Second Generation Intel® Xeon® Scalable Processors

The Foundation for Data-Centric Innovation

Empowering Transformation in a Data-Centric Era

Across an evolving digital world, disruptive and emerging technology trends in business, industry, science, and entertainment increasingly impact the world's economies. By 2020, the success of half of the world's Global 2000 companies will depend on their abilities to create digitally enhanced products, services, and experiences,1 and large organizations expect to see an 80 percent increase in their digital revenues,2 all driven by advancements in technology and usage models they enable.

This global transformation is rapidly scaling the demands for flexible compute, networking, and storage. Future workloads will necessitate infrastructures that can seamlessly scale to support immediate responsiveness and widely diverse performance requirements. The exponential growth of data generation and consumption, the rapid expansion of cloud-scale computing, emerging 5G networks, and the extension of high performance computing (HPC) and artificial intelligence (AI) into new usages require that today's data centers and networks urgently evolve—or be left behind in a highly competitive environment. These demands are driving the architecture of modernized, future-ready data centers and networks that can quickly flex and scale.

The Intel® Xeon® Scalable processor family provides the foundation for a powerful data center platform that creates an evolutionary leap in agility and scalability. Disruptive by design, this innovative processor sets a new level of platform convergence and capabilities across compute, storage, memory, network, and security. Enterprises and cloud and communications service providers can now drive forward their most ambitious digital initiatives with a feature-rich, highly versatile platform.

Enabling Greater Efficiencies and Lower TCO
Across infrastructures, from enterprise to technical computing applications, the Intel® Xeon® Scalable processor family is designed for data center modernization to drive operational efficiencies that lead to improved total cost of ownership (TCO) and higher productivity for users. Systems built on the Intel® Xeon® Scalable processor family are designed to deliver agile services with enhanced performance and groundbreaking capabilities, compared to the prior generation.

Performance to Propel Insights

Intel's industry-leading, workload-optimized platform with built-in AI acceleration, provides the seamless performance foundation for the data-centric era from the multicloud to intelligent edge, and back, the Intel® Xeon® Scalable processor family with 2nd Gen Intel® Xeon® Scalable processors enables a new level of consistent, pervasive, and breakthrough performance.

New Intel® Xeon® Platinum 9200 processors3 4

New 2nd Gen Intel® Xeon® Scalable processors5 6 7

2nd Gen Intel® Xeon® Scalable Processor Provides Consistent Performance for Diverse Workloads

  What Matters? Intel® Xeon® Scalable Processor Family Advantages
Enterprise and Cloud

Minimize complexity with compatible virtualization infrastructure

Meet stringent customer SLAs

Deploy quickly. Intel VMs coexist w/ other Intel® technology-based servers.

Fast response times.

HPC
Maximize vector floating point performance and efficiency High-performance with fewer servers.
Storage Ensure deterministic storage response Deterministic performance. Cores, cache, memory, I/O in a single die.
Communications Deliver diverse services efficiently Incredible efficiency and hardware acceleration from a platform with features required for application, control, packet, and signal processing.

Support for Breakthrough Memory Innovation
A new foundation for performance begins with support for Intel's breakthrough Intel® Optane™ DC persistent memory, a new class of memory, and storage innovation architected for data-centric class environments. With individual module capacities up to 512 GB, Intel® Optane™ DC persistent memory can deliver up-to 36 TB of system-level memory capacity when combine with traditional DRAM. Intel® Optane™ DC persistent memory complements DRAM memory by affordably enabling unprecedented system memory capacity to accelerate workload processing and service delivery.

New 2nd Gen Intel® Xeon® Scalable Processors with Intel® Optane™ DC Persistent Memory8 9 10

Foundational Enhancements

  • Higher Per-Core Performance: Up to 56 cores (9200 series) and up to 28 cores (8200 series), delivering high-performance and scalability for compute-intensive workloads across compute, storage, and network usages
  • Greater Memory Bandwidth/Capacity: Support for Intel® Optane™ DC persistent memory, supporting up-to 36 TB of system-level memory capacity when combine with traditional DRAM. 50 percent increased memory bandwidth and capacity. Support for six memory channels and up-to 4 TB of DDR4 memory, per socket, with speeds up-to 2933 MT/s (1 DPC)
  • Expanded I/O: 48 lanes of PCIe* 3.0 bandwidth and throughput for demanding I/O-intensive workloads
  • Intel® Ultra Path Interconnect (Intel® UPI): Four Intel® Ultra Path Interconnect (Intel® UPI) (9200 series) and up to three Intel® Ultra Path Interconnect (Intel® UPI) (8200 series) channels increase scalability of the platform to as many as two sockets (9200 series) and up to eight sockets (8200 series). Intel® Ultra Path Interconnect (Intel® UPI) offers the perfect balance between improved throughput and energy efficiency
  • Intel® Deep Learning Boost (Intel® DL Boost) with VNNI: New Intel® Deep Learning Boost (Intel® DL Boost) with Vector Neural Network Instruction (VNNI) bring enhanced artificial intelligence inference performance, with up to 30X performance improvement over the previous generation4, 2nd Gen Intel® Xeon® Scalable processors help to deliver AI readiness across the data center, to the edge and back
  • Intel® Infrastructure Management Technologies (Intel® IMT): A framework for resource management, Intel® Infrastructure Management Technologies (Intel® IMT), combines multiple Intel capabilities that support platform-level detection, reporting, and configuration. This hardware-enhanced monitoring, management, and control of resources can help enable greater data center resource efficiency and utilization
  • Intel® Security Libraries for Data Center (Intel® SecL-DC): A set of software libraries and components, Intel® SecL-DC enables Intel hardware-based security features. The open-source libraries are modular and have a consistent interface. They can be used by customers and software developers to more easily develop solutions that help secure platforms and help protect data using Intel hardware-enhanced security features at cloud scale
  • Intel® Advanced Vector Extensions 512 (Intel® AVX-512): With double the FLOPS per clock cycle compared to previous-generation Intel® Advanced Vector Extensions 2 (Intel® AVX2), Intel® AVX-512 boosts performance, and throughput for the most demanding computational tasks in applications, such as modeling and simulation, data analytics and machine learning, data compression, visualization, and digital content creation
  • Security without compromise: Limiting encryption overhead and performance on all secure data transactions

Innovative Integrations

Platform integrations deliver improvements in performance and latency across the infrastructure:

  • Integrated Intel® QuickAssist Technology (Intel® QAT): Chipset-based hardware acceleration for growing compression and cryptographic workloads for greater efficiency while delivering enhanced data transport and protection across server, storage, and network infrastructure
  • Integrated Intel® Ethernet with scalable iWARP* RDMA*: Provides up to four 10 Gbps high-speed Ethernet ports for high data throughput and low-latency workloads. Ideal for software-defined storage solutions, NVM Express* over Fabric solutions, and virtual machine migrations. Integrated in the chipset

Industry-leading Memory and Storage Support

Storage innovations can drive significant improvements in efficiency and performance of data-hungry workloads.

  • Support for Intel® Optane™ DC persistent memory: Breakthrough memory and storage memory innovation offering groundbreaking capabilities for fast storage solutions. Can be combined with Intel® Optane™ DC SSDs for the ultimate in storage and data performance
  • Support for Intel® Optane™ DC SSDs and Intel® QLC 3D NAND Solid-State Drives: Delivers industry-leading combination of high throughput, low latency, high QoS, and ultra-high endurance to break through data access bottlenecks
  • Deploy next-generation storage with confidence with Intel® Volume Management Device (Intel® VMD): Enables hot swapping of NVMe SSDs from the PCIe bus without shutting down the system, while standardized LED management helps provide quicker identification of SSD status. This commonality brings enterprise reliability, availability, and serviceability (RAS) features to NVMe SSDs, enabling deployment of next-generation storage with confidence
  • Intel® Intelligent Storage Acceleration Library (Intel® ISA-L): Optimizes storage operations, such as encryption, for increased storage performance

Complementary Offerings for Even Greater Performance, Scalability

Intel offers a broad hardware and software portfolio that complements this new processor.

  • Intel® Ethernet 800 series products support up to 100 GbE port speed with Application Device Queues (ADQ), which addresses latency-sensitive workloads for higher speed data communication. Data Plane Developer Kit (DPDK) is supported across Intel® Ethernet 800 series products for NFV acceleration, advanced packet forwarding, and highly efficient packet processing.
    Learn more at intel.com/ethernet
  • Intel® FPGAs offer flexible, programmable acceleration, for low-latency applications, such as virtual switching, network services, data analytics, and AI.
    Learn more at intel.com/fpga
  • A range of software tools and libraries for general and highly parallel computing help developers optimize applications for Intel® architecture.
    Learn more at software.intel.com

Enhanced Platform Trust
Data and platform reliability and protection are key concerns for enterprises dealing with increasing concerns and scrutiny regarding data security and privacy. Intel® Xeon® Scalable processor family helps build highly trusted infrastructures with platform data protection, resiliency, and uptime.

Increased Data Protection and Reliability Across Every Workload

  • Enhanced Intel® Run Sure Technology: New enhancements deliver advanced Reliability, Availability, and Serviceability (RAS) and server uptime for a company's most critical workloads. Hardware-assisted capabilities, including enhanced MCA and recovery and adaptive multidevice error correction, diagnose, and recover from previously fatal errors. And, they help ensure data integrity within the memory subsystem
  • Intel® Key Protection Technology (Intel® KPT) with Integrated Intel® QuickAssist Technology (Intel® QAT) and Intel® Platform Trust Technology (Intel® PTT): Deliver hardware-enhanced platform security by providing efficient key and data protection at rest, in-use, and in-flight
  • Intel® Trusted Execution Technology (Intel® TXT) with One-Touch Activation: Enhanced platform security, while providing simplified and scalable deployment for Intel® Trusted Execution Technology (Intel® TXT)

As more data-rich workloads flow through the data center, this comprehensive suite of hardware-enhanced features brings better data- and platform-level protection mechanisms for trusted services in enterprise and cloud environments.

Dynamic and Highly Efficient Service Delivery
The convergence of enhanced compute, memory, network, and storage performance, combined with software ecosystem optimizations, make Intel® Xeon® Scalable processor family the ideal platform for fully virtualized, software-defined data centers that dynamically self-provision resources—on-premises, through the network, and in the public cloud—based on workload needs.

Powerful Tools and Technologies for an Agile Data Center

Intel® Virtualization Technology (Intel® VT-x) features:

  • Mode-based execution control (MBE) virtualization: Provides an extra layer of protection from malware attacks in a virtualized environment by enabling hypervisors to more reliably verify and enforce the integrity of kernel level code
  • Timestamp counter scaling (TSC) virtualization: Provides workload optimization in hybrid cloud environments by allowing virtual machines to move across CPUs operating at different base frequencies

Intel® Node Manager (Intel® NM) 4.0: Helps IT intelligently manage and optimize power, cooling, and compute resources in the data center, maximizing efficiency, while reducing the chances of costly overheats.

Faster Time to Value with Intel® Select Solutions

In today's complex data center, hardware and software infrastructure is not “one size fits all". Intel® Select Solutions eliminates guesswork with rigorously benchmark tested and verified solutions optimized for real-world performance. These solutions accelerate infrastructure deployment on Intel® Xeon® processors for today's critical workloads in advanced analytics, hybrid cloud, storage, and networking.

Enterprise and Government – Primed for Business
For enterprise data centers modernizing to take advantage of the era of advanced analytics, the hybrid cloud and future-ready storage, Intel® Select Solutions can speed up your data-fueled, IT-driven business transformation.

Communications Service Providers – Tuned Network Enhancements
For Communication Service Providers transforming their network for a 5G-enabled future, Intel® Select Solutions offer a faster and more efficient deployment path of tested, reliable infrastructure with verified configurations that take full advantage of virtual network enhancements that support new and emerging customer workload demands.

High Performance Computing – Accelerated Time to Insight
For research in academia and government as well as the enterprises, high performance computing (HPC) capabilities with Intel® Select Solutions help push the limits of mainstream data today with deeper insights and more complex problem solving.

Learn more about Intel® Select Solutions featuring new 2nd Gen Intel® Xeon® Scalable processors with Intel® Optane™ DC persistent memory at intel.com/selectsolutions.

Strong, Capable Platforms for the Data-Fueled Enterprise

Enterprises are keen to extract value from the exploding data streams being presented to them for rapid insights that can shape their business initiatives. Traditional and emerging applications in the enterprise, including predictive analytics, machine learning, and HPC, require new levels of powerful compute capabilities and massive tiered data storage volumes. The modernized data center is being architected using a converged and holistic approach that can flexibly deliver new services and improve TCO across infrastructure assets today, while providing the most seamless and scalable on-ramp to a self-governing, hybrid data center.

Yet, organizations running their foundational business workloads, such as OLTP and web infrastructure, seek to reduce TCO with higher performing infrastructures.

The Intel® Xeon® Scalable processor family delivers next-generation enterprise capabilities to businesses through a future-ready platform that can serve the hybrid cloud, data-fueled era, plus it helps improve day-to-day operations. This versatile platform brings disruptive levels of compute performance, coupled with memory and I/O advances, to compute-hungry and latency-sensitive applications. Combined with innovative Intel® Optane™ DC persistent memory and Intel® QLC 3D NAND SSD data center family to manage large data volumes across storage, caching, and memory, platforms built on the Intel® Xeon® Scalable processor family are ready to handle the intense demands of the data and cloud era.

With a scalable portfolio of packaging options to suit diverse workload requirements, the Intel® Xeon® Scalable processor family is a performance workhorse designed for deploying highly efficient, virtualized infrastructures for compute, storage, and networking.

New 2nd Gen Intel® Xeon® Scalable Processors with Intel® Optane™ DC Persistent Memory11 12 13

Highlights for Enterprise Innovation

  • 2nd Gen Intel® Xeon® Scalable processors
  • Intel® Optane™ DC persistent memory
  • Intel® Deep Learning Boost (Intel® DL Boost)
  • Intel® Speed Select Technology (Intel® SST)
  • Intel® Ethernet 800 Series
  • Intel® Optane™ DC SSDs and Intel® QLC 3D NAND SSDs
  • Intel® Infrastructure Management Technologies (Intel® IMT)

Next-generation Platform for Cloud-optimized, 5G-Ready Networks, and Next-generation Virtual Networks

The coming era of 5G will enable entirely new ecosystems and classes of consumer and enterprise services along with media applications on wireless and wireline networks. These data-rich, innovative use cases, driven by the new Internet of Things (IoT), visual computing, and analytics, represent significant future opportunities for communications service providers (CommSPs) to grow revenue.

The transition from purpose-built, fixed function infrastructure to a new generation of open networks is the essential first step to prepare for a 5G-enabled world. Software-defined networking with Network Functions Virtualization (NFV) is enabling new service opportunities and operations efficiencies for both communication services providers and enterprises alike. Using flexible, optimized, industry-standard servers and virtualized, orchestrated network functions will allow future-ready infrastructures to be able to deliver innovative services with efficiency and ease.

Such distributed communications networks can support extreme levels of scalability, agility, programmability, and security across an ever-growing volume and variety of networking workloads—from the network core to the edge.

The Intel® Xeon® Scalable processor family is the basis for next-generation platforms to build virtualized, cloud-optimized, 5G-ready networks. It offers an architecture that scales and adapts with ease to handle the demands of emerging applications and the convergence of key workloads, such as applications and services, control plane processing, high-performance packet processing, and signal processing. This new processor provides a foundation for agile networks that can operate with cloud economics, be highly automated and responsive, and support rapid and more secure delivery of new and enhanced services enabled by 5G.

New 2nd Gen Intel® Xeon® Scalable Processors Specialized for Networking/NFV “N” SKUs14

Highlights for Communication Service Provider Innovation

  • 2nd Gen Intel® Xeon® Scalable processor “N” SKUs, specialized for Networking/NFV
  • Intel® Optane™ DC persistent memory
  • Hardware-based acceleration of encryption and compression using integrated Intel® QAT
  • Intel® Ethernet 800 Series
  • Intel® FPGAs maximize versatility in communications infrastructure
  • Intel® Infrastructure Management Technologies (Intel® IMT)

Additional Resources Optimized for Communication Service Providers
The open-source Data Plane Development Kit (DPDK) enables optimized communications operations on Intel® architecture. DPDK has demonstrated ability to scale performance as processor core count and performance increase; workloads, such as Vector Packet Processing (VPP) IPsec, benefit from this enhanced performance. Additionally, these libraries provide pre-optimized mechanisms to allow new processor capabilities (such as Intel® AVX-512 and memory and I/O enhancements) to be able to utilize the new functionality for improved packet processing performance with less direct development effort.

Intel offers programs, such as Intel® Network Builders University, ideal for network evolution in the 5G era. With solution guidance and training from these programs, CommSPs can drive their network transformation initiatives forward with increased confidence.

Breakthrough HPC and High-performance Data Analytics Innovation

Today's scientific discoveries are fueled by innovative algorithms, new sources and volumes of data, and advances in compute and storage. Benefitting from exponentially expanding volumes and variety of data, HPC clusters are also the engine for running evolving High-performance Data Analytics (HPDA) workloads, leading to incredible discoveries and insight for business and human understanding. Machine learning, deep learning, and AI converge the capabilities of massive compute with the flood of data to drive next-generation applications, such as autonomous systems and self-driving vehicles.

Intel® Xeon® Scalable processor family offers a common platform for AI with high throughput for both inference and training—up to 30x higher inference4 using 9200 series and up to 14x higher inference7 throughput using 8200 series, compared to Intel® Xeon® Scalable processors introduced in July 2017.

HPC is no longer just the domain of large scientific institutions. Enterprises are increasingly consuming a massive number of HPC compute cycles; some of the world's largest HPC clusters are in private oil and gas companies. Research in personalized medicine applies HPC for highly focused treatment plans. New HPC installations are engaging innovative, converged architectures for non-traditional usages that combine simulation, AI, visualization, and analytics in a single supercomputer.

HPC platforms—from the smallest clusters to largest supercomputers—demand a balance across compute, memory, storage, and network. The Intel® Xeon® Scalable processor family was designed to deliver and enable such balance with massive scalability—to tens of thousands of cores. From its improved core count and mesh architecture to newly integrated technologies and support for Intel® Optane™ DC persistent memory and storage devices, the Intel® Xeon® Scalable processor family enables the ultimate goals of HPC—to maximize performance across compute, memory, storage, and network without inducing bottlenecks at any intersection of resources.

The integration of Intel® Omni-Path Architecture (Intel® OPA), an end-to-end high-performance fabric, into the Intel® Xeon® Scalable processor family delivers both increased performance and scaling to distributed, parallel computing clusters. Near linear scaling up to 32 nodes enables building large HPC solutions that are not inhibited by the interconnect. The Intel® Xeon® Scalable processor family and Intel® Omni-Path Architecture (Intel® OPA) can enable new discoveries and faster solutions for highly parallel workloads in many data centers.

New 2nd Gen Intel® Xeon® Scalable Processors for HPC15

  • Intel® Xeon® Platinum 9200 processors
  • Intel® Optane™ DC persistent memory
  • Intel® Ultra Path Interconnect (Intel® UPI)
  • Intel® Deep Learning Boost (Intel® DL Boost)
  • Intel® Advanced Vector Extensions 512 (Intel® AVX-512)
  • Intel® Omni-Path Architecture (Intel® OPA) Host Fabric Interface
  • Intel® Optane™ DC SSDs

Additional Technologies for HPC, HPDA, and AI
A range of high-productivity software tools, optimized libraries, foundational building blocks, and flexible frameworks for general and highly parallel computing help simplify workflows and assist developers to create codes that maximize the capabilities of IA for HPC and AI.

Optimizations for popular deep learning frameworks for IA, including Caffe and TensorFlow* offer increased value and performance for data scientists.

Intel® Parallel Studio XE 2017 includes performance libraries, such as Intel® Math Kernel Library (Intel® MKL) for Deep Neural Networks (Intel® MKL-DNN) to accelerate deep learning frameworks on IA, and Intel® Data Analytics Acceleration Library (Intel® DAAL) to speed big data analytics.

Resources Optimized for HPC
To continue to advance discovery through HPCinto the Exascale era, the Intel® Modern Code Developer Community offers developers and data scientists easily accessible online and face-to-face code modernization technical sessions on techniques, such as vectorization, memory and data layout, multithreading, and multinode programming.

Overview of 2nd Gen Intel® Xeon® Scalable Processors

Intel® Xeon® Scalable processor family

Intel® Xeon® Platinum 9200 Processors

Designed for high performance computing, advanced artificial intelligence and analytics, the Intel® Xeon® Platinum 9200 processors deliver breakthrough levels of performance with the highest Intel® architecture FLOPS per rack, along with the highest DDR native memory bandwidth support of any Intel® Xeon® processor platform.

  • Up to 56 Intel® Xeon® Scalable processing cores per processor
    Two processors per 2U platform
    (Intel® Server System S9200WK Data Center Block)
  • 12 memory channels per processors, 24 memory channels per node
  • Features new Intel® Deep Learning Boost (Intel® DL Boost) instruction for enhanced AI inference acceleration and performance
  • Enhanced multichip package optimized for density and performance

Intel® Xeon® Platinum 8200 Processors

Second-Generation Intel® Xeon® Platinum processors are the foundation for secure, agile, hybrid cloud data centers. With enhanced hardware-based security and exceptional two, four, and eight+ socket processing performance, these processors are built for mission Critical, real-time analytics, machine learning, artificial intelligence and multicloud workloads. With trusted, hardware-enhanced data service delivery, this processor family delivers monumental leaps in I/O, memory, storage, and network technologies to harness actionable insights from our increasingly data-fueled world.

Intel® Xeon® Gold 6200 Processors and Intel® Xeon® Gold 5200 Processors

With support for the higher memory speeds, enhanced memory capacity, and four-socket scalability, the Intel® Xeon® Gold 6200 processors deliver significant improvement in performance, advanced reliability, and hardware-enhanced security. It is optimized for demanding mainstream data center, multicloud compute, and network and storage workloads. The Intel® Xeon® Gold 5200 processors deliver improved performance with affordable advanced reliability and hardware-enhanced security. With up-to four-socket scalability, it is suitable for an expanded range of workloads.

Intel® Xeon® Silver 4200 Processors

Intel® Xeon® Silver processors deliver essential performance, improved memory speed, and power efficiency. Hardware-enhanced performance required for entry data center computes, network, and storage.

Entry-level Performance and HW-enhanced Security

The Intel® Xeon® Bronze processors delivers entry performance for small business and basic storage servers. Hardware-enhanced reliability, availability, and serviceability features designed to meet the needs of these entry solutions.

 

Intel® Xeon® Bronze Processor (3200 Series)

Intel® Xeon® Silver Processor (4200 Series)

Intel® Xeon® Gold Processor (5200 Series)

Intel® Xeon®

Gold Processor

(6200 Series)

Intel® Xeon® Platinum Processor

(8200 Series)

Intel® Xeon® Platinum Processor
(9200 Series)

Pervasive Performance and Security

Highest Core Count Supported

6 cores

16 cores

18 cores

24 cores

28 cores

56 cores

Highest Supported Frequency

1.9 GHz

3.5 GHz

3.9 GHz

4.4 GHz

4.0 GHz

3.8 GHz

Number of CPU Sockets Supported

Up to 2

Up to 2

Up to 4

Up to 4

Up to 8

Up to 2

Intel® Ultra Path Interconnect (Intel® UPI)

2

2

2

3

3

4

Intel® UPI Speed

9.6 GT/s

9.6 GT/s

10.4 GT/s

10.4 GT/s

10.4 GT/s

10.4 GT/s

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

1 FMA

1 FMA

1 FMA

2 FMA

2 FMA

2 FMA

Memory Speed Support (DDR4)

2133 MT/s

2400 MT/s

2666 MT/s

2933 MT/s

2933 MT/s

2933 MT/s

Highest Memory Capacity Supported Per Socket

1 TB

1 TB

1 TB, 2 TB, 4.5 TB

1 TB, 2 TB, 4.5 TB

1 TB, 2 TB, 4.5 TB

1.5 TB

16Gb DDR4 DIMM Support

*

*

*

*

*

*

Intel® Deep Learning Boost (Intel® DL Boost) with Vector Neural Network Instruction (VNNI)

*

*

*

*

*

*

Intel® Optane™ DC Persistent Memory Module Support

 

*

*

*

*

 

Intel® Omni-Path Architecture (Discrete PCIe* card)

*

*

*

*

*

*

Intel® QuickAssist Technology (Integrated in chipset)

*

*

*

*

*

 

Intel® QuickAssist Technology (Discrete PCIe card)

*

*

*

*

*

*

Intel® Optane™ DC SSDs

*

*

*

*

*

*

Intel® DC SSD Data Center Family (3D NAND)

*

*

*

*

*

*

PCIe 3.0

*

*

*

*

*

*

Intel® QuickData Technology (CBDMA)

*

*

*

*

*

*

Non-Transparent Bridge (NTB)

*

*

*

*

*

*

Intel® Turbo Boost Technology 2.0

 

*

*

*

*

*

Intel® Hyper-Threading Technology (Intel® HT Technology)

 

*

*

*

*

*

Node Controller Support

 

 

 

*

*

*

◊ Supported on select processors only
High Reliability

Reliability, Availability, and Serviceability (RAS) Capability

Standard

Standard

Standard

Advanced

Advanced

Advanced

Intel® Run Sure Technology

 

 

 

*

*

*

Agility & Efficiency

Intel® Speed Select Technology (Intel® SST)

 

*

*

*

*

 

Intel® Infrastructure Management Technologies

*

*

*

*

*

*

Intel® Resource Director Technology (Intel® RDT)

*

*

*

*

*

*

Intel® Volume Management Device (Intel® VMD)

*

*

*

*

*

*

Intel® Virtualization Technology (Intel® VT)

*

*

*

*

*

*

Intel® Speed Shift Technology

*

*

*

*

*

*

Intel® Node Manager 4.0

*

*

*

*

*

*

Mode-based Execute Control

*

*

*

*

*

*

Timestamp Counter Scaling (TSC) for Virtualization

*

*

*

*

*

*

◊ Supported on select processors only
Security

Intel® Security Libraries for Data Center (Intel® ISecL-DC)

*

*

*

*

*

*

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

*

*

*

*

*

*

Intel® Key Protection Technology (KPT) w/Integrated Intel® QAT

*

*

*

*

*

*

Intel® Platform Trust Technology (PTT)

*

*

*

*

*

*

Intel® Trusted Execution Technology (Intel® TXT) w/ One-Touch Activation (OTA)

*

*

*

*

*

*

2nd Gen Intel® Xeon® Scalable Processors

SKU Numbering
Processor numbers for the Intel® Xeon® Scalable processor family use an alphanumeric scheme based on performance, features, processor generation, and any options, following the brand and its class.

Do More with Your Cloud Investment

Deliver the powerful performance per dollar you need on Intel® technology. Critical data-heavy workloads such as database, high performance computing (HPC), and web perform better at a lower total cost of ownership on Intel® architecture-based clouds.16 17 18 19 20

2.84x Higher Performance

Up to 2.84x higher performance/$ on database workloads, including HammerDB PostgreSQL*, and MongoDB*.16

Learn more

4.15x Higher Performance

Up to 4.15x higher performance/$ on High Performance LINPACK* and LAMMPS*.17

Learn more

1.74x Better Performance

Better performance/$ on Server-Side Java and 1.74x better performance /$ on WordPress PHP/HHVM.18

Learn more

2.25x Higher Performance

Up to 2.25x higher performance/$ for memory bandwidth applications.19

Learn more

2nd Gen Intel® Xeon® Scalable Processor SKUs

For the most up-to-date information, please visit intel.com/xeon or ark.intel.com

Processor Identifier

Core Count

Cache (MB)

TDP (WATTS)

Processor Base Frequency (GHz)

Max Turbo Frequency Rate (GHz)

Max Memory Speed (MT/s)

Memory Capacities
M/L SKU Suffix

PLATINUM 9282

56

77

400

2.6

3.8

2933

3TB

PLATINUM 9242

48

71.5

350

2.3

3.8

2933

3TB

PLATINUM 9222

32

71.5

250

2.3

3.7

2933

3TB

PLATINUM 8280

28

38.5

205

2.7

4

2933

1TB / 2TB / 4.5TB

PLATINUM 8276

28

38.5

165

2.2

4

2933

1TB / 2TB / 4.5TB

PLATINUM 8270

26

35.75

205

2.7

4

2933

1TB

PLATINUM 8268

24

35.75

205

2.9

3.9

2933

1TB

PLATINUM 8260

24

35.75

165

2.4

3.9

2933

1TB / 2TB / 4.5TB

PLATINUM 8256

4

16.5

105

3.8

3.9

2933

1TB

PLATINUM 8253

16

22

125

2.2

3

2933

1TB

GOLD 6254

18

24.75

200

3.1

4

2933

1TB

GOLD 6252

24

35.75

150

2.1

3.7

2933

1TB

GOLD 6248

20

27.5

150

2.5

3.9

2933

1TB

GOLD 6246

12

24.75

165

3.3

4.2

2933

1TB

GOLD 6244

8

24.75

150

3.6

4.4

2933

1TB

GOLD 6242

16

22

150

2.8

3.9

2933

1TB

GOLD 6240

18

24.75

150

2.6

3.9

2933

1TB / 2TB / 4.5TB

GOLD 6238

22

30.25

140

2.1

3.7

2933

1TB / 2TB / 4.5TB

GOLD 6234

8

24.75

130

3.3

4

2933

1TB

GOLD 6230

20

27.5

125

2.1

3.9

2933

1TB

GOLD 6226

12

19.25

125

2.7

3.7

2933

1TB

GOLD 5222

4

16.5

105

3.8

3.9

2933

1TB

GOLD 5220

18

24.75

125

2.2

3.9

2667

1TB

GOLD 5218

16

22

125

2.3

3.9

2667

1TB

GOLD 5217

8

11

115

3

3.7

2667

1TB

GOLD 5215

10

13.75

85

2.5

3.4

2667

1TB / 2TB / 4.5TB

SILVER 4216

16

22

100

2.1

3.2

2400

1TB

SILVER 4215

8

11

85

2.5

3.5

2400

1TB

SILVER 4214

12

16.5

85

2.2

3.2

2400

1TB

SILVER 4210

10

13.75

85

2.2

3.2

2400

1TB

SILVER 4208

8

11

85

2.1

3.2

2400

1TB

BRONZE 3204

6

8.25

85

1.9

1.9

2133

1TB

Networking/NFV Specialized Featuring Intel® Speed Select Technology (Intel® SST) SKUs

6252N

24

35.75

150

2.3

3.6

2933

1TB

6230N

20

27.5

125

2.3

3.9

2933

1TB

5218N

16

22

105

2.3

3.7

2667

1TB

Search Application Value Specialized SKU

5220S

18

24.75

125

2.7

3.9

2667

1TB

Long-Life Cycle and NEBS-Thermal Friendly SKUs

6238T

22

30.25

125

1.9

3.7

2933

1TB

6230T

20

27.5

125

2.1

3.9

2933

1TB

5220T

18

24.75

105

1.9

3.9

2667

1TB

5218T

16

22

105

2.1

3.8

2667

1TB

4209T

8

11

70

2.2

3.2

2400

1TB

VM Density Value Specialized SKUs

6262V

24

33

135

1.9

3.6

2400

1TB

6222V

20

27.5

115

1.8

3.6

2400

1TB

SKUS Featuring Intel® Speed Select Technology (Intel® SST)

8260Y

24

35.75

165

2.4

3.9

2933

1TB

6240Y

18

24.75

150

2.6

3.9

2933

1TB

4214Y

12

16.5

85

2.2

3.2

2400

1TB

◊ Intel® Xeon® Platinum 9222 processor: Intel® Turbo Boost Technology frequency and base frequency are preliminary; final values to be published at a future date.

PRODUCT NAME

SKU

10Gb/1Gb ETHERNET PORTS

COMPRESSION

ENCRYPTION

RSA

 

Intel® QuickAssist Technology (Intel® QAT)

Intel® C621 chipset

LBG-1G

0/4

N/A

N/A

N/A

Intel® C622 chipset

LBG-2

2/4

N/A

N/A

N/A

Intel® C624 chipset

LBG-4

4/4

N/A

N/A

N/A

Intel® C625 chipset

LBG-E

4/4

20 Gb/s

20 Gb/s

20K Ops/s

Intel® C626 chipset

LBG-M

4/4

40 Gb/s

40 Gb/s

40K Op/s

Intel® C627 chipset

LBG-T

4/4

100 Gb/s

100 Gb/s

100K Ops/s

Intel® C628 chipset

LBG-L

4/4

100 Gb/s

100 Gb/s

100K Ops/s

Intel® Server System S9200WK Data Center Block (DCB) Technical Specifications
supporting the Intel® Xeon® Platinum 9200 Processor

Form Factor

2U rack enclosure; Up to 4 independent warm-swap compute modules

CPU

Intel® Xeon® Platinum 9200 processors up to 56 cores

Memory

DDR4-2933 MT/s DIMMS, 24 DIMMs per platform @ 1DPC

Supports 8GB to 128GB DIMM options, number, and capacity configurable

Storage

Up to 8x M.2 SSDs per DCB (2x per compute module with 1U compute module; Up to 4x M.2 SSDs & 4x hot-swap U.2 NVMe SSDs with 2U Compute Modules)

M.2 and U.2 number and capacity configurable

Ethernet

Integrated 1Gbase-T RJ45 (two ports per compute module), Optional shared 1Gbase-T RJ45 management port chassis card

Cooling

Available with high flow rate air-cooling or integrated liquid-cooling options

I/O

2 x16 Gen3 PCIe slots per 1U compute module; 4 x16 Gen3 PCIe slots per 2U compute module for high-speed networking support

Manageability

Dedicated, consolidated Management Module

Security & Serviceability

TPM 2.0 (optional); Hot swap/redundant fans, and PSUs; light path diagnostic LEDs

Not a comprehensive list of all features and capabilities. Learn more at intel.com/serverproducts

2nd Gen Intel® Xeon® Scalable Processors


More Information

Intel® technologies’ features and benefits depend on system configuration and may require enabled hardware, software, or service activation. Performance varies depending on system configuration.

◊ No product or component can be absolutely secure.

Tests document performance of components on a particular test, in specific systems. Differences in hardware, software, or configuration will affect actual performance. For more complete information about performance and benchmark results, visit https://www.intel.com/benchmarks.

Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, 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 https://www.intel.com/benchmarks.

Intel® Advanced Vector Extensions (Intel® AVX) provides higher throughput to certain processor operations. Due to varying processor power characteristics, utilizing Intel® Advanced Vector Extensions (Intel® AVX) instructions may cause a) some parts to operate at less than the rated frequency and b) some parts with Intel® Turbo Boost Technology 2.0 to not achieve any or maximum turbo frequencies. Performance varies depending on hardware, software, and system configuration and you can learn more at https://www.intel.com/go/turbo.

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Cost reduction scenarios described are intended as examples of how a given Intel-based product, in the specified circumstances and configurations, may affect future costs and provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction.

Intel does not control or audit third-party benchmark data or the web sites referenced in this document. You should visit the referenced web site and confirm whether referenced data are accurate.

© Intel Corporation. Intel, the Intel logo, Intel Optane DC, and Intel Xeon are trademarks of Intel Corporation in the U.S. and/or other countries.
* Other names and brands may be claimed as property of others.

FTC Optimization Notice
If you make any claim about the performance benefits that can be achieved by using Intel® Software Development Tools (compilers or libraries), you must use the entire text on the same viewing plane (slide) as the claim.

Optimization Notice: Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice Revision #20110804
Performance results are based on testing as of dates shown in configuration and may not reflect all publicly available security updates. See configuration disclosure for details. No product or component can be absolutely secure. Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, 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.

Pricing guidance as of March 1, 2019. Intel does not guarantee any costs or cost reduction. You should consult other information and performance tests to assist you in your purchase decision.

Product and Performance Information

3

2x Average Performance Improvement compared with Intel® Xeon® Platinum 8180 processor. Geomean of est SPECrate2017_int_base, est SPECrate2017_fp_base, Stream Triad, Intel® Distribution of Linpack, server side Java. Platinum 92xx vs Platinum 8180: 1-node, 2x Intel® Xeon® Platinum 9282 cpu on Walker Pass with 768 GB (24x 32GB 2933) total memory, ucode 0x400000A on RHEL7.6, 3.10.0-957.el7.x86_65, IC19u1, AVX512, HT on all (off Stream, Linpack), Turbo on all (off Stream, Linpack), result: est int throughput=635, est fp throughput=526, Stream Triad=407, Linpack=6411, server side java=332913, test by Intel on 2/16/2019. vs. 1-node, 2x Intel® Xeon® Platinum 8180 cpu on Wolf Pass with 384 GB (12 X 32GB 2666) total memory, ucode 0x200004D on RHEL7.6, 3.10.0-957.el7.x86_65, IC19u1, AVX512, HT on all (off Stream, Linpack), Turbo on all (off Stream, Linpack), result: est int throughput=307, est fp throughput=251, Stream Triad=204, Linpack=3238, server side java=165724, test by Intel on 1/29/2019.

4

Up to 30X AI performance with Intel® Deep Learning Boost (Intel DL Boost) compared to Intel® Xeon® Platinum 8180 processor (July 2017). Tested by Intel as of 2/26/2019. Platform: Dragon rock 2 socket Intel® Xeon® Platinum 9282(56 cores per socket), HT ON, turbo ON, Total Memory 768 GB (24 slots/ 32 GB/ 2933 MHz), BIOS: SE5C620.86B.0D.01.0241.112020180249, Centos* 7 Kernel 3.10.0-957.5.1.el7. x86_64, Deep Learning Framework: Intel® Optimization for Caffe* version: https://github.com/intel/caffe d554cbf1, ICC 2019.2.187, MKL DNN version: v0.17 (commit hash: 830a10059a018cd-2634d94195140cf2d8790a75a), model: https://github.com/intel/caffe/blob/master/models/intel_optimized_models/int8/resnet50_int8_full_conv.prototxt, BS=64, No datalayer DummyData: 3x224x224, 56 instance/2 socket, Datatype: INT8 vs Tested by Intel as of July 11th 2017: 2S Intel® Xeon® Platinum 8180 cpu @ 2.50GHz (28 cores), HT disabled, turbo disabled, scaling governor set to “performance” via intel_pstate driver, 384GB DDR4-2666 ECC RAM. CentOS* Linux release 7.3.1611 (Core), Linux kernel* 3.10.0-514.10.2.el7.x86_64. SSD: Intel® SSD DC S3700 Series (800GB, 2.5in SATA 6Gb/s, 25nm, MLC).Performance measured with: Environment variables: KMP_AFFINITY=’granularity=fine, compact‘, OMP_NUM_THREADS=56, CPU Freq set with cpupower frequency-set -d 2.5G -u 3.8G -g performance. Caffe: (https://github.com/intel/caffe/), revision f96b759f71b2281835f690af267158b82b150b5c. Inference measured with “caffe time --forward_only” command, training measured with “caffe time” command. For “ConvNet” topologies, dummy dataset was used. For other topologies, data was stored on local storage and cached in memory before training. Topology specs from https://github.com/intel/caffe/tree/master/models/intel_optimized_models (ResNet-50),. Intel C++ compiler ver. 17.0.2 20170213, Intel® Math Kernel Library (Intel® MKL) small libraries version 2018.0.20170425. Caffe run with “numactl -l“.

5

Up to 3.50X 5-Year Refresh Performance Improvement VM density compared to Intel® Xeon® E5-2600 v6 processor: 1-node, 2x E5-2697 v2 on Canon Pass with 256 GB (16 slots / 16GB / 1600) total memory, ucode 0x42c on RHEL7.6, 3.10.0-957.el7.x86_65, 1x Intel 400GB SSD OS Drive, 2x P4500 4TB PCIe*, 2*82599 dual port Ethernet, Virtualization Benchmark, VM kernel 4.19, HT on, Turbo on, score: VM density=74, test by Intel on 1/15/2019. vs. 1-node, 2x 8280 on Wolf Pass with 768 GB (24 slots / 32GB / 2666) total memory, ucode 0x2000056 on RHEL7.6, 3.10.0-957. el7.x86_65, 1x Intel 400GB SSD OS Drive, 2x P4500 4TB PCIe*, 2*82599 dual port Ethernet, Virtualization Benchmark, VM kernel 4.19, HT on, Turbo on, score: VM density=21, test by Intel on 1/15/2019.

6

1.33X Average Performance Improvement compared to Intel® Xeon® Gold 5100 processor: Geomean of est SPECrate2017_int_base, est SPECrate2017_fp_base, Stream Triad, Intel® Distribution for LINPACK* Benchmark, server side Java. Gold 5218 vs Gold 5118: 1-node, 2x Intel® Xeon® Gold 5218 cpu on Wolf Pass with 384 GB (12 X 32GB 2933 (2666)) total memory, ucode 0x4000013 on RHEL7.6, 3.10.0-957.el7.x86_65, IC18u2, AVX2, HT on all (off Stream, Linpack), Turbo on, result: est int throughput=162, est fp throughput=172, Stream Triad=185, Linpack=1088, server side java=98333, test by Intel on 12/7/2018. 1-node, 2x Intel® Xeon® Gold 5118 cpu on Wolf Pass with 384 GB (12 X 32GB 2666 (2400)) total memory, ucode 0x200004D on RHEL7.6, 3.10.0-957.el7.x86_65, IC18u2, AVX2, HT on all (off Stream, Linpack), Turbo on, result: est int throughput=119, est fp throughput=134, Stream Triad=148.6, Linpack=822, server side java=67434, test by Intel on 11/12/2018.

7

Up to 14X AI Performance Improvement with Intel® Deep Learning Boost (Intel DL Boost) compared to Intel® Xeon® Platinum 8180 processor (July 2017). Tested by Intel as of 2/20/2019. 2 socket Intel® Xeon® Platinum 8280 processor, 28 cores HT On Turbo ON Total Memory 384 GB (12 slots/ 32GB/ 2933 MHz), BIOS: SE5C620.86B.0D.01.0271.120720180605 (ucode: 0x200004d), Ubuntu 18.04.1 LTS, kernel 4.15.0-45-generic, SSD 1x sda INTEL SSDSC2BA80 SSD 745.2GB, nvme1n1 INTEL SSDPE2KX040T7 SSD 3.7TB, Deep Learning Framework: Intel® Optimization for Caffe* version: 1.1.3 (commit hash: 7010334f159da247db3fe3a9d96a3116ca06b09a), ICC version 18.0.1, MKL DNN version: v0.17 (commit hash: 830a10059a018cd2634d94195140cf2d8790a75a, model: https://github.com/intel/caffe/blob/master/models/intel_optimized_models/int8/resnet50_int8_full_conv.prototxt, BS=64, DummyData, 4 instance/2 socket, Datatype: INT8 vs Tested by Intel as of July 11th 2017: 2S Intel® Xeon® Platinum 8180 cpu @ 2.50GHz (28 cores), HT disabled, turbo disabled, scaling governor set to “performance” via intel_pstate driver, 384GB DDR4-2666 ECC RAM. CentOS* Linux release 7.3.1611 (Core), Linux kernel* 3.10.0-514.10.2.el7.x86_64. SSD: Intel® SSD DC S3700 Series (800GB, 2.5in SATA 6Gb/s, 25nm, MLC).Performance measured with: Environment variables: KMP_AFFINITY=’granularity=fine, compact‘, OMP_NUM_THREADS=56, CPU Freq set with cpupower frequency-set -d 2.5G -u 3.8G -g performance. Caffe: (https://github.com/intel/caffe/), revision f96b759f71b2281835f690af267158b82b150b5c. Inference measured with “caffe time --forward_only” command, training measured with “caffe time” command. For “ConvNet” topologies, dummy dataset was used. For other topologies, data was stored on local storage and cached in memory before training. Topology specs from https://github.com/intel/caffe/tree/master/models/intel_optimized_models (ResNet-50), Intel® C++ Compiler ver. 17.0.2 20170213, Intel® Math Kernel Library (Intel® MKL) small libraries version 2018.0.20170425. Caffe run with “numactl -l“.

8
9

36% more VMs per node & 30% lower estimated cost per VM configurations.

 

Config1-DDR4 (Similar Cost)

Config2-Intel® Optane™ DC Persistent Memory (Similar Cost)

Test By

Intel

Intel

Test Date

01/31/2019

01/31/2019

Platform

Confidential – Refer to M. Strassmaier if a need to know exists

Confidential – Refer to M. Strassmaier if a need to know exists

# Nodes

1

1

# Sockets

2

2

CPU

Cascade Lake B0 8272L

Cascade Lake B0 8272L

Cores/Socket, Threads/Socket

26/52

26/52

HT

ON

ON

Turbo

ON

ON

BKC Version – E.g. ww47

WW42

WW42

Intel® Optane™ DC Persistent Memory FW Version

5253

5253

System DDR Mem Config: Slots/Cap/Run-speed

24 slots/32 GB/2666

12 slots/16 GB /2666

System DCPMM Config: Slots/Cap/Run-speed

 

8 slots/128 GB/ 2666

Total Memory/Node (DDR, DCPMM)

768 GB, 0

192 GB, 1 TB

Storage – Boot

1x Samsung PM963 M.2 960 GB

1x Samsung PM963 M.2 960 GB

Storage – Application Drives

7 x Samsung PM963 M.2 960 GB, 4x Intel® SSDs S4600 (1.92 TB)

7x Samsung PM963 M.2 960 GB, 4x Intel® SSDs S4600 (1.92 TB)

NIC

1x Intel X520 SR2 (10Gb)

1x Intel X520 SR2 (10 Gb)

PCH

LBG QS/PRQ – T – B2

LBG QS/PRQ – T – B2

Other HW (Accelerator)

 

 

OS

Windows Server 2019 RS5-17763

Windows Server 2019 RS5-17763

Kernel

 

 

Workload & Version

OLTP Cloud Benchmark

OLTP Cloud Benchmark

Compiler    
Libraries    
Other SW (Frameworks, Topologies…)    

 

 

1- Baseline

2- Config Description

# of Systems

1

1

Memory Sub System Per Socket

DRAM- 384GB (12x32GB)

2GB (4X128GB AEP+6x16GB DRAM, 2-2-1, Memory Mode

CPU SKU|# Per System

8276 (CLX, Plat, 28 core) 2

8276 (CLX, Plat, 28 core) 2

Storage Description|Total Storage Cost

# of HDD/SDDs $7200

# of HDD/SDDs $7200

SW License Description| Cost Per System

SW Cost (per/core or per system) $0

SW Cost (per/core or per system) $1

Relevant Value Metric

22.00

30.00

Type of System

DRAM- Purley

AEP- Memory Mode

CPU & Platform Match

TRUE

TRUE

CPU Cost

2x 8276 (CLX, Plat, 28 core) $17,438

2x 8276 (CLX, Plat, 28 core) $17,439

Memory Sub System

Total Cap: 768GB (384 GB/socket) $8,993

Total Cap: 1024GB (512GB/socket) $7,306

DRAM

24x32GB $8,993

12x16GB $2,690

AEP

N/A $0

8x128GB $4,616

Storage

# of HDD/SDDs $7200

# of HDD/SDDs $7200

RBOM

Chassis; PSUs; Bootdrive etc. $1300

Chassis; PSUs; Bootdrive etc. $1300

SW Costs

SW Cost (per/core or per system) $0

SW Cost (per/core or per system) $0

Total System Cost

$34,931

$33,244

System Cost

1

0.951689

Indexed Value Metrics

1

1.36

Indexed Value/$

1

1.43

10


36% more VMs per node & 30% lower estimated cost per VM configurations.


 

Config1-DDR4 (Similar Cost)

Config2-Intel® Optane™ DC Persistent Memory (Similar Cost)

Test By

Intel

Intel

Test Date

01/31/2019

01/31/2019

Platform

Confidential – Refer to M. Strassmaier if a need to know exists

Confidential – Refer to M. Strassmaier if a need to know exists

# Nodes

1

1

# Sockets

2

2

CPU

Cascade Lake B0 8272L

Cascade Lake B0 8272L

Cores/Socket, Threads/Socket

26/52

26/52

HT

ON

ON

Turbo

ON

ON

BKC Version – E.g. ww47

WW42

WW42

Intel® Optane™ DC Persistent Memory FW Version

5253

5253

System DDR Mem Config: Slots/Cap/Run-speed

24 slots/32 GB/2666

12 slots/16 GB /2666

System DCPMM Config: Slots/Cap/Run-speed

 

8 slots/128 GB/ 2666

Total Memory/Node (DDR, DCPMM)

768 GB, 0

192 GB, 1 TB

Storage – Boot

1x Samsung PM963 M.2 960 GB

1x Samsung PM963 M.2 960 GB

Storage – Application Drives

7 x Samsung PM963 M.2 960 GB, 4x Intel® SSDs S4600 (1.92 TB)

7x Samsung PM963 M.2 960 GB, 4x Intel® SSDs S4600 (1.92 TB)

NIC

1x Intel X520 SR2 (10Gb)

1x Intel X520 SR2 (10 Gb)

PCH

LBG QS/PRQ – T – B2

LBG QS/PRQ – T – B2

Other HW (Accelerator)

 

 

OS

Windows Server 2019 RS5-17763

Windows Server 2019 RS5-17763

Kernel

 

 

Workload & Version

OLTP Cloud Benchmark

OLTP Cloud Benchmark

Compiler    
Libraries    
Other SW (Frameworks, Topologies…)    

 

 

1- Baseline

2- Config Description

# of Systems

1

1

Memory Sub System Per Socket

DRAM- 384GB (12x32GB)

2GB (4X128GB AEP+6x16GB DRAM, 2-2-1, Memory Mode

CPU SKU|# Per System

8276 (CLX, Plat, 28 core) 2

8276 (CLX, Plat, 28 core) 2

Storage Description|Total Storage Cost

# of HDD/SDDs $7200

# of HDD/SDDs $7200

SW License Description| Cost Per System

SW Cost (per/core or per system) $0

SW Cost (per/core or per system) $1

Relevant Value Metric

22.00

30.00

Type of System

DRAM- Purley

AEP- Memory Mode

CPU & Platform Match

TRUE

TRUE

CPU Cost

2x 8276 (CLX, Plat, 28 core) $17,438

2x 8276 (CLX, Plat, 28 core) $17,439

Memory Sub System

Total Cap: 768GB (384 GB/socket) $8,993

Total Cap: 1024GB (512GB/socket) $7,306

DRAM

24x32GB $8,993

12x16GB $2,690

AEP

N/A $0

8x128GB $4,616

Storage

# of HDD/SDDs $7200

# of HDD/SDDs $7200

RBOM

Chassis; PSUs; Bootdrive etc. $1300

Chassis; PSUs; Bootdrive etc. $1300

SW Costs

SW Cost (per/core or per system) $0

SW Cost (per/core or per system) $0

Total System Cost

$34,931

$33,244

System Cost

1

0.951689

Indexed Value Metrics

1

1.36

Indexed Value/$

1

1.43

 

11

1. OLTP Warehouse claim of up to 3.7X: 1-node, 2x Intel® Xeon® CPU E5-2697 v2 on Canoe Pass with 256 GB (16 slots / 16 GB / 1866) total memory, ucode 0x42d on RHEL7.6, 3.10.0-957.el7.

x86_65, 2 x Intel DC P3700 PCI-E SSD for DATA, 2 x Intel DC P3700 PCI-E SSD for REDO, HammerDB 3.1, HT on, Turbo on, result: Transactions per minute=2242024, test by Intel on 2/1/2019. vs. 1-node, 2x Intel® Xeon® Platinum 8280 CPU on Wolf Pass with 384 GB (12 slots / 32 GB / 2933) total memory, ucode 0x4000013 on RHEL7.6, 3.10.0-957.el7.x86_65, 2x Intel® SSD DC P4610 for DATA, 2x Intel® SSD DC P4610 for REDO, HammerDB 3.1, HT on, Turbo on, result: Transactions per minute=8459206, test by Intel on 2/1/2019.

12

BigBench* claim of 2.3X: 1+4-node, 2x Intel® Xeon® processor E5-2697 v2 on S2600JF with 128 GB (8 slots / 16GB / 1866) total memory, ucode 0x42d on CentOS-7.6.1810, 4.20.0-1.el7.

x86_64, 1x 180GB SATA3 SSD, 3 x Seagate ST4000NM0033 (4TB), 1x Intel I350, TPCx-BB v1.2 (not for publication) / 3TB/ 2 Streams, Mllib, Oracle Hot-Spot 1.8.0_191, python-2.7.5, Apache Hadoop-2.9.2, Apache Spark-2.0.2, Hive 2.2 + CustomCommit, , HT on, Turbo on, result: Queries per min=265, test by Intel on 1/24/2019. 1+4-node, 2x Intel® Xeon® Gold 6148 processor on S2600WF with 768 GB (384 GB used) (12 slots* / 64 GB / 2400 (384GB used)) total memory, ucode 0x400000A on CentOS-7.6.1810, 4.20.0-1.el7.x86_64, Intel® SSD DC S3710, 6 x Seagate ST2000NX0253 (2TB), 1x Intel X722, TPCx-BB v1.2 (not for publication) / 3TB/ 2 Streams, Mllib, Oracle Hot-Spot 1.8.0_191, python-2.7.5, Apache Hadoop-2.9.2, Apache Spark-2.0.2, Hive 2.2 + CustomCommit,, HT on, Turbo on, result: Queries per min=622, test by Intel on 1/12/2019.

13

HiBench claim of 4.3X: 1+4-node, 2x Intel® Xeon® processor E5-2697 v2 on S2600JF with 128 GB (8 slots / 16GB / 1866 ) total memory, ucode 0x42d on CentOS-7.6.1810, 4.20.0-1.el7.x86_64, 1x 180GB SATA3 SSD, 3 x Seagate ST4000NM0033 (4TB), 1x Intel I350, HiBench v7.1 / bigdata, Mllib, OpenJDK-1.8.0_191, python-2.7.5, Apache Hadoop-2.9.1, Apache Spark-2.2.2, , HT on, Turbo on, result: SparkKmeans=119.5M, HadoopKmeans=49.6M, SparkSort=121.4M, HadoopSort=103M, SparkTerasort=107.4M, HadoopTerasort=109M, test by Intel on 1/23/2019. 1+4-node, 2x Intel® Xeon® Gold 6248 processor on S2600WF with 768 GB (384 GB used) (12 slots* / 64 GB / 2400 (384GB used)) total memory, ucode 0x400000A on CentOS-7.6.1810, 4.20.0-1.el7.x86_64, Intel SSD DC S3710, 6 x Seagate ST2000NX0253 (2TB), 1x Intel X722, HiBench v7.1 / bigdata, Mllib, OpenJDK-1.8.0_191, python-2.7.5, Apache Hadoop-2.9.1, Apache Spark-2.2.2, HT on, Turbo on, result: SparkKmeans=1235.8M, HadoopKmeans=92.8M, SparkSort=518.4M, HadoopSort=363.5M, SparkTerasort=589.3M, HadoopTerasort=457.3M, test by Intel on 1/23/2019.

Type

DataSetSize (B)

Overall* Duration (s)

Overall* Duration (s)

Throughput (B/s)

Throughput (B/s)

Throughput Speedup

 

 

Intel® Xeon® E5-2697 v2 processor

Intel® Xeon® Gold 6248 processor

Intel® Xeon® E5-2697 v2 processor

Intel® Xeon® Gold 6248 processor

 

SparkKmeans

240,981,849,494

2015

195

119,593,969

1,235,804,356

10.33

SparkSort

307,960,500,694

2535

594

121,483,432

518,452,021

4.27

SparkTerasort

600,000,000,000

5586

1018

107,411,385

589,390,962

5.49

 

 

 

 

 

Spark Geomean

6.23

HadoopKmeans

240,981,849,494

4854

2596

49,646,034

92,828,139

1.87

HadoopSort

307,960,500,694

2990

847

103,002,660

363,589,729

3.53

HadoopTerasort

600,000,000,000

5504

1312

109,011,627

457,317,073

4.20

 

 

 

 

 

Hadoop Geomean

3.03

 

 

 

 

 

Overall Geomean

4.34

14

Up to 1.25 to 1.58X NVF Workload Performance Improvement comparing Intel® Xeon® Gold 6230N processor to Intel® Xeon® Gold 6130 processor.

VPP IP Security: Tested by Intel on 1/17/2019 1-Node, 2x Intel® Xeon® Gold 6130 processor on Neon City platform with 12x 16GB DDR4 2666MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYDCRB1.86B.0155.R08.1806130538, ucode: 0x200004d (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.15.0-42-generic, Benchmark: VPP IPSec w/AESNI (AES-GCM-128) (Max Gbits/s (1420B)), Workload version: VPP v17.10, Compiler: gcc7.3.0, Results: 179. Tested by Intel on 1/17/2019 1-Node, 2x Intel® Xeon® Gold 6230N processor on Neon City platform with 12x 16GB DDR4 2999MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYXCRB1.PFT.0569.D08.1901141837, ucode: 0x4000019 (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: VPP IPSec w/AESNI (AES-GCM-128) (Max Gbits/s (1420B)), Workload version: VPP v17.10, Compiler: gcc7.3.0, Results: 225.

VPP FIB: Tested by Intel on 1/17/2019 1-Node, 2x Intel® Xeon® Gold 6130 processor on Neon City platform with 12x 16GB DDR4 2666MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYDCRB1.86B.0155.R08.1806130538, ucode: 0x200004d (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.15.0-42-generic, Benchmark: VPP FIB (Max Mpackets/s (64B)), Workload version: VPP v17.10 in ipv4fib configuration, Compiler: gcc7.3.0, Results: 160. Tested by Intel on 1/17/2019 1-Node, 2x Intel® Xeon® Gold 6230N processor on Neon City platform with 12x 16GB DDR4 2999MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYXCRB1.PFT.0569.D08.1901141837, ucode: 0x4000019 (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: VPP FIB (Max Mpackets/s (64B)), Workload version: VPP v17.10 in ipv4fib configura­tion, Compiler: gcc7.3.0, Results: 212.9.

Virtual Firewall: Tested by Intel on 10/26/2018 1-Node, 2x Intel® Xeon® Gold 6130 processor on Neon City platform with 12x 16GB DDR4 2666MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 4x Intel X710-DA4, Bios: PLYDCRB1.86B.0155.R08.1806130538, ucode: 0x200004d (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.15.0-42-generic, Bench­mark: Virtual Firewall (64B Mpps), Workload version: Opnfv 6.2.0, Compiler: gcc7.3.0, Results: 38.9. Tested by Intel on 2/04/2019 1-Node, 2x Intel® Xeon® Gold 6230N processor on Neon City platform with 12x 16GB DDR4 2999MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYXCRB1.PFT.0569.D08.1901141837, ucode: 0x4000019 (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: Virtual Firewall (64B Mpps), Workload version: Opnfv 6.2.0, Compiler: gcc7.3.0, Results: 52.3.

Virtual Broadband Network Gateway: Tested by Intel on 11/06/2018 1-Node, 2x Intel® Xeon® Gold 6130 processor on Neon City platform with 12x 16GB DDR4 2666MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYDCRB1.86B.0155.R08.1806130538, ucode: 0x200004d (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.15.0-42-generic, Benchmark: Virtual Broadband Network Gateway (88B Mpps), Workload version: DPDK v18.08 ip_pipeline application, Compiler: gcc7.3.0, Results: 56.5. Tested by Intel on 1/2/2019 1-Node, 2x Intel® Xeon® Gold 6230N processor on Neon City platform with 12x 16GB DDR4 2999MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYXCRB1.PFT.0569.D08.1901141837, ucode: 0x4000019 (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: Virtual Broadband Network Gateway (88B Mpps), Workload version: DPDK v18.08 ip_pipeline application, Compiler: gcc7.3.0, Results: 78.7.

VCMTS: Tested by Intel on 1/22/2019 1-Node, 2x Intel® Xeon® Gold 6130 processor on Supermicro*-X11DPH-Tq platform with 12x 16GB DDR4 2666MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 4x Intel XXV710-DA2, Bios: American Megatrends Inc.* version: ‘2.1’, ucode: 0x200004d (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: Virtual Converged Cable Access Platform (iMIX Gbps), Workload version: vcmts 18.10, Compiler: gcc7.3.0 , Other software: Kubernetes* 1.11, Docker* 18.06, DPDK 18.11, Results: 54.8. Tested by Intel on 1/22/2019 1-Node, 2x Intel® Xeon® Gold 6230N processor on Neon City platform with 12x 16GB DDR4 2999MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYXCRB1.PFT.0569.D08.1901141837, ucode: 0x4000019 (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: Virtual Converged Cable Access Platform (iMIX Gbps), Workload version: vcmts 18.10 , Compiler: gcc7.3.0, Other software: Kubernetes* 1.11, Docker* 18.06, DPDK 18.11, Results: 83.7.

OVS DPDK: Tested by Intel on 1/21/2019 1-Node, 2x Intel® Xeon® Gold 6130 processor on Neon City platform with 12x 16GB DDR4 2666MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 4x Intel XXV710-DA2, Bios: PLYXCRB1.86B.0568.D10.1901032132, ucode: 0x200004d (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.15.0-42-generic, Benchmark: Open Virtual Switch (on 4C/4P/8T 64B Mpacket/s), Workload version: OVS 2.10.1, DPDK-17.11.4, Compiler: gcc7.3.0, Other software: QEMU-2.12.1, VPP v18.10, Results: 9.6. Tested by Intel on 1/18/2019 1-Node, 2x Intel® Xeon® Gold 6230N processor on Neon City platform with 12x 16GB DDR4 2999MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYXCRB1.86B.0568.D10.1901032132, ucode: 0x4000019 (HT= ON, Turbo= OFF), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: Open Virtual Switch (on 6P/6C/12T 64B Mpacket/s), Workload version: OVS 2.10.1, DPDK-17.11.4, Compiler: gcc7.3.0, Other software: QEMU-2.12.1, VPP v18.10, Results: 15.2. Tested by Intel on 1/18/2019 1-Node, 2x Intel® Xeon® Gold 6230N processor with SST-BF enabled on Neon City platform with 12x 16GB DDR4 2999MHz (384GB total memory), Storage: 1x Intel® 240GB SSD, Network: 6x Intel XXV710-DA2, Bios: PLYXCRB1.86B.0568.D10.1901032132, ucode: 0x4000019 (HT= ON, Turbo= ON (SST-BF)), OS: Ubuntu* 18.04 with kernel: 4.20.0-042000rc6-generic, Benchmark: Open Virtual Switch (on 6P/6C/12T 64B Mpacket/s), Workload version: OVS 2.10.1, DPDK-17.11.4, Compiler: gcc7.3.0, Other software: QEMU-2.12.1, VPP v18.10, Results: 16.9.

15

Up to 1.7x better floating point perf/core using one copy SPECrate2017_fp_base* 2 socket Intel 8280 vs 2 socket AMD EPYC 7601. Xeon-SP 8280, Intel Xeon-based Reference Platform with 2 Intel® Xeon® 8280 processors (2.7GHz, 28 core), BIOS ver SE5C620.86B.0D.01.0348.011820191451, 01/18/2019, microcode: 0x5000017, HT OFF, Turbo ON, 12x32GB DDR4-2933, 1 SSD, Red Hat EL 7.6 (3.10.0-957.1.3.el7.x86_64), 1-copy SPECrate2017_fp_rate base benchmark compiled with Intel Compiler 19.0.1.144, -xCORE-AVX512 -ipo -O, executed on 1 core using taskset and numactl on core 0. Estimated score = 9.6, as of 2/6/2019 tested by Intel with security mitigations for variants 1,2,3,3a, and L1TF. AMD EPYC 7601, Supermicro AS-2023US-TR4 with 2S AMD EPYC 7601 with 2 AMD EPYC 7601 (2.2GHz, 32 core) processors, BIOS ver 1.1c, 10/4/2018, SMT OFF, Turbo ON, 16x32GB DDR4-2666, 1 SSD, Red Hat EL 7.6 (3.10.0-957.5.1.el7.x86_64), 1-copy SPECrate2017_fp_rate base benchmark compiled with AOCC ver 1.0 -Ofast, -march=znver1, executed on 1 core using taskset and numactl on core 0. Estimated score = 5.56, as of 2/8/2019 tested by Intel. Platinum 8280 vs Platinum 8180: 1-node, 2x Intel® Xeon® Platinum 8280M cpu on Wolf Pass with 384 GB (12 X 32GB 2933) total memory, ucode 0x400000A on RHEL7.6, 3.10.0-957.el7.x86_65, IC19u1, AVX512, HT on all (off Stream, Linpack), Turbo on all (off Stream, Linpack), result: est int throughput=317, est fp throughput=264, Stream Triad=217, Linpack=3462, server side java=177561, AIXPRT OpenVino/RN50=2324, test by Intel on 1/30/2019. vs. 1-node, 2x Intel® Xeon® Platinum 8180 cpu on Wolf Pass with 384 GB (12 X 32GB 2666) total memory, ucode 0x200004D on RHEL7.6, 3.10.0-957.el7.x86_65, IC19u1, AVX512, HT on all (off Stream, Linpack), Turbo on all (off Stream, Linpack), result: est int throughput=307, est fp throughput=251, Stream Triad=204, Linpack=3238, server side java=165724, AIXPRT OpenVino/RN50=1170, test by Intel on 1/29/2019.

16

Results calculated by Intel P2CA using AWS pricing ($/hour, standard 1-year term, no up-front) as of 12th January, 2019.
Performance per dollar testing done on AWS* EC2 R5 and R5a instances (https://aws.amazon.com/ec2/instance-types/), comparing 96 vCPU Intel® Xeon® Scalable processor performance per dollar to AMD EPYC* processor performance per dollar.

Workload: HammerDB* PostgreSQL*
Results: AMD EPYC performance per dollar = baseline of 1; Intel® Xeon® Scalable processor performance per dollar = 1.85X (higher is better)
Database: HammerDB – PostgreSQL (higher is better):
AWS R5.24xlarge (Intel) Instance, HammerDB 3.0 PostgreSQL 10.2, Memory: 768GB, Hypervisor: KVM; Storage Type: EBS io1, Disk Volume 200GB, Total Storage 200GB, Docker version: 18.06.1-ce, RedHat* Enterprise Linux 7.6, 3.10.0-957.el7.x86_64, 6400MB shared_buffer, 256 warehouses, 96 users. Score “NOPM” 439931, measured by Intel on 12/11/18-12/14/18.
AWS R5a.24xlarge (AMD) Instance, HammerDB 3.0 PostgreSQL 10.2, Memory: 768GB, Hypervisor: KVM; Storage Type: EBS io1, Disk Volume 200GB, Total Storage 200GB, Docker version: 18.06.1-ce, RedHat* Enterprise Linux 7.6, 3.10.0-957.el7.x86_64, 6400MB shared_buffer, 256 warehouses, 96 users. Score “NOPM” 212903, measured by Intel on 12/20/18.

Workload: MongoDB*
Results: AMD EPYC performance per dollar = baseline of 1; Intel® Xeon® Scalable processor performance per dollar = 2.84X (higher is better)
Database: MongoDB (higher is better):
AWS R5.24xlarge (Intel) Instance, MongoDB v4.0, journal disabled, sync to filesystem disabled, wiredTigeCache=27GB, maxPoolSize = 256; 7 MongoDB instances, 14 client VMs, 1 YCSB client per VM, 96 threads per YCSB client, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, Score 1229288 ops/sec, measured by Intel on 12/10/18.
AWS R5a.24xlarge (AMD) Instance, MongoDB v4.0, journal disabled, sync to filesystem disabled, wiredTigeCache=27GB, maxPoolSize = 256; 7 MongoDB instances, 14 client VMs, 1 YCSB client per VM, 96 threads per YCSB client, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, Score 388596 ops/sec, measured by Intel on 12/10/18.
For more details visit www.intel.com/benchmarks.

17

Results calculated by Intel P2CA using AWS pricing ($/hour, standard 1-year term, no up-front) as of 12th January, 2019.
Performance per dollar testing done on AWS* EC2 M5 and M5a instances (https://aws.amazon.com/ec2/instance-types/), comparing 96 vCPU Intel® Xeon® Scalable processor performance per dollar to AMD EPYC* processor performance per dollar.

Workload: LAMMPS*
Results: AMD EPYC performance per dollar = baseline of 1; Intel® Xeon® Scalable processor performance per dollar = 4.15X (higher is better)
HPC Materials Science – LAMMPS (higher is better):
AWS M5.24xlarge (Intel) Instance, LAMMPS version: 2018-08-22 (Code: https://lammps.sandia.gov/download.html), Workload: Water – 512K Particles, Intel ICC 18.0.3.20180410, Intel® MPI Library for Linux* OS, Version 2018 Update 3 Build 20180411, 48 MPI Ranks, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, OMP_NUM_THREADS=2, Score 137.5 timesteps/sec, measured by Intel on 10/31/18.
AWS M5a.24xlarge (AMD) Instance, LAMMPS version: 2018-08-22 (Code: https://lammps.sandia.gov/download.html), Workload: Water – 512K Particles, Intel ICC 18.0.3.20180410, Intel® MPI Library for Linux* OS, Version 2018 Update 3 Build 20180411, 48 MPI Ranks, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, OMP_NUM_THREADS=2, Score 55.8 timesteps/sec, measured by Intel on 11/7/18.
Changes for AMD to support AVX2 (AMD only supports AVX2, so these changes were necessary):
sed -i 's/-xHost/-xCORE-AVX2/g' Makefile.intel_cpu_intelmpi
sed -i 's/-qopt-zmm-usage=high/-xCORE-AVX2/g' Makefile.intel_cpu_intelmpi

Workload: High-performance Linpack*
Results: AMD EPYC performance per dollar = baseline of 1; Intel® Xeon® Scalable processor performance per dollar = 4.15X (higher is better)
HPC Linpack (higher is better):
AWS M5.24xlarge (Intel) Instance, HP Linpack Version 2.2 (https://software.intel.com/en-us/articles/intel-mkl-benchmarks-suite Directory: benchmarks_2018.3.222/linux/mkl/benchmarks/mp_linpack/bin_intel/intel64), Intel ICC 18.0.3.20180410 with AVX512, Intel® MPI Library for Linux* OS, Version 2018 Update 3 Build 20180411, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, OMP_NUM_THREADS=24, 2 MPI processes, Score 3152 GB/s, measured by Intel on 10/31/18.
AWS M5a.24xlarge (AMD) Instance, HP Linpack Version 2.2, (HPL Source: http://www.netlib.org/benchmark/hpl/hpl-2.2.tar.gz; Version 2.2; icc (ICC) 18.0.2 20180210 used to compile and link to BLIS library version 0.4.0; https://github.com/flame/blis; Addt’l Compiler flags: -O3 -funroll-loops -W -Wall –qopenmp; make arch=zen OMP_NUM_THREADS=8; 6 MPI processes.), Intel ICC 18.0.3.20180410 with AVX2, Intel® MPI Library for Linux* OS, Version 2018 Update 3 Build 20180411, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, OMP_NUM_THREADS=8, 6 MPI processes, Score 677.7 GB/s, measured by Intel on 11/7/18.

18

Results calculated by Intel P2CA using AWS pricing ($/hour, standard 1-year term, no up-front) as of 12th January, 2019.
Performance per dollar testing done on AWS* EC2 M5 and M5a instances (https://aws.amazon.com/ec2/instance-types/), comparing 96 vCPU Intel® Xeon® Scalable processor performance per dollar to AMD EPYC* processor performance per dollar.

Workload: Server Side Java* 1 JVM
Results: AMD EPYC performance per dollar = baseline of 1; Intel® Xeon® Scalable processor performance per dollar = 1.74X (higher is better)
Server Side Java (higher is better):
AWS M5.24xlarge (Intel) Instance, Java Server Benchmark No NUMA binding, 2JVM, OpenJDK 10.0.1, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, Score 101767 Transactions/sec, measured by Intel on 11/16/18.
AWS M5a.24xlarge (AMD) Instance, Java Server Benchmark No NUMA binding, 2JVM, OpenJDK 10.0.1, RedHat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, Score 52068 Transactions/sec, measured by Intel on 11/16/18.

Workload: Wordpress* PHP/HHVM*
Results: AMD EPYC performance per dollar = baseline of 1; Intel® Xeon® Scalable processor performance per dollar = 1.75X (higher is better)
Web Front End Wordpress (higher is better):
AWS M5.24xlarge (Intel) Instance, oss-performance/wordpress Ver 4.2.0; Ver 10.2.19-MariaDB-1:10.2.19+maria~bionic; Workload Version': u'4.2.0; Client Threads: 200; PHP 7.2.12-1; perfkitbenchmarker_version="v1.12.0-944-g82392cc; Ubuntu 18.04, Kernel Linux 4.15.0-1025-aws, Score 3626.11 TPS, measured by Intel on 11/16/18.
AWS M5a.24xlarge (AMD) Instance, oss-performance/wordpress Ver 4.2.0; Ver 10.2.19-MariaDB-1:10.2.19+maria~bionic; Workload Version': u'4.2.0; Client Threads: 200; PHP 7.2.12-1; perfkitbenchmarker_version="v1.12.0-944-g82392cc; Ubuntu 18.04, Kernel Linux 4.15.0-1025-aws, Score 1838.48 TPS, measured by Intel on 11/16/18.
For more details visit www.intel.com/benchmarks.

19

AWS M5.4xlarge (Intel) Instance, McCalpin Stream (OMP version), (Source: https://www.cs.virginia.edu/stream/FTP/Code/stream.c); Intel ICC 18.0.3 20180410 with AVX512, -qopt-zmm-usage=high, -DSTREAM_ARRAY_SIZE=134217728 -DNTIMES=100 -DOFFSET=0 –qopenmp, -qoptstreaming-stores always -o $OUT stream.c, Red Hat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, OMP_NUM_THREADS: 8, KMP_AFFINITY: proclist=[0-7:1], granularity=thread, explicit, Score 81216.7 MB/s, measured by Intel on 12/6/18.
AWS M5a.4xlarge (AMD) Instance, McCalpin Stream (OMP version), (Source: https://www.cs.virginia.edu/stream/FTP/Code/stream.c); Intel ICC 18.0.3 20180410 with AVX2, -DSTREAM_ARRAY_SIZE=134217728, -DNTIMES=100 -DOFFSET=0 -qopenmp -qopt-streaming-stores always -o $OUT stream.c, Red Hat* Enterprise Linux 7.5, Kernel 3.10.0-862.el7.x86_64, OMP_NUM_THREADS: 8, KMP_AFFINITY : proclist=[0-7:1], granularity=thread,explicit, Score 32154.4 MB/s, measured by Intel on 12/6/18.
OpenFOAM Disclaimer: This offering is not approved or endorsed by OpenCFD Limited, producer and distributor of the OpenFOAM software via www.openfoam.com, and owner of the OpenFOAM* and OpenCFD* trademark.
AWS pricing as of 12th January 2019 Standard 1-Year term Reserved Instance Pricing (https://aws.amazon.com/ec2/pricing/reserved-instances/pricing/) On Demand Linux/Unix Usage Pricing per hour (https://aws.amazon.com/ec2/pricing/on-demand/).

20

Up to 30x Inference Throughput Improvement on Intel® Xeon® Platinum 9282 processor with Intel® Deep Learning Boost (Intel® DL Boost): Tested by Intel as of 2/26/2019. Platform: Dragon rock 2 socket Intel® Xeon® Platinum 9282 processor (56 cores per socket), HT ON, turbo ON, Total Memory 768 GB (24 slots/ 32 GB/ 2933 MHz), BIOS:SE5C620.86B.0D.01.0241.112020180249, CentOS 7 Kernel 3.10.0-957.5.1.el7.x86_64, Deep Learning Framework: Intel® Optimization for Caffe* version: https://github.com/intel/caffe d554cbf1, ICC 2019.2.187, MKL DNN version: v0.17 (commit hash: 830a10059a018cd2634d94195140cf2d8790a75a), model: https://github.com/intel/caffe/blob/master/models/intel_optimized_models/int8/resnet50_int8_full_conv.prototxt, BS=64, No datalayer syntheticData:3x224x224, 56 instance/2 socket, Datatype: INT8 vs Tested by Intel as of July 11th 2017: 2S Intel® Xeon® Platinum 8180 processor CPU @ 2.50GHz (28 cores), HT disabled, turbo disabled, scaling governor set to "performance" via intel_pstate driver, 384GB DDR4-2666 ECC RAM. CentOS Linux* release 7.3.1611 (Core), Linux* kernel 3.10.0-514.10.2.el7.x86_64. SSD: Intel® SSD Data Center S3700 Series (800GB, 2.5in SATA 6Gb/s, 25nm, MLC). Performance measured with: Environment variables: KMP_AFFINITY='granularity=fine, compact‘, OMP_NUM_THREADS=56, CPU freq set with CPU Power frequency-set -d 2.5G -u 3.8G -g performance. Caffe: (http://github.com/intel/caffe/), revision f96b759f71b2281835f690af267158b82b150b5c. Inference measured with “caffe time --forward_only” command, training measured with "caffe time" command. For "ConvNet" topologies, synthetic dataset was used. For other topologies, data was stored on local storage and cached in memory before training. Topology specs from https://github.com/intel/caffe/tree/master/models/intel_optimized_models(ResNet-50). Intel® C++ Compiler ver. 17.0.2 20170213, Intel® Math Kernel Library (Intel® MKL) small libraries version 2018.0.20170425. Caffe run with "numactl -l".