From Model to Metal: An Open Source Stack for Accelerating Intelligence

Stop rewriting AI code for every new chip. A new open-source stack lets you write once and run anywhere, from model to metal.

#1about 3 minutes

The challenge of a fragmented AI software stack

The proliferation of AI workloads across diverse hardware has created a fragmented ecosystem with vendor-specific libraries and duplicated optimization efforts.

#2about 3 minutes

Unifying AI development with the UXL Foundation

The UXL Foundation leverages Intel's oneAPI to create a unified, open-source library suite that ensures portability and performance across different hardware architectures.

#3about 3 minutes

Exploring core UXL components for compute and math

A breakdown of oneDNN for accelerating deep learning primitives and oneMKL for high-performance mathematical functions like BLAS and FFT.

#4about 2 minutes

Managing parallelism and data with UXL libraries

An overview of oneTBB for task scheduling, oneCCL for multi-node communication, and oneDAL for managing data analysis and machine learning pipelines.

#5about 2 minutes

Visualizing the end-to-end UXL software stack

The complete architecture shows how UXL libraries abstract hardware and accelerate operations for frameworks during training, inference, and serving.

#6about 3 minutes

The benefits of an open and unified AI stack

An open-source, unified stack increases developer productivity, fosters community innovation, and ensures software evolves in lockstep with new hardware releases.

#7about 1 minute