AMD, Intel simplify AI development on x86 CPUs with PyTorch

AMD and Intel have announced a collaboration to combine their x86 CPU optimization work for PyTorch in oneDNN, an open-source deep learning library governed by the Unified Acceleration Foundation (UXL) that helps AI workloads run efficiently on CPUs. 

This move, recommended by the x86 Ecosystem Advisory Group, aims to give developers a common software path for optimized AI workloads across AMD and Intel CPUs, reducing fragmentation in the AI ecosystem, AMD said.

AMD and Intel have aligned on oneDNN as the default open-source library for x86 acceleration within PyTorch. AMD is integrating its ZenDNN optimizations into oneDNN and has joined the UXL Foundation as a steering member to further advance this work through open collaboration.

Developers will have one place to access CPU optimizations for PyTorch across AMD and Intel processors, making applications easier to build, maintain and deploy AI applications across the x86 ecosystem.

“AMD is advancing an open software ecosystem that gives developers greater choice and makes it easier to build high-performance AI applications,” said Robert Hormuth, corporate vice president, Architecture and Strategy, AMD. “By working with the x86 Ecosystem Advisory Group, we’re bringing the industry together around common technologies that simplify development across x86 processors.”

“Working with AMD through oneDNN gives the PyTorch community a consistent approach for modern processors and a way to bring future capabilities, including AI Compute Extensions, into the framework,” said Jeff McVeigh, vice president and general manager, Data Center Strategic Programs, Intel. 

Stephen Watt, vice president, Office of the Chief Technology Officer, and distinguished engineer, Red Hat, and PyTorch ambassador, said AMD and Intel coming together to standardize x86 CPU optimizations through oneDNN in PyTorch was a major step forward in eliminating ecosystem fragmentation. 

AMD and Intel are also collaborating on AI Compute Extensions (ACE), a next-generation instruction set architecture (ISA) for x86. ACE is designed to accelerate matrix multiplication, a core mathematical operation in AI workloads, and will be integrated within PyTorch through future oneDNN updates, AMD said.