Advanced Intelligence for High-Density Edge Solutions

The data center is expanding outward, closer-and-closer to the data generating and consuming endpoints.

Technology is constantly changing our world, disrupting the lives of both industries and individuals. With the rise of new technologies and data-driven services, people and devices that consume and generate data are growing exponentially, from smartphones to IOT-enabled industrial equipment to autonomous cars. This rapid growth of data requires advanced intelligence closer to the endpoints that are both generating and consuming data. To capture and accelerate this opportunity, the powerful data processing and analytics capabilities that have traditionally lived in the heart of the data center must be strategically placed closer-and-closer to the data generating and consuming endpoints, at the “edge”. By expanding the powerful capabilities of the data center outward, service and network providers can deliver more powerful services, reduce application latency by processing more data closer to the edge, and optimize TCO.

Industries and customers use the edge differently
The Intel® Xeon® Scalable processor delivers the ultimate performance to support the largest variety of high-demand applications and services, from the data center core to the edge. As the needs of the edge become more complex and varied, some services and applications will require a different balance of performance, power consumption, and size. The new Intel® Xeon® D-2100 processor brings the advanced intelligence of the Intel® Xeon® Scalable processor architecture into an optimized, dense, lower-power system-on-a-chip (SoC) form factor for environments constrained by space and power. And at the outermost edge, the Intel Atom® C3000 processor delivers data center-class capabilities to purpose-built edge use cases requiring small physical size, very low power, and operating in extreme temperatures.

Along all points, from the data center core, to the edge, to the endpoint device, Intel offers a portfolio of products with advanced data center intelligence to build and accelerate data-driven services and solutions.

Introducing the new Intel® Xeon® D-2100 Processor
The new Intel® Xeon® D-2100 processor delivers Intel’s most transformative and ground-breaking data center processor architecture in a form factor optimized for flexible, scalable, high-density network, storage, and cloud edge solutions. It brings the architectural innovations of the Intel® Xeon® Scalable platform to a system-on-a-chip (SoC) processor for lower-power, high-density solutions, integrating essential network, security, and acceleration capabilities. A software-programmable platform featuring robust virtualization support, with low latency, high-bandwidth capabilities through a flexible design, for a variety of solution and service deployments in space and power constrained environments. Design innovation delivers seamless solution scalability from the data center to the network edge.

Intel® Xeon® D-2100 Processor
Advanced Intelligence for High-Density Edge Solutions

Designed and manufactured with Intel® Mesh Architecture and using Intel’s industry-leading 14nm silicon process technology, the Intel® Xeon® D-2100 processor is the first offering of a line of processors that will address a broad range of lower-power, high-density edge computing needs.

With a range of 4 to 18 cores, up-to 512 GB of addressable memory, this system-on-a-chip (SoC) has an integrated Platform Controller Hub (PCH), integrated high-speed I/O, up-to four integrated 10 Gigabit Intel® Ethernet ports, and a thermal design point (TDP) of 60 watts to 110 watts. It can run the same instruction set as more robust Intel Xeon Scalable processors to provide software consistency and scale from the data center to the edge. It also provides advanced server-class capabilities, including:

  • New Intel® Advanced Vector Extensions 512 (Intel® AVX-512) delivers workload-optimized performance and throughput increases for advanced analytics, compute-intensive applications, cryptography, and data compression.
  • Enhanced Intel® QuickAssist Technology (Intel® QAT), available as an integrated option, delivers chipset-based hardware acceleration, up-to 100 Gbps, for growing cryptography, encryption, and decryption workloads for greater efficiency while delivering enhanced transport and protection across server, storage, and network infrastructure.
  • Built-In Hardware Virtualization using Intel® Virtualization Technology (Intel® VT) to enable dynamic provisioning of services as communication service providers extend network functions virtualization (NFV) to the network edge.
  • Intel x86 64-bit Software Support for scalable performance and broad application compatibility.
  • Enhanced Reliability, Availability, and Serviceability (RAS) features, including support for error-correcting code (ECC) memory and platform-level error management and resilience.
  • Intel® Platform Storage Extensions to enable smarter and more cost-effective storage solutions through integrated technologies that accelerate data movement, protect data, and simplify data management.
  • Fast Encryption and Decryption Intel® Advanced Encryption Standard New Instructions (Intel® AES-NI) accelerates data encryption and decryption for secure websites.

For more information,1 2 3 4 view a full comparison between the Intel® Xeon® D-2187NT processor, D-1553N processor Network Series and the D-1567 processor.
Download the brief ›

Network Transformation at the Edge
As network traffic volume and complexity increases, operators must both optimize their infrastructure and increase value-added services to drive revenue. This requires more compute capability at all points of the network including the edge. These highly scalable, compact, and energy-efficient SoCs are an ideal solution for equipment makers seeking the best performance per watt when edge computing is constrained by operational space and lower-power requirements.

The diverse requirements of 5G

Multi-Access Edge Computing (MEC)
Growing data capacity and performance to serve endpoint growth
Intel® Xeon® D-2100 processor-based platforms enable Communication Service Providers to bring Multi-access Edge Computing (MEC) next generation, low latency, and high-bandwidth applications to end users in power and space efficient commercial off the shelf servers with advanced analytics. Communications Service Providers will be able to scale and deploy these applications and analytics either at the edge, core or cloud to optimize business agility and efficiency. Enhanced memory support and enhanced I/O deliver more capacity and faster processing. New Intel® Advanced Vector Extension 512 (Intel® AVX-512) and enhanced Intel® QuickAssist Technology enable faster data transfer, faster encryption, and cryptography processing. End users will be able to benefit from a much richer user experience, like Virtual Reality/Augmented Reality and Autonomous Driving, today on the path to the upcoming 5G world thanks to the increased capacity, enhanced, security and performance delivered by the Intel® Xeon® D-2100 processor.

Customer Premise Equipment (CPE)
Enhanced capabilities and capacity for space-constrained vCPE solutions
Intel® Xeon® D-2100 processor-based platforms enable Communications Service Providers to bring intelligent services to the network edge by reducing the total cost of ownership for enterprises to establish next-generation branch office Software Defined Wide Area Network (SD-WAN) applications, in power and space efficient commercial off-the-shelf servers. Enhanced memory support and enhanced Intel® QuickAssist Technology deliver greater application scale combined with faster cryptography processing. With enhanced I/O and higher core count, Intel® Xeon® D-2100 processor offers increased implementation flexibility supporting more virtualized network functions (NFVi). Communications Service Providers can choose which Intel Architecture based-processor (Intel Atom® C3000 processor, Intel® Xeon D-2100 processor, Intel® Xeon® Scalable Processor) meets the performance, space efficiency requirement based on the number of end users (from 10s to 1000s) and size of each enterprise’s branch office.

Supporting Endpoint Demand at the Cloud Service Edge
As the number of endpoints increase, cloud services must optimize their infrastructure and increase capacity to support service quality and drive revenue. This requires more compute capability positioned closer to the endpoints at the edge. These highly scalable, compact, and energy-efficient SoCs are an ideal solution for specialty cloud services such as web-tier and content distribution seeking the best performance per watt when strategically placing service resources closer to the endpoints.

The increasing demands of endpoint growth

Intelligent Foundation for Cloud Warm Storage
Enhanced capabilities and capacity for cloud warm storage scale-out

The Intel® Xeon® D-2100 processor provides an intelligent, highly reliable foundation for large-capacity warm storage solutions in cloud environments. Powerful reliability, availability, and serviceability (RAS) features support error-correcting code (ECC) as well as memory and platform-level error management and resilience. Because the processors have built-in hardware virtualization technology and lower-power versions ranging from around 60 to 110 watts, cloud service providers can pack more storage and performance into each rack, improving performance and availability within the same footprint and reducing total cost of ownership. Intel® SSD Data Center Family for NVMe* delivers fully featured line of solid-state drives to accelerate changes in cloud storage infrastructure and compliment the Intel® Xeon® D-2100 platform.

Specialty Cloud Services with Web-Tier to Edge
Enhancing service scalability for the increasing requirements of content-rich, low-latency, dense data endpoints

The Intel® Xeon® D-2100 processor provides an intelligent, highly reliable foundation for dense cloud content edge services. Delivers a feature-rich platform to drive a lower total cost of ownership (TCO) for specialty, service-optimized solutions such as web-tier and content delivery cloud edge solutions. Additional cores and threads combined with lower TDP requirements deliver more compute per rack with improved performance/watt. New Intel® Advanced Vector Extensions 512 (Intel® AVX-512) and enhanced Intel® QuickAssist Technology deliver enhanced integrations for faster data transfers, faster encryption and faster cryptography processing, enhancing service scalability for the increasing requirements of content-rich, low-latency, data dense cloud edge services.

Intel® Xeon® D-2100 Processor Overview

   

Intel® Xeon® Scalable Processor Intelligence in a Lower-Power SoC

Up to 2.9X1 2 the networking performance and up to 2.8X1 3 the storage performance of the Intel® Xeon® D-1500 processor. Includes up to 18 cores, up to four integrated ports of 10 Gigabit Intel® Ethernet, plus support for up to 512 GB of memory. Also includes Intel® 64-bit software support, Intel® Turbo Boost 2.0 Technology, Intel® Speed Shift Technology, and Intel® Hyper-Threading Technology.

Intel® Mesh Architecture

Designed and manufactured with Intel® Mesh Architecture and using Intel’s industry-leading 14nm silicon process technology enables high density, lower-power system designs with thermal design points of 60W to 110W.

Intel® QuickAssist Technology (Intel® QAT)

Hardware acceleration for compute-intensive workloads, such as cryptography, encryption, and decryption, by offloading the functions to a specialized logic engine (integrated into the chipset), freeing the processor to focus on other workload operations delivering up to 100 Gbps of offload acceleration performance. Available as an integrated option.

Intel® Advanced Vector Extensions 512 (Intel® AVX-512)

Hardware acceleration for compute-intensive workloads delivers workload-optimized performance and throughput increases for advanced analytics, compute-intensive applications, cryptography, and data compression.

Built-In Intel® Virtualization Technology

Delivers near-native compute and I/O performance in virtualized data centers, network infrastructure, and cloud computing, with advanced monitoring of cache and memory bandwidth for better service level and infrastructure management.

Server-Class Reliability, Availability, and Serviceability (RAS)

Provides high system reliability and data integrity with support for error correction code (ECC) memory, single device data correction (SDDC), memory demand and patrol scrubbing, and much more.

Hardware-Enhanced Security and Compliance

Intel Advanced Encryption Standard New Instructions (Intel AES-NI) provide integrated support for fast, low-overhead encryption and Intel® Trusted Execution Technology (Intel® TXT) provides platform verification (through authenticated boot) to enable strong security with reduced performance impact.

Server-Class Manageability

Includes Intel® Node Manager Base for adaptive power management.

Intel® Platform Storage Extensions

Enables fast data movement and high availability through integrated support for non-transparent bridging (NTB), asynchronous DRAM self-refresh (ADR), and Intel® QuickData Technology, which provides a direct memory access (DMA) engine within the SoC.

제품 및 성능 정보

1

벤치마크 결과는 “스펙터”와 “멜트다운”으로 알려진 공격에 대응하기 위한 목적의 최신 소프트웨어 패치 및 펌웨어 업데이트를 적용하기 이전에 얻어진 것입니다. 이러한 업데이트를 적용할 경우 이와 같은 결과가 귀하의 장치 또는 시스템에는 해당하지 않을 수 있습니다.

성능 테스트에 사용된 소프트웨어 및 워크로드는 인텔® 마이크로프로세서에만 적합하도록 최적화되었을 수 있습니다. SYSmark* 및 MobileMark*와 같은 성능 테스트는 특정 컴퓨터 시스템, 구성 요소, 소프트웨어, 운영 및 기능을 사용해서 수행합니다. 해당 요소에 변경이 생기면 결과가 달라질 수 있습니다. 구매를 고려 중인 제품을 제대로 평가하려면 다른 제품과 결합하여 사용할 경우 해당 제품의 성능을 포함한 기타 정보 및 성능 테스트를 참고해야 합니다. 자세한 내용은 http://www.intel.co.kr/benchmarks를 참조하십시오.

2

인텔® 제온® D-2187NT 프로세서의 최대 2.9배 향상된 성능: 인텔® 퀵어시스트 기술(인텔® QAT)이 통합된 이전 세대의 인텔® 제온® D-1553N 프로세서의 웹 서버 처리량을 비교한 결과. 구성 및 워크로드 정보: NGINX 웹 서버: 인텔® 제온® D-1553N 프로세서(12M, 2.30GHz) 1개, 플랫폼: Echo Canyon, 4 x 8GB(32GB 2400MHz 삼성* M494A1G43DB0-CPB), OS: Ubuntu* 16.04.2(4.4.0-21), 벤치마크: NGINX(1.9.6*)-웹서버 처리량 인텔® QAT(ECDHE-ECDSA 최대 성능), 컴파일러: NA, BIOS: GNVDINT1.86B.0010.D22.1611201908, 스토리지: NA, 네트워크 장치: 인텔® 이더넷 컨트롤러 X710(4x 10G/카드) 2개, 네트워크 속도: NA, 인텔® QAT 버전: 1.0.3-42, 점수: 15.7. vs. 인텔® 제온® D-2187NT 프로세서(22M, 2.0GHz) 1개, 플랫폼: Yuba City, 4 x16GB(64GB 2666MHz Micron* 36ASF2G72PZ-2G6B2), OS: Ubuntu*17.10(4.13.0-21-lowlatency), 벤치마크: NGINX(1.10.3)-웹서버 처리량 인텔® QAT (ECDHE-ECDSA 최대 성능), 컴파일러: NA, BIOS: BKVDTRL1.86B.0005.D08.1712070559, 스토리지: NA, 네트워크 장치: 인텔® 이더넷 컨트롤러 X710DA2(2x 25G/카드) 4개, 네트워크 속도: NA, 인텔® QAT 버전: 1.0.3-42, 점수: 46.8.

3

인텔® 제온® D-2183IT 프로세서의 ISA-L(암호화 해시) 최대 2.8배 향상: 이전 세대의 인텔® 제온® D-1587 프로세서와 비교한 결과. 구성 및 워크로드 정보: ISA-L(암호화 해시): 인텔® 제온® D-1587 프로세서(24M, 1.70GHz) 1개, 플랫폼: Durango, 4 x 8GB(32GB 2400MHz), OS: Red Hat Enterprise Linux* 7.4(커널 3.10.0-693.el7.x86_64), 벤치마크: ISA-L (2.21)- 암호화 해시(multibinary_sha512), 컴파일러: NA, BIOS: GNVDINT1.86B.0085.V13.1512071754, 스토리지: 4 x 2TB DC P3700 시리즈 PCIe NVMe*, 네트워크 장치: NA, 네트워크 속도: 1x50GbE, 인텔® 퀵어시스트 기술 버전: NA, 점수: 3.074. vs. 인텔® 제온® D-2183IT 프로세서(22M, 2.20GHz) 1개, 플랫폼: Yuba City, 4 x 8GB(32GB 2400MHz), OS: Red Hat Enterprise Linux* 7.4(커널 3.10.0-693.el7.x86_64), 벤치마크: ISA-L (2.21)- 암호화 해시(multibinary_sha512), 컴파일러: NA, BIOS: BKVDTRL1.86B.0005.D08.1712070559, 스토리지: 4 x 1.6TB DC P4600 시리즈 PCIe NVMe, 네트워크 장치: NA, 네트워크 속도: 2x50GbE, 인텔® 퀵어시스트 기술 버전: NA, 점수: 1.075.

4

인텔® 제온® D-2183IT 프로세서의 최대 1.6배 향상된 성능: 이전 세대의 인텔® 제온® D-1581 프로세서의 Integer 응용 프로그램 처리량을 비교한 결과. 구성 및 워크로드 정보: SPECrate*2017_int_base - 인텔 내부 하드웨어로 측정한 결과: 인텔® 제온® D-1581 프로세서(24M, 1.80GHz) 1개, 4 x 16GB(64GB 2133MHz Micron* 36ASF2G72PZ-2G6B1), OS: redhat-7.4(3.10.0-693.el7.x86_64 x86_64), 컴파일러: IC18, BIOS: 1.0b, 스토리지: 인텔® SSD S3520 800GB, 네트워크 장치: NA, 네트워크 속도: NA, QAT 버전: NA, 점수: 44. vs. 인텔® 제온® D-2183IT 프로세서(22M, 2.20 GHz) 1개, 4 x 16GB(64GB 2400MHz Micron* 36ASF2G72PZ-2G6B1), OS: redhat-7.4(3.10.0-693.el7.x86_64 x86_64), 컴파일러: IC18, BIOS: BKVDTRL1.86B.0005.D08.1712070559, 스토리지: 인텔® SSD S3520 800GB, 네트워크 장치: NA, 네트워크 속도: NA, QAT 버전: NA, 점수: 72.1.