02/12/2022 20:57, Tyler Retzlaff:
> On Fri, Dec 02, 2022 at 09:03:25AM +0100, Morten Brørup wrote:
> > +Bruce, FreeBSD EAL maintainer
> >
> >
> >
> > This is one of the consequences of a bloated EAL.
> >
> > How is an application supposed to run on top of an EAL that isn't fully
> > implemente
The reset flag in the query structure are cleared by mistake, cause
the flow count never be reset, so the query API will always has count
value even the flow has stopped, and this will cause the flow never
been aged.
Fixes: 30ecce522732 ("net/nfp: support flow API")
Cc: chaoyong...@corigine.com
S
https://bugs.dpdk.org/show_bug.cgi?id=1121
jiang,yu (yux.ji...@intel.com) changed:
What|Removed |Added
Status|UNCONFIRMED |RESOLVED
Resolution|---
> 08/12/2022 19:14, Akhil Goyal:
> > > By default 'test-meson-builds.sh' script clones the repository which the
> > > script is in, and selects a configured branch ('DPDK_ABI_REF_VERSION')
> > > as a reference for ABI check.
> > >
> > > This patch enables selecting different repository to close for
> -Original Message-
> From: Wu, Jingjing
> Sent: Thursday, December 8, 2022 11:31 AM
> To: dev@dpdk.org
> Cc: Wu, Jingjing ; Xing, Beilei
> ;
> sta...@dpdk.org
> Subject: [PATCH] net/idpf: fix build option check
>
> When enable_iova_as_pa option is disabled, idpf driver should avoid
在 2022/12/8 19:20, Bruce Richardson 写道:
On Thu, Dec 08, 2022 at 11:55:16AM +0100, Morten Brørup wrote:
+To: Bruce and Stephen might also have opinions on this.
From: Huisong Li [mailto:lihuis...@huawei.com]
Sent: Thursday, 8 December 2022 09.06
The 'dev_flags', 'rx_offloads', 'tx_offloads'
From: Long Wu
The NFP PMD driver retrieves the linkspeed by reading the
NFP_NET_CFG_STS_LINK register. This register is not set by all versions
of the firmware.
Add a second preferred method to read the linkspeed from the port table
instead, while keeping the old lookup method as a fallback in c
Hi Abhishek,
I agree with Xiao.
I think it will be better you just add subvendor and subdevice you want to be
take care of by this vdpa driver.
> -Original Message-
> From: Wang, Xiao W
> Sent: Thursday, December 8, 2022 9:09 PM
> To: Maheshwari, Abhishek
> Cc: dev@dpdk.org; sta...@dpd
https://bugs.dpdk.org/show_bug.cgi?id=1145
Bug ID: 1145
Summary: net/ice fdir flow create/destroy failed with
RTE_LIBRTE_ICE_16BYTE_RX_DESC defined
Product: DPDK
Version: 21.11
Hardware: All
OS: All
From: Peng Zhang
All the queue pairs are shared between VF and PF for NFP,
and there exist different assignment policy for different
firmware application.
The user can create VFs up to the max number of queue pairs,
which will cause the last few VFs has no queue pairs and
cannot be used, because
On Tue, 6 Dec 2022 09:28:24 -0800
Tyler Retzlaff wrote:
> + /* Wait for the control thread to initialize successfully */
> + while ((ctrl_thread_status =
> + __atomic_load_n(¶ms->ctrl_thread_status,
> + __ATOMIC_ACQUIRE)) == CTRL_THREAD_LAUNCHING)
Remove rte_ctrl_thread_create API which exposes pthread_t and provide
new rte_control_thread_create API based on EALs rte_thread_t.
To limit compatibility regression risk and ease of removal of the
existing rte_ctrl_thread_create in the future duplicate most of the
existing implementation. The dup
Give notice of rte_ctrl_thread_create deprecation.
Signed-off-by: Tyler Retzlaff
---
doc/guides/rel_notes/deprecation.rst | 4
1 file changed, 4 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes/deprecation.rst
index b9b02dc..ce3b4b7 100644
--- a/doc/g
Add rte_control_thread_create API as a replacement for
rte_ctrl_thread_create to allow deprecation of the use of platform
specific types in DPDK public API.
Signed-off-by: Tyler Retzlaff
---
lib/eal/common/eal_common_thread.c | 89 ++
lib/eal/include/rte_threa
Duplicate the rte_ctrl_thread_create test adapted to use
rte_control_thread create to keep both apis under test until
rte_ctrl_thread_create is removed.
Signed-off-by: Tyler Retzlaff
---
app/test/test_lcores.c | 42 ++
1 file changed, 42 insertions(+)
dif
On Thu, Dec 08, 2022 at 10:59:13PM +0100, Mattias Rönnblom wrote:
> On 2022-12-07 17:38, Tyler Retzlaff wrote:
> >
> >>
> >>>+ } u;
> >>> void *arg;
> >>> int ret;
> >>
> >>Why is 'ret' needed? (This question is unrelated to your patch.)
> >
> >i'm not the original author so difficult to answe
On 2022-12-07 17:38, Tyler Retzlaff wrote:
On Wed, Dec 07, 2022 at 10:13:39AM +0100, Mattias Rönnblom wrote:
On 2022-12-06 18:28, Tyler Retzlaff wrote:
Add rte_control_thread_create API as a replacement for
rte_ctrl_thread_create to allow deprecation of the use of platform
specific types in DPD
* Replace the use of pthread_t in struct lcore_config with the EAL
rte_thread_t type.
* Replace the direct use of pthread_create(), pthread_self()
pthread_getaffinity_np() and pthread_setaffinity_np().
Minor tweaks to return value comparisons to align with current DPDK
style.
Signed-off-by:
Added user guide for Marvell cnxk ML driver for Marvell Octeon
cnxk Soc family. Added details about device initialization,
debug options and runtime device args supported by the driver.
Signed-off-by: Srikanth Yalavarthi
---
v2:
* Fixed typos
MAINTAINERS | 1 +
doc/guides/inde
Added device argument "poll_mem" to select the memory
region to be used for polling in fast-path requests.
Implemented support to use scratch registers for polling.
Available pool of scratch registers one-to-one mapped with
the internal request queue.
poll_mem:
ddr: Use DDR memory location f
Added device argument "hw_queue_lock" to select the JCMDQ enqueue
ROC function to be used in fast path.
hw_queue_lock:
0: Disable, use lock free version of JCMDQ enqueue ROC function for
job queuing. To avoid race condition in request queuing to
hardware, disabling hw_queue_lock
Added device argument "ocm_alloc_mode" to select OCM allocation
method during model start. Two modes are supported by the driver.
Added implementation for ocm_alloc_mode lowest as default.
ocm_alloc_mode:
lowest: Allocate from first available free slot / lowest
tile ID in OCM (default)
Added device argument 'cache_model_data' to enable model data
caching. An inference request would be executed with dummy data
in synchronous mode during model start stage. This run would
cache the model weights and bias in the memory and result in
improved inference throughput.
cache_model_data =
Enabled support to enable and report DPE warnings from ML
firmware. Configure firmware load flags based on the device
arguments.
Default values:
enable_dpe_errors = 1
report_dpe_errors = 0
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 94 +++
Enabled support to retrieve xstats in either cycles or ns.
Access to sclk is enabled only if an RVU device is probed
during initialization. Driver would return the xstats in
nanoseconds only when an RVU device is probed, else would
fallback to cycles.
Signed-off-by: Srikanth Yalavarthi
---
drive
Enabled support to get and reset ML device stats. Device stats
include number of requests enqueued/dequeued and error count.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 55 --
drivers/ml/cnxk/cn10k_ml_ops.h | 3 ++
2 files changed, 55
Added internal function to execute ML inference requests
in synchronous mode. Sync mode inference execution is used
to launch inference requests without using a queue-pair.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 53 ++
drivers/ml/c
Added support to handle ML device extended stats. Support
is enabled to get xstats names and stats values and reset
xstats. Supported xstats include avg, min and max hardware
and firmware latency.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.h | 3 +
drivers/ml/cnxk/cn
Enabled driver support to dequeue inference requests from
internal queue. Dequeue checks for request completion by
polling the status field of the job request.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 61 ++
drivers/ml/cnxk/cn10k_ml_
Added support for device selftest. Device selftest includes
checking the status of firmware.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 57 ++
1 file changed, 57 insertions(+)
diff --git a/drivers/ml/cnxk/cn10k_ml_ops.c b/drivers/ml/c
Enabled support for error handling. Added error types and subtypes
supported by ML firmware. Enabled support to get device specific
error code and message for a completed ML request.
Signed-off-by: Srikanth Yalavarthi
---
v2:
* Fixed typos
drivers/ml/cnxk/cn10k_ml_dev.c | 4 +-
drivers/ml/cnx
Enabled driver support to enqueue a burst of inference requests
to ML device. Enqueue uses internal ML request structure to queue
the inferences and job completion through polling.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 96 ++
driv
Implemented driver functions to quantize / dequantize input
and output data. Support is enabled for multiple batches.
Quantization / dequantization use the type conversion functions
defined in ML common code.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 150 +++
Added support to dump device debug information. Debug info on
cn10k device includes model state info, OCM usage info, firmware
debug and exception buffer.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ocm.c | 51 +
drivers/ml/cnxk/cn10k_ml_ocm.h | 1 +
drivers/ml/cnx
Added driver functions to get input and output buffer sizes
for a given batch size. This function would compute the buffer
size based on specific requirements of the device.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 52 ++
1 file chan
Added cnxk driver functions to update model params or weights
and bias after a models is loaded. Updating model params would
not require reloading the model.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 31 +++
1 file changed, 31 insertions(
Added driver functions to get model information. Added
internal functions to set and get model info.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_model.c | 54
drivers/ml/cnxk/cn10k_ml_model.h | 9 ++
drivers/ml/cnxk/cn10k_ml_ops.c | 37
Implemented model stop driver function. A model stop job is
enqueued through scratch registers and is checked for
completion through polling in a synchronous mode. OCM pages
are released after model stop completion.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 115
Implemented model start driver function. A model start job
is checked for completion in synchronous mode. Tilemask and
OCM slot is calculated before starting the model. Model start
is enqueued through scratch registers. OCM pages are reserved
after model start completion.
Signed-off-by: Srikanth
Added support to reserve and free OCM pages for a model. OCM
pages are reserved upon completion of model start and are
released after model stop.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ocm.c | 131 -
drivers/ml/cnxk/cn10k_ml_ocm.h | 3 +
Added JD structures for load, unload and run jobs. Initialize
job command and allocate memory for request structures for slow
path jobs.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.h | 99
drivers/ml/cnxk/cn10k_ml_model.h | 4 ++
driver
Added internal structures to handle tile and OCM information and
OCM to model memory mapping. Initialize the fields to platform
specific defaults and compute the OCM / tile requirements for model.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.h | 5 ++
drivers/ml/cnxk/cn
Added support to compute OCM tilemask and page start for a
model. The computed tilemask and page start are used during
model start to copy model weights and bias to OCM. OCM slot
for a model is allocated from the tiles with maximum amount
of free memory.
Signed-off-by: Srikanth Yalavarthi
---
dr
Added model metadata structure and enabled metadata check
during model load. Remap cnxk IO types with RTE IO types.
Store and update model metadata in model structure.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_model.c | 196 +++
drivers/ml/cnxk/cn10k_ml_mode
Added internal structures to handle derived address fields
and enabled support to compute DMA addresses for model start.
Enabled updating internal model fields.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_model.c | 88
drivers/ml/cnxk/cn10k_ml
Added cnxk driver implementations to load and unload ML models.
Enabled support in configure stage to allocate model handles
array. Assign model ID and allocate resources per each model
during load stage and release resources during model unload.
Added internal structures to handle ML models.
Sign
Enabled support to create and destroy device queue-pairs. Updated
configure stage to create array to store queue-pair handles. Added
internal structure for queue-pair, queue and ML inference requests.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 207 +++
Implemented ML driver functions to start and stop ML device.
Start / Stop would enable or disable ML device to accept
inference requests.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 42 +++---
1 file changed, 39 insertions(+), 3 deletions(-
Enabled parsing ML firmware path for cn10k. Default path is set
as "/lib/firmware/mlip-fw.bin", when args are not provided. Added
internal structures for ML firmware.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 71 ++
drivers/ml/cnxk/cn
Enabled device initialization and firmware load on simulator
platform. Firmware load stage on simulator would involve
launching a firmware handshake request only.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 119 +
1 file changed, 107 in
Enabled support to load ML firmware on cn10ka ROC model. Reset
MLIP device during dev_close driver operation. Device can't be
reconfigured after a call to close. Job execution is disabled
after firmware load, execution is enabled in device start state.
Added internal request structure.
Signed-off-
Implemented driver functions to configure and close ML devices.
Added skeleton code and support to reconfigure ML device. PCI
device remove is enabled in device close.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 2 ++
drivers/ml/cnxk/cn10k_ml_dev.h | 21
ML inference engine on cn10k platform is a PCI based device. Added
driver support to probe and remove the device for cn10k poll mode
driver. The device is named by the PMD as "ml_cn10k".
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 114 +
Added support to get the cn10k ML device information. This is a
driver implementation for the RTE function rte_ml_dev_info_get.
ML device on cn10k supports one queue-pair in lock-free mode and
does not support segmented input output data.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn
Added initial source files and build files for ML cnxk driver.
Signed-off-by: Srikanth Yalavarthi
---
Depends-on: patch-120600 ("common/cnxk: add ML headers and ROC code for cnxk")
MAINTAINERS| 2 ++
drivers/meson.build| 1 +
drivers/ml/cnxk/cn10k_ml_dev.c | 8
Marvell ML CNXK Driver
--
This patch series implements Machine Learning (ML) driver for Marvell
Octeon 10 (cnxk) platform. ML inferencing is supported on cnxk platform
through an integrated ML inferencing processor. The current driver
supports programming the ML hardware engine
Added user guide for Marvell cnxk ML driver for Marvell Octeon
cnxk Soc family. Added details about device initialization,
debug options and runtime device args supported by the driver.
Signed-off-by: Srikanth Yalavarthi
---
MAINTAINERS | 1 +
doc/guides/index.rst| 1
Added device argument "poll_mem" to select the memory
region to be used for polling in fast-path requests.
Implemented support to use scratch registers for polling.
Available pool of scratch registers one-to-one mapped with
the internal request queue.
poll_mem:
ddr: Use DDR memory location f
Added device argument "hw_queue_lock" to select the JCMDQ enqueue
ROC function to be used in fast path.
hw_queue_lock:
0: Disable, use lock free version of JCMDQ enqueue ROC function for
job queuing. To avoid race condition in request queuing to
hardware, disabling hw_queue_lock
Added device argument 'cache_model_data' to enable model data
caching. An inference request would be executed with dummy data
in synchronous mode during model start stage. This run would
cache the model weights and bias in the memory and result in
improved inference throughput.
cache_model_data =
Added support to handle ML device extended stats. Support
is enabled to get xstats names and stats values and reset
xstats. Supported xstats include avg, min and max hardware
and firmware latency.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.h | 3 +
drivers/ml/cnxk/cn
Enabled support for error handling. Added error types and subtypes
supported by ML firmware. Enabled support to get device specific
error code and message for a completed ML request.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 4 +-
drivers/ml/cnxk/cn10k_ml_dev.h |
Added device argument "ocm_alloc_mode" to select OCM allocation
method during model start. Two modes are supported by the driver.
Added implementation for ocm_alloc_mode lowest as default.
ocm_alloc_mode:
lowest: Allocate from first available free slot / lowest
tile ID in OCM (default)
Added internal function to execute ML inference requests
in synchronous mode. Sync mode inference execution is used
to launch inference requests without using a queue-pair.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 53 ++
drivers/ml/c
Enabled support to enable and report DPE warnings from ML
firmware. Configure firmware load flags based on the device
arguments.
Default values:
enable_dpe_errors = 1
report_dpe_errors = 0
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 94 +++
Enabled driver support to enqueue a burst of inference requests
to ML device. Enqueue uses internal ML request structure to queue
the inferences and job completion through polling.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 96 ++
driv
Enabled support to retrieve xstats in either cycles or ns.
Access to sclk is enabled only if an RVU device is probed
during initialization. Driver would return the xstats in
nanoseconds only when an RVU device is probed, else would
fallback to cycles.
Signed-off-by: Srikanth Yalavarthi
---
drive
Implemented driver functions to quantize / dequantize input
and output data. Support is enabled for multiple batches.
Quantization / dequantization use the type conversion functions
defined in ML common code.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 150 +++
Enabled support to get and reset ML device stats. Device stats
include number of requests enqueued/dequeued and error count.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 55 --
drivers/ml/cnxk/cn10k_ml_ops.h | 3 ++
2 files changed, 55
Enabled driver support to dequeue inference requests from
internal queue. Dequeue checks for request completion by
polling the status field of the job request.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 61 ++
drivers/ml/cnxk/cn10k_ml_
Added support for device selftest. Device selftest includes
checking the status of firmware.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 57 ++
1 file changed, 57 insertions(+)
diff --git a/drivers/ml/cnxk/cn10k_ml_ops.c b/drivers/ml/c
Added support to reserve and free OCM pages for a model. OCM
pages are reserved upon completion of model start and are
released after model stop.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ocm.c | 131 -
drivers/ml/cnxk/cn10k_ml_ocm.h | 3 +
Added support to dump device debug information. Debug info on
cn10k device includes model state info, OCM usage info, firmware
debug and exception buffer.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ocm.c | 51 +
drivers/ml/cnxk/cn10k_ml_ocm.h | 1 +
drivers/ml/cnx
Added support to compute OCM tilemask and page start for a
model. The computed tilemask and page start are used during
model start to copy model weights and bias to OCM. OCM slot
for a model is allocated from the tiles with maximum amount
of free memory.
Signed-off-by: Srikanth Yalavarthi
---
dr
Added driver functions to get input and output buffer sizes
for a given batch size. This function would compute the buffer
size based on specific requirements of the device.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 52 ++
1 file chan
Added JD structures for load, unload and run jobs. Initialize
job command and allocate memory for request structures for slow
path jobs.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.h | 99
drivers/ml/cnxk/cn10k_ml_model.h | 4 ++
driver
Added internal structures to handle tile and OCM information and
OCM to model memory mapping. Initialize the fields to platform
specific defaults and compute the OCM / tile requirements for model.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.h | 5 ++
drivers/ml/cnxk/cn
Added cnxk driver functions to update model params or weights
and bias after a models is loaded. Updating model params would
not require reloading the model.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 31 +++
1 file changed, 31 insertions(
Added model metadata structure and enabled metadata check
during model load. Remap cnxk IO types with RTE IO types.
Store and update model metadata in model structure.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_model.c | 196 +++
drivers/ml/cnxk/cn10k_ml_mode
Added driver functions to get model information. Added
internal functions to set and get model info.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_model.c | 54
drivers/ml/cnxk/cn10k_ml_model.h | 9 ++
drivers/ml/cnxk/cn10k_ml_ops.c | 37
Enabled support to create and destroy device queue-pairs. Updated
configure stage to create array to store queue-pair handles. Added
internal structure for queue-pair, queue and ML inference requests.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 207 +++
Implemented model stop driver function. A model stop job is
enqueued through scratch registers and is checked for
completion through polling in a synchronous mode. OCM pages
are released after model stop completion.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 115
Implemented ML driver functions to start and stop ML device.
Start / Stop would enable or disable ML device to accept
inference requests.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_ops.c | 42 +++---
1 file changed, 39 insertions(+), 3 deletions(-
Implemented model start driver function. A model start job
is checked for completion in synchronous mode. Tilemask and
OCM slot is calculated before starting the model. Model start
is enqueued through scratch registers. OCM pages are reserved
after model start completion.
Signed-off-by: Srikanth
Enabled support to load ML firmware on cn10ka ROC model. Reset
MLIP device during dev_close driver operation. Device can't be
reconfigured after a call to close. Job execution is disabled
after firmware load, execution is enabled in device start state.
Added internal request structure.
Signed-off-
Added internal structures to handle derived address fields
and enabled support to compute DMA addresses for model start.
Enabled updating internal model fields.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_model.c | 88
drivers/ml/cnxk/cn10k_ml
Added cnxk driver implementations to load and unload ML models.
Enabled support in configure stage to allocate model handles
array. Assign model ID and allocate resources per each model
during load stage and release resources during model unload.
Added internal structures to handle ML models.
Sign
Enabled parsing ML firmware path for cn10k. Default path is set
as "/lib/firmware/mlip-fw.bin", when args are not provided. Added
internal structures for ML firmware.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 71 ++
drivers/ml/cnxk/cn
Implemented driver functions to configure and close ML devices.
Added skeleton code and support to reconfigure ML device. PCI
device remove is enabled in device close.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 2 ++
drivers/ml/cnxk/cn10k_ml_dev.h | 21
Enabled device initialization and firmware load on simulator
platform. Firmware load stage on simulator would involve
launching a firmware handshake request only.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 119 +
1 file changed, 107 in
Added support to get the cn10k ML device information. This is a
driver implementation for the RTE function rte_ml_dev_info_get.
ML device on cn10k supports one queue-pair in lock-free mode and
does not support segmented input output data.
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn
Added initial source files and build files for ML cnxk driver.
Signed-off-by: Srikanth Yalavarthi
---
Depends-on: patch-120600 ("common/cnxk: add ML headers and ROC code for cnxk")
MAINTAINERS| 2 ++
drivers/meson.build| 1 +
drivers/ml/cnxk/cn10k_ml_dev.c | 8
ML inference engine on cn10k platform is a PCI based device. Added
driver support to probe and remove the device for cn10k poll mode
driver. The device is named by the PMD as "ml_cn10k".
Signed-off-by: Srikanth Yalavarthi
---
drivers/ml/cnxk/cn10k_ml_dev.c | 114 +
Marvell ML CNXK Driver
--
This patch series implements Machine Learning (ML) driver for Marvell
Octeon 10 (cnxk) platform. ML inferencing is supported on cnxk platform
through an integrated ML inferencing processor. The current driver
supports programming the ML hardware engine
Added ML cnxk headers for register, structure definitions and
ROC layer. Implemented ROC functions, registered logtype for
ML module with the name pmd.ml.cnxk and defined ML hardware ID.
Signed-off-by: Srikanth Yalavarthi
---
Depends-on: series-26047 ("implementation of ML common code")
MAINTAI
08/12/2022 19:14, Akhil Goyal:
> > By default 'test-meson-builds.sh' script clones the repository which the
> > script is in, and selects a configured branch ('DPDK_ABI_REF_VERSION')
> > as a reference for ABI check.
> >
> > This patch enables selecting different repository to close for reference
Added ARM NEON intrinsic based implementations to support conversion
of data types. Support is enabled to handle int8, uint8, int16, uint16,
float16, float32 and bfloat16 types.
Signed-off-by: Srikanth Yalavarthi
---
drivers/common/ml/meson.build | 5 +
drivers/common/ml/ml_utils.c |
Added generic implementations to support conversion of data types.
Support is enabled to handle int8, uint8, int16, uint16, float16,
float32 and bfloat16 types.
Signed-off-by: Srikanth Yalavarthi
---
drivers/common/ml/meson.build| 2 +
drivers/common/ml/ml_utils.c | 86 +---
d
Type conversion routines transform data from higher to lower
precision data types or vice-versa. These conversion functions
can be used by the ML driver implementations for quantization
and de-quantization.
Added driver routines for type conversion. These driver routines
invoke the architecture sp
Added initial files for common ML driver code. Implemented ML
type to size conversion, type to string and format to string
conversion utility functions.
Signed-off-by: Srikanth Yalavarthi
---
Depends-on: series-26046 ("app/mldev: implement test framework for mldev")
MAINTAINERS
1 - 100 of 147 matches
Mail list logo
