Intel® Xeon® Processor E5-2600 v4 Tech Computing Applications Showcase

Intel® Xeon® Processor E5-2600 v4 Product Family Applications ShowcasePerformance Orchestration security

Technical Computing March 2016

* Other Names and Brands May Be Claimed as the Property of Others 2

Software Partners Enabling on the Intel® Xeon® processor E5-2600 v4 Family

http://www.mysql.com/

http://www.mysql.com/

Intel® Xeon® processor E5-2600 v4platform value proposition

3


+

Intel® Xeon® processor E5-2600 v4

product family

Intel® SSD DC Family D3700/3600 & P3320

+Intel® Ethernet

OR

Intel® omni-path architecture

The New 2016 Platform Optimized for the Cloud


Intel® Xeon® Processor E5-2600 v4 Product FamilyNew Processor Technologies

• New Features and Enhancements• Intel® Transactional Synchronization Extensions (TSX)

• Optimized Intel® AVX 2.0

• Gather Improvements

• Posted Interrupts

• Page Modification Logging

• VM Enter/Exit latency Reduction

Performance

• New Capabilities• Cache Monitoring Technology (introduced on Xeon® E5-2600 v3)

• Cache Allocation Technology

• Code and Data Prioritization

• Memory Bandwidth Monitoring

Orchestration

• New Features• Crypto Speedup

• New Random Seed Generator (RDSEED)

• #VE (Processor Virtualization exception)

• Supervisor Mode Access Protection (SMAP)

Security

Performance info

Orchestration info

Security info

Inte

l® R

eso

urc

e

Dir

ect

or

Te

chn

olo

gy

* Other Names and Brands May Be Claimed as the Property of Others

Software platform value propositionIntel® Xeon® Processor E5-2600 v4 product Family

6

With software solutions running on the Intel® Xeon® processor E5-2600 v4 product family, you can:

Accelerate cloud deployments through a robust portfolio of capabilities in the software defined infrastructure space, to better manage shared platform resources. See how new features such as Intel® RDT can offer higher throughput for higher priority workloads for better utilization overall.

Catalyze business innovation with cloud-based service and application delivery models that increase efficiency and lower TCO. Learn how software optimizations for this latest generation processor can deliver improved user experiences.

Break through the “performance wall” with the Intel Xeon processor E5-2600 v4 product family for many High Performance Computing applications, as seen here.

Stay competitive by enabling the IT organization to be more agile, flexible and responsive to evolving business needs and to scale on demand.


Technical computing


Technical Computing

8

Telecom.

& Cloud

Up to

Faster1

5.54X

Financial

Services &

Security

Big Data

AnalyticsCore Business

Enterprise

Database

Break Down Your “Performance Wall”

Whether you’re designing a product,

identifying a disease marker, or exploring the

subsurface, faster access to deeper insight is a

major advantage. The Intel® Xeon® processor

E5-2600 v4 product family with Intel®

Advanced Vector Extensions 2.0 (Intel® AVX

2.0) delivers significant gains in performance,

density, and efficiency. In combination with

Intel innovations across the HPC platform,

these processors offer a powerful new

resource for accelerating discovery.

View the following slides to see how

compelling the performance gains can be.

1 – Demonstrated with LAMMPS* proof point, slide 9.


0

1

2

3

4

5

No

rmal

ized

Per

form

ance

2S Intel® Xeon® processor E5-2697 v3


2S Intel® Xeon® processor E5-2697 v4 and Intel® AVX2 Optimizations

Up to 30%faster!!

LAMMPS increased performance by up to 5.54X with the 2S Intel® Xeon® processor E5-2697 v4

and Intel® AVX2

LAMMPS*Large-Scale Atomic/Molecular Massively Parallel Simulator

“The new Intel® Xeon® processor E5-2697 V4, combined with software optimizations to exploit Intel® AVX2, produces impressive speedups for LAMMPS, allowing scientists to perform more realistic simulations with molecular dynamics.”

Steve Plimpton – Distinguished Member of Technical Staff, Sandia National Laboratories

9

http://lammps.sandia.gov/

Optimizations to exploit Intel® AVX2 give simulation rates that are up to 5.54X faster1

Improved memory bandwidth and increased core counts allow unmodified code in LAMMPS to perform simulations up to 30% faster on E5-2697v4 processors without an increase in the processor TDP2

Optimizations are available in the USER-INTEL package provided with LAMMPS*

Technical Computing - Life Sciences

1,2 - Testing conducted on LAMMPS* software comparing 2S Intel® Xeon® Processor E5-2697 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by Intel® corporation. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.

Intel® Xeon® Processor E5-2600 v4 Product Family

More realistic simulations help develop better therapeutics

Up to 5.54Xfaster!

Workload: LAMMPS* Stillinger-Weber Silicon Benchmark – 512K atoms.

Intel Better Together: XEON + AVX2

to be edited

http://www.intel.com/performance


0

1

2

2S Intel® Xeon® processor E5-2697 v3 + HDD

2S Intel® Xeon® processor E5-2699 v4 + Intel SSD DC

INTES PERMAS increased performance by up to 2.81X with the 2S Intel® Xeon® processor E5-2699 v4 and Intel®

SSD DC P3600 Series

INTES*PERMAS

“The combination of the new Intel® Xeon® processor E5-2699 v4 with Intel® AVX2 and Intel® Solid State Drives provides a new level of PERMAS application performance. This allows our customers to run more complex simulations in the same time to achieve better product designs.”1

Dr Reinhard Helfrich – CEO, INTES

10

https://www.intes.de/

General improvements: The Intel® Xeon® processor E5-2600 v4 increased memory bandwidth, allows better utilization of computational resources, and significantly improved run time.

PERMAS time-based application benefits using Intel® SSD Data Center Family for NVMe* from lower latency and increased efficiency leading to much higher I/O throughput and better parallelization with additional significant run time savings.

The Intel® Xeon® processor E5-2697 v4 delivers about 10%2 improvement in performance compared to E5-2697 v3.

Technical Computing - Manufacturing

Up to 2.81X faster

1 - Testing conducted on ISV* software comparing 2S Intel® Xeon® Processor E5-2699 v4 to 2S Intel® Xeon® Processor E5-2697 v3. 2 – Estimated improvement for Intel® Xeon® Processor E5-2697 v4 compared to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31. 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 http://www.intel.com/performance.

Intel Better Together: XEON + SSD


Intel® Xeon® processor E5-2699 v4 with Intel® SSD Data Center Family reduce manufacturing runtimes Workload: Permas processing time.

No

rma

lize

d P

erf

orm

an

ce

E5-2697 v4 est. ~ 1.10X

to be edited



0

1



Product increased performance with 2S Intel® Xeon® processor E5-2600 v4

ANSYS*Mechanical* 17

“ANSYS helps customers turn their design concepts into successful, innovative products. The combination of ANSYS Mechanical software running on the Intel® Xeon® processor E5-2697 v4 and taking advantage of both the Intel® Solid State Drive and the Intel® AVX2 really boosted performance to amazing levels compared to the previous generation processors.”

Dr. Wim Slagter – Director of HPC and Cloud Marketing, ANSYS

11

ANSYS Mechanical 17.0 has improved scalability to leverage more cores and achieve higher performance on the newest Intel® Xeon® processors

With higher core counts and more on-board memory, users can employ higher fidelity models to achieve more accurate and detailed results.

Higher memory bandwidth helps to maintain per-core performance even with a higher core density on socket

Higher performance means a shorter turn-around time on structural analysis and the ability to cover more design points in design optimization.


Up to 70%

faster

1 - Testing conducted on ISV* software comparing 2S Intel® Xeon® Processor E5-2697 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.


Turn high-fidelity models into products faster Workload: V17SP-5 - Core Solver Rating.

No

rma

lize

d P

erf

orm

an

ce

www.ansys.com

Intel® Xeon® + Intel® AVX2 + Intel® SSD


to be edited


0

1

2S Intel® Xeon® processor E5-2697 v3 (28 cores)



Up to 32%

faster

ANSYS* Fluent* 17 Computational Fluid Dynamics

““Thanks to latest Intel® Xeon® processor E5-2600 v4 product family, ANSYS Fluent* is able to achieve performance levels beyond our expectations. Its unrivaled performance enables our customers to simulate higher-fidelity models without having to expand their cluster nodes.”1

Dr. Wim Slagter – Director of HPC and cloud marketing, ANSYS

12

The Intel® Xeon® E5-2699 v4 provides higher Fluent performance compared to the previous generation processor, resulting in faster turn-around times.

Benefitting from Intel® MPI, Fluent scales out to fully utilize all available server cores.

Better performance allows for higher fidelity simulations and higher quality flow visualizations.

Coupled with the ANSYS Workbench* for parametric studies, design engineers can cover more design space in the product design cycle.

Up to 49%

faster

1 - Testing conducted on ANSYS Fluent* comparing 2S Intel® Xeon® Processor E5-2697 v4 and 2S Intel® Xeon® Processor E5-2699 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.


Up to 49% better performance over the previous generation Intel® Xeon® server Workload: Exhaust_system_33m, a 33 million cell vehicle exhaust

system model, part of the Fluent benchmarking suite.

No

rma

lize

d P

erf

orm

an

ce

ANSYS Fluent* 17.0 solver rating increased by up to 1.49X with the 2S Intel® Xeon® E5-2699 v4

www.ansys.com


Intel® Xeon® + Intel® MPI


to be edited


2226.8

3462.9

0

500

1000

1500

2000

2500

3000

3500

0 288 576 864 1152

So

lve

r R

ati

ng

Number of Cores, 36 cores per node

Intel® Xeon® E5-2697 v4

with FDR InfiniBand* Fabric

with Intel® Omni-Path Architecture

ANSYS Fluent* 17 solver rating increased by up to 1.55X with Intel® Omni-Path Architecture scaling on a

32-node cluster

ANSYS*Fluent* 17 Computational Fluid Dynamics

“Thanks to Intel® OPA and the latest Intel® Xeon® processor E5-2600 v4 product family, ANSYS Fluent* is able to achieve performance levels beyond our expectations. Its unrivaled performance enables our customers to simulate higher-fidelity models without having to expand their cluster nodes.”

Dr. Wim Slagter – Director of HPC and cloud marketing, ANSYS

13

www.ansys.com

Intel® Omni-Path Architecture (Intel® OPA) is a powerful low latency communications interface specifically designed for High Performance Computing.

Cluster users will get better utilization of cluster nodes through better scaling.

Cluster performance means better time-to-solution on CFD simulations.

Coupled with Intel® MPI, and utilizing standard Fluent runtime options to access TMI, Fluent is ready and proven for out-of-the-box performance on Intel OPA-ready clusters.

Technical Computing

Up to 55% better

1 - Testing conducted on ISV* software on 2S Intel® Xeon® Processor E5-2697 v4 comparing Intel® OPA to FDR InfiniBand* fabric. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.


Up to 55% performance advantage with Intel® OPA compared to FDR fabric on a 32 node cluster Workload: 12 million cell combustor model, part of the Fluent

benchmarking suite. Fluent 17.0

to be edited



0

1



ANSYS* CFX* 17 - Computational Fluid Dynamics

“Hardware and software improvements should go hand in hand. The latest combination of ANSYS CFX 17.0 and the Intel® Xeon® processor E5-2600 v4 product family is a clearly testament of significant performance gains achieved for customers who wants to increase their engineering productivity.”

Dr. Wim Slagter – Director of HPC and Cloud Marketing, ANSYS

14

The transition from CFX15 on the Intel® Xeon® processor E5-2697 v3 to the latest CFX17 and Intel® Xeon® processor E5-2697 v4 produces up to 1.61X higher performance for solving a computational fluid dynamics workload1

For end-users, this means faster turnaround or solving larger tasks with the same resources along with lower TCO.

Up to 61%faster

1 - Testing conducted on ANSYS CFX* comparing 2S Intel® Xeon® Processor E5-2697 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.


Large tasks completed quicker with the latest software and hardware

Workload: Sysbench OLTP.

No

rma

lize

d P

erf

orm

an

ce

ANSYS CFX 15 increased performance by up to 1.61X with ANSYS CFX 17 and the 2S Intel® Xeon® processor

E5-2697 v4

www.ansys.com



to be edited


0

1



S&I HiFUN* reduced analysis time by up to 1.44X with the 2S Intel® Xeon® processor E5-2697 v4

S&I Engineering Solutions Pvt. Ltd.*S&I High Resolution Flow Solver on Unstructured Meshes* (HiFUN)

“It is exciting to see the availability of a larger cache in the Intel® Xeon® processor E5-2697 v4 narrowing the gap between processor and memory access speeds, thereby improving the single process performance of HiFUN*. And the higher core-density per processor means compact parallel cluster and improved intra-node parallel performance. These factors add up to increase productivity for our clients.”

Nikhil Vijay Shende - Director, SandI Engineering Solutions

.

15

The Intel® Xeon® processor E5-2697 v4 reduced HiFUN* Computational Fluid Dynamics analysis time up to 1.44X faster1; increased productivity for companies

The Intel® Xeon® processor E5-2697 v4 larger cache & cores paired with a highly scalable algorithm allows better utilization of computational resources, and significantly improved intra-node scalability and runtimes


Up to 44%faster

1 - Testing conducted on HiFUN* comparing 2S Intel® Xeon® Processor E5-2697 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by S&I and Intel. For complete testing configuration details, SEE SLIDE 31. 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 http://www.intel.com/performance.

Boost your CFD performance with HiFUN fluid flow analysis on Intel® Xeon® processor E5-2697 v4 by up to 44%

Workload: Aerospace CFD

No

rma

lize

d P

erf

orm

an

ce

http://sandi.co.in/


to be edited


0

1



Simulia Abaqus/Explicit increased performance by up to 1.37X with the 2S Intel® Xeon® processor

E5-2697 v4

Simulia*Abaqus/Explicit - Machine Intelligence* for the Enterprise

“Computational Engineering and Biology are two of the most compute-intensive domains bottlenecking businesses today. The over 35% performance improvements we’ve seen with the Intel® Xeon® processor E5-2697 v4 can directly translate into better products and reduced time to market for our customers. And with Intel® AVX2, we’ve seen an additional performance boost. In the future, performance improvements will be measured in number of lives saved.”

Steve Levine - PhD. Executive Director, The Living Heart Project

16

www.3ds.com/products-services/simulia/

End-Users can benefit from this application by getting a lower TCO and faster time to analysis, up to 1.37X faster1.

General improvements: The Intel® Xeon® processor E5-2697 v4, with higher peak floating-point performance and increased DRAM bandwidth, allows better utilization of computational resources and significantly improved runtimes.


Up to 37%

faster

1 - Testing conducted on ISV* software comparing 2S Intel® Xeon® Processor E5-2697 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by ISV. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.


Leading auto manufacturers go to market fasterWorkload: e5 benchmark (blast loaded plate)

No

rma

lize

d p

erf

orm

an

ce

Intel® Xeon® + Intel® AVX2

to be edited



0

1



Up to 32%faster

LSTC LS-DYNA increased performance by up to 1.32X with the 2S Intel® Xeon® processor E5-2697 v4

Livermore Software Tech Corp*LS-DYNA*

“We are excited about LS-DYNA performance on the new Intel® Xeon® processor E5-2697 v4. On the Explicit workload, our benchmark testing showed up to a 32% speed up in run times, leading to faster and more productive results for our LS-DYNA users. This performance will accelerate crash results in the automotive design phase, reducing time to market.”1

Nathan A. Hallquist – Systems Software Specialist, LSTC

17

Intel® AVX2, Intel® Fast Memory Access (Intel® FMA), and better memory bandwidth are delivering significant speed up in element processing and contact algorithms which are very floating point intensive.

LS-DYNA is the leading product in the crash simulation market. It is used by the automobile, aerospace, construction, military, manufacturing, and bioengineering industries in worldwide.

Technical Computing


Accelerated crash results in the design phase reduces time-to-market for LS-DYNA users Workload: Topcrunch.org 3-cars model crash simulation.

No

rma

lize

d P

erf

orm

an

ce

www.lstc.com


Intel® Xeon® + Intel® AVX2 + Intel® FMA



26570

14047

7588

40932736

0

5000

10000

15000

20000

25000

1 2 4 8 16

Ela

pse

d t

ime

, se

con

ds

-L

ow

er

is b

ett

er

Nodes

LSTC LS-DYNA MPP performance - Effect of increasing core count for an Intel® Xeon® processor

E5-2690 v4 cluster

Livermore Software Tech Corp*LS-DYNA*

“We are excited about LS-DYNA performance on the new Intel® Xeon® processor E5-2600 v4 product family. Our benchmark testing showed a significant speed up in run times, leading to faster and more productive results for LS-DYNA users. This performance will accelerate crash results in the automotive design phase, reducing time to market.”1

Nathan A. Hallquist – Systems Software Specialist, LSTC

18

Intel® AVX2, Intel® Fast Memory Access (Intel® FMA), and better memory bandwidth are delivering significant speed up in element processing and contact algorithms which are very floating point intensive.

LS-DYNA is the leading product in the crash simulation market. It is used by the automobile, aerospace, construction, military, manufacturing, and bioengineering industries in worldwide.


1 - Testing conducted on LS-DYNA* software on 2S Intel® Xeon® Processor E5-2690 v4 16-node cluster. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.

Accelerated crash results in the design phase reduces time-to-market for LS-DYNA users Workload: Topcrunch.org car2car model crash simulation.

www.lstc.com


Cluster Result!

Intel® Xeon® + Intel® AVX2 + Intel® FMA



0

1




Paradigm EarthStudy 360 increased performance by up to 1.43X with the 2S Intel® Xeon® processor

E5-2699 v41

Paradigm®EarthStudy 360® - Full-azimuth angle domain seismic imaging

“Our continued investment in the optimization of the EarthStudy 360® seismic imaging software, benefitting from the Intel® Compilers and the Intel® MKL library, enables our customers to take immediate advantage of this latest generation of Intel® Xeon® processors.”

Duane Dopkin - Executive Vice President of Geoscience

19

EarthStudy 360® is an HPC solution that maximizes the information that can be extracted from recorded seismic data by decomposing that data into full-azimuth, angle-dependent reflectivities and directional (dip and azimuth) data components. These components can be combined to produce improved seismic images, wave propagation models and subsurface velocity models, providing a deeper insight into the subsurface.

Customer benefits: Geophysicists can choose to apply the scalable performance improvements to produce higher resolution subsurface images or to improve existing workload throughput.

Technical Computing - Geoscience

1 - Testing conducted on Paradigm software comparing 2S Intel® Xeon® Processor E5-2697 v4 and 2S Intel® Xeon® Processor E5-2699 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.

Paradigm EarthStudy 360® benefits from multicore code enablement to take full advantage of the latest generation of Intel

HPC servers!

No

rma

lize

d P

erf

orm

an

ce

Up to 43% more

www.pdgm.com

Workload: Paradigm EPOS_geodepth - migration time


Up to 25% more

Intel® Xeon® + Intel® MKL



0

1



iconCFD increased performance by up to 1.3X with the 2S Intel® Xeon® processor E5-2699 v4

ICON Technology & Process Consulting*Numerical Simulation in Fluid Dynamics

“The increased number of cores and increased memory bandwidth compared to the previous generation have shown up to 30% performance gain on iconCFDsolvers.”1

Jacques Papper – Technical Director, ICON

20

www.iconcfd.com

Additional cores offer increased parallelization and faster results per node

Users will usually see a significant reduction in simulation runtimes due to the additional cores and larger memory bandwidth

General improvements: The Intel® Xeon® processor E5-2699 v4 increased memory bandwidth, allows better utilization of computational resources, and significantly improved runtimes


Up to 30%faster



ICON and Intel work together to drive down engineering analysis turnaround time

Workload: Automotive Shape Optimization

No

rma

lize

d P

erf

orm

an

ce

to be edited



0

1



Autodesk vRED improved performance by up to 1.28X with the 2S Intel® Xeon® processor E5-2699 v4

Autodesk*vRED*

“Autodesk vRED Professional 2017 (v9.0) saw a significant performance increase for 3D visualization and virtual prototyping, up to 28%, with the Intel® Xeon® processor E5-2699 v4 compared to the previous generation processor. This reduces the time-to-market for vehicle creation by major auto manufactures and is a great benefit for our customers.”1

Michael Russell – Automotive Business Line Manager, Autodesk

21

www.autodesk.com

Autodesk vRED Professional 2017 (v9.0) 3D visualization and virtual prototyping reduced rendering time by up to 1.28X

Autodesk vRED is used by industry-leading automotive manufacturers and the performance increase realized by the Intel® Xeon® processor E5-2699 v4 is a meaningful benefit

The new processor has more cores, more cache and supports faster memory speeds which reduces overall processing time compared to the previous generation processor


Up to 28% faster

1 - Testing conducted on Autodesk vRED* software comparing 2S Intel® Xeon® Processor E5-2699 v4 to 2S Intel® Xeon® Processor E5-2699 v3. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.


Reduces the time-to-market for vehicle creationWorkload: vRED Professional 2017 v9.0 geomean.

No

rma

lize

d P

erf

orm

an

ce

to be edited



0

1



Software Cradle scSTREAM increased performance by up to 1.27X with the 2S Intel® Xeon® processor

E5-2697 v4

Software Cradle Co., Ltd.scSTREAM*

“scSTREAM powered by the Intel® Xeon® processor E5-2697 v4 showed a speed-up by a factor of 1.27X compared to the previous generation processor. This power is available for everyone and no doubt expands the possibility for compute simulation more and more. It is our pleasure to be able to contribute to the speed-up of our customers' product development through scSCTREAM.

Hiroyuki Kuroishi – Deputy General Manager, Software Engineering Dept., Software Cradle Co., Ltd.

22

The Intel® Xeon® processor E5-2697 v4 reduced scSTREAM processing time from 164 to 129 seconds, up to 1.27X faster.

scSTREAM is an industry-leading structured mesh computational thermal fluid (CFD) analysis system for use with systems such as heating, ventilation, air conditioning, electrical & electronic equipment and environment engineering.

The Intel® Xeon® processor E5-2697 v4 increased memory bandwidth allows better utilization of computational resources, and significantly improved intra-node scalability and runtimes.


Up to 27%faster

1 - Testing conducted on ISV* software comparing 2S Intel® Xeon® Processor E5-2697 v4 to 2S Intel® Xeon® Processor E5-2697 v3. Testing done by Software Cradle and Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.

Boost your CFD performance with scSTREAM on Intel® Xeon® processor E5-2697 v4 Workload: Aero_10M

No

rma

lize

d p

erf

orm

an

ce

www.cradle-cfd.com



to be edited


0

1



Up to 27%faster

STAR-CCM+ increased performance by up to 1.27X with the 2S Intel® Xeon® processor E5-2699 v4

CD-adapco*STAR-CCM+ Multi-Disciplinary Engineering Analysis Tool*

“By working closely with Intel, we can ensure that STAR-CCM+ provides optimal performance on the very latest Intel® Xeon® processor technologies.”

Keith Foston – Product Manager, CD-adapco

23

The STAR-CCM+ multi-disciplinary engineering analysis tool benefits from the increased memory bandwidth and the improved computational resources of the Intel® Xeon® processor E5-2699 v4, significantly improving run times.

Users will usually see significant reduction in simulation runtimes due to the additional cores and larger memory bandwidth.

The tested system with two Intel® Xeon® processor E5-2699 v4 generated up to 1.27X speedup1 for STAR-CCM+ compared to a system based on the previous generation processor. This reduces the simulation/prototyping time and reduces the manufacturing time-to-market.



CD-adapco and Intel work together to drive down engineering analysis turnaround time

Workload: STAR-CCM+ 10.06.010 simulation run time.

No

rma

lize

d P

erf

orm

an

ce


www.cd-adapco.com/



0

1



Up to 25%faster

Altair RADIOSS increased performance by up to 1.25X with the 2S Intel® Xeon® processor E5-2699 v4

Altair*RADIOSS*

“The Intel® Xeon® processor E5-2600 v4 product family offers amazing computing power for running Altair HyperWorks* solvers and especially RADIOSS. Altair is very pleased it is now available to our customers.”

Eric Lequiniou – HPC Director, Altair

24

The increased memory bandwidth of the Intel® Xeon® E5-2699 v4 allows better utilization of its computational resources, significantly improving run times.

In addition to the larger memory bandwidth, users will see a reduction in simulation runtimes due to the additional cores.

System with two E5-2699V4 processors brings up to 1.27x speedup compared to the previous generation processor, diminishing the simulation/prototyping time and reducing the time-to-market for manufacturers.


1 - Testing conducted on RADIOSS* software comparing 2S Intel® Xeon® Processor E5-2699 v4 to 2S Intel® Xeon® Processor E5-2699 v3. Testing done by Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.

More memory bandwidth and more cores means faster runtimes and quicker time-to-market scenarios

Workload: Altair RADIOSS - Neon 8ms total time.

No

rma

lize

d P

erf

orm

an

ce


www.altair.com/



0

1



Up to 20%more

Neusoft CT increased transactions/second by up to 1.2X with the 2S Intel® Xeon® processor E5-2699 v4

Neusoft*CT*

“Based on the Intel® Xeon® processor E5-2699 v4, Neusoft CT showed a great performance boost compared with the previous generation processor. This will give our Neusoft CT customers a better user experience and improve the clinical efficiency. It is one of our preferred platforms.”1

Shanshan Lou – CT Physics & Image Reconstruction Manager

25

The Intel® Xeon® processor E5-2699 v4 improved Neusoft CT transactions per second from 6.85 to 8.24, up to 1.2X more.

Neusoft is the leading software solution and service provider in China. Neusoft CT (X-ray computed tomography) is its key digital health solution focusing on medical image processing, i.e. computing the axial images of the target using specific complicated algorithms.

The Intel® Xeon® processor E5-2699 v4 computing capability helps Neusoft CT to finish CT image processing faster.

Technical Computing - Healthcare

1 - Testing conducted on ISV* software comparing 2S Intel® Xeon® Processor E5-2699 v4 to 2S Intel® Xeon® Processor E5-2699 v3. Testing done by Neusoft and Intel. For complete testing configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.

Improved clinical efficiency helps deliver patient services faster

Workload: Transactions per second.

No

rma

lize

d P

erf

orm

an

ce

http://medical.neusoft.com




Software Performance OptimizationFirst Institute of Oceanography Parallel Ocean Program* (POP)

““As a key HPC application of FIO-ESM, POP has high requirement for performance. Great to see a performance improvement on the Intel® Xeon® Processor E5-2699 v4 compared to previous generation processor, and the new Intel® AVX2 also contributes to the performance gain. This new platform helps our application to deliver better service to its endusers.”1

Zhenya Song – Associate Professor

1,2,3 - Testing conducted on ISV applications comparing 2S Intel® Xeon® Processor E5-2699 v4 to 2S Intel® Xeon® Processor E5-2699 v3. Testing done by Intel. For complete configuration details, SEE SLIDE 31.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 http://www.intel.com/performance.


www.fio.org.cn

PerkinElmer Acapella*

PerkinElmer Acapella showed performance improvement with the Intel® Xeon® processor E-2699 v4 compared to the previous generation processor.2

www.perkinelmer.com

Dassault Systemes BIOVIA*

Dassault Systemes BIOVIA showed performance improvement with the Intel® Xeon® processor E-2699 v4 compared to the previous generation processor. Powered by the 3DEXPERIENCE* platform, BIOVIA provides global, collaborative product lifecycle experiences to transform scientific innovation.3 www.3ds.com/products-services/biovia

Leading Solutions Providers Rely on Intel® Xeon® Processors to Deliver Results!


2x2 and Better together stories

27


Reliable and Accurate Fluid Dynamics Solutions with ANSYS* CFX and Intel® Xeon® Processor E5-2697 v4

28

Solving Fluid Flow problems faster, more reliably and accurately

2014 2016

Software UpgradeANSYS CFX v17

Enhanced features for: 3-D Blade Design Tool

2-D Through-Flow Analysis

Advanced Meshing

Hardware UpgradeIntel® Xeon® processor E5-2697 v4 Increased parallelism - up to 22 cores, up to 2-sockets per server

natively

Up to 1.5TB of DDR4 memory supported per socket1

Reduce transaction bottlenecks with newer

Intel® SSD Data Center Series

SoftwareBaseline ANSYS CFX

v15

Better Together Up to 1.6X more simulations per cluster per day2

Intel® and ANSYS* CFX enables faster turnaround or solving larger tasks with the same resources

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.

1 Up to 3TB of memory supported per 2-socket server. Each socket supports 4 memory channels @ 3 DIMMs per channel = 12 DIMM slots per socket. Using 128GB memory DIMMS = 1.5TB per socket = 3 TB of memory per 2P server.

2 Up to 1.6x more simulations per cluster per day comparing baseline Intel® Server platform with two Intel® Xeon® processor E5-2697 v3, 128GB Memory (to an Intel® Server platform with two Intel® Xeon® processor E5-2697 v4, 128GB Memory (source: ANSYS* internal testing).

For more information, visit intel.com/performance

HardwareBaseline Intel® Xeon®

processor

E5-2697 v3

*Other names and brands may be claimed as the property of others.

Benchmark : Sysbench OLTP

+


92.94

57.44

0

10

20

30

40

50

60

70

80

90

100

E5-2697 v3 + ANSYS* CFX v15 E5-2697 v4 + ANSYS* CFX v17

Ge

o T

ime

Reliable and Accurate Fluid Dynamics Solutions with ANSYS* CFX and Intel® Xeon® Processor E5-2697 v4

29

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. Configuration details on next slide.

For more complete information visit http://www.intel.com/performance.


Lower is better

Up to 1.6X moreSimulations per

cluster per day

+


Configuration Details

30

ProcessorIntel® Xeon® processor E5-2697 v3

(14 cores, 28 threads)Intel® Xeon® processor E5-2697 v4

(18 Cores, 36 Threads)

Memory 128GB (8x 16GB 2133)

OS Distribution Red Hat* Enterprise Linux 6.4

ANSYS* CFX Version v15 v17

Geo time 92.94 57.44

Source ANSYS* Internal Testing

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 http://www.intel.com/performance.


+Reliable and Accurate Fluid Dynamics Solutions with ANSYS* CFX and Intel® Xeon® Processor E5-2697 v4


Configurations & Disclaimers

31


Proof point Configuration Details:LAMMPS*: LAMMPS Stillinger-Weber Silicon Benchmark – 512K atoms workload. Testing by Intel, 3/21/2016BASELINE: Intel® Xeon®Processor E5-2697 v3 on Grantley-EP (Wellsburg), with 64 GB Total Memory, 8 slots / 8 GB / 2133MT/s / DDR4 RDIMM, HT on, on Red Hat EnterpriseLinux* 6.5 kernel 2.6.32-431, LAMMPS: (25 Sep 2015+ LOCAL),compilers_and_libraries_2016.0.109,mpi5.1.2.RC1, Request Number: 2196NEW: Intel® Xeon®Processor E5-2697 v4 on Grantley-EP (Wellsburg), with 64 GB Total Memory, 8 slots / 8 GB / 2400MT/s / DDR4 RDIMM, HT on, on Red Hat EnterpriseLinux* 6.5 kernel 2.6.32-431, LAMMPS: (25 Sep 2015+ LOCAL),compilers_and_libraries_2016.0.109,mpi5.1.2.RC1, Request Number: 2196

Intes PERMAS*: Total processing time workload. Testing by Intel, 2/16/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v3 on Grantley-EP (Wellsburg) with 256 GB Total Memory, 16 slots / 16 GB / 1866 MT/s / DDR4 RDIMM, 4x Seagate R10K 1TB, turbo on, on Red Hat Enterprise Linux* 7.1 kernel 3.10.0-229. Data Source: Request Number: 1939NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 256 GB Total Memory, 16 slots / 16 GB / 2133 MT/s / DDR4 RDIMM, 4x Intel SSD P3600 1.6TB, turbo on, on Red Hat Enterprise Linux* 7.1 kernel 3.10.0-229. Data Source: Request Number: 1939

Ansys Mechanical* v17.0: V17SP-5 - Core Solver Rating. Testing done by Intel, 2/23/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v3 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2133 MT/s / DDR4 RDIMM / Home Snoop (default), IEEL Lustre connected via 1 GE ethernet (cluster storge device), HT and turbo on, on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Intel MPI 5.0.3 (default). Data Source: Request Number: 1997NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM / Home Snoop (default), IEEL Lustre connected via 1 GbE ethernet (cluster storge device), HT and turbo on, on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Intel MPI 5.0.3 (default). Data Source: Request Number: 1997

ANSYS Fluent 17.0: Exhaust_system_33m, a 33 million cell vehicle exhaust system model, part of the Fluent benchmarking suite. Testing by Intel, 3/10/2016.BASELINE: Intel® Xeon® processor E5-2697 v4, 2.3 GHz, 36 cores, Grantley-EP (Wellsburg),128GB DDR4/2400 DIMM, Mellanox FDR HCA, Lustre cluster file system used, 36 cores per cluster node used (fully subscribed), Intel® MPI 5.0.3 as distributed with ANSYS Fluent, home snoop, HT and turbo on, Red Hat Enterprise Linux* 6.4kernel 2.6.32-358, Request Number: 1907NEW: Intel® Xeon® processor E5-2697 v4, 2.3 GHz, 36 cores, Grantley-EP (Wellsburg),128GB DDR4/2400 DIMM, Intel® OPA® interconnect, Lustre cluster file system used, 36 cores per cluster node used (fully subscribed), Intel® MPI 5.0.3 as distributed with ANSYS Fluent, home snoop, HT and turbo on, Red Hat Enterprise Linux* 6.4kernel 2.6.32-358, Request Number: 1907

ANSYS Fluent 17.0: Combustor_12m workload; Intel OPA vs. FDR. Testing by Intel, 3/10/2016.BASELINE: Intel® Xeon® processor E5-2697 v4, 2.3 GHz, 36 cores, Grantley-EP (Wellsburg),128GB DDR4/2400 DIMM, Mellanox FDR HCA, Lustre cluster file system used, 36 cores per cluster node used (fully subscribed), Intel® MPI 5.0.3 as distributed with ANSYS Fluent, home snoop, HT and turbo on, Red Hat Enterprise Linux* 6.4kernel 2.6.32-358, Request Number: 1907NEW: Intel® Xeon® processor E5-2697 v4, 2.3 GHz, 36 cores, Grantley-EP (Wellsburg),128GB DDR4/2400 DIMM, Intel® OPA® interconnect, Lustre cluster file system used, 36 cores per cluster node used (fully subscribed), Intel® MPI 5.0.3 as distributed with ANSYS Fluent, home snoop, HT and turbo on, Red Hat Enterprise Linux* 6.4kernel 2.6.32-358, Request Number: 1907

ANSYS CFX* 17: Sysbench OLTP workload, CFX 15 on E5-2697 v3 compared to CFX 17 on E5-2697 v4. Testing by ANSYS, February 15, 2016.BASELINE: Red Hat Enterprise Linux Server release 6.4, 2 Intel® Xeon® processors E5-2697 v3, 2.6GHz, 14 cores, on Grantley-EP (Wellsburg), 64GB DDR3/2133, regular DIMM, Request Number: 1906NEW: Red Hat Enterprise Linux Server release 6.4, 2 Intel® Xeon® processors E5-2697 v4, 2.3GHz, 18 cores, 64GB DDR4/2133, regular DIMM, Request Number: 1906

32


Proof point Configuration Details:S&I HiFUN*: Aerospace CFD workload. Testing by SandI and Intel, 2/16/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v3 on Grantley-EP (Wellsburg) with 32 GB Total Memory, 4 slots / 8 GB / 2133 MT/s / DDR4 RDIMM / 32 GB, HT and turbo on, on Red Hat Enterprise Linux* 7.1 kernel 3.10.0-229. Data Source: Request Number: 1960NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v4 on Grantley-EP (Wellsburg) with 32 GB Total Memory, 4 slots / 8 GB / 2133 MT/s / DDR4 RDIMM / 32 GB, HT and turbo on, on Red Hat Enterprise Linux* 7.1 kernel 3.10.0-229. Data Source: Request Number: 196

Simulia Abaqus v2016.0: e5 benchmark (blast loaded plate). Testing by Intel, 1/22/2016BASELINE: Intel® Xeon® Processor E5-2697 v3, (35M Cache, 2.60 GHz) Grantley-EP (Wellsburg), 128 GB Total Memory, 16 slots / 8 GB / 2133 MT/s /DDR4 RDIMM, Intel SSD DC, turbo on, on Red Hat Enterprise Linux* 6.4kernel 2.6.32-358, Request Number: 1979 NEW: Intel® Xeon® Processor E5-2697 v4 on Grantley-EP (Wellsburg), 64 GB Total Memory, 8 slots / 8 GB / 2400 MT/s /DDR4 RDIMM, Intel SSD DC, turbo on, on Red Hat Enterprise Linux* 6.4kernel 2.6.32-358, Request Number: 1979

LSTC LS-Dyna*: 3-cars model crash simulation workload. Testing by Intel, 2/22/2016BASELINE: Intel® Xeon® Processor E5-2697 v3 (35M Cache, 2.60 GHz) Grantley-EP (Wellsburg), 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s /DDR4 RDIMM, HT and turbo on, on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Data Source: Request Number: 1941NEW: Intel® Xeon® Processor E5-2697 v4 (45M Cache, 2.30 GHz) Grantley-EP (Wellsburg), 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s /DDR4 RDIMM, 1 SSD, turbo on, on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Data Source: Request Number: 1941

LSTC LS-Dyna*: LS-DYNA R7.1.2, Topcrunch.org car2car model crash simulation core scaling workload. Testing by Intel, 2/22/2016SYSTEM TESTED: Intel® Xeon® Processor E5-2690 v4 Grantley-EP (Wellsburg), 128GB total memory, 8 slots / 8 GB / 2400 MT/s / DDR4 RDIMM, turbo on, on Red Hat Enterprise Linux* 6.5 kernel 3.10.0, Request Number: 1992

Paradigm EPOS_GeoDepth*: Migration time workload. Testing done by Turbo Systems and Intel, 2/21/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v3 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, HT and turbo on, on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358. Data Source: Request Number: 1900NEXT GEN: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, HT and turbo on, on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358. Data Source: Request Number: 1900NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, HT and turbo on, on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358. Data Source: Request Number: 1900

33


Proof point Configuration Details:iconCFD*: Camaro Shape Optimization workload. Testing by Intel, 2/16/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, HT and turbo on, on Red Hat Enterprise Linux* 7.2-kernel 3.10.0-327. Data Source: Request Number: 1936NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, HT and turbo on, on Red Hat Enterprise Linux* 7.2-kernel 3.10.0-327. Data Source: Request Number: 1936

Autodesk vRED* Professional v9.0: 3D visualization and virtual prototyping using Autodesk VRED Professional v9.0 workload. Testing by Intel, 2/24/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 32 GB Total Memory, 4 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, HT and turbo on, on Windows 7 Professional 64-bit. Data Source: Request Number: 1908NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 32 GB Total Memory, 4 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, HT and turbo on, on Windows 7 Professional 64-bit. Data Source: Request Number: 1908

Software scSTREAM: Aero_10M workload. Testing by Software Cradle and Intel, 2/11/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v3 on Grantley-EP (Wellsburg) with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, turbo on, on RHEL release 6.6 (updated kernel) 3.10.0-327.0.el6.x86_64.knl1. Data Source: Request Number: 1963NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, turbo on, on RHEL release 6.6 (updated kernel) 3.10.0-327.0.el6.x86_64.knl1. Data Source: Request Number: 1963

CD-Adapco Star-CCM+: STAR-CCM+ 10.06.010 simulation run time. Testing by Intel, 2/16/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, SSD SSDSC2BA80, turbo on, on Red Hat Enterprise Linux* 7.2-kernel 3.10.0-327. Data Source: Request Number: 1977NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, SSD SSDSC2BA80, turbo on, on Red Hat Enterprise Linux* 7.2-kernel 3.10.0-327. Data Source: Request Number: 1977

Altair RADIOSS*: Neon 8ms total time workload. Testing by Intel, 2/16/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, SSD SSDSC2BA80, CoD = enable, HT and turbo on, on Red Hat Enterprise Linux* 7.2-kernel 3.10.0-327. Data Source: Request Number: 1903NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, SSD SSDSC2BA80, CoD = enable, HT and turbo on, on Red Hat Enterprise Linux* 7.2-kernel 3.10.0-327. Data Source: Request Number: 1903

34


Proof point Configuration Details:Neusoft CT: Transactions per second workload. Testing done by Neusoft and Intel, 1/28/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, HDD: 1TB SATA ST9500424AS, NIC: Intel I350, HT and turbo on Windows Server* 2012 R2 Standard using Visual Studio 2012, Intel Parallel Studio XE 2013. Data Source: Request Number: 1950NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4 RDIMM, HDD: 1TB SATA ST9500424AS, NIC: Intel I350, HT and turbo on Windows Server* 2012 R2 Standard using Visual Studio 2012, Intel Parallel Studio XE 2013. Data Source: Request Number: 1950

First Institute of Oceanography POP: Parallel Ocean Program version 2.0 workload. Testing by Intel, 1/28/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2133 MT/s / DDR4 RDIMM, BIOS version: SE5C610.86B.01.01.0008.021120151325, turbo on, on Red Hat Enterprise Linux* 6.5 kernel 2.6.32-431 using AVX 2.0. Data Source: Request Number: 1924NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM, BIOS version: GRRFSDP1.86B.0271.R00.1510301446, turbo on, on CentOS* 2.6.32-573.el6.x86_64 CentOS release 6.7using using AVX 2.0. Data Source: Request Number: 1924

PerkinElmer Acapella: Medical imaging workload. Testing by Intel, 1/21/2016BASELINE: Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg), with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4RDIMM / NUMA off, HT and turbo on, on Red Hat Enterprise Linux* 7.1 kernel3.10.0-229, Request Number: 1954NEW: Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg), with 64 GB Total Memory, 8 slots / 8 GB / 2133 MT/s / DDR4RDIMM / NUMA off, HT and turbo on, on Red Hat Enterprise Linux* 6.4 kernel2.6.32-358, Request Number: 1954

Dassault Systemes BIOVIA*: CASTEP/Forcite workload. Testing by Intel, 2/23/2016BASELINE: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v3 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2133 MT/s / DDR4 RDIMM / Dual rank, 1 HDD, 1TB, SATA, turbo on, on Red Hat Enterprise Linux* 7.1 kernel 3.10.0-229. Data Source: Request Number: 1998NEW: 1-Node, 2 x Intel® Xeon® Processor E5-2697 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory, 8 slots / 16 GB / 2400 MT/s / DDR4 RDIMM / Dual rank, 1 HDD, 1TB, SATA, turbo on, on Red Hat Enterprise Linux* 7.1 kernel 3.10.0-229. Data Source: Request Number: 1998

35


Legal Notices and DisclaimersIntel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Learn more at intel.com, or from the OEM or retailer.

No computer system 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. Consult other sources of information to evaluate performance as you consider your purchase. For more complete information about performance and benchmark results, visit http://www.intel.com/performance.

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.

This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications and roadmaps.

No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.

Statements in this document that refer to Intel’s plans and expectations for the quarter, the year, and the future, are forward-looking statements that involve a number of risks and uncertainties. A detailed discussion of the factors that could affect Intel’s results and plans is included in Intel’s SEC filings, including the annual report on Form 10-K.

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.

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 http://www.intel.com/performance.

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

© 2016 Intel Corporation.

3636363636 36



Copyright © 2016, Intel Corporation. All rights reserved.

Date post:	15-Apr-2017
Category:	Technology
Upload:	intel-it-center
View:	794 times
Download:	2 times