Post on 15-Apr-2017
transcript
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
Intel® Xeon® processor E5-2600 v4platform value proposition
3
* Other Names and Brands May Be Claimed as the Property of Others 4
+
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
* Other Names and Brands May Be Claimed as the Property of Others 5
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.
* Other Names and Brands May Be Claimed as the Property of Others 7
Technical computing
* Other Names and Brands May Be Claimed as the Property of Others
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.
* Other Names and Brands May Be Claimed as the Property of Others
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
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
* Other Names and Brands May Be Claimed as the Property of Others
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 E5-2600 v4 Product Family
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
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3
2S Intel® Xeon® processor E5-2697 v4
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.
Technical Computing - Manufacturing
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.
Intel® Xeon® Processor E5-2600 v4 Product Family
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
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3 (28 cores)
2S Intel® Xeon® processor E5-2697 v4 (36 cores)
2S Intel® Xeon® processor E5-2699 v4 (44 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.
Intel® Xeon® Processor E5-2600 v4 Product Family
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
Technical Computing - Manufacturing
Intel® Xeon® + Intel® MPI
* Other Names and Brands May Be Claimed as the Property of Others
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.
Intel® Xeon® Processor E5-2600 v4 Product Family
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
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3
2S Intel® Xeon® processor E5-2697 v4
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.
Intel® Xeon® Processor E5-2600 v4 Product Family
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
Technical Computing - Manufacturing
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3
2S Intel® Xeon® processor E5-2697 v4
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
Technical Computing - Manufacturing
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/
Intel® Xeon® Processor E5-2600 v4 Product Family
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3
2S Intel® Xeon® processor E5-2697 v4
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.
Technical Computing - Manufacturing
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.
Intel® Xeon® Processor E5-2600 v4 Product Family
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
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3
2S Intel® Xeon® processor E5-2697 v4
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
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.
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® Processor E5-2600 v4 Product Family
Intel® Xeon® + Intel® AVX2 + Intel® FMA
* Other Names and Brands May Be Claimed as the Property of Others
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.
Technical Computing - Manufacturing
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
Intel® Xeon® Processor E5-2600 v4 Product Family
Cluster Result!
Intel® Xeon® + Intel® AVX2 + Intel® FMA
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3 (14 cores)
2S Intel® Xeon® processor E5-2697 v4 (18 cores)
2S Intel® Xeon® processor E5-2699 v4 (22 cores)
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
Intel® Xeon® Processor E5-2600 v4 Product Family
Up to 25% more
Intel® Xeon® + Intel® MKL
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2699 v3
2S Intel® Xeon® processor E5-2699 v4
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
Technical Computing - Manufacturing
Up to 30%faster
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 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® Xeon® Processor E5-2600 v4 Product Family
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
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2699 v3
2S Intel® Xeon® processor E5-2699 v4
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
Technical Computing - Manufacturing
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.
Intel® Xeon® Processor E5-2600 v4 Product Family
Reduces the time-to-market for vehicle creationWorkload: vRED Professional 2017 v9.0 geomean.
No
rma
lize
d P
erf
orm
an
ce
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2697 v3
2S Intel® Xeon® processor E5-2697 v4
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.
Technical Computing - Manufacturing
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
Intel® Xeon® Processor E5-2600 v4 Product Family
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2699 v3
2S Intel® Xeon® processor E5-2699 v4
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.
Technical Computing - Manufacturing
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 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.
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
Intel® Xeon® Processor E5-2600 v4 Product Family
www.cd-adapco.com/
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2699 v3
2S Intel® Xeon® processor E5-2699 v4
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.
Technical Computing - Manufacturing
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
Intel® Xeon® Processor E5-2600 v4 Product Family
www.altair.com/
* Other Names and Brands May Be Claimed as the Property of Others
0
1
2S Intel® Xeon® processor E5-2699 v3
2S Intel® Xeon® processor E5-2699 v4
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
Intel® Xeon® Processor E5-2600 v4 Product Family
* Other Names and Brands May Be Claimed as the Property of Others 26
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.
Intel® Xeon® Processor E5-2600 v4 Product Family
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
* Other Names and Brands May Be Claimed as the Property of Others
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
+
* Other Names and Brands May Be Claimed as the Property of Others
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.
*Other names and brands may be claimed as the property of others.
Lower is better
Up to 1.6X moreSimulations per
cluster per day
+
* Other Names and Brands May Be Claimed as the Property of Others
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.
*Other names and brands may be claimed as the property of others.
+Reliable and Accurate Fluid Dynamics Solutions with ANSYS* CFX and Intel® Xeon® Processor E5-2697 v4
Configurations & Disclaimers
31
* Other Names and Brands May Be Claimed as the Property of Others
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
* Other Names and Brands May Be Claimed as the Property of Others
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
* Other Names and Brands May Be Claimed as the Property of Others
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
* Other Names and Brands May Be Claimed as the Property of Others
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
* Other Names and Brands May Be Claimed as the Property of Others
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.