memzone: remove unnecessary null checks

The function rte_memzone_free() already checks if the argument is NULL.
Add it to the coccinelle fix script and correct all the existing code.

Signed-off-by:

memzone: remove unnecessary null checks

The function rte_memzone_free() already checks if the argument is NULL.
Add it to the coccinelle fix script and correct all the existing code.

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

show more ...

app/mldev: fix file and buffer freeing

Addressed issues reported by klocwork static analysis tool.

Fixes: fccf444cfe05 ("app/mldev: add function for file read")
Cc: stable@dpdk.org

Signed-off-by:

app/mldev: fix file and buffer freeing

Addressed issues reported by klocwork static analysis tool.

Fixes: fccf444cfe05 ("app/mldev: add function for file read")
Cc: stable@dpdk.org

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 ...

app/mldev: support pre-quantized I/O

Enabled support for pre-quantized input and output in ML
test application.

Signed-off-by: Anup Prabhu <aprabhu@marvell.com>
Acked-by: Shivah Shankar S <sshankar

app/mldev: support pre-quantized I/O

Enabled support for pre-quantized input and output in ML
test application.

Signed-off-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 ...

app/mldev: fix error reporting on IO failure

Application is reporting the test output as success when a
failure occurs in writing the output. Fix incorrect error
reporting on failure to write output

app/mldev: fix error reporting on IO failure

Application is reporting the test output as success when a
failure occurs in writing the output. Fix incorrect error
reporting on failure to write output files.

Fixes: da6793390596 ("app/mldev: support inference validation")
Cc: stable@dpdk.org

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

show more ...

app/mldev: improve checks for invalid options

Improve checks for ML application options. Check for negative,
non-integral and hexadecimal values. Check for number of entries
in filelist option. Impr

app/mldev: improve checks for invalid options

Improve checks for ML application options. Check for negative,
non-integral and hexadecimal values. Check for number of entries
in filelist option. Improve error reporting for invalid options.

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

show more ...

app/mldev: add function for file read

Added internal function to read model, input and reference
files with required error checks. This change fixes the
unchecked return value and improper use of ne

app/mldev: add function for file read

Added internal function to read model, input and reference
files with required error checks. This change fixes the
unchecked return value and improper use of negative value
issues reported by coverity scan for file read operations.

Coverity issue: 383742, 383743
Fixes: f6661e6d9a3a ("app/mldev: validate model operations")
Fixes: da6793390596 ("app/mldev: support inference validation")
Cc: stable@dpdk.org

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

show more ...

app/mldev: fix code formatting and typos

Updated ML application source files to have uniform code formatting
style across. Remove extra blank lines. Fix typos in application help.

Fixes: 8cb22a5454

app/mldev: fix code formatting and typos

Updated ML application source files to have uniform code formatting
style across. Remove extra blank lines. Fix typos in application help.

Fixes: 8cb22a545447 ("app/mldev: fix debug build")
Fixes: da6793390596 ("app/mldev: support inference validation")
Fixes: c0e871657d6a ("app/mldev: support queue pairs and size")
Cc: stable@dpdk.org

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

show more ...

app/mldev: check model and filelist option

Application currently doesn't check for empty models list and
filelist entries. This causes the app to report an incorrect
error messages and test status w

app/mldev: check model and filelist option

Application currently doesn't check for empty models list and
filelist entries. This causes the app to report an incorrect
error messages and test status when the lists are empty.

Fixes: bbd272edcb14 ("app/mldev: add ordered inferences")
Fixes: f6661e6d9a3a ("app/mldev: validate model operations")
Cc: stable@dpdk.org

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

show more ...

app/mldev: enable reporting xstats

Enabled reporting xstats in ML test application. Enabled
stats option for model_ops test case. Added common files
for xstats and throughput functions.

Signed-off-

app/mldev: enable reporting xstats

Enabled reporting xstats in ML test application. Enabled
stats option for model_ops test case. Added common files
for xstats and throughput functions.

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: remove unnecessary null checks

These are places where mldev is doing unnecessary checks
for calling free() style functions.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acke

mldev: remove unnecessary null checks

These are places where mldev is doing unnecessary checks
for calling free() style functions.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...

app/mldev: fix debug build

Compiling with -O0 and -g triggers these warnings:

../app/test-mldev/test_inference_common.c: In function
‘ml_request_finish’:
../app/test-mldev/test_inference_common.c:

app/mldev: fix debug build

Compiling with -O0 and -g triggers these warnings:

../app/test-mldev/test_inference_common.c: In function
‘ml_request_finish’:
../app/test-mldev/test_inference_common.c:946:51:
error: ‘.q.’ directive output may be truncated writing 3 bytes
into a region of size between 0 and 4095
[-Werror=format-truncation=]
946 | snprintf(str, sizeof(str) - 1, "%s.q.%d",
| ^~~
t->cmn.opt->filelist[req->fid].output, obj_idx);
../app/test-mldev/test_inference_common.c:946:48: note: using the range
[-2147483648, 2147483647] for directive argument
946 | snprintf(str, sizeof(str) - 1, "%s.q.%d",
| ^~~~~~~~~
t->cmn.opt->filelist[req->fid].output, obj_idx);
../app/test-mldev/test_inference_common.c:946:17: note: ‘snprintf’
output between 5 and 4110 bytes into a destination of size 4095
946 | snprintf(str, sizeof(str) - 1, "%s.q.%d",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
t->cmn.opt->filelist[req->fid].output, obj_idx);
../app/test-mldev/test_inference_common.c:952:51: error: ‘.’ directive
output may be truncated writing 1 byte into a region of size
between 0 and 4095 [-Werror=format-truncation=]
952 | snprintf(str, sizeof(str) - 1, "%s.%d",
| ^
t->cmn.opt->filelist[req->fid].output, obj_idx);
../app/test-mldev/test_inference_common.c:952:48: note: using the range
[-2147483648, 2147483647] for directive argument
952 | snprintf(str, sizeof(str) - 1, "%s.%d",
| ^~~~~~~
t->cmn.opt->filelist[req->fid].output, obj_idx);
../app/test-mldev/test_inference_common.c:952:17: note: ‘snprintf’
output between 3 and 4108 bytes into a destination of size 4095
952 | snprintf(str, sizeof(str) - 1, "%s.%d",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
t->cmn.opt->filelist[req->fid].output, obj_idx);
../app/test-mldev/test_inference_common.c:929:51: error: ‘.q’ directive
output may be truncated writing 2 bytes into a region of size
between 0 and 4095 [-Werror=format-truncation=]
929 | snprintf(str, sizeof(str) - 1, "%s.q",
| ^~
t->cmn.opt->filelist[req->fid].output);
../app/test-mldev/test_inference_common.c:929:17: note: ‘snprintf’
output between 3 and 4098 bytes into a destination of size 4095
929 | snprintf(str, sizeof(str) - 1, "%s.q",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
t->cmn.opt->filelist[req->fid].output);
../app/test-mldev/test_inference_common.c:935:51: error: ‘snprintf’
output may be truncated before the last format character
[-Werror=format-truncation=]
935 | snprintf(str, sizeof(str) - 1, "%s",
| ^
t->cmn.opt->filelist[req->fid].output);
../app/test-mldev/test_inference_common.c:935:17: note: ‘snprintf’
output between 1 and 4096 bytes into a destination of size 4095
935 | snprintf(str, sizeof(str) - 1, "%s",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
t->cmn.opt->filelist[req->fid].output);

Fix unsigned integer format, and switch to dynamic allocations.

Fixes: da6793390596 ("app/mldev: support inference validation")

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Srikanth Yalavarthi <syalavarthi@marvell.com>

show more ...

app/mldev: add statistics

Enable reporting driver xstats and inference end-to-end
latency and throughput in mldev inference tests. Reporting
of stats can be enabled using "--stats" option.

Signed-o

app/mldev: add statistics

Enable reporting driver xstats and inference end-to-end
latency and throughput in mldev inference tests. Reporting
of stats can be enabled using "--stats" option.

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

show more ...

app/mldev: support inference validation

Enabled support to validate inference output with reference
output provided by the user. Validation would be successful
only when the inference outputs are wi

app/mldev: support inference validation

Enabled support to validate inference output with reference
output provided by the user. Validation would be successful
only when the inference outputs are within the 'tolerance'
specified through command line option "--tolerance".

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

show more ...

app/mldev: support inference batches

Enabled support to execute multiple batches of inferences
per each enqueue request. Input and reference for the test
should be appropriately provided for multi-b

app/mldev: support inference batches

Enabled support to execute multiple batches of inferences
per each enqueue request. Input and reference for the test
should be appropriately provided for multi-batch run. Number
of batches can be specified through "--batches" option.

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

show more ...

app/mldev: support queue pairs and size

Added support to create multiple queue-pairs per device to
enqueue and dequeue inference requests. Number of queue pairs
to be created can be specified throug

app/mldev: support queue pairs and size

Added support to create multiple queue-pairs per device to
enqueue and dequeue inference requests. Number of queue pairs
to be created can be specified through "--queue_pairs" option.
Support is also enabled to control the number of descriptors
per each queue pair through "--queue_size" option. Inference
requests for a model are distributed across all available
queue-pairs.

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

show more ...

app/mldev: support for burst inferences

Added 'burst_size' support for inference tests. Burst size
controls the number of inference requests handled during
the burst enqueue and dequeue operations o

app/mldev: support for burst inferences

Added 'burst_size' support for inference tests. Burst size
controls the number of inference requests handled during
the burst enqueue and dequeue operations of the test case.

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

show more ...

app/mldev: add ordered inferences

Added an ordered test case to execute inferences with single
or multiple models. In this test case inference requests for
a model are enqueued after completion of a

app/mldev: add ordered inferences

Added an ordered test case to execute inferences with single
or multiple models. In this test case inference requests for
a model are enqueued after completion of all requests for
the previous model. Test supports inference repetitions.

Operations sequence when testing with N models and R reps,

(load -> start -> (enqueue + dequeue) x R -> stop -> unload) x N

Test case can be executed by selecting "inference_ordered" test
and repetitions can be specified through "--repetitions" argument.

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

show more ...