#include <rte_mldev.h>

Data Fields
uint16_t	model_id

uint16_t	nb_batches

uint32_t	reserved

struct rte_mempool *	mempool

struct rte_ml_buff_seg	input

struct rte_ml_buff_seg	output

enum rte_ml_op_status	status

uint64_t	impl_opaque

uint64_t	user_u64

void *	user_ptr

Detailed Description

ML Operation.

This structure contains data related to performing an ML operation on the buffers using the model specified through model_id.

Definition at line 421 of file rte_mldev.h.

Field Documentation

◆ model_id

uint16_t model_id

Model ID to be used for the operation.

Definition at line 422 of file rte_mldev.h.

◆ nb_batches

uint16_t nb_batches

Number of batches. Minimum value must be one. Input buffer must hold inference data for each batch as contiguous.

Definition at line 424 of file rte_mldev.h.

◆ reserved

uint32_t reserved

Reserved for future use.

Definition at line 428 of file rte_mldev.h.

◆ mempool

struct rte_mempool* mempool

Pool from which operation is allocated.

Definition at line 430 of file rte_mldev.h.

◆ input

struct rte_ml_buff_seg input

Input buffer to hold the inference data.

Definition at line 432 of file rte_mldev.h.

◆ output

struct rte_ml_buff_seg output

Output buffer to hold the inference output by the driver.

Definition at line 434 of file rte_mldev.h.

◆ user_u64

uint64_t user_u64

User data as uint64_t.

Definition at line 438 of file rte_mldev.h.

◆ user_ptr

void* user_ptr

User data as void*.

Definition at line 440 of file rte_mldev.h.

◆ status

enum rte_ml_op_status status

Operation status.

Definition at line 443 of file rte_mldev.h.

◆ impl_opaque

uint64_t impl_opaque

Implementation specific opaque value. An implementation may use this field to hold implementation specific value to share between dequeue and enqueue operation. The application should not modify this field.

Definition at line 445 of file rte_mldev.h.

The documentation for this struct was generated from the following file:

lib/mldev/rte_mldev.h

Data Fields