Summary
Dell PowerEdge XR4000 is a compact multi-node server designed for the edge. This Tech Note discusses the Intel Xeon D processor, which powers the XR4000 server. These CPUs are unique, being primarily designed for edge deployments. New integrated technology that enables faster performance over the previous generation helps create a solution for designs with space and power constraints while also lowering TCO.
Introduction
Dell PowerEdge XR4000 is the latest addition to Dell Technologies’ portfolio of rugged PowerEdge servers. It is Dell’s shortest-depth edge server, with a unique sled and chassis form factor, withstanding an extended temperature range of –5°C to 55°C. The XR4000 provides a sustainable solution for customers to deploy various edge workloads in challenging environments.
The brain of this server is the Intel Xeon D CPU, which features a one-package design with integrated AI, security, advanced I/O, and Ethernet, plus dense compute, to deliver high data throughput and address key edge requirements. To broaden the range of usage models, the Xeon system-on-a-chip (SoC) is available in two distinct packages: the high-core-count Xeon D-2700 processor, optimized for performance, and the Xeon D-1700 processor, which is optimized for cost and power
consumption. With options ranging from 4 to 20 cores, the Xeon D-2700 processor is suited to demanding workloads, such as handling high data-plane throughput, making it more suitable for edge deployments. Extended operating temperature ranges and industrial-class reliability make Xeon D-1700 and D-2700 SoCs ideal for high- performance rugged equipment.
Improved performance for the edge
Dell PowerEdge XR4000 is based on the Xeon D-2700 SoC. This SoC is an HCC 52.5 x 45 mm package, supporting up to 20 cores and using Intel’s Sunny Cove cores to boost performance for edge use cases. The Xeon D-2700 offers a CPU performance gain of up to 2.97 times and improved AI inferencing that is 7.4 times faster than its previous-generation Xeon D-1577 processor.
Memory speeds have increased by 20 percent, jumping from 2,666 MT/s to 3,200 MT/s. Also, the maximum memory capacity for HCC Xeon D-2700 SKUs is now up to 1,024 GB (with LRDIMM)—two times as much as most Xeon D-2100 SKUs (code named Skylake-D). The increased memory speed and capacity significantly reduce data transfer times for memory-intensive workloads for the edge, such as manufacturing and retail applications, and AI/ML-based applications.
PCIe throughput has also improved by a factor of 2, with support for up to 32 lanes of PCIe Gen 4.0. Throughput speed is 16 GT/s for PCIe Gen 4.0 compared with 8 GT/s for PCIe Gen 3.0. The increased bandwidth of PCIe Gen 4.0 improves the efficiency of workloads such as AI/ML and of edge computing by providing high transfer speeds, while also reducing latency.
Ethernet connectivity
The Xeon D-2700 HCC SoC provides great strides for Ethernet when compared to the previous generation. It increases Ethernet connectivity by 400 percent, providing networking up to 100 GbE with a variety of port options with up to eight ports at 25 Gbps, 10 Gbps, or 1 Gbps with RDMA (iWARP and RoCEv2). Ethernet processing throughput is up by 150 percent with 50 Gbps and 100 Gbps throughput options.
Increased acceleration and compute performance
The Xeon D-2700 and D-1700 processors integrate the following hardware technologies to accelerate workloads:
- Intel Deep Learning Boost (Intel DL Boost)
- Intel AES New Instructions (Intel AES-NI)
- Intel Advanced Vector Extensions 512 (Intel AVX-512)
- Intel QuickAssist Technology (Intel QAT) with inline IPSec support
Intel QAT v1.8 accelerates crypto SSL up to 100 Gbps and compression up to 70 Gbps, which offers better Integrated cryptographic and AI acceleration compared to the previous generation. It includes new instructions to accelerate AI/deep learning workloads. (See Intel QAT: Performance, Scale, and Efficiency.)
Intel hardware-based security
Intel Xeon D processors offer integrated security features including Intel Total Memory Encryption, which provides full memory encryption with segmentation for up to 64 tenant-provided keys. The processors support Intel Software Guard Extensions (Intel SGX), which provides fine-grain data protection through application isolation in memory. This protection could be crucial for data exchange between the cloud and edge. Xeon D processors also support Intel Secure Hash Algorithm Extensions with integrated accelerators for SHA cryptographic algorithms and Intel Platform Firmware Resilience (Intel PFR), which uses an Intel field programmable gate array (FPGA) to protect, detect, and correct platform firmware.
Conclusion
The Intel Xeon D processor is a cost-effective offering that is built specifically for edge deployments. It allows users to tailor their solutions to the level of compute and performance they need while allowing for edge implementation-specific space and power constraints. The Xeon D processor and the PowerEdge XR4000 server help customers deploy solutions with lower TCO and a low-power budget in a rugged environment. The solutions are well suited for various edge workloads in retail, manufacturing, and defense.
