Performance Specifications

The Atlas training products do not support the JPEGE function described in this section.

Performance Specifications

This section describes only the performance specifications of the Ascend AI Processor of each product, which may differ based on the memory and CPU configurations of the respective product. For details about the product performance specifications, see the official descriptions at the Ascend community.

This section takes a single Ascend AI Processor as an example to describe the performance specifications in basic scenarios, as shown in the table below. The performance at other resolutions can be estimated in the same way.

In the following table, one channel corresponds to one thread, 1080p indicates a resolution of 1920 × 1080 pixels, and 4K indicates a resolution of 3840 × 2160 pixels.

**Table 1** Ascend AI Processor performance specifications of the Atlas inference products
Scenario with YUV420 8-Bit Input	Total Frame Rate
n-channel 1080p (1 ≤ n ≤ 8)	n × 128 FPS
n-channel 1080p (n > 8)	1024 FPS
n-channel 4K (1 ≤ n ≤ 8)	n × 32 FPS
n-channel 4K (n > 8)	256 FPS

**Table 2** Ascend AI Processor performance specifications of the Atlas 200I/500 A2 inference products
Scenario with YUV420 8-Bit Input	Total Frame Rate
n-channel 1080p	256 FPS
n-channel 4K	64 FPS

**Table 3** Ascend AI Processor performance specifications of the Atlas A2 training products/Atlas A2 inference products
Scenario with YUV420 8-Bit Input	Total Frame Rate
n-channel 1080p (1 ≤ n ≤ 4)	n × 256 FPS
n-channel 1080p (n > 4)	1024 FPS
n-channel 4K (1 ≤ n ≤ 4)	n × 64 FPS
n-channel 4K (n > 4)	256 FPS

Parent topic: Video Encoding (VENC) and JPEG Encoder (JPEGE)