From: Srikanth Yalavarthi <syalavarthi@marvell.com>
To: Srikanth Yalavarthi <syalavarthi@marvell.com>
Cc: <dev@dpdk.org>, <sshankarnara@marvell.com>, <aprabhu@marvell.com>,
<ptakkar@marvell.com>
Subject: [PATCH v3 3/4] mldev: drop input and output size get APIs
Date: Wed, 27 Sep 2023 11:11:57 -0700 [thread overview]
Message-ID: <20230927181159.9794-4-syalavarthi@marvell.com> (raw)
In-Reply-To: <20230927181159.9794-1-syalavarthi@marvell.com>
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>
---
drivers/ml/cnxk/cn10k_ml_ops.c | 50 ----------------------------
lib/mldev/rte_mldev.c | 38 ---------------------
lib/mldev/rte_mldev.h | 60 ----------------------------------
lib/mldev/rte_mldev_core.h | 54 ------------------------------
lib/mldev/version.map | 2 --
5 files changed, 204 deletions(-)
diff --git a/drivers/ml/cnxk/cn10k_ml_ops.c b/drivers/ml/cnxk/cn10k_ml_ops.c
index 1d72fb52a6..4abf4ae0d3 100644
--- a/drivers/ml/cnxk/cn10k_ml_ops.c
+++ b/drivers/ml/cnxk/cn10k_ml_ops.c
@@ -2110,54 +2110,6 @@ cn10k_ml_model_params_update(struct rte_ml_dev *dev, uint16_t model_id, void *bu
return 0;
}
-static int
-cn10k_ml_io_input_size_get(struct rte_ml_dev *dev, uint16_t model_id, uint32_t nb_batches,
- uint64_t *input_qsize, uint64_t *input_dsize)
-{
- struct cn10k_ml_model *model;
-
- model = dev->data->models[model_id];
-
- if (model == NULL) {
- plt_err("Invalid model_id = %u", model_id);
- return -EINVAL;
- }
-
- if (input_qsize != NULL)
- *input_qsize = PLT_U64_CAST(model->addr.total_input_sz_q *
- PLT_DIV_CEIL(nb_batches, model->batch_size));
-
- if (input_dsize != NULL)
- *input_dsize = PLT_U64_CAST(model->addr.total_input_sz_d *
- PLT_DIV_CEIL(nb_batches, model->batch_size));
-
- return 0;
-}
-
-static int
-cn10k_ml_io_output_size_get(struct rte_ml_dev *dev, uint16_t model_id, uint32_t nb_batches,
- uint64_t *output_qsize, uint64_t *output_dsize)
-{
- struct cn10k_ml_model *model;
-
- model = dev->data->models[model_id];
-
- if (model == NULL) {
- plt_err("Invalid model_id = %u", model_id);
- return -EINVAL;
- }
-
- if (output_qsize != NULL)
- *output_qsize = PLT_U64_CAST(model->addr.total_output_sz_q *
- PLT_DIV_CEIL(nb_batches, model->batch_size));
-
- if (output_dsize != NULL)
- *output_dsize = PLT_U64_CAST(model->addr.total_output_sz_d *
- PLT_DIV_CEIL(nb_batches, model->batch_size));
-
- return 0;
-}
-
static int
cn10k_ml_io_quantize(struct rte_ml_dev *dev, uint16_t model_id, struct rte_ml_buff_seg **dbuffer,
struct rte_ml_buff_seg **qbuffer)
@@ -2636,8 +2588,6 @@ struct rte_ml_dev_ops cn10k_ml_ops = {
.model_params_update = cn10k_ml_model_params_update,
/* I/O ops */
- .io_input_size_get = cn10k_ml_io_input_size_get,
- .io_output_size_get = cn10k_ml_io_output_size_get,
.io_quantize = cn10k_ml_io_quantize,
.io_dequantize = cn10k_ml_io_dequantize,
};
diff --git a/lib/mldev/rte_mldev.c b/lib/mldev/rte_mldev.c
index 9a48ed3e94..cc5f2e0cc6 100644
--- a/lib/mldev/rte_mldev.c
+++ b/lib/mldev/rte_mldev.c
@@ -691,44 +691,6 @@ rte_ml_model_params_update(int16_t dev_id, uint16_t model_id, void *buffer)
return (*dev->dev_ops->model_params_update)(dev, model_id, buffer);
}
-int
-rte_ml_io_input_size_get(int16_t dev_id, uint16_t model_id, uint32_t nb_batches,
- uint64_t *input_qsize, uint64_t *input_dsize)
-{
- struct rte_ml_dev *dev;
-
- if (!rte_ml_dev_is_valid_dev(dev_id)) {
- RTE_MLDEV_LOG(ERR, "Invalid dev_id = %d\n", dev_id);
- return -EINVAL;
- }
-
- dev = rte_ml_dev_pmd_get_dev(dev_id);
- if (*dev->dev_ops->io_input_size_get == NULL)
- return -ENOTSUP;
-
- return (*dev->dev_ops->io_input_size_get)(dev, model_id, nb_batches, input_qsize,
- input_dsize);
-}
-
-int
-rte_ml_io_output_size_get(int16_t dev_id, uint16_t model_id, uint32_t nb_batches,
- uint64_t *output_qsize, uint64_t *output_dsize)
-{
- struct rte_ml_dev *dev;
-
- if (!rte_ml_dev_is_valid_dev(dev_id)) {
- RTE_MLDEV_LOG(ERR, "Invalid dev_id = %d\n", dev_id);
- return -EINVAL;
- }
-
- dev = rte_ml_dev_pmd_get_dev(dev_id);
- if (*dev->dev_ops->io_output_size_get == NULL)
- return -ENOTSUP;
-
- return (*dev->dev_ops->io_output_size_get)(dev, model_id, nb_batches, output_qsize,
- output_dsize);
-}
-
int
rte_ml_io_quantize(int16_t dev_id, uint16_t model_id, struct rte_ml_buff_seg **dbuffer,
struct rte_ml_buff_seg **qbuffer)
diff --git a/lib/mldev/rte_mldev.h b/lib/mldev/rte_mldev.h
index 316c6fd018..63b2670bb0 100644
--- a/lib/mldev/rte_mldev.h
+++ b/lib/mldev/rte_mldev.h
@@ -1008,66 +1008,6 @@ rte_ml_model_params_update(int16_t dev_id, uint16_t model_id, void *buffer);
/* IO operations */
-/**
- * Get size of quantized and dequantized input buffers.
- *
- * Calculate the size of buffers required for quantized and dequantized input data.
- * This API would return the buffer sizes for the number of batches provided and would
- * consider the alignment requirements as per the PMD. Input sizes computed by this API can
- * be used by the application to allocate buffers.
- *
- * @param[in] dev_id
- * The identifier of the device.
- * @param[in] model_id
- * Identifier for the model created
- * @param[in] nb_batches
- * Number of batches of input to be processed in a single inference job
- * @param[out] input_qsize
- * Quantized input size pointer.
- * NULL value is allowed, in which case input_qsize is not calculated by the driver.
- * @param[out] input_dsize
- * Dequantized input size pointer.
- * NULL value is allowed, in which case input_dsize is not calculated by the driver.
- *
- * @return
- * - Returns 0 on success
- * - Returns negative value on failure
- */
-__rte_experimental
-int
-rte_ml_io_input_size_get(int16_t dev_id, uint16_t model_id, uint32_t nb_batches,
- uint64_t *input_qsize, uint64_t *input_dsize);
-
-/**
- * Get size of quantized and dequantized output buffers.
- *
- * Calculate the size of buffers required for quantized and dequantized output data.
- * This API would return the buffer sizes for the number of batches provided and would consider
- * the alignment requirements as per the PMD. Output sizes computed by this API can be used by the
- * application to allocate buffers.
- *
- * @param[in] dev_id
- * The identifier of the device.
- * @param[in] model_id
- * Identifier for the model created
- * @param[in] nb_batches
- * Number of batches of input to be processed in a single inference job
- * @param[out] output_qsize
- * Quantized output size pointer.
- * NULL value is allowed, in which case output_qsize is not calculated by the driver.
- * @param[out] output_dsize
- * Dequantized output size pointer.
- * NULL value is allowed, in which case output_dsize is not calculated by the driver.
- *
- * @return
- * - Returns 0 on success
- * - Returns negative value on failure
- */
-__rte_experimental
-int
-rte_ml_io_output_size_get(int16_t dev_id, uint16_t model_id, uint32_t nb_batches,
- uint64_t *output_qsize, uint64_t *output_dsize);
-
/**
* Quantize input data.
*
diff --git a/lib/mldev/rte_mldev_core.h b/lib/mldev/rte_mldev_core.h
index 8530b07316..2279b1dcec 100644
--- a/lib/mldev/rte_mldev_core.h
+++ b/lib/mldev/rte_mldev_core.h
@@ -466,54 +466,6 @@ typedef int (*mldev_model_info_get_t)(struct rte_ml_dev *dev, uint16_t model_id,
*/
typedef int (*mldev_model_params_update_t)(struct rte_ml_dev *dev, uint16_t model_id, void *buffer);
-/**
- * @internal
- *
- * Get size of input buffers.
- *
- * @param dev
- * ML device pointer.
- * @param model_id
- * Model ID to use.
- * @param nb_batches
- * Number of batches.
- * @param input_qsize
- * Size of quantized input.
- * @param input_dsize
- * Size of dequantized input.
- *
- * @return
- * - 0 on success.
- * - <0, error on failure.
- */
-typedef int (*mldev_io_input_size_get_t)(struct rte_ml_dev *dev, uint16_t model_id,
- uint32_t nb_batches, uint64_t *input_qsize,
- uint64_t *input_dsize);
-
-/**
- * @internal
- *
- * Get size of output buffers.
- *
- * @param dev
- * ML device pointer.
- * @param model_id
- * Model ID to use.
- * @param nb_batches
- * Number of batches.
- * @param output_qsize
- * Size of quantized output.
- * @param output_dsize
- * Size of dequantized output.
- *
- * @return
- * - 0 on success.
- * - <0, error on failure.
- */
-typedef int (*mldev_io_output_size_get_t)(struct rte_ml_dev *dev, uint16_t model_id,
- uint32_t nb_batches, uint64_t *output_qsize,
- uint64_t *output_dsize);
-
/**
* @internal
*
@@ -627,12 +579,6 @@ struct rte_ml_dev_ops {
/** Update model params. */
mldev_model_params_update_t model_params_update;
- /** Get input buffer size. */
- mldev_io_input_size_get_t io_input_size_get;
-
- /** Get output buffer size. */
- mldev_io_output_size_get_t io_output_size_get;
-
/** Quantize data */
mldev_io_quantize_t io_quantize;
diff --git a/lib/mldev/version.map b/lib/mldev/version.map
index 40ff27f4b9..99841db6aa 100644
--- a/lib/mldev/version.map
+++ b/lib/mldev/version.map
@@ -23,8 +23,6 @@ EXPERIMENTAL {
rte_ml_dev_xstats_reset;
rte_ml_enqueue_burst;
rte_ml_io_dequantize;
- rte_ml_io_input_size_get;
- rte_ml_io_output_size_get;
rte_ml_io_quantize;
rte_ml_model_info_get;
rte_ml_model_load;
--
2.41.0
next prev parent reply other threads:[~2023-09-27 18:12 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-30 15:52 [PATCH v1 0/3] Spec changes to support multi I/O models Srikanth Yalavarthi
2023-08-30 15:53 ` [PATCH v1 1/3] mldev: add support for arbitrary shape dimensions Srikanth Yalavarthi
2023-08-30 15:53 ` [PATCH v1 2/3] mldev: introduce support for IO layout Srikanth Yalavarthi
2023-08-30 15:53 ` [PATCH v1 3/3] mldev: drop input and output size get APIs Srikanth Yalavarthi
2023-09-20 7:19 ` [PATCH v2 0/3] Spec changes to support multi I/O models Srikanth Yalavarthi
2023-09-20 7:19 ` [PATCH v2 1/3] mldev: add support for arbitrary shape dimensions Srikanth Yalavarthi
2023-09-20 7:19 ` [PATCH v2 2/3] mldev: introduce support for IO layout Srikanth Yalavarthi
2023-09-20 7:19 ` [PATCH v2 3/3] mldev: drop input and output size get APIs Srikanth Yalavarthi
2023-10-03 6:10 ` Anup Prabhu
2023-09-27 18:11 ` [PATCH v3 0/4] Spec changes to support multi I/O models Srikanth Yalavarthi
2023-09-27 18:11 ` [PATCH v3 1/4] mldev: add support for arbitrary shape dimensions Srikanth Yalavarthi
2023-09-27 18:11 ` [PATCH v3 2/4] mldev: introduce support for IO layout Srikanth Yalavarthi
2023-09-27 18:11 ` Srikanth Yalavarthi [this message]
2023-09-27 18:11 ` [PATCH v3 4/4] mldev: update release notes for 23.11 Srikanth Yalavarthi
2023-09-29 3:39 ` Jerin Jacob
2023-10-02 9:59 ` [EXT] " Srikanth Yalavarthi
2023-10-02 9:58 ` [PATCH v4 0/3] Spec changes to support multi I/O models Srikanth Yalavarthi
2023-10-02 9:58 ` [PATCH v4 1/3] mldev: add support for arbitrary shape dimensions Srikanth Yalavarthi
2023-10-04 14:42 ` Anup Prabhu
2023-10-05 9:12 ` Shivah Shankar Shankar Narayan Rao
2023-10-02 9:58 ` [PATCH v4 2/3] mldev: introduce support for IO layout Srikanth Yalavarthi
2023-10-05 9:10 ` Shivah Shankar Shankar Narayan Rao
2023-10-02 9:58 ` [PATCH v4 3/3] mldev: drop input and output size get APIs Srikanth Yalavarthi
2023-10-03 6:12 ` Anup Prabhu
2023-10-05 9:06 ` Shivah Shankar Shankar Narayan Rao
2023-10-11 14:45 ` [PATCH v4 0/3] Spec changes to support multi I/O models Thomas Monjalon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230927181159.9794-4-syalavarthi@marvell.com \
--to=syalavarthi@marvell.com \
--cc=aprabhu@marvell.com \
--cc=dev@dpdk.org \
--cc=ptakkar@marvell.com \
--cc=sshankarnara@marvell.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).