2
Cray Inc. • 901 Fifth Avenue, Suite 1000 • Seattle, WA 98164 • Tel: 206.701.2000 • Fax: 206.701.2500 • www.cray.com © 2017 Cray Inc. All rights reserved. Specifications are subject to change without notice. Cray and the Cray logo are registered trademarks, and Cray XC is a trademark of Cray Inc. Intel Xeon, Xeon Phi and the Intel logo are trademarks of Intel Corporation in the U.S. and/or other countries. All other trademarks mentioned herein are the properties of their respective owners. 20171109ES Cray ® XC50 ™ Supercomputer Adaptive Computing Reaches New Heights The Cray ® XC50 ™ supercomputer is a massively parallel processing (MPP) architecture designed for environments where engi- neering, research, scientific, analytics and deep learning applications can leverage the processing power of today’s advanced Intel ® Xeon ® , Intel ® Xeon Phi™ and Cavium processors and NVIDIA ® Tesla ® GPU accelerators. Building on Cray’s adaptive super- computing vision, the XC50 system integrates extreme performance HPC interconnect capabilities with best-in-class processing technologies to produce a single, scalable architecture. Cray XC50 Compute Blade For production supercomputing and user productivity, the Cray XC50 compute blade implements two Intel Xeon Scalable processor engines per compute node and has four compute nodes per blade. Compute blades stack 16 to a chassis and each cabinet can be populated with up to three chassis, resulting in 384 sockets per cabinet and providing performance of more than 619 TF per cabinet. Cray XC50 supercomputers can be configured up to hundreds of cabinets and upgraded to nearly 300 PF per system with CPU blades and over 500 PF per system with a combination of CPU and GPU blades. CPU/GPU Compute Blades For GPU-accelerated compute requirements, the XC50 CPU/GPU compute blade features four compute nodes, each including one Intel Xeon CPU and one NVIDIA Tesla P100 PCIe GPU. A full cabinet of 192 nodes provides up to 1 PF of peak performance. Network Topology and Interconnect Designed for System Scale and Performance The Cray XC50 supercomputer utilizes the performance-optimized Cray Aries interconnect technology. This innovative intercom- munication technology, implemented with a high-bandwidth, low-diameter network topology called Dragonfly, provides substantial improvements on all the network performance metrics for HPC: bandwidth, latency, message rate and more. Delivering unprece- dented global bandwidth scalability at reasonable cost across a distributed memory system, this network provides programmers with global access to all the memory of parallel applications and supports the most demanding global communication patterns. Performance and Insight — Comprehensive Programming Environment The Cray Programming Environment is designed to drive maximum computing performance and enable productive programma- bility. This feature-rich, flexible software environment facilitates the development of massively scalable applications, targeting optimization for intramode performance as well as system scaling across a multitude of nodes and compute cabinets. Scalable Software Advantages The Cray XC50 system delivers the latest Cray Linux Environment (CLE), a suite of high performance software including a Linux-based operating system designed to scale efficiently and run large, sophisticated HPC applications. When running highly scalable applications, Cray’s Extreme Scalability Mode (ESM) ensures operating system services do not interfere with applica- tion performance. Real-world applications have proven this optimized design scales to hundreds of thousands of cores and is capable of scaling to more than one million cores. To get the most workload production out of your supercomputing system, Cray provides a robust system management stack with a broad variety of utilities and support.
