From e951c56e44c056a174868351bc179d02bbf74627 Mon Sep 17 00:00:00 2001 From: qihuiz93 Date: Fri, 11 Jul 2025 10:28:40 +0800 Subject: [PATCH] update 2025 release plan with format modification Change-Id: I5ed383fc21fb51bc815fc8e21a69b79edcdf3a57 --- computing native sub group intro.md | 93 ++++++++++++++++------------- 1 file changed, 50 insertions(+), 43 deletions(-) diff --git a/computing native sub group intro.md b/computing native sub group intro.md index adfb374..f3e96e5 100644 --- a/computing native sub group intro.md +++ b/computing native sub group intro.md @@ -1,71 +1,78 @@ -#### **Heterogeneous-Accelerator Migration Sub-group** +# **Heterogeneous-Accelerator Migration Sub-group** -* **Project Facts** -**Project Creation Date:** 2023/08/08 +## Project Facts +Project Creation Date: 2023/08/08 -**Primary Contact:** Qihui Zhao & zhaoqihui@chinamobile.com +Primary Contact: Qihui Zhao, zhaoqihui@chinamobile.com -**Project Lead:** Qihui Zhao & zhaoqihui@chinamobile.com; Lei Huang & huangleiyjy@chinamobile.com +Project Lead: Qihui Zhao, zhaoqihui@chinamobile.com & Lei Huang, huangleiyjy@chinamobile.com -**Committers:** zhaoqihui@chinamobile.com shileiyjy@chinamobile.com +Committers: -**Mailing List:**[https://computing-force-network@lists.opendev.org](%3Cspan%3E%3Cdiv%3Ehttps://computing-force-network@lists.opendev.org%3C/div%3E%3C/span%3E) +* Qihui Zhao, zhaoqihui@chinamobile.com +* Lei Shi, shileiyjy@chinamobile.com +* Lei Huang, huangleiyjy@chinamobile.com -**Meetings:** Same as CFN bi-weekly meeting +Mailing List: [computing-force-network@lists.opendev.org](computing-force-network@lists.opendev.org) -**Repository:** [https://opendev.org/cfn/computing-native](%3Cspan%3E%3Cdiv%3Ehttps://opendev.org/cfn/computing-native%3C/div%3E%3C/span%3E) +Meetings: No sub-group meeting time. Use bi-weekly meeting of CFN WG. -**StoryBoard:** [https://storyboard.openstack.org/#!/project_group/computing-force-network](%3Cspan%3E%3Cdiv%3Ehttps://storyboard.openstack.org/#!/project_group/computing-force-network%3C/div%3E%3C/span%3E) +Repository: [https://opendev.org/cfn/computing-native](%3Cspan%3E%3Cdiv%3Ehttps://opendev.org/cfn/computing-native%3C/div%3E%3C/span%3E) -**Introduction** +StoryBoard: [https://storyboard.openstack.org/#!/project_group/computing-force-network](%3Cspan%3E%3Cdiv%3Ehttps://storyboard.openstack.org/#!/project_group/computing-force-network%3C/div%3E%3C/span%3E) - The intelligent computing ecology is mainly composed of - middleware/framework + tool chain + hardware. Each vendors build - corresponding tool chain around its own hardware, and generates branch - version matching different AI framework. +Open Bugs: N/A - The ecosystem is becoming diverse, cross-architecture and cross-stack - migration of upper-layer applications is extremely complex, which brings - development challenges to application developers, computing force - service providers and chip vendors. +## Introduction - In order to facing ecological challenges, we proposed a technology named - Heterogeneous-Accelerator Migration Technology , the goal of which is to - break the existing compile-link-execute tightly coupled tool chain - ecology, establish a new collaboration mechanism.Shield the underlying - hardware differences, and realize cross-architecture non-sensing - migration and execution of applications. Build traction model of the - intelligent computing industry chain with software as the core, and - prosper the ecology of intelligent computing industry. +The intelligent computing ecology is mainly composed of +middleware/framework + tool chain + hardware. Each vendors build +corresponding tool chain around its own hardware, and generates branch +version matching different AI framework. - The Heterogeneous-Accelerator Migration Technology architecture mainly - consists of two layers: the heterogeneous-accelerator migration - abstraction layer and the computing force pooling layer. Among them, the - heterogeneous-accelerator migration abstraction layer mainly includes - native interfaces based on a unified programming model and converters, - as well as a hardware-native stack formed by a cross-architecture - comprehensive compiler and runtime, generating a unified executable - program format. The computing force pooling layer mainly consists of - components for heterogeneous computing power registration management, - scheduling, and pooling, achieving unified management and pooled - execution of heterogeneous computing power resources. +The ecosystem is becoming diverse, cross-architecture and cross-stack +migration of upper-layer applications is extremely complex, which brings +development challenges to application developers, computing force +service providers and chip vendors. -![1b84f41a8453933ca5fdc0e00a4fc660.png](en-resource://database/544:0) - Fig. Initial Architecture of Heterogeneous-Accelerator Migration Technology +In order to facing ecological challenges, we proposed a technology named +Heterogeneous-Accelerator Migration Technology , the goal of which is to +break the existing compile-link-execute tightly coupled tool chain +ecology, establish a new collaboration mechanism.Shield the underlying +hardware differences, and realize cross-architecture non-sensing +migration and execution of applications. Build traction model of the +intelligent computing industry chain with software as the core, and +prosper the ecology of intelligent computing industry. -**Release Planning & Release Notes** +The Heterogeneous-Accelerator Migration Technology architecture mainly +consists of two layers: the heterogeneous-accelerator migration +abstraction layer and the computing force pooling layer. Among them, the +heterogeneous-accelerator migration abstraction layer mainly includes +native interfaces based on a unified programming model and converters, +as well as a hardware-native stack formed by a cross-architecture +comprehensive compiler and runtime, generating a unified executable +program format. The computing force pooling layer mainly consists of +components for heterogeneous computing power registration management, +scheduling, and pooling, achieving unified management and pooled +execution of heterogeneous computing power resources. + +## Documentation & Training +N/A + +## Release Planning & Release Notes For release of year 2025, 1.Update and documentation of corss-arch adaptive runtime API -Release 2024 contents: +## Previous Releases +**Release 2024 contents:** 1.Implementation on corss-arch adaptive runtime API 2.Runtime adaptation of Nvidia backend -Release 2023 contents: +**Release 2023 contents:** 1.Heterogeneous-Accelerator Migration Technology Solution: Introduction of Heterogeneous-Accelerator Migration Technology solution, including user guide, architecture description, etc.