hi_mpi_vdec_create_chn

Applicability

Description

Creates a decoding channel based on the configured channel attributes.

Prototype

hi_s32 hi_mpi_vdec_create_chn (hi_vdec_chn chn, const hi_vdec_chn_attr *attr)

Parameters

Returns

• 0: success
• Other values: failure. For details, see VDEC/JPEGD Return Codes.

Restrictions

• The channel ID of a single device cannot exceed the maximum channel ID.
• Before this API call, ensure that a decoding channel has not been created yet or has been destroyed. Otherwise, a failure is returned.
• If the OS memory is insufficient, the error code HI_ERR_VDEC_NO_MEM is returned. In this case, you can expand the OS memory as needed.
• For H.264 and H.265 decoding, the minimum video buffer (VB) allocation per decoding channel is the sum of the number of reference frames and the number of display frames plus 1. For JPEG decoding, the minimum VB allocation per decoding channel is the number of display frames plus 1. The requested VB allocation varies according to the decode protocol and can be queried by using the hi_vdec_get_pic_buf_size call.
• If the H.264 stream to be decoded has B-frames or the H.265 stream to be decoded supports temporal motion vector prediction (TMVP) (sps_temporal_mvp_enabled_flag = 1), set temporal_mvp_en to 1 for the created channel and allocate VBs for the temporal motion vector (TMV) output of each frame. The requested VB count of TMV output is the sum of the number of reference frames and the number of display frames plus 1. The TMV buffer size is much smaller than the image VB size, and can be queried by using hi_vdec_get_tmv_buf_size. This is to avoid artifacts.
• To skip decoding B-frames in H.264 streams or skip decoding H.265 streams with TMVP support (sps_temporal_mvp_enabled_flag = 1), set temporal_mvp_en to 0 for the created channel. In this case, no TMV information is output, and therefore you do not need to allocate a TMV VB pool. This helps you save memory.
• Set the requested frame VB size (frame_buf_size) and count (frame_buf_cnt) as well as the requested TMV VB size (tmv_buf_size) based on the stream to be decoded. The decoder allocates private VB pools based on these configurations.
• As long as the allocated frame VB and TMV VB are large enough, the decoding channel can decode a stream with any resolution in the valid range. The channel width and height are related only to the size of the stream buffer and start code detector buffer (SCD buffer).
• This API fetches the VDEC decode results from both the input and output buffers.
• For JPEGD decoding of JPEG (420), JPEG (422), or JPEG (440) images, if the input width and height are odd numbers, the output width and height are rounded down to the nearest multiples of 2 by default. For JPEGD decoding of JPEG (444) or JPEG (400) images, the output width and height are consistent with the input width and height by default. To adjust the width and height alignment mode of the output image, call hi_mpi_vdec_set_jpegd_precision_mode.
• For Ascend virtual instances, the requirements on the number of channels are as follows:

  For Atlas A2 training products / Atlas A2 inference products : Number of VDEC channels = (Number of allocated VDEC hardware units/Number of VDEC hardware units) x 32. If the total number of channels is not an integer, round down the value. The number of JPEGD channels is independent of the computing power, but the maximum number of JPEGD and VDEC channels is 256.

  For Atlas 200I/500 A2 inference products : Number of VDEC channels = (Number of allocated VDEC hardware units/Number of VDEC hardware units) x 128. If the total number of channels is not an integer, round down the value. The number of JPEGD channels is independent of the computing power, but the maximum number of JPEGD and VDEC channels is 128.

  For Atlas inference products : Total number of JPEGD+VDEC channels = (Total number of allocated JPEGD+VDEC hardware units/Total number of JPEGD+VDEC hardware units) x 256. If the total number of channels is not an integer, round down the value.

  To check the compute resource specifications of the Ascend virtual instances in different scenarios, run the npu-smi info -t template-info command on the server with the Ascend AI Processor installed.

See Also

For details about the API call sequence and example, see JPEGD and VDEC.