter dequeue function. Signed-off-by: Srikanth Yalavarthi --- drivers/event/cnxk/cn10k_worker.h | 3 +++ drivers/ml/cnxk/cn10k_ml_event_dp.h | 2 ++ drivers/ml/cnxk/cn10k_ml_ops.c | 17 + drivers/ml/cnxk/version.map | 1 + 4 files changed, 23

[PATCH 3/4] ml/cnxk: add adapter enqueue function

Implemented ML adapter enqueue function. Rename internal fast-path JD preparation function for poll mode. Added JD preparation function for event mode. Updated meson build dependencies for ml/cnxk driver. Signed-off-by: Srikanth Yalavarthi --- drivers/event/cnxk/cn10k_eventdev.c | 3

[PATCH 2/4] event/cnxk: implement queue pair add and delete

Added structures for ML event adapter. Implemented ML event adapter queue-pair add and delete functions. Signed-off-by: Srikanth Yalavarthi --- drivers/event/cnxk/cn10k_eventdev.c | 103 drivers/event/cnxk/cnxk_eventdev.h | 4 ++ drivers/ml/cnxk/cnxk_ml_ops.h

[PATCH 1/4] event/cnxk: add ML adapter capabilities get

Implemented driver function to get ML adapter capabilities. Signed-off-by: Srikanth Yalavarthi --- Depends-on: series-30752 ("Introduce Event ML Adapter") drivers/event/cnxk/cn10k_eventdev.c | 15 +++ drivers/event/cnxk/meson.build | 2 +- drivers/ml/cnxk/cn10

[PATCH 0/4] Implementation of CNXK ML event adapter driver

This series of patches is an implementation of event ML adapter for Marvell's Octeon platform. Srikanth Yalavarthi (4): event/cnxk: add ML adapter capabilities get event/cnxk: implement queue pair add and delete ml/cnxk: add adapter enqueue function ml/cnxk: add adapter dequeue fun

[PATCH 09/11] event/ml: add support for runtime params

Added support to set and get runtime params for ML adapter. Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/rte_event_ml_adapter.c | 99 + 1 file changed, 99 insertions(+) diff --git a/lib/eventdev/rte_event_ml_adapter.c b/lib/eventdev/rte_event_ml_adapter.c

[PATCH 08/11] event/ml: add support to get adapter service ID

Added support to get ML adapter service ID. Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/rte_event_ml_adapter.c | 20 1 file changed, 20 insertions(+) diff --git a/lib/eventdev/rte_event_ml_adapter.c b/lib/eventdev/rte_event_ml_adapter.c index 60c10caef68

[PATCH 07/11] event/ml: add adapter start and stop

Added ML adapter start and stop functions. Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/eventdev_pmd.h | 42 lib/eventdev/rte_event_ml_adapter.c | 75 + 2 files changed, 117 insertions(+) diff --git a/lib/eventdev/eventdev_pmd.h b/lib

[PATCH 06/11] event/ml: add support for service function

Added support for ML adapter service function for software based event devices. Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/rte_event_ml_adapter.c | 538 1 file changed, 538 insertions(+) diff --git a/lib/eventdev/rte_event_ml_adapter.c b/lib/eventdev

[PATCH 05/11] event/ml: add adapter queue pair add and delete

Added ML adapter queue-pair add and delete functions Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/eventdev_pmd.h | 54 lib/eventdev/rte_event_ml_adapter.c | 193 2 files changed, 247 insertions(+) diff --git a/lib/eventdev/eventdev_pmd.h b

[PATCH 04/11] event/ml: add adapter port get

Added ML adapter port get function. Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/rte_event_ml_adapter.c | 19 +++ 1 file changed, 19 insertions(+) diff --git a/lib/eventdev/rte_event_ml_adapter.c b/lib/eventdev/rte_event_ml_adapter.c index fed3b67c858..93ba58b3e9e

[PATCH 03/11] event/ml: add adapter create and free

Added ML event adapter create and free functions. Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/rte_event_ml_adapter.c | 317 1 file changed, 317 insertions(+) diff --git a/lib/eventdev/rte_event_ml_adapter.c b/lib/eventdev/rte_event_ml_adapter.c index

[PATCH 02/11] event/ml: add ml adapter capabilities get

Added library function to get ML adapter capabilities. Signed-off-by: Srikanth Yalavarthi --- lib/eventdev/eventdev_pmd.h | 29 + lib/eventdev/rte_eventdev.c | 27 +++ 2 files changed, 56 insertions(+) diff --git a/lib/eventdev/eventdev_pmd.h

[PATCH 01/11] eventdev: introduce ML event adapter library

Introduce event ML adapter APIs. This patch provides information on adapter modes and usage. Application can use this event adapter interface to transfer packets between ML device and event device. Signed-off-by: Srikanth Yalavarthi --- MAINTAINERS |6

[PATCH 00/11] Introduce Event ML Adapter

If HW supports the capability RTE_EVENT_ML_ADAPTER_CAP_INTERNAL_PORT_QP_EV_BIND, event information must be passed to the add API. Srikanth Yalavarthi (11): eventdev: introduce ML event adapter library event/ml: add ml adapter capabilities get event/ml: add adapter create and free event/ml: add adapter port get

[PATCH 1/3] mldev: add conversion routines for 32-bit integers

Added routines to convert data from 32-bit integer type to float32_t and vice-versa. Signed-off-by: Srikanth Yalavarthi --- lib/mldev/mldev_utils.h| 92 + lib/mldev/mldev_utils_neon.c | 242 + lib/mldev/mldev_utils_scalar.c | 98

[PATCH 3/3] ml/cnxk: add support for additional integer types

Added support quantization and dequantization of 32-bit and 64-bit integer types. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cnxk_ml_io.c | 24 drivers/ml/cnxk/mvtvm_ml_model.c | 4 2 files changed, 28 insertions(+) diff --git a/drivers/ml/cnxk

[PATCH 2/3] mldev: add support for 64-integer data type

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 --- lib/mldev/mldev_utils.c| 4 + lib/mldev/mldev_utils.h| 92 ++ lib/mldev/mldev_utils_neon.c

[PATCH 0/3] add support for additional data types

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

[PATCH 1/1] ml/cnxk: enable data caching for TVM models

Enabled data caching for TVM models with MRVL only layers. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 9 +++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/ml/cnxk/cn10k_ml_ops.c b/drivers/ml/cnxk/cn10k_ml_ops.c index 53700387335

[PATCH 1/1] ml/cnxk: exclude caching run stats from xstats

From: Anup Prabhu Exclude the hardware and firmware latency of model data caching run from xstats calculation. Fixes: 9cfad6c334f2 ("ml/cnxk: update device and model xstats functions") Cc: sta...@dpdk.org Signed-off-by: Anup Prabhu Acked-by: Srikanth Yalavarthi --- drive

[PATCH 1/1] ml/cnxk: exclude caching run stats from xstats

From: Anup Prabhu Exclude the hardware and firmware latency of model data caching run from xstats calculation. Fixes: 9cfad6c334f2 ("ml/cnxk: update device and model xstats functions") Signed-off-by: Anup Prabhu Acked-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_

[PATCH v2 1/1] ml/cnxk: fix reading model and layer ID

Using model_id from op structure as layer index for TVM models with multiple MRVL layers is incorrect. This patch fixes the issue by reading the layer index from the job descriptor structure. Fixes: 31cc30b5f088 ("ml/cnxk: update model start/stop functions") Signed-off-by: Srikanth

RE: [EXT] Re: [PATCH 1/1] ml/cnxk: fix name of TVM model with single layer

> -Original Message- > From: Bruce Richardson > Sent: 22 November 2023 22:21 > To: Srikanth Yalavarthi > Cc: Prince Takkar ; dev@dpdk.org; Shivah Shankar > Shankar Narayan Rao ; Anup Prabhu > ; Jerin Jacob Kollanukkaran > Subject: [EXT] Re: [PATCH 1/1] ml/cnx

[PATCH v2 1/1] ml/cnxk: fix name of TVM model with single layer

Name field of TVM model with single MRVL layer is currently set to empty string. Update the name with the field from metadata. Fixes: 5cea2c67edfc ("ml/cnxk: update internal TVM model info structure") Signed-off-by: Srikanth Yalavarthi --- v2: - Replaced rte_memcpy with strlcpy

[PATCH 1/1] ml/cnxk: fix reading model and layer ID

Using model_id from op structure as layer index for TVM models with multiple MRVL layers is incorrect. This patch fixes the issue by reading the layer index from the job descriptor structure. Fixes: 31cc30b5f088 ("ml/cnxk: update model start/stop functions") Signed-off-by: Srikanth

[PATCH 1/1] ml/cnxk: fix name of TVM model with single layer

Name field of TVM model with single MRVL layer is currently set to empty string. Update the name with the field from metadata. Fixes: 5cea2c67edfc ("ml/cnxk: update internal TVM model info structure") Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/mvtvm_ml_model.c | 4 ++

[PATCH v1 1/1] ml/cnxk: fix fast-path synchronization

handle value. Fixes: 88001b4d88de ("ml/cnxk: update fast path functions") Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cnxk_ml_ops.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ml/cnxk/cnxk_ml_ops.c b/drivers/ml/cnxk/cnxk_ml_ops.c index 81866ceaa6..971362b242 10

RE: [EXT] Re: [PATCH v2 1/1] devtools: update sources in build tags script

> -Original Message- > From: Thomas Monjalon > Sent: 08 November 2023 16:54 > To: Srikanth Yalavarthi > Cc: Bruce Richardson ; David Marchand > ; Morten Brørup > ; Stephen Hemminger > ; dev@dpdk.org; Srikanth Yalavarthi > ; Shivah Shankar Shankar Narayan Rao &g

RE: [EXT] Re: [PATCH v1 1/1] devtools: update sources in build tags script

> -Original Message- > From: Ferruh Yigit > Sent: 08 November 2023 14:19 > To: Srikanth Yalavarthi > Cc: dev@dpdk.org; Shivah Shankar Shankar Narayan Rao > ; Jerin Jacob Kollanukkaran > ; tho...@monjalon.net > Subject: [EXT] Re: [PATCH v1 1/1] devtools: upda

[PATCH v2 1/1] devtools: update sources in build tags script

As part of deprecating kmods meson option, 'kernel/linux' directory is removed from the repository. This patch removes non-existing 'kernel/linux' directory from linux_sources of build tags script. Fixes: a52d472c5c94 ("build: deprecate kmods meson option") Sign

[PATCH v1 1/1] devtools: update sources in build tags script

As part of deprecating kmods meson option, 'kernel/linux' directory is removed from the repository. This patch removes non-existing 'kernel/linux' directory from linux_sources of build tags script. Signed-off-by: Srikanth Yalavarthi --- devtools/build-tags.sh | 1 - 1 file

RE: [EXT] Re: [PATCH v4 1/1] build: add libarchive to external deps

> -Original Message- > From: Bruce Richardson > Sent: 03 November 2023 22:21 > To: Srikanth Yalavarthi > Cc: David Marchand ; Aaron Conole > ; Igor Russkikh ; > dev@dpdk.org; Shivah Shankar Shankar Narayan Rao > ; Anup Prabhu ; > Prince Takkar ; sta...@d

[PATCH v5 1/1] build: add libarchive to external deps

_args and c_link_args externally. Fixes: 40edb9c0d36b ("eal: handle compressed firmware") Cc: sta...@dpdk.org Signed-off-by: Srikanth Yalavarthi --- v5: - Updated as per review comments v4: - Rebase over latest main v3: - Add to libarchive ext_deps v2: - Update ml/cnxk meson

[PATCH v2 1/1] ml/cnxk: fix updating internal I/O info

Update scale factor in IO info of TVM models from metadata. Fixes: 35c3e790b4a0 ("ml/cnxk: update internal info for TVM model") Signed-off-by: Srikanth Yalavarthi --- v2: - Rebase over latest main v1: - Initial PATCH drivers/ml/cnxk/mvtvm_ml_model.c | 2 ++ 1 file changed, 2

[PATCH v4 1/1] build: add libarchive to external deps

_args and c_link_args externally. Fixes: 40edb9c0d36b ("eal: handle compressed firmware") Cc: sta...@dpdk.org Signed-off-by: Srikanth Yalavarthi --- v4: - Rebase over latest main v3: - Add to libarchive ext_deps v2: - Update ml/cnxk meson config v1: - Initial patch config/meso

[PATCH v1 1/1] ml/cnxk: fix updating internal I/O info

Update scale factor in IO info of TVM models from metadata. Fixes: 35c3e790b4a0 ("ml/cnxk: update internal info for TVM model") Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/mvtvm_ml_model.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/ml/cnxk/mvtvm_ml

[PATCH v3 1/1] build: add libarchive to external deps

_args and c_link_args externally. Fixes: 40edb9c0d36b ("eal: handle compressed firmware") Cc: sta...@dpdk.org Signed-off-by: Srikanth Yalavarthi --- Depends-on: series-30002 ("Implementation of revised ml/cnxk driver") v3: - Updated depends on series information v2: - U

[PATCH v2 1/1] build: add libarchive to external deps

_args and c_link_args externally. Fixes: 40edb9c0d36b ("eal: handle compressed firmware") Cc: sta...@dpdk.org Signed-off-by: Srikanth Yalavarthi --- config/meson.build | 5 - drivers/ml/cnxk/meson.build | 1 + lib/eal/meson.build | 3 +++ 3 files changed, 4 i

RE: [EXT] Re: [PATCH 1/1] build: update link args and includes for libarchive

> -Original Message- > From: Srikanth Yalavarthi > Sent: 23 October 2023 19:32 > To: Bruce Richardson > Cc: dmitry.kozl...@gmail.com; Aaron Conole ; Igor > Russkikh ; David Marchand > ; dev@dpdk.org; Shivah Shankar Shankar > Narayan Rao ; Jerin Jacob Kollanukk

[PATCH v2 1/1] app/mldev: enable support for pre-quantized I/O

From: Anup Prabhu Enabled support for pre-quantized input and output in ML test application. Signed-off-by: Anup Prabhu --- v2: - Updated application help v1: - Initial changes app/test-mldev/ml_options.c| 11 +- app/test-mldev/ml_options.h| 28 ++

[PATCH v9 34/34] ml/cnxk: enable creation of mvtvm virtual device

Enable support to create a mvtvm virtual device on system's without a PCI based ML HW accelerator. Signed-off-by: Srikanth Yalavarthi --- doc/guides/mldevs/cnxk.rst | 50 +++- drivers/ml/cnxk/cn10k_ml_dev.c | 8 ++ drivers/ml/cnxk/cn10k_ml_dev.h | 3 + drivers/ml

[PATCH v9 32/34] ml/cnxk: support quantize and dequantize callback

From: Prince Takkar Added support for quantize and dequantize callback functions for TVM models. Signed-off-by: Prince Takkar --- drivers/ml/cnxk/mvtvm_ml_ops.c | 129 + drivers/ml/cnxk/mvtvm_ml_ops.h | 4 + 2 files changed, 133 insertions(+) diff --git a/dri

[PATCH v9 30/34] ml/cnxk: implement I/O alloc and free callbacks

Implemented callback functions for IO allocation and free for Glow layers. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 87 ++ drivers/ml/cnxk/cn10k_ml_ops.h | 3 ++ drivers/ml/cnxk/mvtvm_ml_ops.c | 2 + 3 files changed, 92 insertions

[PATCH v9 27/34] ml/cnxk: update internal TVM model info structure

From: Prince Takkar Added support to update internal model info structure for TVM models. Signed-off-by: Prince Takkar Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/mvtvm_ml_model.c | 66 drivers/ml/cnxk/mvtvm_ml_model.h | 2 + drivers/ml/cnxk

[PATCH v9 26/34] ml/cnxk: support start and stop for TVM models

Added support to start and stop TVM models. TVM model start would invoke layer start for all Glow layers part of the model. TVM model stop would invoke layer stop for all Glow layers part of the model. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Anup Prabhu --- drivers/ml/cnxk

[PATCH v9 33/34] ml/cnxk: enable fast-path ops for TVM models

by the driver. Signed-off-by: Anup Prabhu Signed-off-by: Srikanth Yalavarthi --- doc/guides/rel_notes/release_23_11.rst | 3 + drivers/ml/cnxk/cn10k_ml_ops.c | 4 - drivers/ml/cnxk/cnxk_ml_ops.c | 4 + drivers/ml/cnxk/cnxk_ml_ops.h | 5 + drivers/ml/cnxk

[PATCH v9 25/34] ml/cnxk: enable OCM check for multilayer TVM model

From: Anup Prabhu Enabled check for OCM size requirement for multi-layer TVM model. Compute OCM scratch and WB requirement for all layers during the load stage. Signed-off-by: Anup Prabhu --- drivers/ml/cnxk/cnxk_ml_ops.c | 60 +++ 1 file changed, 60 insertions(

[PATCH v9 31/34] ml/cnxk: add generic ML malloc and free callback

Implemented generic ML malloc and free callbacks Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 30 ++ drivers/ml/cnxk/cn10k_ml_ops.h | 3 +++ drivers/ml/cnxk/mvtvm_ml_ops.c | 2 ++ 3 files changed, 35 insertions(+) diff --git a/drivers/ml

[PATCH v9 23/34] ml/cnxk: update internal info for TVM model

Enabled updating internal IO info structures for TVM model. Compute static fields related to the model I/O. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cnxk_ml_ops.c| 4 + drivers/ml/cnxk/mvtvm_ml_model.c | 133 +++ drivers/ml/cnxk/mvtvm_ml_model.h

[PATCH v9 22/34] ml/cnxk: fetch layer info and load TVM model

Added support to fetch TVM model layer information and update internal structures based on the layer information Set callback functions for layer load and unload and enable model loading using TVMDP library. Added support to fetch full metadata after model load. Signed-off-by: Srikanth Yalavarthi

[PATCH v9 29/34] ml/cnxk: enable reporting model runtime as xstats

Added model xstats entries to compute runtime latency. Allocated internal resources for TVM model xstats. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 9 +++ drivers/ml/cnxk/cn10k_ml_ops.h | 2 + drivers/ml/cnxk/cnxk_ml_ops.c| 131

[PATCH v9 21/34] ml/cnxk: add support to parse TVM model objects

Added support to parse TVM model objects from the model archive buffer. Added support to check for all expected objects and copy TVM model objects to internal buffers. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Anup Prabhu --- drivers/ml/cnxk/cnxk_ml_ops.c| 5 ++- drivers/ml/cnxk

[PATCH v9 18/34] ml/cnxk: support config and close of tvmdp library

Added support to configure and close TVMDP library based on ML device configuration options. Updated meson build to enable Jansson, TVM runtime, TVMDP library as build dependencies. Signed-off-by: Srikanth Yalavarthi --- config/arm/arm64_cn10k_linux_gcc | 1 + config/arm/arm64_cn9k_linux_gcc

[PATCH v9 28/34] ml/cnxk: support device dump for TVM models

Enabled support to print TVM model layer info. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cnxk_ml_model.c | 7 +++- drivers/ml/cnxk/mvtvm_ml_model.c | 59 drivers/ml/cnxk/mvtvm_ml_model.h | 2 ++ drivers/ml/cnxk/mvtvm_ml_stubs.c | 8

[PATCH v9 17/34] ml/cnxk: move error handling to cnxk layer

Move error type structures to cnxk layer. cn10k layer to handle fw and hw error sub-types only. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.h | 41 ++- drivers/ml/cnxk/cn10k_ml_ops.c | 93 +- drivers/ml/cnxk/cnxk_ml_dev.c | 8

[PATCH v9 24/34] ml/cnxk: enable model unload in tvmdp library

Enable unloading model using external tvmdp library. Updated layer unload callback to support multiple layers. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Anup Prabhu --- drivers/ml/cnxk/cn10k_ml_ops.c | 8 +--- drivers/ml/cnxk/cnxk_ml_ops.c| 7 +-- drivers/ml/cnxk

[PATCH v9 16/34] ml/cnxk: update fast path functions

as argument. Updated function arguments to enable the function to be used as callback by TVM HW runtime. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.h | 5 - drivers/ml/cnxk/cn10k_ml_ops.c | 241 drivers/ml/cnxk/cn10k_ml_ops.h | 13

[PATCH v9 20/34] ml/cnxk: add support for identify model type

Enable support to parse model buffer to identify the model type and model sub-type. Enabled basic checks for Glow model type buffer. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Anup Prabhu --- drivers/ml/cnxk/cnxk_ml_model.c | 49 drivers/ml/cnxk

[PATCH v9 12/34] ml/cnxk: update data quantization functions

Added cnxk wrapper functions to quantize input data and dequantize output data. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 164 - drivers/ml/cnxk/cn10k_ml_ops.h | 7 -- drivers/ml/cnxk/cnxk_ml_io.c | 95

[PATCH v9 19/34] ml/cnxk: add structures to support TVM model type

Introduced model type, sub-type and layer type. Added internal structures for TVM model objects. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ocm.c | 3 ++ drivers/ml/cnxk/cn10k_ml_ops.c | 6 ++- drivers/ml/cnxk/cnxk_ml_model.h | 66

[PATCH v9 09/34] ml/cnxk: update model load and unload functions

Implemented cnxk wrapper functions to load and unload ML models. Wrapper functions would invoke the cn10k model load and unload functions. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_model.c | 244 - drivers/ml/cnxk/cn10k_ml_model.h | 26 ++- drivers

[PATCH v9 15/34] ml/cnxk: update device and model xstats functions

Added cnxk wrapper function to handle ML device and model extended stats. Handling resources for the xstats is done in the cnxk layer. Introduced internal xstats group. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.h | 4 - drivers/ml/cnxk/cn10k_ml_ops.c | 531

[PATCH v9 07/34] ml/cnxk: update device handling functions

Implement CNXK wrapper functions for dev_info_get, dev_configure, dev_close, dev_start and dev_stop. The wrapper functions allocate / release common resources for the ML driver and invoke device specific functions. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 230

[PATCH v9 14/34] ml/cnxk: update device stats functions

Added cnxk wrapper function to handle ML device stats Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 32 -- drivers/ml/cnxk/cn10k_ml_ops.h | 2 -- drivers/ml/cnxk/cnxk_ml_ops.c | 36 -- 3 files changed, 34

[PATCH v9 06/34] ml/cnxk: rename cnxk ops function pointers struct

Renamed cn10k ML ops structure with cnxk prefix. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.c | 2 +- drivers/ml/cnxk/cn10k_ml_ops.c | 73 +- drivers/ml/cnxk/cn10k_ml_ops.h | 34 +++- drivers/ml/cnxk/cnxk_ml_ops.c | 36

[PATCH v9 13/34] ml/cnxk: update device debug functions

Added cnxk wrapper for device dump and selftest debug functions. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_model.c | 118 + drivers/ml/cnxk/cn10k_ml_model.h | 1 + drivers/ml/cnxk/cn10k_ml_ocm.c | 8 +- drivers/ml/cnxk/cn10k_ml_ocm.h | 2

[PATCH v9 11/34] ml/cnxk: update model utility functions

Added cnxk wrapper function to update model params and fetch model info. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 38 ++- drivers/ml/cnxk/cn10k_ml_ops.h | 5 ++-- drivers/ml/cnxk/cnxk_ml_ops.c | 48 -- 3

[PATCH v9 05/34] ml/cnxk: add generic cnxk xstats structures

Introduced generic xstats structures and renamed cn10k xstats enumerations with cnxk prefix. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.h | 86 +--- drivers/ml/cnxk/cn10k_ml_model.h | 6 +- drivers/ml/cnxk/cn10k_ml_ops.c | 169

[PATCH v9 10/34] ml/cnxk: update model start and stop functions

Implemented cnxk wrapper functions to start and stop ML models. Wrapper functions would invoke the cn10k model start and stop functions. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ocm.c | 28 ++-- drivers/ml/cnxk/cn10k_ml_ocm.h | 12 +- drivers/ml/cnxk/cn10k_ml_ops.c

[PATCH v9 08/34] ml/cnxk: update queue-pair handling functions

Added cnxk wrapper function to handle ML device queue-pairs. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 135 + drivers/ml/cnxk/cn10k_ml_ops.h | 7 +- drivers/ml/cnxk/cnxk_ml_ops.c | 153 - drivers/ml

[PATCH v9 03/34] ml/cnxk: add generic model and layer structures

Introduce generic cnxk model and layer structure. These structures would enable supporting models with multiple layers. A model is a collection of multiple independent layers with flow dependencies between the layers. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.h | 9

[PATCH v9 04/34] ml/cnxk: add generic cnxk request structure

Added generic cnxk request structure. Moved common fields from cn10k structures to cnxk structure. Moved job related structures and enumerations to ops headers. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.c | 72 +++ drivers/ml/cnxk/cn10k_ml_dev.h | 269

[PATCH v9 02/34] ml/cnxk: add generic cnxk device structure

Introduce generic cnxk device structure. This structure is a top level device structure for the driver, which would encapsulate the target / platform specific device structure. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_dev.c | 316 ++-- drivers/ml/cnxk

[PATCH v9 01/34] ml/cnxk: drop support for register polling

Dropped support for device argument "poll_mem" for cnxk ML driver. Support to use registers for polling is removed and DDR addresses would be used for polling. Signed-off-by: Srikanth Yalavarthi --- doc/guides/mldevs/cnxk.rst | 16 - drivers/ml/cnxk/cn10k_ml_d

[PATCH v9 00/34] Implementation of revised ml/cnxk driver

Srikanth Yalavarthi (30): ml/cnxk: drop support for register polling ml/cnxk: add generic cnxk device structure ml/cnxk: add generic model and layer structures ml/cnxk: add generic cnxk request structure ml/cnxk: add generic cnxk xstats structures ml/cnxk: rename cnxk ops function

RE: [EXT] Re: [PATCH 1/1] build: update link args and includes for libarchive

> -Original Message- > From: Bruce Richardson > Sent: 23 October 2023 18:36 > To: Srikanth Yalavarthi > Cc: dmitry.kozl...@gmail.com; Aaron Conole ; Igor > Russkikh ; David Marchand > ; dev@dpdk.org; Shivah Shankar Shankar > Narayan Rao ; Jerin Jacob Kollanukk

RE: [EXT] Re: [PATCH 1/1] build: update link args and includes for libarchive

> -Original Message- > From: Bruce Richardson > Sent: 23 October 2023 17:24 > To: Srikanth Yalavarthi > Cc: Aaron Conole ; Igor Russkikh > ; David Marchand ; > dev@dpdk.org; Shivah Shankar Shankar Narayan Rao > ; Jerin Jacob Kollanukkaran > ; sta...@dpdk.

RE: [EXT] Re: [PATCH 1/1] build: update link args and includes for libarchive

> -Original Message- > From: Bruce Richardson > Sent: 23 October 2023 14:56 > To: Srikanth Yalavarthi > Cc: Aaron Conole ; Igor Russkikh > ; David Marchand ; > dev@dpdk.org; Shivah Shankar Shankar Narayan Rao > ; Jerin Jacob Kollanukkaran > ; sta...@dpdk.org &g

[PATCH v8 18/34] ml/cnxk: support config and close of tvmdp library

Added support to configure and close TVMDP library based on ML device configuration options. Updated meson build to enable Jansson, TVM runtime, TVMDP library as build dependencies. Signed-off-by: Srikanth Yalavarthi --- config/arm/arm64_cn10k_linux_gcc | 1 + config/arm/arm64_cn9k_linux_gcc

[PATCH v8 34/34] ml/cnxk: enable creation of mvtvm virtual device

Enable support to create a mvtvm virtual device on system's without a PCI based ML HW accelerator. Signed-off-by: Srikanth Yalavarthi --- doc/guides/mldevs/cnxk.rst | 50 +++- drivers/ml/cnxk/cn10k_ml_dev.c | 8 ++ drivers/ml/cnxk/cn10k_ml_dev.h | 3 + drivers/ml

[PATCH v8 33/34] ml/cnxk: enable fast-path ops for TVM models

by the driver. Signed-off-by: Anup Prabhu Signed-off-by: Srikanth Yalavarthi --- doc/guides/rel_notes/release_23_11.rst | 3 + drivers/ml/cnxk/cn10k_ml_ops.c | 4 - drivers/ml/cnxk/cnxk_ml_io.h | 6 ++ drivers/ml/cnxk/cnxk_ml_ops.c | 4 + drivers/ml/cnxk

[PATCH v8 30/34] ml/cnxk: implement I/O alloc and free callbacks

Implemented callback functions for IO allocation and free for Glow layers. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 87 ++ drivers/ml/cnxk/cn10k_ml_ops.h | 3 ++ drivers/ml/cnxk/mvtvm_ml_ops.c | 2 + 3 files changed, 92 insertions

[PATCH v8 32/34] ml/cnxk: support quantize and dequantize callback

From: Prince Takkar Added support for quantize and dequantize callback functions for TVM models. Signed-off-by: Prince Takkar --- drivers/ml/cnxk/mvtvm_ml_ops.c | 129 + drivers/ml/cnxk/mvtvm_ml_ops.h | 4 + 2 files changed, 133 insertions(+) diff --git a/dri

[PATCH v8 27/34] ml/cnxk: update internal TVM model info structure

From: Prince Takkar Added support to update internal model info structure for TVM models. Signed-off-by: Prince Takkar Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/mvtvm_ml_model.c | 65 drivers/ml/cnxk/mvtvm_ml_model.h | 2 + drivers/ml/cnxk

[PATCH v8 31/34] ml/cnxk: add generic ML malloc and free callback

Implemented generic ML malloc and free callbacks Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 30 ++ drivers/ml/cnxk/cn10k_ml_ops.h | 3 +++ drivers/ml/cnxk/mvtvm_ml_ops.c | 2 ++ 3 files changed, 35 insertions(+) diff --git a/drivers/ml

[PATCH v8 24/34] ml/cnxk: enable model unload in tvmdp library

Enable unloading model using external tvmdp library. Updated layer unload callback to support multiple layers. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Anup Prabhu --- drivers/ml/cnxk/cn10k_ml_ops.c | 8 +--- drivers/ml/cnxk/cnxk_ml_ops.c| 7 +-- drivers/ml/cnxk

[PATCH v8 23/34] ml/cnxk: update internal info for TVM model

Enabled updating internal IO info structures for TVM model. Compute static fields related to the model I/O. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cnxk_ml_ops.c| 4 ++ drivers/ml/cnxk/mvtvm_ml_model.c | 111 +++ drivers/ml/cnxk/mvtvm_ml_model.h

[PATCH v8 29/34] ml/cnxk: enable reporting model runtime as xstats

Added model xstats entries to compute runtime latency. Allocated internal resources for TVM model xstats. Signed-off-by: Srikanth Yalavarthi --- drivers/ml/cnxk/cn10k_ml_ops.c | 9 +++ drivers/ml/cnxk/cn10k_ml_ops.h | 2 + drivers/ml/cnxk/cnxk_ml_ops.c| 131

[PATCH v8 20/34] ml/cnxk: add support for identify model type

Enable support to parse model buffer to identify the model type and model sub-type. Enabled basic checks for Glow model type buffer. Signed-off-by: Srikanth Yalavarthi Signed-off-by: Anup Prabhu --- drivers/ml/cnxk/cnxk_ml_model.c | 49 drivers/ml/cnxk

  1   2   3   4   5   6   7   8   9   >