GB/T 42018-2022Information technology—Artificial intelligence—Platform computing resource specification (English PDF)
信息技术 人工智能 平台计算资源规范
This is a limited preview
Buy now to download the full PDF (21 pages)
Need quotation for your management?
Get a formal quotation for GB/T 42018-2022 in 30 minutes.
Issued by
SAMR; SAC
Level / Type
National · Recommended
Issue date
October 14, 2022
Implementation date
May 1, 2023
Scope
GB/T 42018-2022 is the English-translated version of 信息技术 人工智能 平台计算资源规范.
GB/T 42018-2022 fixes what the computing resources of a machine-learning artificial intelligence platform have to deliver, setting technical requirements for physical computing resources - artificial intelligence servers, accelerator cards and accelerator modules - and for virtual computing resources, and describing the test methods for the physical ones.
Clause 1 states that resource management and scheduling requirements are not covered, and applies the document to the design and testing of machine-learning artificial intelligence platforms.
Its contents list adds a normative annex of training and inference test models, plus informative annexes mapping test methods onto the technical requirements and giving the configuration of the physical computing resource test system.
It quotes GB/T 9813.3-2017, GB/T 20090.2-2013 and GB/T 41867-2022, from which it also takes its terms. Issued 14 October 2022, applied from 1 May 2023.
Found what you need?
Document preview — GB/T 42018-2022
National Standard of the People's Republic of China
- ICS
- 35.240
- Classification
- L 70
Issued by: State Administration for Market Regulation; Standardization Administration of the PRC
Contents
- Preface
- Introduction
- 1 Scope
- 2 Normative references
- 3 Terms and Definitions
- 4 Abbreviations
- 5 Overview
- 6 Technical requirements
- 6.1 Physical Computing Resources
- 6.2 Virtual Computing Resources
- 7 Test method
- 7.1 General Features
- 7.2 Physical Computing Resources
- 7.3 Virtual Computing Resources
- Appendix A (Informative) Correspondence between test methods and technical requirements for physical computing resources of artificial intelligence platforms
- Appendix B (Informative) Configuration of Physical Computing Resource Test System
- Appendix C (normative) training and inference testing models
- Reference
Foreword
This document is in accordance with the provisions of GB/T 1.1-2020 "Guidelines for Standardization Work Part 1: Structure and Drafting Rules of Standardization Documents" drafted.
Introduction
An artificial intelligence platform is a software and hardware system that provides various resources for artificial intelligence applications. perception, natural language processing, sound processing, etc.) implementation. When forming an artificial intelligence platform, it is necessary to use artificial intelligence physical computing resources and virtual Proposed computing resources. Physical computing resources refer to the entity of computing equipment, including artificial intelligence servers, artificial intelligence accelerator cards, and artificial intelligence acceleration cards. modules, etc. Virtual computing resources are based on physical computing resources, after abstracting and shielding heterogeneity to a certain extent, the logical computing resources formed. count resources.
The purpose of this document is to provide a standard basis for the construction of artificial intelligence platforms, and to provide a standard basis for the construction of artificial intelligence platforms.
It proposes basic common requirements for related technical parameters with virtual computing resources, and proposes testing methods for physical computing resources.
1 Scope
This document specifies the physical computing resources of the artificial intelligence platform for machine learning (including artificial intelligence servers, artificial intelligence acceleration Cards, artificial intelligence acceleration modules) and technical requirements for virtual computing resources, describe the testing methods of physical computing resources. This document does not source management and scheduling requirements.
This document applies to the design and testing of AI platforms for machine learning.
2 Normative references
The contents of the following documents constitute essential provisions of this document through normative references in the text. Among them, dated citations documents, only the version corresponding to that date applies to this document; for undated references, the latest edition (including all amendments) applies to this document.
GB/T 9813.3-2017 General Specification for Computer Part 3: Server
GB/T 17235.1-1998 Digital compression and coding of continuous tone still images for information technology - Part 1: Requirements and guidelines
GB/T 20090.2-2013 Information Technology Advanced Audio and Video Coding Part 2: Video
GB/T 41867-2022 Information Technology Artificial Intelligence Terminology ISO /IEC 15948:2004 Information Technology Computer Graphics and Image Processing Portable Network Graphics. Functional Specification [Informa-services)
3 Terms and Definitions
The terms and definitions defined in GB/T 41867-2022 and the following apply to this document.
3.1 artificial intelligence platform
Software and hardware systems that provide various resources for artificial intelligence applications.
3.2 artificial intelligence platform computing resource
In an artificial intelligence platform, the hardware and software used to process artificial intelligence computing tasks.
Note: AI platform computing resources include physical computing resources and virtual computing resources. [Source: ISO /IEC 30145.3-2020, 3.1.6, with modifications]
......
This preview omits tables, figures, formulas and parts of the technical clauses. The complete document — 21 pages — is available in the English PDF.
Referenced standards
Normative references
- GB/T 9813.3-2017General specification for computer—Part 3: Server
- GB/T 17235.1-1998Information technology. Digital compression and coding of continuous-tone still images. Part 1: Requirements and guidelines
- GB/T 20090.2-2013Information technology—Advanced coding of audio and video—Part 2: Video
- GB/T 41867-2022Information technology—Artificial intelligence—Terminology
Cited by
- GB/T 45288.1-2025Artificial intelligence - Large models - Part 1: General requirements
- GB/T 45288.3-2025Artificial intelligence - Large models - Part 3: Service capability framework and maturity assessment
- GB/T 45401.2-2025Artificial intelligence — Scheduling and cooperation for computing devices — Part 2: Framework for distributed computing
- GB/T 46346-2025Artificial intelligence - Computing center - Computing capacity assessment
Similar standards
How to Download GB/T 42018-2022
- 1
Add to cart
Click "Download PDF" on this page and choose "Buy this standard". You can add more standards before checkout.
- 2
Checkout
Enter your email and billing details. Payment is processed securely by Stripe (cards or bank transfer). Prefer bank details? Request a quotation (min. order $300).
- 3
Instant delivery (0–9 sec)
Delivery is automatic: within seconds of payment you'll receive an email with a secure download link. The link stays valid for 72 hours.
- 4
Invoice included
A tax invoice is attached to the confirmation email. Need a custom invoice? Contact us.
Related Standards
GB/T 17235.1-1998 — Information technology. Digital compression and coding of continuous-tone still images. Part 1: Requirements and guidelines
GB/T 20090.2-2013 — Information technology—Advanced coding of audio and video—Part 2: Video
GB/T 41867-2022 — Information technology—Artificial intelligence—Terminology
Secure payment via Stripe
Payments accepted
GB/T 42018-2022
$360.00