Addressing Challenges of Cross-Architecture Dynamic Migration Over Heterogeneous Acceleration Systems
Offered By: CNCF [Cloud Native Computing Foundation] via YouTube
Course Description
Overview
Explore a conference talk addressing the challenges of cross-architecture dynamic migration over heterogeneous acceleration systems. Dive into China Mobile's innovative practices for enabling AI applications to migrate smoothly between diverse accelerators such as GPUs, FPGAs, and NPUs. Learn about a unified abstraction for various accelerators, a middle-compiler approach utilizing existing compilers like CUDA, ROCm, and oneAPI to achieve cross-architecture compilation, and a runtime supporting dynamic and replaceable linking. Discover how these solutions aim to overcome tool chain and vendor lock-in issues, allowing applications to migrate freely between different accelerators without altering development habits. Gain insights into the architecture design, open source plans, and witness a demonstration of this groundbreaking approach to cross-system application development and migration.
Syllabus
Addressing Challenges of Cross-Architecture Dynamic Migration Over Heterogeneous... - Yanjun Chen
Taught by
CNCF [Cloud Native Computing Foundation]
Related Courses
FPGA computing systems: Partial Dynamic ReconfigurationPolitecnico di Milano via Coursera FPGA Architecture Based System for Industrial Application
L&T EduTech via Coursera Digital design with FPGAs
St. Petersburg State Polytechnic University via Coursera Electrónica Digital Bit a Bit: Diseñando en Verilog para FPGA
Pontificia Universidad Católica de Chile via Coursera Electrónica Digital Bit a Bit: Fundamentos, Verilog y FPGA
Pontificia Universidad Católica de Chile via Coursera