Accelerating Data-Centric Innovation with Processing Performance Leadership

Introducing Cascade Lake Advanced Performance and Intel® Xeon® E Processors for Servers

Earlier this summer, Intel unveiled its strategy for delivering a silicon foundation for data-centric infrastructure with a focus on moving data faster, storing more data, and processing everything. This focus drives our technology investment and work with industry leaders to drive optimized solution delivery that addresses customer requirements for the data-centric era. Last week, I announced a major step forward in our pursuit of re-architecting the memory-storage pyramid to enable better usage and storage of data with the introduction of our Intel® Optane™ DC Persistent Memory beta program. Already, many ecosystem partners have announced intent to deliver early access solutions and services to customers based on this beta program including Google’s announcement of the first cloud service delivery featuring this breakthrough memory technology.

Today, we’re sharing more about our continued pursuit to deliver the right compute platform and capabilities to process everything, and that means support for a wide range of data-centric application requirements. In advance of Supercomputing 2018, we are announcing plans to deliver Cascade Lake advanced performance, a new class of Intel® Xeon® Scalable processors aimed at demanding HPC (High Performance and Technical Computing) applications, such as weather modeling, seismic, and manufacturing CFD (Computational Fluid Dynamics), Artificial Intelligence (AI), and Infrastructure as a Service (IaaS) workloads. With Cascade Lake advanced performance’s entry into the market, we expect to continue delivering performance leadership and unprecedented CPU memory bandwidth via a performance optimized multi-chip package. These advanced performance Cascade Lake processors will be delivered via two socket configurations featuring 48 cores per CPU and 12 DDR4 memory channels per socket.

The mixture of increased Intel® Xeon® Scalable processor cores and improved memory bandwidth per socket are expected to yield significant performance advancements, especially on HPC workloads that will be a focus at SC’18 later this month. These include expected delivery of Linpack performance gains of up to 1.21X vs the Intel® Xeon® Scalable 8180 processor and 3.4X vs the best in market competitive performance showcasing Cascade Lake advanced performance’s pure core performance advancements. It also includes Stream Triad performance gains of 1.83X vs the Intel® Xeon® Scalable 8180 processor and 1.3X vs the best in market competitive performance highlighting major advancements in memory bandwidth vs. Intel’s current generation platform. We expect the new processor to hold performance leadership across a range of data-centric workloads through 2019 vs any other CPUs entering the market. Cascade Lake advanced performance will also take advantage of the Intel® Deep Learning Boost capability featured on all Cascade Lake processors to improve AI/deep learning inference performance up to 17X vs Intel® Xeon® Platinum processor measurements at launch last July.1 We’re working with our OEM customers now to drive these solutions to the market with expected market introduction in the first half of 2019.

Today, I’m also excited to announce that we’re bringing the Intel® Xeon® E processor to servers, delivering essential performance for 1S entry server solutions and offering a platform foundation for trusted enclave delivery via enhanced Intel® Software Guard Extensions (Intel® SGX). Trusted enclaves provide a capability for businesses to store their most valuable data and applications in a digital vault within a server and has been tapped by industry partners to deliver trusted key protection as well as trusted blockchain transaction management. Leading cloud service providers including Microsoft and IBM have also utilized the technology to offer hardware-enhanced confidential computing services to customers. To find out more about this new processor, please check out our webcast.

These two announcements provide a great testament to Intel’s tireless pursuit in driving workload optimized innovation to fuel a wide range of customer requirements for the data-centric era. The new class of Intel® Xeon® Scalable performance combined with new entry of Intel® Xeon® E processors extends and enhances the compute alternatives offered through the Intel portfolio from Intel Atom® and Intel® Xeon® processors to Intel® Stratix® and Intel® Arria® FPGA acceleration and future advancements via Intel® NNP and GPU delivery. I can’t wait to share more details with you on these latest entries of our compute portfolio as solutions enter the market.


1 Software and workloads used in performance tests may have been optimized for performance only on Intel® microprocessors. Performance tests are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit www.intel.com/benchmarks. Performance results are based on testing as of 10/12/2018 and may not reflect all publicly available security updates. See configuration disclosure for details. No product can be absolutely secure. Results have been estimated or simulated using internal Intel analysis or architecture simulation or modeling, and provided to you for informational purposes. Any differences in your system hardware, software or configuration may affect your actual performance.