Intel® Advanced Matrix Extensions (Intel® AMX)
Intel advances AI capabilities with Intel® Xeon® Scalable processors and Intel® AMX, delivering higher inference and training performance.
Accelerate AI Workloads with Intel® AMX
Intel® AMX is a new built-in accelerator that improves the performance of deep-learning training and inference on the CPU and is ideal for workloads like natural-language processing, recommendation systems and image recognition.
What Is Intel® AMX
Expand, simplify, and accelerate your AI capabilities to meet compute demands for deep learning workloads with this integrated accelerator on Intel® Xeon® Scalable processors.
Intel® AMX Enhances AI Inference Performance
Alibaba Cloud’s machine learning platform (PAI) used 4th Gen Intel® Xeon® Scalable processors, featuring Intel® AMX and optimization tools to improve end-to-end inferencing over a previous generation platform.
Optimizing Machine Learning (ML) Models with Intel® AMX
Using Intel® AMX, Intel and Tencent demonstrated BERT model throughput gains compared to the previous generation. Now, Tencent can use the optimized BERT model to deliver better service experiences and to help reduce TCO.
See All Accelerators
Intel® Accelerator Engines are purpose-built integrated accelerators on Intel® Xeon® Scalable processors that deliver performance and power efficiency advantages across many of today’s fastest-growing workloads.1
Accelerate AI with Intel® Advanced Matrix Extensions
Where to Buy
Products featuring Intel® Xeon® Scalable processors and related products are available from our trusted ecosystem of vendors and OEMs.
Intel Insights
Sign up today for the Intel Insights newsletter and get updated weekly on the business technology topics that interest you most.
Product and Performance Information
Availability of accelerators varies depending on SKU. Visit the Intel Product Specifications page for additional product details.