Using Batch Processing APIs of VPC to Reduce Delay

Background

The media data processing section provides the following two types of APIs for operations such as image cropping and resizing:

• APIs that process one image at a time, for example, acldvppVpcCropAsync

  In this mode, if there are multiple input images, the for loop mode is typically used, which means the acldvppVpcCropAsync API is called once for each image.

• APIs that process multiple images at a time (batch processing), for example, acldvppVpcBatchCropAsync

  In this mode, if there are multiple input images, only the acldvppVpcBatchCropAsync API needs to be called once.

The following table lists the mapping between these two types of APIs.

Principles

The Ascend AI Processor has a built-in DVPP unit, which contains multiple VPC modules for functions like image cropping, resizing, and format conversion.

When a batch processing API is called, batch tasks are evenly distributed to multiple VPC modules for parallel processing, reducing the processing delay and improving performance.

Sample

We use batch image cropping and resizing as an example to describe how to call the batch processing API acldvppVpcBatchCropResizeAsync. Refer to batchcrop to obtain the sample.