aclmdlExecuteV2

Applicability

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product / Atlas A3 inference product	√
Atlas A2 training product / Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	√
Atlas inference product	√
Atlas training product	√

Function Usage

Performs model inference based on the attributes configured by the aclmdlSetExecConfigOpt API until the inference result is returned. This API is enhanced based on aclmdlExecute. It allows you to control configuration parameters during model inference.

This API must be used together with other APIs to implement model execution. The API call sequence is as follows:

Call aclmdlCreateExecConfigHandle to create a configuration object for model execution.
Call aclmdlSetExecConfigOpt multiple times to set the value of each attribute in the configuration object.
Call aclmdlExecuteV2 to specify the configuration required for model execution and execute the model.
After the model is successfully loaded, call aclmdlDestroyExecConfigHandle to destroy the configuration object.

Prototype

      
           aclError aclmdlExecuteV2(uint32_t modelId, const aclmdlDataset *input, aclmdlDataset *output, aclrtStream stream, const aclmdlExecConfigHandle *handle)

Parameters

Parameter

Input/Output

Description

modelId

Input

Model ID for inference.

After a model loading API (such as aclmdlLoadFromFile or aclmdlLoadFromMem) is successfully called, the model ID is returned. This ID is used as the input of this API.

input

Input

Pointer to the input data for model inference. For details about the type definition, see aclmdlDataset.

output

Output

Pointer to the output data for model inference. For details about the type definition, see aclmdlDataset.

When calling aclCreateDataBuffer to create the aclDataBuffer type for storing output data of the corresponding index, you can pass nullptr to the data parameter and set size to 0 to create an empty aclDataBuffer type. During model execution, the system automatically calculates and allocates the index output memory. This method saves memory. However, you need to free the memory and reset the aclDataBuffer after using the data. In addition, memory copy is involved when the system allocates memory, which may cause performance loss.

The sample code for freeing the memory and resetting the aclDataBuffer is as follows:

            
                 aclDataBuffer *dataBuffer = aclmdlGetDatasetBuffer(output, 0); // Obtain the corresponding data buffer based on the index.
void *data = aclGetDataBufferAddr(dataBuffer);  // Obtain the device pointer to data.
aclrtFree(data ); // Free the device memory.
aclUpdateDataBuffer(dataBuffer, nullptr, 0); // Reset the content in the data buffer for next inference.

stream

Input

Stream. For details about the type definition, see aclrtStream.

If NULL is passed, the attribute value configured by the aclmdlSetExecConfigOpt API does not take effect.

handle

Input

Pointer to the configuration object executed by the model. For details about the type definition, see aclmdlExecConfigHandle.

The value must be the same as that of handle in aclmdlSetExecConfigOpt.

Returns

0 on success; else, failure. For details, see aclError.

Restrictions

The restrictions are the same as those of aclmdlExecute.

Parent topic: Model Execution