Saturday, June 6, 2026

Top 5 This Week

Related Posts

Computex 2026: Intel’s next steps in artificial intelligence start with Xeon 6+

At Computex 2026 in Taipei, Intel launched new Xeon 6+ processors, expanded its 800 Series Ethernet portfolio with new Intel Ethernet E835 controllers and network adapters, and provided an update on its artificial intelligence accelerator roadmap, including new details about Crescent Island.

Intel expands its artificial intelligence and data center portfolio with new chips and networking solutions. (Intel)
Intel expands its artificial intelligence and data center portfolio with new chips and networking solutions. (Intel)
Shaurya Sharma

Shaurya Sharma is Technology Editor at Hindustan Times Digital Streams, overseeing technology coverage on digital and social platforms. He has over eight years of experience in editing, video production, and digital media with a focus on smartphones, artificial intelligence, consumer electronics, and developing audience-first content strategies for the modern tech consumer.

He began his career as a fashion cinematographer in 2018 before turning a lifelong passion for technology into a career. From a childhood immersed in tech magazines, video games and the latest gadgets to today covering the global consumer tech industry, technology has remained a constant throughout his journey.

Over the years, Shaurya has worked with some of India’s leading media organizations, including CNN-News18, Sportskeeda and Guiding Tech, where he led video initiatives that combined strong editorial storytelling with engaging visual and social-first execution.

A graduate in Journalism and Mass Communication from Manipal University, Shaurya has reviewed hundreds of products across categories including smartphones, laptops, gaming consoles, cameras and wearables. As well as his work, he is passionate about animal welfare, environmental causes and cars, especially turbo-petrol cars

Read moreRead less

What are the new features of Intel Xeon 6+?

Intel said the Xeon 6+ processors focus on performance density, energy efficiency and operational scale and are designed for cloud-native, agent-powered AI-driven workloads.

These processors are built on Intel 18A and are designed to meet the orchestration, concurrency and data movement needs of agent AI. Intel says they are optimized for environments where watts per rack, per-core throughput and latency predictability are critical.

According to Intel, the processor features up to 288 high-efficiency cores, delivering a 2.5x performance improvement over the previous generation and a 45% improvement in performance per watt and per thread.

Other features include 12-channel DDR5 memory, 96-lane PCIe Gen 5, CXL support, Intel Applications Energy Telemetry, up to 9:1 server consolidation, and on-chip security.

Intel said the processors have been tested in telecom network infrastructure and are being configured for data center deployment.

What’s new in Intel Ethernet E835?

As artificial intelligence, cloud and distributed workloads continue to expand, Intel has launched the Intel Ethernet E835 controller and network adapter, which the company says are designed to provide high-performance, energy-efficient connectivity for modern data center, enterprise and artificial intelligence environments.

Key highlights include:

  • Supports configuration of up to 200GbE throughput across multiple controllers and adapters, with data rates ranging from 10GbE to 200GbE.
  • Multiple port configurations including 2x25GbE, 4x25GbE, 2x200GbE, and 1x200GbE, with additional configurations enabled through the Intel Ethernet Port Configuration Tool.
  • Improve power efficiency. Intel claims that the performance per watt of the Intel E835-CQDA2 network adapter is 1.9 times higher than the NVIDIA ConnectX-6 Dx CX614106A and 1.4 times higher than the Broadcom BCM957508P2100G.
  • The life cycle is more than 10 years.

Intel said companies including Cisco, Dell, HPE, Lenovo and Advanced Micro Devices will integrate the new networking solutions.

Intel Crescent Island

Intel says Crescent Island is its next-generation data center GPU designed to meet the growing demands of edge and artificial intelligence workloads, particularly in areas such as memory capacity, bandwidth and efficiency.

The GPU is built on the Xe3P architecture, designed to increase efficiency and performance per watt while maintaining broad software compatibility for modern AI workloads.

It features up to 480GB of LPDDR5X memory to handle large, token-intensive workloads while helping lower total cost of ownership.

According to the company, the GPU features a 350W air-cooled PCIe design and takes advantage of Intel’s multi-generation Xe installed base.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Popular Articles