@@ -465,4 +465,98 @@ 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, uint16_t nb_batches, void *dbuffer,
+ void *qbuffer)
+{
+ 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_quantize == NULL)
+ return -ENOTSUP;
+
+ if (dbuffer == NULL) {
+ RTE_MLDEV_LOG(ERR, "Dev %d, dbuffer cannot be NULL\n", dev_id);
+ return -EINVAL;
+ }
+
+ if (qbuffer == NULL) {
+ RTE_MLDEV_LOG(ERR, "Dev %d, qbuffer cannot be NULL\n", dev_id);
+ return -EINVAL;
+ }
+
+ return (*dev->dev_ops->io_quantize)(dev, model_id, nb_batches, dbuffer, qbuffer);
+}
+
+int
+rte_ml_io_dequantize(int16_t dev_id, uint16_t model_id, uint16_t nb_batches, void *qbuffer,
+ void *dbuffer)
+{
+ 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_dequantize == NULL)
+ return -ENOTSUP;
+
+ if (qbuffer == NULL) {
+ RTE_MLDEV_LOG(ERR, "Dev %d, qbuffer cannot be NULL\n", dev_id);
+ return -EINVAL;
+ }
+
+ if (dbuffer == NULL) {
+ RTE_MLDEV_LOG(ERR, "Dev %d, dbuffer cannot be NULL\n", dev_id);
+ return -EINVAL;
+ }
+
+ return (*dev->dev_ops->io_dequantize)(dev, model_id, nb_batches, qbuffer, dbuffer);
+}
+
RTE_LOG_REGISTER_DEFAULT(rte_ml_dev_logtype, INFO);
@@ -255,6 +255,100 @@ 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
+ *
+ * Quantize model data.
+ *
+ * @param dev
+ * ML device pointer.
+ * @param model_id
+ * Model ID to use.
+ * @param nb_batches
+ * Number of batches.
+ * @param dbuffer
+ * Pointer t de-quantized data buffer.
+ * @param qbuffer
+ * Pointer t de-quantized data buffer.
+ *
+ * @return
+ * - 0 on success.
+ * - <0, error on failure.
+ */
+typedef int (*mldev_io_quantize_t)(struct rte_ml_dev *dev, uint16_t model_id, uint16_t nb_batches,
+ void *dbuffer, void *qbuffer);
+
+/**
+ * @internal
+ *
+ * Quantize model data.
+ *
+ * @param dev
+ * ML device pointer.
+ * @param model_id
+ * Model ID to use.
+ * @param nb_batches
+ * Number of batches.
+ * @param qbuffer
+ * Pointer t de-quantized data buffer.
+ * @param dbuffer
+ * Pointer t de-quantized data buffer.
+ *
+ * @return
+ * - 0 on success.
+ * - <0, error on failure.
+ */
+typedef int (*mldev_io_dequantize_t)(struct rte_ml_dev *dev, uint16_t model_id, uint16_t nb_batches,
+ void *qbuffer, void *dbuffer);
+
/**
* @internal
*
@@ -299,6 +393,18 @@ 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;
+
+ /** De-quantize data */
+ mldev_io_dequantize_t io_dequantize;
};
/**
@@ -11,6 +11,10 @@ EXPERIMENTAL {
rte_ml_dev_socket_id;
rte_ml_dev_start;
rte_ml_dev_stop;
+ 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;
rte_ml_model_params_update;