Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

Intel Details Lunar Lake Architecture, Gaudi AI Accelerator, Unveils Xeon 6 Processors

Share

Intel Xeon 6 processors were launched at AMD’s annual Computex event as the company shared details of its AI strategy. Like Nvidia, Asus, and other participants at the event, the chipmaker also introduced its AI-led portfolio including new hardware, data centre innovation, and AI accelerators to power servers with AI handling capabilities. Notably, the company also shared details about its Lunar Lake Platform and explained how the architecture will bolster AI PCs. Intel also revealed the pricing for its Gaudi 2 and Gaudi 3 AI accelerators.

Intel shares details of Lunar Lake Architecture

To power the next wave of AI PCs, Intel announced its Lunar Lake CPUs as the successor to Meteor Lake chipsets last month. During the ongoing Computex event, the chipmaker shared more details about its architecture. There is a new system-on-chip design which the company claims triples the size and offers more than four times the performance of its AI accelerator. It is also claimed to provide up to 14 percent faster CPU performance, 50 percent higher graphics performance, and up to 60 percent better battery efficiency compared to its predecessor.

The Lunar Lake processors feature a fourth-generation Neural Processing Unit (NPU) capable of handling up to 48 tera-operations per second (TOPS) of AI performance. A new GPU design, codenamed Battlemage, significantly improves gaming and graphics performance and offers up to 67 TOPS of performance in AI content creations.

Other notable changes include an integrated 16 of 32GB of LPDDR5X memory into the system instead of a separate memory stick. This means there is no option to connect more RAM.

Intel Xeon 6 processors launched

Just six months after launching the 5th generation Intel Xeon processors, the tech giant is now introducing the first Xeon 6 chipsets including the Xeon 6 E-core and the Xeon 6 P-core. Also known as Efficient-core, the Intel Xeon 6 E-core is designed to deliver AI-focused performance with lower power consumption. The P-core, on the other hand, offers higher performance outputs. These processors are meant for data centres to power server-based AI features and AI computing for devices.

The Intel Xeon 6 E-core processors are now available to purchase and the company will launch the Xeon 6 P-core processors in the third quarter of the year. The prices were not disclosed.

Intel Gaudi 2, Gaudi 3 AI accelerator kits price revealed

Intel also shared pricing details of its Gaudi 2 and Gaudi 3 AI accelerator kits, which the company has positioned as an alternative to Nvidia’s H100 chips. Aimed at customers with heavy AI workflows, these AI accelerators are said to provide performance improvements for training and inference tasks for major open-source AI models.

As per the company, the Intel Gaudi 3 is a cluster of 8,192 accelerators that offer up to 40 percent faster time-to-train AI models compared to the H100 GPU clusters. The company found the numbers running tests to train the Llama-2 70B AI model. Intel says the inferencing is also faster with its accelerators.

The standard AI kit with eight Intel Gaudi 2 accelerators and a universal baseboard (UBB) will be offered to system providers for the price of $65,000 (roughly Rs. 54,33,100). The Intel Gaudi 3 with a similar setup will be available for $125,000 (roughly Rs. 10,448,200).