Intel detailed new desktop, Xeon, AI, and GPU chips at its annual conference. Credit: Intel Corporation Intel took the wraps off a number of new chip designs during its Innovation 2023 event in San Jose, Calif. Among the highlights is a preview of fifth-generation Xeon processors, which gain performance improvements and faster memory while using the same amount of power as the current generation. Scheduled to launch beginning December 14 and going into 2024, the fifth generation of Xeon processors splits the structure into two different core designs: the P (for performance) core, codenamed Granite Rapids, and the E (for efficient) core, codenamed Sierra Forest. P cores are high-performance cores for maximum computing power, while E cores are smaller, much less power-hungry, and designed for simpler tasks. The Granite Rapids processor will offer two- to three-times better AI performance compared to 4th Gen Xeon. The new Sierra Forest Xeon processor, including a version with 288 E-cores, will deliver 2.5 times better rack density and 2.4 times higher performance per watt over 4th Gen Xeon when it ships in the first half of 2024 Intel details future Meteor Lake design Intel also gave a deep dive on what to expect from its client processors. For a glimpse of what’s coming next in the Xeon lineup, it’s important to watch what’s happening with the Core line of desktop processors, because that’s where new features are introduced first. Intel first introduced its mix of Performance and Efficiency cores with the Alder Lake generation of desktop and mobile processors, for example. Looking ahead, Intel will ship Core Ultra processors, code-named Meteor Lake, on December 14. On the same day, we’ll see Intel’s first integrated neural processing unit, or NPU, for power-efficient AI acceleration and local inference on the PC. Intel CEO Pat Gelsinger confirmed Core Ultra will also launch on Dec. 14. Meteor Lake introduces a new design for Intel CPUs: tiles (or chiplets) rather than a single monolithic piece of silicon. It comes with four tiles – one for the CPU, GPU, SoC, and I/O – bound together with a high-speed interconnect. AMD has used this design for several years now. What’s interesting is that this processor was partly made by Intel and partly made by TSMC rather than entirely made by Intel. The NPU is another new element in Meteor Lake. The NPU, or AI accelerator, is part of the CPU tile. Intel hasn’t gone beyond the talking stage, so it’s not clear exactly what it does, but it will probably be similar to the AI processor in the AMD 7004 series of server processors. Intel supercomputer news As part of the keynote kicking off the show, Gelsinger announced a large AI supercomputer will be built entirely on Intel Xeon processors and Intel Gaudi AI hardware accelerators from Intel’s Habana Labs acquisition. The supercomputer is being built in partnership with Stability AI, the creator of the Stability Diffusion text-to-image model. The supercomputer will be the largest AI system in Europe and among the world’s top 15 AI supercomputers when it’s completed, according to Gelsinger. The company did not say when it will complete the supercomputer. Gelsinger also announced the launch of Project Strata to promote the development of an edge-native software platform for building an intelligent edge infrastructure powered by AI. The solution will provide developers with modular building blocks to build, deploy, run, manage, connect and secure distributed edge infrastructure and applications. Lastly, the Intel Developer Cloud has exited beta and is now generally available, giving developers access to AI/HPC security workloads across Intel’s array of data center and product offerings. Related content news High-bandwidth memory nearly sold out until 2026 While it might be tempting to blame Nvidia for the shortage of HBM, it’s not alone in driving high-performance computing and demand for the memory HPC requires. By Andy Patrizio May 13, 2024 3 mins CPUs and Processors High-Performance Computing Data Center news CHIPS Act to fund $285 million for semiconductor digital twins Plans call for building an institute to develop digital twins for semiconductor manufacturing and share resources among chip developers. By Andy Patrizio May 10, 2024 3 mins CPUs and Processors Data Center news HPE launches storage system for HPC and AI clusters The HPE Cray Storage Systems C500 is tuned to avoid I/O bottlenecks and offers a lower entry price than Cray systems designed for top supercomputers. By Andy Patrizio May 07, 2024 3 mins Supercomputers Enterprise Storage Data Center news Lenovo ships all-AMD AI systems New systems are designed to support generative AI and on-prem Azure. By Andy Patrizio Apr 30, 2024 3 mins CPUs and Processors Data Center PODCASTS VIDEOS RESOURCES EVENTS NEWSLETTERS Newsletter Promo Module Test Description for newsletter promo module. Please enter a valid email address Subscribe