Intel® Xeon® Processor E5-2600 v4 Product Family World Record Benchmarks

The powerful new Intel® Xeon® processor E5-2600 v4 product family offers unparalleled versatility across diverse data center workloads. These processors are designed for architecting next-generation data centers running on software-defined infrastructure and supercharged for efficiency, performance, and agility across cloud-native and traditional applications.

Optimal Workload Performance Meets Intelligent Orchestration For Your Modern Data Center.

The Intel® Xeon® processor E5-2600 v4 product family is the right architectural foundation for software-defined enterprise data centers optimized for cloud deployments that require increased scalability, automation, and orchestration capabilities across compute, storage, and network workloads. Built-in features provide preferential allocation of resources based on priority workloads for better utilization overall and enable greater performance across cloud-native and traditional applications while maintaining service level agreements (SLAs). The digital services of tomorrow will require modern, programmable data centers optimized for agility, operational efficiency, and scale on demand. Architect that next-generation foundation today with software-defined infrastructure solutions built on the Intel Xeon processor E5-2600 v4 product family.

  • Up to 47% higher generational performance on a financial services option pricing workload1
  • Up to 27% average performance improvement across a variety of key industry-standard workloads and applications2
  • Up to 50% average energy efficiency (performance per watt) improvement across a variety of key industry-standard workloads and applications using improved components and newer, higher capacity SSDs3
  • Support to 2.4x more VMs/server reducing operational expenses and cost per VM by up to 58% maximizing CSP profitability versus two-generations-old servers (E5 v2) 4

Platform Performance Highlights

Over 25 new world record performance benchmark results with the best Intel® Xeon® processor E5-2600 v4 product family-based platforms (as of March 16, 2016).

Partner

Platform

Segment - Benchmark

Importance

Cisco UCS* C220 M4 General Server Throughput Computing: SPECint*_rate_base2006 2-socket world record (tie)
Cisco UCS* C220 M4 General Server Speed Computing: SPECint*_base2006 2-socket world record
Cisco UCS* C220 M4 Technical Computing Throughput:  SPECfp*_rate_base2006 2-socket x86 world record (tie)
Cisco UCS* C220 M4 Technical Speed Computing: SPECfp*_base2006 2-socket world record (tie)
Cisco UCS* B200 M4 Blade Server Technical Computing: SPECompG*_base2012 2-socket world record
Cisco UCS* C240 M4 Rack Server Business Processing - Enterprise Resource Planning (ERP): Two-tier SAP Sales and Distribution* 2-socket world record (Windows*)
Cisco UCS* C220 M4 Server-side Java*: SPECjbb*2015 Multi-JVM Critical-jOPS 2-socket world record

Partner

Platform

Segment - Benchmark

Importance

Dell PowerEdge* R730 Business Processing - Enterprise Resource Planning (ERP): Two-tier SAP Sales and Distribution* 2-socket world record (Linux)
Dell PowerEdge* R630 Technical Computing Throughput: SPECfp*_rate_base2006 2-socket x86 world record (tie)

Partner

Platform

Segment - Benchmark

Importance

Fujitsu PRIMERGY* RX2560 M2 General Server Throughput Computing: SPECint*_rate_base2006 2-socket world record (tie)
Fujitsu PRIMERGY* RX2540 M2 Technical Computing Throughput: SPECfp*_rate_base2006 2-socket x86 world record (tie)
Fujitsu PRIMERGY* RX2540 M2 Infrastructure/Virtualization: VMmark* 2.5.2 Performance (matched pair) 2-socket world record
Fujitsu PRIMERGY* RX2540 M2 Infrastructure/Virtualization: VMmark* 2.5.2 Performance with Server Power World record
Fujitsu PRIMERGY* RX2540 M2 Business Processing ERP/Energy Efficiency: SAP Server Power (2-tier)* World record
Fujitsu PRIMERGY* RX2560 M2 General Server Energy Efficiency: SPECpower_ssj*2008 World record

Partner Platform Segment - Benchmark Importance
HPE ProLiant* XL450 Gen9 Technical Speed Computing: SPECfp*_base2006 2-socket world record (tie)
HPE ProLiant* DL380 Gen9 Big Data Analytics: TPC Benchmark* H @ 1TB non-clustered World record
HPE ProLiant* DL380 Gen9 Big Data Analytics: TPC Benchmark* Express Big Bench @ 3000 (NEW!) World record
HPE ProLiant* DL380 Gen9 Server-side Java*: SPECjbb*2015 Distributed Max-jOPS World record
HPE ProLiant* DL360 Gen9 Server-side Java: SPECjbb*2015 Distributed Critical-jOPS World record
HPE ProLiant* ML350 Gen9 Server-side Java: SPECjbb*2015 Composite Max-jOPS World record
HPE ProLiant* DL360 Gen9 Server-side Java: SPECjbb*2015 Composite Critical-jOPS World record
HPE ProLiant* DL360 Gen9 Server-side Java: SPECjbb*2015 Multi-JVM Max-jOPS
2-socket x86 world record  

Partner

Platform

Segment - Benchmark

Importance

Huawei RH2288H* v3 General Server Throughput Computing: SPECint*_rate_base2006 2-socket world record (tie)

  Platform Segment - Benchmark Importance
Lenovo* System x*3650 M5 Technical Speed Computing: SPECfp*_base2006 2-socket world record (tie)
Lenovo* System x3650 M5 Technical Computing Throughput: SPECfp*_rate_base2006 2-socket x86 world record (tie)
Lenovo* System x3650 M5 Infrastructure/Virtualization: SPECvirt_sc*2013 2-socket x86 world record
Lenovo* System x3650 M5 Infrastructure/Virtualization: SPECvirt_sc*2013 PPW (Server and Storage Performance per Watt) World record
Lenovo* System x3650 M5 Infrastructure/Virtualization: SPECvirt_sc*2013 ServerPPW (Server Performance per Watt) World record
Lenovo* System x3650 M5 Business Processing: TPC Benchmark* E 2-socket world record

Partner Platform Segment - Benchmark Importance
Oracle Server* X6-2 Business Processing: SPECjEnterprise*2010 2-socket world record

Partner Platform Segment - Benchmark Importance

SGI ICE XA* IP-125

Technical Computing: SPECmpiL*2007 32 and 64-Node, 2-socket world record
SGI Rackable* C2112-4GP3 Technical Computing: SPECmpiL*2007 and SPECmpiM*2007 up to 16-Node, 2-socket world record

Partner Platform Segment - Benchmark Importance
Supermicro SuperServer* 6028TP-HTFR Technical Speed Computing: SPECfp*_base2006 2-socket world record (tie)

World Record Configurations

Cisco:

Claim based on best published two-socket SPECint*_rate_base2006 result submitted to/published at https://www.spec.org/cpu2006/results/ as of 16 March, 2016. New configuration: Cisco UCS* C220 M4 platform with 2x Intel® Xeon® processor E5-2699 v4 (22 cores, 44 threads), Red Hat* Enterprise Linux* 7.2, Intel Compiler 16.0, Score: 1760, (tied), source: http://www.cisco.com/c/dam/en/us/products/collateral/servers-unified-computing/specint-rate-benchmark-disclosure.pdf.

Claim based on best published two-socket SPECint*_base2006 result submitted to/published at https://www.spec.org/cpu2006/results/ as of 16 March, 2016. New configuration: Cisco UCS* C220 M4 platform with two Intel® Xeon® processor E5-2699 v4 (22 cores, 44 threads), Red Hat* Enterprise Linux* 7.2, Intel Compiler 16.0, Score: 73.1, source: http://www.cisco.com/c/dam/en/us/products/collateral/servers-unified-computing/specint-benchmark-disclosure.pdf.

Claim based on best published two-socket x86 SPECfp*_rate_base2006 result submitted to/published at https://www.spec.org/cpu2006/results/ as of 16 March, 2016. New configuration: Cisco UCS* C220 M4 platform with 2x Intel® Xeon® processor E5-2699 v4 (2.2 GHz, 22 cores), SUSE* Linux Enterprise Server 12 SP1 using Intel Compiler 16.0 scoring 1100, source: http://www.cisco.com/c/dam/en/us/products/collateral/servers-unified-computing/specfp-rate-benchmark-disclosure.pdf.

Claim based on best published two-socket SPECfp*_base2006 result submitted to/published at https://www.spec.org/cpu2006/results as of 16 March 2016. New configuration: Cisco UCS* C220 M4 platform with 2x Intel® Xeon® processor E5-2667 v4 (3.2 GHz, 8 cores), Red Hat* Enterprise Linux* 7.2, Intel Compiler 16.0, Score: 125 (tied), source: http://www.cisco.com/c/dam/en/us/products/collateral/servers-unified-computing/specfp-benchmark-disclosure.pdf.

Claim based on best published two-socket SPECompG*_base2012 result submitted to/published at https://www.spec.org/omp2012/results as of 16 March 2016. New configuration: Cisco UCS* B200 M4 server with 2x Intel® Xeon® processor E5-2699 v4 on Red Hat* Enterprise Linux* 6.7 using Intel Compiler 16.0 scoring 12.4 with 88 base threads, source: http://www.cisco.com/c/dam/en/us/products/collateral/servers-unified-computing/specomp-2012-benchmark-disclosure.pdf.

Claim based on best published two-socket Two-tier SAP SD* (Windows*) with enhancement package 5 for SAP ERP 6.0 benchmark result submitted to/published at http://global.sap.com/solutions/benchmark/sd2tier.epx as of 16 March 2016. New configuration: Cisco UCS* C240 M4 with 2x Intel® Xeon® processor E5-2699 v4 on Microsoft Windows Server* 2012 Datacenter Edition using IBM DB2* 10.1 scoring 21210 SD Benchmark Users. The SAP certification number was not available at press time and can be found at the following Web page: http://global.sap.com/solutions/benchmark/sd2tier.epx.

Claim based on best published two-socket SPECjbb*2015 Multi-JVM Critical-jOPS result submitted to/published at https://www.spec.org/jbb2015/results/ as of 16 March 2016. New configuration: Cisco UCS* C220 M4 platform with 2x Intel® Xeon® processor E5-2699 v4 (22 cores, 44 threads), Red Hat* Enterprise Linux* 7.2, Oracle HotSpot* 1.8.0, Score: 71951 critical jOPS, source: http://www.cisco.com/c/dam/en/us/products/collateral/servers-unified-computing/specjbb-2015-critical-benchmark-disclosure.pdf.

Dell:

Claim based on best published two-socket Two-tier SAP SD* (Linux*) with enhancement package 5 for SAP ERP* 6.0 benchmark result submitted to/published at http://global.sap.com/solutions/benchmark/sd2tier.epx as of 16 March 2016. New configuration: Dell PowerEdge* R730 with 2x Intel® Xeon® processor E5-2699 v4 on Red Hat* Enterprise Linux* Server 7 using SAP ASE* 16 scoring 21,050 SD Benchmark Users. The SAP certification number was not available at press time and can be found at the following Web page, see http://global.sap.com/solutions/benchmark/sd2tier.epx.

Claim based on best published two-socket x86 SPECfp*_rate_base2006 result submitted to/published at https://www.spec.org/cpu2006/results/ as of 16 March 2016. New configuration: Dell PowerEdge* R630 with 2x Intel® Xeon® processor E5-2699 v4 (2.20GHz, 22 cores), SUSE* Linux Enterprise Server 12 SP1 using Intel Compiler 16.0 scoring 1100, source: submitted to www.spec.org.

Fujitsu:

Claim based on best published two-socket SPECint*_rate_base2006 result submitted to/published at https://www.spec.org/cpu2006/results/ as of 16 March 2016. New configuration: Fujitsu PRIMERGY* RX2540 M2 platform with 2x Intel® Xeon® processor E5-2699 v4 (22 cores, 44 threads), Red Hat* Enterprise Linux* 7.2, Intel Compiler 16.0, Score: 1760. (tied), source: http://docs.ts.fujitsu.com/dl.aspx?id=35eb35f4-8dc8-479a-af16-aa8b283fceb0

Claim based on best published two-socket x86 SPECfp*_rate_base2006 result submitted to/published at https://www.spec.org/cpu2006/results/ as of 16 March 2016. New configuration: Fujitsu Server PRIMERGY RX2540 M2 with 2x Intel® Xeon® processor E5-2699 v4 (2.20GHz, 22 cores), SUSE* Linux Enterprise Server 12 using Intel Compiler 16.0.0.101 scoring 1100, source: http://docs.ts.fujitsu.com/dl.aspx?id=a398416d-5599-435e-b35d-3be52ee0c467.

Claim based on best published two-socket VMmark* 2.5.x performance (matched pair) result submitted to/published at https://www.vmware.com/a/vmmark/1/pair/1/ as of 16 March, 2016. New configuration: Fujitsu PRIMERGY* RX2540 M2 platform with 2x Intel® Xeon® processor E5-2699 v4 (22 cores, 44 threads), 512 GB memory, running VMware* ESXi 6.0.0 U1b Build 3380124 and vCenter Server 6.0.0 Build 3018524; Fibre Channel SAN storage. Score: 34.74 @ 28 Tiles, source: http://www.vmware.com/a/assets/vmmark/pdf/2016-03-31-Fujitsu-RX2540M2.pdf.

Claim based on best published two-socket VMmark* 2.5.x performance with server power result submitted to/published at http://www.vmware.com/a/vmmark/2/ as of 16 March 2016. New configuration: Fujitsu PRIMERGY* RX2540 M2 platform with 2x Intel® Xeon® processor E5-2699 v4 (22 cores, 44 threads), 512 GB memory, running VMware* ESXi 6.0.0 U1b Build 3380124 and vCenter Server 6.0.0 Build 3018524; Fibre Channel SAN storage. Score: PPKW Score: 38.3065 @ 28 Tiles. Source: http://www.vmware.com/a/assets/vmmark/pdf/2016-03-31-Fujitsu-RX2540M2-serverPPKW.pdf.

Claim based on best published two-socket SAP* Server Power 2-tier result published at  http://global.sap.com/solutions/benchmark/Power_Benchmark_results.htm as of 16 March, 2016. New configuration: Fujitsu Server PRIMERGY RX2540 M2 with 2x Intel® Xeon® processor E5-2699 v4 (2.2GHz, 22 cores), 512 GB memory, running Windows Server* 2012 R2 Standard Edition, SQL Server* 2012, SAP* enhancement package 5 for SAP ERP 6.0. Score: 4.27 watts/kSAPS. Source: The SAP certification number was not available at press time and can be found at the following Web page: http://global.sap.com/solutions/benchmark/Power_Benchmark_results.htm.

Claim based on best published one-node SPECpower*_ssj2008 results as of 16 March, 2016, currently under review with the SPECpower committee. Once accepted, result will be published at https://www.spec.org/power_ssj2008/results. New configuration: Fujitsu Server PRIMERGY* RX2560 M2 with 2x Intel® Xeon® processor E5-2699 v4, 64 GB memory, running Microsoft* Windows Server* 2012 R2 Standard, JVM version: Oracle Java HotSpot* 64-Bit Server VM (build 24.80-b11, mixed mode), version 1.7.0_80, Score: 12,079 overall ssj_ops/watt.

HPE:

Claim based on best published two-socket SPECfp*_base2006 results submitted to/published at https://www.spec.org/cpu2006/results as of 16 March, 2016. New configuration: HPE ProLiant* XL450 Gen9 with 2x Intel® Xeon® processor E5-2667 v4 (3.2 GHz, 8 cores), SUSE Linux Enterprise Server* 12 SP1, Kernel 3.12.49-11-default, Intel Compiler 16.0, Score: 125 (tied), source: submitted to www.spec.org.

Claim based on best published non-clustered TPC Benchmark* H @ 1TB result submitted to/published at www.tpc.org as of 16 March 2016. New configuration: HPE ProLiant* DL380 Gen9 with 2x Intel® Xeon® processor E5-2699 v4 on Microsoft* Windows Server* 2012 R2 Standard Edition using Microsoft SQL Server* 2016 Enterprise Edition scoring 678,492 QphH @ 1TB @ $0.64/QphH @ 1TB available 7/31/16, source: submitted to www.tpc.org.

Claim based on best published TPC Benchmark* Express-BigBench@3000 result published at www.tpc.org as of 25 March, 2016. New configuration: 9x HPE ProLiant* DL380 Gen9 & 3x DL360 Gen9 servers with 2x Intel® Xeon® processor E5-2697A v4 for worker nodes on Red Hat* Enterprise Linux 6.7 using Cloudera* Enterprise 5.6 scoring 337 BBQpm@3000 @ $1102.94/BBQpm@3000 available 3/31/16, source: submitted to www.tpc.org.

Claim based on best published SPECjbb*2015-Distributed result submitted to/published at www.spec.org as of 16 March, 2016. New configuration: HPE ProLiant* DL380 Gen9 with 2x Intel® Xeon® processor E5-2699 v4 (2.20GHz, 22 cores/44 threads, 55MB cache), 16x 16GB 2Rx4 PC4-2400T-R, on Red Hat* Enterprise Linux 7.2 scoring 120674 SPECjbb*2015-Distributed max-jOPS. Source: submitted to www.spec.org.

Claim based on best published SPECjbb*2015-Distributed result submitted to/published at www.spec.org as of 16 March 2016. New configuration: HPE ProLiant* DL360 Gen9 with 2x Intel® Xeon® processor E5-2699 v4 (2.20GHz, 22 cores/44 threads, 55MB cache), 16x 32 GB 2Rx4 PC4-2400T-R, on Red Hat* Enterprise Linux 7.2 scoring 55858 SPECjbb*2015-Distributed critical-jOPS. Source: submitted to www.spec.org.

Claim based on best published SPECjbb*2015-Composite result submitted to/published at www.spec.org as of 16 March 2016. New configuration: HPE ProLiant* ML350 Gen9 with 2x Intel® Xeon® processor E5-2699 v4 (2.20GHz, 22 cores/44 threads, 55MB cache), 16x 32 GB 2Rx4 PC4-2400T-R, on Red Hat* Enterprise Linux 7.2 scoring 104194 SPECjbb*2015-Composite max-jOPS. Source: submitted to www.spec.org.

Claim based on best published SPECjbb*2015-Composite result submitted to/published at www.spec.org as of 16 March, 2016. New configuration: HPE ProLiant* DL360 Gen9 with 2x Intel® Xeon® processor E5-2699 v4 (2.20GHz, 22 cores/44 threads, 55MB cache), 16x 32 GB 2Rx4 PC4-2400T-R, on Red Hat* Enterprise Linux 7.2 scoring 63386 SPECjbb*2015-Composite critical-jOPS. Source: submitted to www.spec.org.

Claim based on best published SPECjbb*2015-Multi-JVM result submitted to/published at
www.spec.org as of 16 March, 2016. New configuration: HPE ProLiant* DL360 Gen9 with
2x Intel® Xeon® processor E5-2699 v4 (2.20GHz, 22 cores/44 threads, 55MB cache),
16x 32 GB 2Rx4 PC4-2400T-R, on Red Hat* Enterprise Linux 7.2 scoring 119302 SPECjbb*2015 Multi-JVM Max-jOPS. Source: submitted to www.spec.org.

Huawei:

Claim based on best published two-socket SPECint*_rate_base2006 result submitted to/published at https://www.spec.org/cpu2006/results as of 16 March, 2016. New configuration: Huawei RH2288H V3 with 2x Intel® Xeon® processor E5-2699 v4 (22 cores, 44 threads), Red Hat* Enterprise Linux* 7.0, Intel Compiler 16.0, Score: 1760. (tied), source: submitted to www.spec.org.

Lenovo:

Claim based on best published two-socket SPECfp*_base2006 speed benchmark at https://www.spec.org/cpu2006/results as of 16 March, 2016. New configuration: Lenovo* System x*3650 M5 with 2x Intel® Xeon® processor E5-2667 v4 on SUSE* Linux Enterprise Server 12 SP1 using Intel Compiler 16.0 scoring 125, source: submitted to www.spec.org.

Claim based on best published two-socket x86 SPECfp*_rate_base2006 result submitted to/published at https://www.spec.org/cpu2006/results as of 16 March, 2016. New configuration: Lenovo* System x*3650 M5 with 2x Intel® Xeon® processor E5-2699 v4 (2.2 GHz, 22 cores), SUSE* Linux Enterprise Server 12 SP1 using Intel Compiler 16.0 scoring 1100, source: submitted to www.spec.org.

Claim based on best published two-socket x86 SPECvirt_sc*2013 result submitted to/published at https://www.spec.org/virt_sc2013/results as of 16 March, 2016. New configuration: Lenovo* System x*3650 M5 server with 2x Intel® Xeon® processor E5-2699 v4 on Red Hat* Enterprise Linux Server release 7 (KVM) scoring 2342 @ 132 VMs, source: submitted to www.spec.org.

Claim based on best published SPECvirt_sc*2013 PPW (Server and Storage Performance per Watt) result submitted to/published at https://www.spec.org/virt_sc2013/results as of 16 March, 2016. New configuration: Lenovo* System x*3650 M5 server with 2x Intel® Xeon® processor E5-2699 v4 on Red Hat* Enterprise Linux* Server release 7 (KVM) scoring  SPECvirt_sc2013_PPW 4.206 @ 132 VMs, source: submitted to www.spec.org.

Claim based on best published SPECvirt_sc*2013_ServerPPW (Server Performance per Watt) result submitted to/published at https://www.spec.org/virt_sc2013/results as of 16 March 2016. New configuration: Lenovo* System x*3650 M5 server with 2x Intel® Xeon® processor E5-2699 v4 on Red Hat* Enterprise Linux* Server release 7 (KVM) scoring  SPECvirt_sc2013_ServerPPW 4.206 @ 132 VMs, source: submitted to www.spec.org.

Claim based on non-clustered best published two-socket TPC benchmark* E result submitted to/published at http://www.tpc.org as of 16 March, 2016. New configuration: Lenovo* System x*3650 M5 with 2x Intel® Xeon® processor E5-2699 v4 2.2GHz, (2 processor, 44 cores, 88 threads), 512GB DDR4, running Windows Server* 2012 SE, SQL Server* 2016 Enterprise Edition, 2x 900GB SAS (RAID-1), 4x 800GB SAS SSD (RAID-10), 53x 800GB SAS SSD. Availability: July 31, 2016. Source: www.tpc.org/4076. Score: 4,938.14 tpsE, at a price of $117.91 USD/tpsE. 

Oracle:

Claim based on best published two-socket SPECjEnterprise*2010 result submitted to/published at https://www.spec.org/jEnterprise2010/results/jEnterprise2010.html as of 16 March, 2016. New configuration: Oracle WebLogic Server Standard Edition Release 12 on Oracle Server* X6-2 with 2x Intel® Xeon® processor E5-2699 v4 on Oracle* Linux x86_64 using Oracle Java HotSpot* 64-Bit Server VM, version 1.8 scoring 27509 EjOPS, source: submitted to www.spec.org.

SGI:

Claim based on best 2, 4, 8, 16, 32, and 64-node two-socket SPECmpiL*2007 benchmark results submitted to/published at https://www.spec.org/mpi2007/results as of 16 March, 2016. New configurations: SGI Rackable C2112-4GP3 with 2, 4, 8, and 16-node or ICE XA servers with 32 and 64-node 2x Intel® Xeon® processor E5-269x v4 using Intel Compiler 14.0, source: submitted to www.spec.org.

Claim based on best 1, 2, 4, 8, and 16-node two-socket SPECmpiM*2007 benchmark results submitted to/published at https://www.spec.org/mpi2007/results as of 16 March, 2016. New configuration: SGI Rackable C2112-4GP3 server with 2x Intel® Xeon® processor E5-2699 v4 using Intel Compiler 14.0 source: submitted to www.spec.org.

Supermicro:

Claim based on best published two-socket SPECfp*_base2006 speed benchmark at https://www.spec.org/cpu2006/results as of 16 March, 2016. New configuration: Supermicro SuperServer 6028TP-HTFR with 2x Intel® Xeon® processor E5-2667 v4 on SUSE* Linux Enterprise Server 12, Kernel 3.12.28-4-default, using Intel Compiler 16.0 scoring 125, source: submitted to www.spec.org.

Additional information: 5 6 7 8 9 10 11 12 13 14

Product and Performance Information

1E5 v4 up to 47% vs. previous-generation E5 v3 performance based on binomialcpu v3.0_AVX2 financial services workload results as of 16 March 2016) comparing 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 128 GB Total Memory on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Options per second Score: 106025 vs. 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Options per second Score: 156141 Higher is better. Data Source: Request Number: 1871
2E5 v4 up to 27% vs. previous-generation E5 v3 average performance based on key industry-standard benchmarks calculations submitted by OEMs as of 16 March 2016) comparing 2-socket Intel® Xeon® processor E5 v3 to v4 family.  Key industry benchmarks include: SPECint*_rate_base2006, SPECint*_base 2006 (Speed), SPECfp*_rate_base 2006, SPECfp*_base2006 (Speed), SPECmpiL*_base2007, SPECmpiM*_base2007, SPECompG*_base2012, SPECvirt_sc*2013, VMmark* 2.5 performance (matched pairs), TPC-E*, SPECjEnterprise*2010, Two-tier SAP SD* Windows*/Linux, 1-Node TPC-H* 1TB, TPCx-BB* and SPECjbb*2015 MultiJVM. See http://www.intel.com/performance/datacenter for full configuration details.
3E5 v4 up to 50% vs. previous-generation E5 v3 average performance per watt improvement based on key industry-standard benchmarks calculations submitted by OEMs as of 16 March 2016) comparing 2-socket Intel® Xeon® processor E5 v3 to v4 family.  Key industry benchmarks include: SPECvirt_sc*2013_Server PPW, SPECvirt_sc*2013_PPW, SPEC power_ ssj*2008 and VMmark 2.5 server power. See http://www.intel.com/performance/datacenter for full configuration details.
4

(E5 v4 up to 2.4x more VMs/server vs. E5 v2 performance at 58% lower cost per VM based on SPECvirt_sc*2013 virtualization infrastructure consolidation workload submitted/published at https://www.spec.org/virt_sc2013/results/ as of 16 March 2016) comparing 1-Node, 2 x Intel® Xeon® Processor E5-2697 v2 on IBM System x*3650 M4* with 512 GB Total Memory on Red Hat Enterprise Linux* 6.4. Data Source: https://www.spec.org/virt_sc2013/results/res2013q3/virt_sc2013-20130820-00004-perf.html, Score: 947 @ 53 VMs vs. 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Lenovo System x*3650 M5* with 512 GB Total Memory on Red Hat Enterprise Linux* 7. Data Source: submitted to www.spec.org, Score: 2325 @ 132 VMs Higher is better.  Four year TCO analysis for 58% lower cost per VM at ~same total performance/VM level details:

a. New 10x 2-socket Intel® Xeon® processor E5-2699 v4 estimates (total 4-year cost of $124,597 supporting 1320 VMs @ $94.39/VM)

i. Server maintenance ($2399/server) = $95,960

ii. Power and cooling ($0.10/KwH @ 60% CPU utilization) = $21,837

iii. Rack/Floor space ($155/server) = $6,200

iv. Networking ($15/server) = $600

b. Existing 25x 2-socket Intel® Xeon® processor E5-2697 v2 estimates (total 4-year cost of $298,247 supporting 1325 VMs @ $225.09/VM)

i. Server maintenance ($2399/server) = $239,900

ii. Power and cooling ($0.10/KwH @ 60% CPU utilization) = $41,347

iii. Rack/Floor space ($155/server) = $15,500

iv. Networking ($15/server) = $1,500 [SRA1]

 

5

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 information, go to http://www.intel.com.au/content/www/au/en/benchmarks/benchmark.html.

6

Intel does not control or audit the design or implementation of third party benchmarks or websites referenced in this document. Intel encourages all of its customers to visit the referenced websites or others where similar performance benchmarks are reported and confirm whether the referenced benchmarks are accurate and reflect performance of systems available for purchase.

7

Relative performance is calculated by assigning a baseline value of 1.0 to one benchmark result, and then dividing the actual benchmark result for the baseline platform into each of the specific benchmark results of each of the other platforms, and assigning them a relative performance number that correlates with the performance improvements reported.

8

Optimization Notice: Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel® microprocessors. These optimizations include Intel® Streaming SIMD Extensions 2 (Intel® SSE2), Intel® SSE3, and Supplemental Streaming SIMD Extensions 3 (SSSE3) instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel® microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice Revision #20110804

9

Intel® technologies' features and benefits depend on system configuration and may require enabled hardware, software, or service activation. Performance varies depending on system configuration. No computer system can be absolutely secure. Check with your software vendor, system manufacturer, or retailer, or learn more at http://www.intel.com/software/tsx.

10

SPEC* and the benchmark names SPECint*, SPECfp*, SPECjbb*, SPECjEnterprise*, SPECvirt_sc*, SPECpower_ssj*, SPECompG*, and SPECmpi* are registered trademarks of the Standard Performance Evaluation Corporation.

11

TPC Benchmark, TPCx-BB, TPC-C, tpmC, TPC-H, QphH, TPC-E, and tpsE are trademarks of the Transaction Processing Council. See www.tpc.org for more information.

12

SAP and SAP NetWeaver are the registered trademarks of SAP AG in Germany and in several other countries. See www.sap.com/benchmark for more information.

13

VMware* is a registered trademark and VMmark* is a trademark of VMware*, Inc.

14

Intel® processors of the same SKU may vary in frequency or power as a result of natural variability in the production process.

Product and Performance Information

1E5 v4 up to 47% vs. previous-generation E5 v3 performance based on binomialcpu v3.0_AVX2 financial services workload results as of 16 March 2016) comparing 1-Node, 2 x Intel® Xeon® Processor E5-2699 v3 on Grantley-EP (Wellsburg) with 128 GB Total Memory on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Options per second Score: 106025 vs. 2 x Intel® Xeon® Processor E5-2699 v4 on Grantley-EP (Wellsburg) with 128 GB Total Memory on Red Hat Enterprise Linux* 6.4 kernel 2.6.32-358, Options per second Score: 156141 Higher is better. Data Source: Request Number: 1871
2E5 v4 up to 27% vs. previous-generation E5 v3 average performance based on key industry-standard benchmarks calculations submitted by OEMs as of 16 March 2016) comparing 2-socket Intel® Xeon® processor E5 v3 to v4 family.  Key industry benchmarks include: SPECint*_rate_base2006, SPECint*_base 2006 (Speed), SPECfp*_rate_base 2006, SPECfp*_base2006 (Speed), SPECmpiL*_base2007, SPECmpiM*_base2007, SPECompG*_base2012, SPECvirt_sc*2013, VMmark* 2.5 performance (matched pairs), TPC-E*, SPECjEnterprise*2010, Two-tier SAP SD* Windows*/Linux, 1-Node TPC-H* 1TB, TPCx-BB* and SPECjbb*2015 MultiJVM. See http://www.intel.com/performance/datacenter for full configuration details.
3E5 v4 up to 50% vs. previous-generation E5 v3 average performance per watt improvement based on key industry-standard benchmarks calculations submitted by OEMs as of 16 March 2016) comparing 2-socket Intel® Xeon® processor E5 v3 to v4 family.  Key industry benchmarks include: SPECvirt_sc*2013_Server PPW, SPECvirt_sc*2013_PPW, SPEC power_ ssj*2008 and VMmark 2.5 server power. See http://www.intel.com/performance/datacenter for full configuration details.
4

(E5 v4 up to 2.4x more VMs/server vs. E5 v2 performance at 58% lower cost per VM based on SPECvirt_sc*2013 virtualization infrastructure consolidation workload submitted/published at https://www.spec.org/virt_sc2013/results/ as of 16 March 2016) comparing 1-Node, 2 x Intel® Xeon® Processor E5-2697 v2 on IBM System x*3650 M4* with 512 GB Total Memory on Red Hat Enterprise Linux* 6.4. Data Source: https://www.spec.org/virt_sc2013/results/res2013q3/virt_sc2013-20130820-00004-perf.html, Score: 947 @ 53 VMs vs. 1-Node, 2 x Intel® Xeon® Processor E5-2699 v4 on Lenovo System x*3650 M5* with 512 GB Total Memory on Red Hat Enterprise Linux* 7. Data Source: submitted to www.spec.org, Score: 2325 @ 132 VMs Higher is better.  Four year TCO analysis for 58% lower cost per VM at ~same total performance/VM level details:

a. New 10x 2-socket Intel® Xeon® processor E5-2699 v4 estimates (total 4-year cost of $124,597 supporting 1320 VMs @ $94.39/VM)

i. Server maintenance ($2399/server) = $95,960

ii. Power and cooling ($0.10/KwH @ 60% CPU utilization) = $21,837

iii. Rack/Floor space ($155/server) = $6,200

iv. Networking ($15/server) = $600

b. Existing 25x 2-socket Intel® Xeon® processor E5-2697 v2 estimates (total 4-year cost of $298,247 supporting 1325 VMs @ $225.09/VM)

i. Server maintenance ($2399/server) = $239,900

ii. Power and cooling ($0.10/KwH @ 60% CPU utilization) = $41,347

iii. Rack/Floor space ($155/server) = $15,500

iv. Networking ($15/server) = $1,500 [SRA1]

 

5

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 information, go to http://www.intel.com.au/content/www/au/en/benchmarks/benchmark.html.

6

Intel does not control or audit the design or implementation of third party benchmarks or websites referenced in this document. Intel encourages all of its customers to visit the referenced websites or others where similar performance benchmarks are reported and confirm whether the referenced benchmarks are accurate and reflect performance of systems available for purchase.

7

Relative performance is calculated by assigning a baseline value of 1.0 to one benchmark result, and then dividing the actual benchmark result for the baseline platform into each of the specific benchmark results of each of the other platforms, and assigning them a relative performance number that correlates with the performance improvements reported.

8

Optimization Notice: Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel® microprocessors. These optimizations include Intel® Streaming SIMD Extensions 2 (Intel® SSE2), Intel® SSE3, and Supplemental Streaming SIMD Extensions 3 (SSSE3) instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel® microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice Revision #20110804

9

Intel® technologies' features and benefits depend on system configuration and may require enabled hardware, software, or service activation. Performance varies depending on system configuration. No computer system can be absolutely secure. Check with your software vendor, system manufacturer, or retailer, or learn more at http://www.intel.com/software/tsx.

10

SPEC* and the benchmark names SPECint*, SPECfp*, SPECjbb*, SPECjEnterprise*, SPECvirt_sc*, SPECpower_ssj*, SPECompG*, and SPECmpi* are registered trademarks of the Standard Performance Evaluation Corporation.

11

TPC Benchmark, TPCx-BB, TPC-C, tpmC, TPC-H, QphH, TPC-E, and tpsE are trademarks of the Transaction Processing Council. See www.tpc.org for more information.

12

SAP and SAP NetWeaver are the registered trademarks of SAP AG in Germany and in several other countries. See www.sap.com/benchmark for more information.

13

VMware* is a registered trademark and VMmark* is a trademark of VMware*, Inc.

14

Intel® processors of the same SKU may vary in frequency or power as a result of natural variability in the production process.