WEBVTT

00:00:05 --> 00:01:35
Arm architecture and growing compute requirements for machine learning

00:01:35 --> 00:03:06
Addressing software fragmentation in long-tail machine learning workloads

00:03:06 --> 00:04:15
The need for unified open tooling across hardware vendors

00:04:15 --> 00:06:24
Introduction to the unified acceleration library and oneAPI specification

00:06:24 --> 00:08:05
Optimizing neural networks and integrating frameworks with oneDNN

00:08:05 --> 00:09:03
Consolidating mathematical function implementations using the oneMath library

00:09:03 --> 00:10:02
Handling task parallelism and scheduling consistently with oneTBB

00:10:02 --> 00:11:21
Scaling multi-node communications and building machine learning pipelines

00:11:21 --> 00:13:11
Integrating the UXL stack from hardware execution to frameworks

00:13:11 --> 00:16:09
Democratizing intelligent computing via an open hardware-agnostic stack

00:16:09 --> 99:59:59
Contributing code and micro kernels to the UXL Foundation