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.

Performance Specifications (Atlas inference products)

The following performance data is based on executing aclrtSynchronizeStream once after 64 asynchronous media data processing tasks are delivered to a stream, and the host server is configured as: Intel(R) Xeon(R) CPU E5-2680 v4@2.40 GHz as the CPU frequency, with 14 CPU cores.

In the single-device scenario, the performance specifications are as follows (one channel corresponds to one thread).
Table 1 Ascend AI Processor performance specifications of the Atlas inference products

Scenario

Total Frame Rate

  • Input resolution: 1080p (1920 × 1080)
  • Output resolution: 1080p (1920 × 1080)
  • Input/Output format: YUV420SP
  • n channels (1 ≤ n ≤ 12)

n × 360 FPS

  • Input resolution: 1080p (1920 × 1080)
  • Output resolution: 1080p (1920 × 1080)
  • Input/Output format: YUV420SP
  • n channels (n > 12)

4320 FPS

  • Input resolution: 4K (3840 × 2160)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (1 ≤ n ≤ 12)

n × 90 FPS

  • Input resolution: 4K (3840 × 2160)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n > 12)

1080 FPS

  • Input resolution: 8K (7680 × 4320)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (1 ≤ n ≤ 12)

n × 22.5 FPS

  • Input resolution: 8K (7680 × 4320)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n > 12)

270 FPS

A VPC batch processing API (whose name contains "Batch", for example, acldvppVpcBatchCropAsync) allows parallel image processing of multiple VPC hardware units in the DVPP. Therefore, a single channel can reach the maximum total frame rate.

Performance Specifications (Atlas training products)

The following performance data is based on executing aclrtSynchronizeStream once after 10 asynchronous media data processing tasks are delivered to a stream.

  • For non-8K images in the single-device scenario, the performance specifications are as follows (one channel corresponds to one thread):
    Table 2 Ascend AI Processor performance specifications of the Atlas training products

    Scenario

    Total Frame Rate

    • Input resolution: 1080p (1920 × 1080)
    • Output resolution: 1080p (1920 × 1080)
    • Input/Output format: YUV420SP
    • n channels (n < 16)

    n × 360 FPS

    • Input resolution: 1080p (1920 × 1080)
    • Output resolution: 1080p (1920 × 1080)
    • Input/Output format: YUV420SP
    • n channels (n ≥ 16)

    5760 FPS

    • Input resolution: 4K (3840 × 2160)
    • Output resolution: 4K (3840 × 2160)
    • Input/Output format: YUV420SP
    • n channels (n < 16)

    n × 90 FPS

    • Input resolution: 4K (3840 × 2160)
    • Output resolution: 4K (3840 × 2160)
    • Input/Output format: YUV420SP
    • n channels (n ≥ 16)

    1440 FPS

  • For 8K images in the single-device scenario, the performance specifications are as follows (one channel corresponds to one thread).
    Table 3 Ascend AI Processor performance specifications of the Atlas training products

    Scenario

    Total Frame Rate

    • Input resolution: 8K (7680 × 4320)
    • Output resolution: 1080p (1920 × 1080)
    • Input/Output format: YUV420SP
    • n channels (n < 16)

    n × 25 FPS

    • Input resolution: 8K (7680 × 4320)
    • Output resolution: 1080p (1920 × 1080)
    • Input/Output format: YUV420SP
    • n channels (n ≥ 16)

    400 FPS

    • Input resolution: 8K (7680 × 4320)
    • Output resolution: 4K (3840 × 2160)
    • Input/Output format: YUV420SP
    • n channels (n < 16)

    n × 25 FPS

    • Input resolution: 8K (7680 × 4320)
    • Output resolution: 4K (3840 × 2160)
    • Input/Output format: YUV420SP
    • n channels (n ≥ 16)

    400 FPS

    A VPC batch processing API (whose name contains "Batch", for example, acldvppVpcBatchCropAsync) allows parallel image processing of multiple VPC hardware units in the DVPP. Therefore, a single channel can reach the maximum total frame rate.

Performance Specifications (Atlas 200I/500 A2 inference products)

In the single-device scenario, the performance specifications are as follows (one channel corresponds to one thread; n channels correspond to n threads).

Table 4 Ascend AI Processor performance specifications of the Atlas 200I/500 A2 inference products

Scenario

Total Frame Rate

  • Input resolution: 1080p (1920 × 1080)
  • Output resolution: 1080p (1920 × 1080)
  • Input/Output format: YUV420SP
  • n channels (n < 2)

n × 800 FPS

  • Input resolution: 1080p (1920 × 1080)
  • Output resolution: 1080p (1920 × 1080)
  • Input/Output format: YUV420SP
  • n channels (n ≥ 2)

1600 FPS

  • Input resolution: 4K (3840 × 2160)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n < 2)

n × 200 FPS

  • Input resolution: 4K (3840 × 2160)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n ≥ 2)

400 FPS

  • Input resolution: 8K (7680 × 4320)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n < 2)

n × 100 FPS

  • Input resolution: 8K (7680 × 4320)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n ≥ 2)

200 FPS

A VPC batch processing API (whose name includes "batch", such as acldvppVpcBatchCropAsync) allows parallel image processing of multiple VPC hardware units in the DVPP. Therefore, a single channel can reach the maximum total frame rate.

Performance Specifications (Atlas A2 training products/Atlas A2 inference products)

Table 5 Ascend AI Processor performance specifications of the Atlas A2 training products/Atlas A2 inference products

Scenario

Total Frame Rate

  • Input resolution: 1080p (1920 × 1080)
  • Output resolution: 1080p (1920 × 1080)
  • Input/Output format: YUV420SP
  • n channels (1 ≤ n ≤ 10)

n × 1440 FPS

  • Input resolution: 1080p (1920 × 1080)
  • Output resolution: 1080p (1920 × 1080)
  • Input/Output format: YUV420SP
  • n channels (n > 10)

14400 FPS

  • Input resolution: 4K (3840 × 2160)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (1 ≤ n ≤ 10)

n × 360 FPS

  • Input resolution: 4K (3840 × 2160)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n > 10)

3600 FPS

  • Input resolution: 8K (7680 × 4320)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (1 ≤ n ≤ 10)

n × 90 FPS

  • Input resolution: 8K (7680 × 4320)
  • Output resolution: 4K (3840 × 2160)
  • Input/Output format: YUV420SP
  • n channels (n > 10)

900 FPS