Help Center/ Elastic Cloud Server/ Service Overview/ x86 ECS Specifications and Types/ AI-accelerated ECSs
Updated on 2024-06-11 GMT+08:00
View PDF

AI-accelerated ECSs

AI-accelerated ECSs, powered by Ascend processors and software stacks, are dedicated for accelerating AI applications.

AI inference-accelerated ECSs use self-developed Ascend 310 processors for AI inference acceleration.

Public Images Supported by AI-accelerated ECSs

Table 1 Public images

Type

Series

Public Images

Enhanced AI inference-accelerated (type II)

Ai2

Ubuntu Server 18.04 64bit

CentOS 7.8 64bit

CentOS 7.6 64bit

Enhanced AI Inference-accelerated Ai2 (Type II)

Overview

Ai2 ECSs use Ascend 310P processors for AI acceleration. Featuring low power consumption and high computing power, Ascend 310P processors have significantly improved energy efficiency ratio (EER), promoting the wide application of AI inference. AI inference-accelerated Ai2 ECSs enable you to easily use the powerful processing capability of Ascend 310P processors.

Ai2 ECSs are ideal for computer vision, smart campus, smart city, smart transportation, smart retail, Internet-based real-time communication, and video encoding and decoding scenarios.

Specifications

Table 2 Ai2 ECS specifications

Flavor

vCPUs

Memory

(GiB)

Max./Assured Bandwidth

Max. PPS

(10,000)

Ascend 310P

Ascend RAM

(GiB)

Max. NIC Queues

Max. NICs

Virtualization

ai2.4xlarge.4

16

64

20/6

280

1

24

8

8

KVM

ai2.8xlarge.4

32

128

30/12

550

2

48

8

8

KVM

ai2.16xlarge.4

64

256

36/24

800

4

96

16

8

KVM

ai2.24xlarge.4

96

384

40/36

850

6

144

32

8

KVM

Features

Ai2 ECSs have the following features:

  • 1:4 ratio of vCPUs to memory
  • CPU: 3rd Generation Intel® Xeon® Scalable 6348 processors (2.6 GHz of base frequency and 3.5 GHz of turbo frequency), or Intel® Xeon® Scalable 8378A processors (3.0 GHz of base frequency and 3.4 GHz of turbo frequency)
  • Each Atlas 300I Pro accelerator card is equipped with one Ascend 310P processor, including eight DaVinci AI cores and eight self-developed CPU cores.
  • 140 TeraOPS of integer-precision (INT8) on a single GPU
  • 24 GiB of GPU memory with a bandwidth of 204.8 GiB/s on a single GPU
  • Built-in hardware video codec engine for HD video decoder (H.264/265) and JPEG image encoding and decoding

Notes

  1. Ai2 ECSs support the following public images:
    • Ubuntu Server 18.04 64bit
    • CentOS 7.8 64bit
    • CentOS 7.6 64bit
  2. Ai2 ECSs do not support modification of specifications.
  3. Ai2 ECSs support automatic recovery when the hosts accommodating such ECSs become faulty.

Using an AI-accelerated ECS

Perform the following steps:

  1. Create an ECS. For details, see Step 1: Configure Basic Settings.
    • In the Specifications field, select AI-accelerated specifications.
    • In the Image field, select Public image or Private image.
      • Public image: The CANN 3.1.0 development kit has been included and environment variables have been configured in public images by default. You need to verify the environment availability.
      • Private image: You need to install the driver, firmware, and development kit, and configure environment variables by yourself. For details, see the CANN Software Installation Guide of the corresponding version in Ascend Documentation.
  2. Remotely log in to the ECS.

    If your Ai1 ECS runs Linux, use an SSH password to log in to the ECS.

  3. Verify the environment availability.

    Use a sample for compilation and running. For details, see "Sample Overview" in the Model Development Learning Map of the corresponding CANN edition in Ascend Documentation.

    The sample shows how to classify images (decode, resize, and infer images) based on the Caffe ResNet-50 network.