Introduced Intel Xeon 6 processors and Gaudi 3 AI accelerators with the ability to handle advanced AI workloads

Intel recently unveiled new hardware aimed at improving artificial intelligence (AI) workflows. On Tuesday, the company introduced the Xeon 6 processor with new Performance-cores (P-cores) and the Gaudi 3 AI Accelerator for business users and data centers. The chipmaker claims the new hardware will offer both higher bandwidth and better cost optimization to enable optimal performance per watt and lower total cost of ownership. These devices were launched to enable companies to cope with the ever-increasing workload demands of more advanced AI models, according to the chip maker.

Intel Xeon 6 processor launched

The chipmaker says its new Intel Xeon 6 is equipped with Performance cores. These processors are not intended for retail consumers and will instead power enterprise data centers to help them run cloud servers.

Intel claims that the Xeon 6 processor offers twice the performance of its predecessor due to the increased number of cores. It also offers double the memory bandwidth and AI acceleration capabilities.

Since it is hardware accelerated, it can easily drive support for very large language models (LLM). It can “meet AI performance requirements from the edge to the data center and cloud environments,” according to Intel.

Intel introduces Gaudi 3 AI accelerators

Gaudi 3 is a new generation of AI accelerator from Intel. These are specialized hardware chips designed to help machines speed up artificial intelligence tasks, especially those related to deep learning, machine learning, and neural networks. These include GPUs, application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), and neural processing units (NPUs).

The Gaudi 3 AI Accelerator features 64 Tensor processing cores and eight Matrix Multiplication Engines (MMEs) designed to accelerate deep neural network calculations. It has 128GB of HBM2e memory for training and inference and 24 200GB Ethernet ports to allow server scaling.

Intel’s new AI Accelerator is compatible with the PyTorch framework and advanced Hugging Face transformer and diffuser models. The company has already tied up with IBM to deploy Gaudi 3 for IBM Clouds. Dell Technologies also uses the infrastructure for its data centers.