With Intel Xeon 6 processors, Gaudi accelerators and Lunar Lake architecture, Intel delivers the best artificial intelligence across cloud, network, client and edge solutions.
Taipei, Taiwan, June 4, 2024 – At Computex Taipei, Intel unveiled cutting-edge technologies and architectures that promise to dramatically accelerate the artificial intelligence ecosystem—from the data center, cloud, and network to the edge and PCs.
Intel® Xeon® 6 processor with high-efficiency cores (E-Core) delivers performance and energy efficiency for high-density, scale-out workloads in the data center. Achieving 3:1 rack integration, rack-level performance improvement of up to 4.2 times, and performance per watt improvement of up to 2.6×1.
Meanwhile, Intel says the Intel® Gaudi® 2 and Intel® Gaudi® 3 AI accelerator kits are priced to deliver high performance at up to one-third less cost than competing platforms2. The combination of Xeon processors and Gaudi AI accelerators in the system provides a powerful solution that makes AI faster, cheaper and easier to use.
“Artificial intelligence is driving one of the most important eras of innovation the industry has ever seen,” said Intel CEO Pat Gelsinger. “The magic of silicon is once again enabling exponential advances in computing that will exceed what humans can achieve. potential and power the global economy in the coming years.”
Gelsinger continued: “Intel is one of the only companies in the world innovating across all areas of the AI market opportunity—from semiconductor manufacturing to PCs, networking, edge and data center systems. Our latest The Xeon, Gaudi and Core Ultra platforms, combined with the power of our hardware and software ecosystem, are providing our customers with flexible, secure, sustainable and cost-effective solutions to maximize the tremendous opportunities ahead.”
Intel makes AI everywhere
In this Computex keynote speech, Kissinger’s views were supported by many well-known figures and industry-leading companies. His view shows that the advantages of open standards and Intel’s strong ecosystem can help accelerate the development of artificial intelligence opportunities.
In addition, Gelsinger and others also made it clear that Intel is revolutionizing artificial intelligence innovation and launching next-generation technology ahead of schedule. In just six months, the company has gone from launching the fifth generation Intel® Xeon® processors to launching the first member of the Xeon 6 family; from previewing the Gaudi AI accelerator to delivering cost-effective, high-performance generation to enterprise customers GenAI (GenAI) training and inference systems; starting the AI PC era with more than 8 million devices powered by Intel® Core™ Ultra processors, to launching a client architecture slated for release later this year.
With these developments, Intel is accelerating execution while pushing the boundaries of innovation and production speed to democratize AI and advance the industry.
Intel Xeon processors are ideal CPU head nodes for AI workloads and run in systems equipped with the Intel Gaudi AI accelerator, which is designed for AI workloads. Together, the two provide a powerful solution that integrates seamlessly into existing infrastructure.
As the only MLPerf benchmark alternative to the Nvidia H100 for large language model (LLM) training and inference, the Gaudi architecture gives customers the GenAI performance they seek with price/performance advantages, offering choice and speed at a lower total cost. Deployment time.
Intel Gaudi 3 accelerator will bring significant performance improvements to training and inference tasks on leading GenAI models, helping enterprises unlock the value of their proprietary data. Training times on Intel Gaudi 3 in an 8,192-accelerator cluster are expected to be 40% faster compared to a comparably sized Nvidia H100 GPU cluster, while training throughput in a 64-accelerator cluster will be 15% faster than the Nvidia H100 Llama2-70B model. Additionally, Intel Gaudi 3 is expected to deliver an average of 2x faster inference compared to Nvidia H100, running popular LLMs such as Llama-70B and Mistral-7B.
To make these AI systems widely available, Intel is working with at least 10 of the world’s top system providers, including six new providers who have announced they will bring Intel Gaudi 3 to market. Today’s new partners include Asus, Foxconn, Gigabyte, Inventec, Quanta and Wistron, expanding the production offerings of leading system suppliers Dell, Hewlett Packard Enterprise, Lenovo and Super Micro.
Accelerate on-device AI for laptops; new architecture delivers 3x AI computing and incredible energy efficiency
In addition to the data center, Intel is also expanding its AI footprint at the edge and in PCs. For decades, Intel has delivered more than 90,000 edge deployments and 200 million CPUs into the ecosystem, providing enterprises with choice.
Today, the AI PC category is changing every aspect of the computing experience, and Intel is at the forefront of this category-creating moment. It’s no longer just about faster processing speeds or sleeker designs, but about creating edge devices that learn and evolve in real time—anticipating user needs, adapting to their preferences, and heralding a new era of productivity, efficiency, and creativity.
According to the Boston Consulting Group, AI-powered PCs are expected to account for 80% of the PC market by 2028. To this end, Intel moved quickly to create the best hardware and software platform for AI PC, supporting more than 100 independent software vendors (ISVs), 300 functions, and supporting 500 AI models on its Core Ultra platform.
With these unparalleled advantages, the company today announced the architectural details of Lunar Lake – the next-generation flagship processor for AI PCs. With a huge leap in graphics and AI processing power, and a focus on energy-efficient computing performance in thin and light parts, Lunar Lake will provide up to 40% reduction in SoC power consumption3 and more than 3x AI computing8. Shipping is expected in the third quarter of 2024, in time for the holiday buying season.
Post time: Jun-07-2024