Intel® Xeon® Processor E7 Family

World Record Benchmark Performance

- Tagged AsServers, Intel® Xeon® Processor E7 Family

Intel® Xeon® Processor E7 Family

Top-of-the-line, scalable performance with advanced reliability for your most business-critical applications, the Intel® Xeon® processor E7-8800/4800/2800 product families increase business productivity allowing you to confidently run business-class applications. The next generation platforms enable faster responses to customers, new trends, and competitors. Your employees can get more done and respond to customers faster with less downtime and easier access to information. Get more computing power when you need it with performance that adapts to spikes in your workload ¹ [with Intel® Turbo Boost Technology 2.0].

Platform Performance Highlights

Over 25 world record performance benchmark results with Intel® Xeon® processor E7 family-based platforms (as of May 8, 2012)

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
Server-side Java* Middle-ware – SPECjbb*2005	UCS* C460 M2 / 4-socket	Oracle Java* 6 Update 27 JVM	2,798,763bops; 699,691 bops/JVM (+38%)	Top 4-socket result
Technical Computing - SPECfp*_rate_base2006	UCS* C460 M2 / 4-socket	Intel® Compiler XE 12.1; SUSE* 11 Linux OS	739 base score (+28%)	Top 4-socket x86 result
General Purpose Computing – SPECint*_rate_base2006	UCS* C460 M2 / 4-socket	Intel® Compiler XE 12.1; Red Hat* Enterprise Linux 6.1	1100 base score (+37%)	Top 4-socket x86 result
High-Performance Computing – SPECompM*_base2001	UCS* C460 M2 / 4-socket	Intel® Compiler XE2011; Red Hat* 5.5 Linux OS	115,176 base score (+15%)	Top 4-chip result
High-Performance Computing – SPECompL*_base2001	UCS* C460 M2 / 4-socket	Intel® Compiler XE2011; Red Hat* 5.5 Linux OS	727,635 base score (+18%)	Top 4-chip result
Business Intelligence – TPC Benchmark* H @ 1,000GB	UCS* C460 M2 / 4-socket	Microsoft SQL Server* 2008 R2	134,117 QphH @ $1.30/QphH @ 1000GB (+32%)	Top 4-socket non-clustered Microsoft SQL Server* result
Datacenter virtualized server management – VMmark* 2.1	4-node UCS* C460 M2 / 4-socket (16 sockets)	VMware* ESX 4.1 U1 / vCenter* 4.1.0	35.06 score @ 35 tiles (N/A)	World Record

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
Application Server – SPECjEnterprise*2010	PowerEdge* R910 / 4-socket	Oracle Weblogic* Server Standard Edition Release 10.3.4	11,946.60 SPECjEnterprise2010 EjOPS(2.3x)	Top 4-socket single-node result
Business Intelligence – TPC Benchmark* H @ 300GB	PowerEdge* R910 / 4-socket	VectorWise 1.6; Red Hat* Enterprise Linux 6.0	400,931.8 QphH @ $0.35/QphH @ 300GB (N/A)	World Record non-clustered columnar database result
Business Intelligence – TPC Benchmark* H @ 1,000GB	PowerEdge* R910 / 4-socket	VectorWise 1.6; Red Hat* Enterprise Linux 6.0	436,788.9 QphH @ $0.88/QphH @ 1000GB (N/A)	World Record non-clustered columnar database result

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
Datacenter virtualized server management – VMmark* 2.1	PRIMERGY* RX600 S6 / 4-socket	VMware* ESX 4.1 U1 / vCenter* 4.1.0	18.2 score @ 18 tiles (N/A)	Top 4-socket result (matched pair)
Datacenter virtualized server management – VMmark* 2.1	PRIMERGY* RX900 S2 / 8-socket	VMware* ESX 4.1 U1 / vCenter* 4.1.0	29.03 score @ 30 tiles (N/A)	World Record (matched pair)

Benchmark

Partner/Platform

Software Details

Results (Up to relative gain over Intel® Xeon® processor X7560)

Importance

Datacenter virtualized server management – VMmark* 2.1

PRIMERGY* RX600 S6 / 4-socket

VMware* ESX 4.1 U1 / vCenter* 4.1.0

18.2 score @ 18 tiles (N/A)

Top 4-socket result

(matched pair)

Datacenter virtualized server management – VMmark* 2.1

PRIMERGY* RX900 S2 / 8-socket

VMware* ESX 4.1 U1 / vCenter* 4.1.0

29.03 score @ 30 tiles (N/A)

World Record (matched pair)

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
General Purpose Computing – SPECint*_rate_base2006	ProLiant* DL980 G7 / 8-sockets	Intel® Compiler XE2011; SUSE* LINUX Enterprise Server 11	2070 base score (+37%)	Top 8-socket x86 result
Server-side Java* Middle-ware – SPECjbb*2005	ProLiant* DL980 G7 / 8-sockets	Oracle Java* 6 Update 25 JVM	5,307,339bops; 663,417 bops/JVM (+39%)	Top 8-socket result
Business Intelligence – TPC Benchmark* H @ 1,000GB	ProLiant* DL980 G7 / 8-socket	Microsoft SQL Server* 2008 R2	219,887 QphH @ $1.86/QphH @ 1000GB (2.2x scale over 4-socket Intel® Xeon® processor X7560)	Top 8-socket non-clustered result
Virtualized Consolidation – SPECvirt_sc*2010	ProLiant* DL580 G7 / 4-socket	Red Hat* Enterprise LINUX Server 6.1 KVM	4,682 score @ 288 VMs (+70%)	Top 4-socket result
Virtualized Consolidation – SPECvirt_sc*2010	ProLiant* DL980 G7 / 8-socket	Red Hat* Enterprise LINUX Server 6.1 KVM	8,956 score @ 552 VMs (+64%)	World Record

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
Enterprise Resource Planning – SAP* SD 2-Tier	System x* 3850 X5 / 4-socket	SAP enhancement package 4 for SAP ERP 6.0; IBM DB2 9.7	14,000 benchmark users (+33%)	Top 4-socket Microsoft Windows* result
Enterprise Resource Planning – SAP* SD 2-Tier	System x* 3850 X5 / 8-sockets	SAP enhancement package 4 for SAP ERP 6.0; IBM DB2* 9.7	25,500 benchmark users (+29%)	Top 8-socket Microsoft Windows* result
Business Processing OLTP – TPC Benchmark* C	System x* 3850 X5 / 4-socket	IBM DB2* 9.7	3,014,684 @ $0.59 /tpmC (+31%)	Top 4-socket result
Business Processing OLTP – TPC Benchmark* E	System x* 3850 X5 / 4-socket	Microsoft SQL Server* 2008 R2	2,862 tpsE @ $129.66/tpsE (+40%)	Top 4-socket result

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
Business Processing OLTP – TPC Benchmark* E	Express5800/A1080a-E / 8-sockets	Microsoft SQL Server* 2012 Enterprise Edition	4,614 tpsE @ $450.18 /tpsE (+21%)	World Record

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
Business Processing OLTP – TPC Benchmark* C	Sun Fire* X4800 M2 / 8-sockets	Oracle* Database 11g Enterprise Edition	5,055,888 tpmC @ $0.89 /tpmC (N/A)	Top 8-socket result
Application Server – SPECjEnterprise*2010	Sun Fire* X4800 M2 / 8-sockets	Oracle Weblogic* Server Standard Edition Release 12.1.1	27,150 EjOPS (N/A)	Single-node World Record
Enterprise Resource Planning – SAP SD* Parallel	Sun Fire* X4800 M2 / 8-sockets	SAP enhancement package 4 for SAP ERP 6.0; Oracle 11g* Real Application Clusters (RAC); Solaris* 10	180,000 benchmark users; 1,016,380 SAPS (N/A)	Multi-node World Record

Benchmark	Partner/Platform	Software Details	Results (Up to relative gain over Intel® Xeon® processor X7560)	Importance
General Purpose Computing - SPECint*_rate_base2006	Altix* UV1000 / 128-socket	Intel® Compiler XE2011; SUSE* Linux OS	27,900 base score (+35%)	World Record
Technical Computing - SPECfp*_rate_base2006	Altix* UV1000 / 128-socket	Intel® Compiler XE2011; SUSE* Linux OS	20,500 base score (+28%)	World Record
Server-side Java* Middle-ware – SPECjbb*2005	Altix* UV1000 / 64-socket	Oracle Java* 6 Update 24 JVM	32,643,008 bops; 510,047 bops/JVM (+24%)	World Record
Memory Bandwidth – STREAM	Altix* UV1000 / 192-sockets E7-4870 + 64-sockets E7-8837	Intel® Compiler XE2011; SUSE* Linux OS	5.8 TB/s TRIAD (N/A)	World Record

Configuration Details

Best benchmark results published to SPEC.org, TPC.org, and VMware.com* web sites as of May 8, 2012.

Cisco

Server-side Java* Middle-ware performance – using SPECjbb*2005

Comparison based on best performing 4-socket server systems published at www.spec.org as of 6 March 2012. SPEC® and the benchmark name SPECjbb® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECjbb2005, see www.spec.org/jbb2005/.

Top 4-socket result: Cisco UCS* C460 M2 with four Intel® Xeon® processors E7-4870 (30M cache, 2.40 GHz, 6.40 GT/s Intel QPI) ran on Oracle Java* 6 Update 27 JVM referenced as published at 2,798,763 SPECjbb*2005 bops and 699,691 bops/JVM. Source: http://www.spec.org/osg/jbb2005/results/res2011q4/jbb2005-20111004-01018.html
(+38%) in comparison to Cisco UCS* C460 M1 with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at 2,021,525 SPECjbb*2005 bops and 126,345 bops/JVM. Source: http://www.spec.org/osg/jbb2005/results/res2010q2/jbb2005-20100331-00838.html

Technical Computing: Floating-point throughput performance using - SPECfp*_rate_base2006

Comparison based on best performing 4-socket x86-based server systems published at www.spec.org as of 6 March 2012. SPEC® and the benchmark name SPECfp® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECcpu2006, see www.spec.org/cpu2006/.

Top 4-socket x86 result: Cisco UCS* C460 M2 with four Intel® Xeon® processors E7-4870 (30M cache, 2.40 GHz, 6.40 GT/s Intel QPI) ran using Intel Compiler 12.1 referenced as published at 739 baseline score. Source: http://www.spec.org/cpu2006/results/res2012q1/cpu2006-20111223-19280.html
(+28%) in comparison to Cisco UCS* C460 M1 with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at 578 baseline score. Source: http://www.spec.org/cpu2006/results/res2011q2/cpu2006-20110329-15466.html

General Purpose Computing: Integer throughput performance using – SPECint*_rate_base2006

Comparison based on best performing 4-socket x86-based server systems published at www.spec.org as of 6 March 2012. SPEC® and the benchmark name SPECint® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECcpu2006, see www.spec.org/cpu2006/.

Top 4-socket x86 result: Cisco UCS* C460 M2 with four Intel® Xeon® processors E7-4870 (30M cache, 2.40 GHz, 6.40 GT/s Intel QPI) ran using Intel Compiler 12.1 referenced as published at 1100 baseline score. Source: http://www.spec.org/cpu2006/results/res2012q1/cpu2006-20111223-19278.html
(+37%) in comparison to Cisco UCS* C460 M1 with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at 802 baseline score. Source: http://www.spec.org/cpu2006/results/res2011q3/cpu2006-20110523-16565.html

High-Performance Computing – SPECompM_base2001 / High-Performance Computing – SPECompL_base2001

OpenMP* and shared-memory systems performance using SPEComp*2001 SPEComp* results on Intel® Xeon® processor E7-4800 series-based server were obtained using 80 OpenMP threads over four sockets. Top 4-chips record SPEComp*base2001 claims based on published result using Cisco UCS servers with all other 4-chips results. SPEC® and the benchmark name SPEComp® are registered trademarks of the Standard Performance Evaluation Corporation. For the latest SPEC OMP benchmark results, see http://www.spec.org/omp/results.

Top 4-chip SPECompMbase2001 result: Cisco UCS* C460 M2 server platform with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI), Intel® Compiler XE2011. Referenced as published SPECompMbase2001 baseline score of 115,176. Source: http://www.spec.org/omp/results/res2011q2/omp2001-20110406-00413.html.
(+15%) in comparison to Cisco UCS* C460 M1 with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at SPECompMbase2001 baseline score of 100,258. Source: http://www.spec.org/omp/results/res2010q2/omp2001-20100329-00380.html.
Top 4-chip SPECompLbase2001 result: Cisco UCS* C460 M2 server platform with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI), Intel® Compiler XE2011. Referenced as published SPECompLbase2001 baseline score of 725,475. Source: http://www.spec.org/omp/results/res2011q2/omp2001-20110406-00414.html.
(+18%) in comparison to Oracle Sun Fire* X4470 server platform with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at SPECompLbase2001 baseline score of 615,790. Source: http://www.spec.org/omp/results/res2010q3/omp2001-20100617-00384.html.

Business Intelligence – performance using TPC Benchmark* H @ 1,000 GB

Comparison based on best performing 4-socket, non-clustered server systems using 1,000 GB Microsoft SQL Server* scale factor databases published at www.tpc.org as of 6 March 2012. TPC® and the benchmark name TPC Benchmark® H are registered trademarks of the Transaction Processing Performance Council. For ranked results on TPC-H, see http://www.tpc.org/tpch/results/tpch_perf_results.asp?resulttype=noncluster.

Top 4-socket non-clustered result: Cisco UCS* C460 M2 server platform with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI) using Microsoft SQL Server* 2008 R2 database. Referenced as published score of 134,117 QphH@1000GB, $1.30 / QphH@1000GB, available 12/7/11. Source: http://www.tpc.org/tpch/results/tpch_result_detail.asp?id=111120801.
(+32%) in comparison to IBM System x* 3850 X5 with IBM MAX5 server platform with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) using Microsoft SQL Server* 2008 R2 database. Referenced as published score of 101,719 QphH, $1.76 / QphH, available 3/3/11. Source: http://www.tpc.org/tpch/results/tpch_result_detail.asp?id=111030301.

Datacenter virtualized server management – performance using VMmark* 2.1

Comparison based on all server systems published at http://www.vmware.com/a/vmmark/ as of 6 March 2012. VMware® and the benchmark name VMmark®2 are registered trademarks of the VMware Corporation. For more information about VMmark, see http://www.vmware.com/products/vmmark/overview.html.

World record result: Non-matched pair Cisco UCS* C460 M2 server platforms each with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published score of 35.06 @ 35 tiles. Source: http://www.vmware.com/a/assets/vmmark/pdf/2011-09-20-Cisco-C460M2.pdf

Dell

Application Server: Java* performance using – SPECjEnterprise* 2010

Comparison based on best performing 4-socket, single-node server systems published at www.spec.org as of 6 March 2012. SPEC® and the benchmark name SPECjEnterprise® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECjEnterprise2010, see http://www.spec.org/jEnterprise2010/.

Top 4-socket single-node result: Dell PowerEdge* R910 server platform four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published at EjOPS score of 11,947. Source: http://www.spec.org/jEnterprise2010/results/res2011q2/jEnterprise2010-20110323-00021.html.
(2.3x) in comparison to IBM System x* 3850 X5 server platform with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at EjOPS score of 5,141. Source: http://www.spec.org/jEnterprise2010/results/res2010q2/jEnterprise2010-20100407-00010.html.

Business Intelligence – performance using TPC Benchmark* H @ 300 GB

Comparison based on all non-clustered server systems using 300 GB scale factor published at www.tpc.org as of 6 March 2012. TPC® and the benchmark name TPC Benchmark® H are registered trademarks of the Transaction Processing Performance Council. For ranked results on TPC-H, see http://www.tpc.org/tpch/results/tpch_perf_results.asp?resulttype=noncluster.

World record non-clustered columnar database result: Dell PowerEdge* R910 server platform four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI) using VectorWise* 1.6 columnar database. Referenced as published score of 400,931 QphH@300GB, $0.35 / QphH@300GB, available 5/3/11. Source: http://www.tpc.org/tpch/results/tpch_result_detail.asp?id=111050401.

Business Intelligence – performance using TPC Benchmark* H @ 1,000 GB

Comparison based on all non-clustered server systems using 1,000 GB scale factor published at www.tpc.org as of 6 March 2012. TPC® and the benchmark name TPC Benchmark® H are registered trademarks of the Transaction Processing Performance Council. For ranked results on TPC-H, see http://www.tpc.org/tpch/results/tpch_perf_results.asp?resulttype=noncluster.

World record non-clustered columnar database result: Dell PowerEdge* R910 server platform four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI) using VectorWise* 1.6 columnar database. Referenced as published score of 436,788 QphH@1000GB, $0.88 / QphH@1000GB, available 5/3/11. Source: http://www.tpc.org/tpch/results/tpch_result_detail.asp?id=111050402.

Fujitsu

Datacenter virtualized server management – performance using VMmark* 2.1

Top 4-socket result: Matched-pair Fujitsu PRIMERGY* RX600 S6 server platforms each with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published score of 18.2 @ 18 tiles. Source: http://www.vmware.com/a/assets/vmmark/pdf/2011-11-29-Fujitsu-RX600S6.pdf.
Matched pair world record result: Matched-pair Fujitsu PRIMERGY* RX900 S2 server platforms each with eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published score of 29.03 @ 30 tiles. Source: http://www.vmware.com/a/assets/vmmark/pdf/2011-08-23-Fujitsu-RX900S2.pdf.

Hewlett-Packard

General Purpose Computing - Integer throughput performance using SPECint*_rate_base2006

Comparison based on best performing 8-socket x86-based server systems published at www.spec.org as of 6 March 2012. SPEC® and the benchmark name SPECint® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECcpu2006, see www.spec.org/cpu2006/.

Top 8-socket x86 result: HP ProLiant* DL980 G7 server platform with eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published baseline score of 2070. Source: http://www.spec.org/cpu2006/results/res2011q4/cpu2006-20110923-18595.html.
(+37%) in comparison to HP ProLiant* DL980 G7 server platform with eight Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at baseline score of 1510. Source: http://www.spec.org/cpu2006/results/res2011q1/cpu2006-20110128-14145.html.

Server-side Java* Middle-ware – performance using SPECjbb*2005

Comparison based on best performing 8-socket server systems published at www.spec.org as of 6 March 2012. SPEC® and the benchmark name SPECjbb® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECjbb2005, see www.spec.org/jbb2005/.

Top 8-socket result: HP ProLiant* DL980 G7 server platform with eight Intel® Xeon® processors E7-8870 (30M cache, 2.40 GHz, 6.40 GT/s Intel QPI) ran on Oracle Java* 6 Update 25 JVM referenced as published at 5,307,339 SPECjbb*2005 bops and 663,417 bops/JVM. Source: http://www.spec.org/osg/jbb2005/results/res2011q3/jbb2005-20110815-01005.html.
(+39%) in comparison to HP ProLiant* DL980 G7 server platform with eight Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) published at 3,816,799 SPECjbb*2005 bops and 119,275 bops/JVM. Source: http://www.spec.org/osg/jbb2005/results/res2010q3/jbb2005-20100816-00914.html.

Business Intelligence – performance using TPC Benchmark* H @ 1,000 GB

Comparison based on best performing 8-socket, non-clustered server systems using 1,000 GB Microsoft SQL Server* scale factor databases published at www.tpc.org as of 6 March 2012. TPC® and the benchmark name TPC Benchmark® H are registered trademarks of the Transaction Processing Performance Council. For ranked results on TPC-H, see http://www.tpc.org/tpch/results/tpch_perf_results.asp?resulttype=noncluster.

Top 8-socket non-clustered result: HP ProLiant* DL980 G7 server platform eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI) using Microsoft SQL Server* 2008 R2 database. Referenced as published score of 219,887 QphH@1000GB, $1.86 / QphH@1000GB, available 8/30/11. Source: http://www.tpc.org/tpch/results/tpch_result_detail.asp?id=111090101.
(2.2x scale over 4-socket) in comparison to IBM System x* 3850 X5 with IBM MAX5 server platform with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) using Microsoft SQL Server* 2008 R2 database. Referenced as published score of 101,719 QphH@1000GB, $1.76 / QphH@1000GB, available 3/3/11. Source: http://www.tpc.org/tpch/results/tpch_result_detail.asp?id=111030301.

Virtualized Consolidation performance on SPECvirt_sc*2010

Comparison based on best performing 4- or 8-socket server systems published at www.spec.org as of 6 March 2012. SPEC® and the benchmark name SPECvirt_sc® are registered trademarks of the Standard Performance Evaluation Corporation. For more information on SPECvirt_sc2010, visit http://www.spec.org/virt_sc2010.

Top 4-socket result: HP ProLiant* DL580 G7 server platform with four Intel Xeon processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI) using Red Hat* Enterprise LINUX Server 6.1 (KVM). Referenced as published score of 4,682 @ 288 VMs. Source: http://www.spec.org/virt_sc2010/results/res2011q4/virt_sc2010-20111115-00039-perf.html.
(+68%) in comparison to IBM System x* 3850 X5 server platform with four Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) using VMware* ESXi 4.1. Referenced as published score of 2,742 @ 168 VMs. Source: http://www.spec.org/virt_sc2010/results/res2011q1/virt_sc2010-20110208-00023-perf.html.
World record result: HP ProLiant* DL980 G7 server platform with eight Intel Xeon processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI) using Red Hat* Enterprise LINUX Server 6.1 (KVM). Referenced as published score of 8,956 @ 552 VMs. Source: http://www.spec.org/virt_sc2010/results/res2011q4/virt_sc2010-20111212-00040-perf.html.
(+64%) in comparison to IBM System x* 3850 X5 server platform with eight Intel Xeon processors X7560 (24M cache, 2.26 GHz, 6.40 GT/s Intel QPI) Red Hat* Enterprise LINUX Server 6.0 (KVM). Referenced as published score of 5,467 @ 336 VMs. Source: http://www.spec.org/virt_sc2010/results/res2010q4/virt_sc2010-20101130-00019-perf.html.

IBM

Enterprise Resource Planning performance on SAP* SD 2-Tier

Comparison based on best performing 4- and 8-socket servers systems published at www.sap.com as of 6 March 2012. SAP and SAP NetWeaver are the registered trademarks of SAP AG in Germany and in several other countries. For more information and scores, see http://www.sap.com/solutions/benchmark/sd2tier.epx.

Top 4-socket x86 result: IBM System x* 3850 X5 server platform with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published result of 14,000 benchmark users using SAP enhancement package 4 for SP ERP 6.0 and IBM DB2* 9.7 database. Certification #2011015.
(+33%) in comparison to HP ProLiant* DL580 G7 server platform with four Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published score of 10,490 benchmark users using SAP* Enhancement package 4 for SAP* ERP 6.0 and Microsoft SQL Server* database. Certification #2010032.
Top 8-socket x86 result: IBM System x* 3850 X5 server platform with eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published result of 25,500 benchmark users using SAP enhancement package 4 for SP ERP 6.0 and IBM DB2* 9.7 database. Certification #2011034.
(+29%) in comparison to IBM System x* 3850 X5 server platform with eight Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published score of 19,700 benchmark users using SAP* Enhancement package 4 for SAP* ERP 6.0 and IBM DB2* 9.7 database. Certification #2010044.

Business Processing OLTP: Database performance on TPC Benchmark* C

Comparison based on best performing 4-socket server systems published at www.tpc.org as of April 2012. TPC Benchmark™, TPC-C, and tpmC are trademarks of the Transaction Processing Performance Council. For more information, see http://www.tpc.org/tpce/results/tpce_perf_results.asp.

Top 4-socket result: IBM System x*3850 X5 server platform with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published result of 3,014,684 tpmC at $0.59/tpmC available 9/22/11. Source: http://www.tpc.org/tpcc/results/tpcc_result_detail.asp?id=111071101.
(+31%) in comparison to IBM System x*3850 X5 server platform with four Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel QPI). Referenced as published score of 2,308,099 tpmC at $0.60/tpmC available 5/20/11. Source: http://www.tpc.org/tpcc/results/tpcc_result_detail.asp?id=110111601.

Business Processing OLTP: Database performance on TPC Benchmark* E

Comparison based on all or 4-socket best performing server systems published at www.tpc.org as of 6 March 2012. TPC Benchmark™, TPC-E, and tpsE are trademarks of the Transaction Processing Performance Council. For more information, see http://www.tpc.org/tpce/results/tpce_perf_results.asp.

Top 4-socket result: IBM System x* 3850 X5 server platform with four Intel® Xeon® processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published result of 2,862 tpsE at $129.66/tpsE available 6/27/11. Source: http://www.tpc.org/tpce/results/tpce_result_detail.asp?id=111062701.
(+40%) in comparison to Fujitsu PRIMERGY* RX600 S5 server platform with four Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published result of 2,046.96 tpsE at $193.68/tpsE available 9/1/10. Source: http://www.tpc.org/tpce/results/tpce_result_detail.asp?id=110061801.
World record result: IBM System x* 3850 X5 server platform with eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published result of 4,593.17 tpsE at $140.56/tpsE available 8/26/11. Source: http://www.tpc.org/tpce/results/tpce_result_detail.asp?id=111082601.
(+21%) in comparison to Fujitsu PRIMERGY* RX900 S1 server platform with eight Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published result of 3,800 tpsE at $245.82/tpsE available 10/1/10. Source: http://www.tpc.org/tpce/results/tpce_result_detail.asp?id=110092401.

NEC

Business Processing OLTP: Database performance on TPC Benchmark* E

Comparison based on all server systems published at www.tpc.org as of 8 May 2012. TPC Benchmark™, TPC-E, and tpsE are trademarks of the Transaction Processing Performance Council. For more information, see http://www.tpc.org/tpce/results/tpce_perf_results.asp.

World record result: NEC Express*5800/A1080a-E server platform with eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published result of 4,614.22 tpsE at $450.18/tpsE available 4/2/12. Source: http://www.tpc.org/tpce/results/tpce_result_detail.asp?id=112032702.
(+21%) in comparison to Fujitsu PRIMERGY* RX900 S1 server platform with eight Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published result of 3,800 tpsE at $245.82/tpsE available 10/1/10. Source: http://www.tpc.org/tpce/results/tpce_result_detail.asp?id=110092401.

Oracle

Business Processing OLTP: Database performance on TPC Benchmark* C

Comparison based on best performing 8-socket server systems published at www.tpc.org as of April 2012. TPC Benchmark™, TPC-C, and tpmC are trademarks of the Transaction Processing Performance Council. For more information, see http://www.tpc.org/tpce/results/tpce_perf_results.asp.

Top 8-socket result: Oracle Sun Fire* X4800 M2 server platform with eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published result of 5,055,888 tpmC at $0.89/tpmC available 6/26/12. Source: http://www.tpc.org/tpcc/results/tpcc_result_detail.asp?id=112032701.

Application Server: Java* performance using SPECjEnterprise* 2010

Comparison based on best performing all single-node server systems published at www.spec.org as of 4 April 2012. SPEC® and the benchmark name SPECjEnterprise® are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPECjEnterprise2010, see http://www.spec.org/jEnterprise2010/.

World record single-node result: Oracle Sun Fire* X4800 M2 server platform eight Intel® Xeon® processors E7-8870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI). Referenced as published at EjOPS score of 27,150. Source: http://www.spec.org/jEnterprise2010/results/res2012q1/jEnterprise2010-20120306-00029.html.

SGI

General Purpose Computing: Integer - throughput performance using SPECint*_rate_base2006

Comparison based on all server systems published at www.spec.org as of 6 March 2012. SPEC® and SPECint® are trademarks of the Standard Performance Evaluation Corp. (SPEC). See http://www.spec.org/cpu2006 for more information.

World record result: SGI Altix* UV1000 server platform with 128 Intel Xeon processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI), 4TB memory, Intel® C++ Compiler XE2011, SUSE* Linux Enterprise Server 11 SP1 (x86_64). Referenced as published baseline score of 27,900. Source: http://www.spec.org/cpu2006/results/res2011q2/cpu2006-20110326-15188.html.
(+35%) in comparison to SGI Altix* UV1000 server platform with 128 Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published baseline score of 2032. Source: http://www.spec.org/cpu2006/results/res2010q3/cpu2006-20100629-12036.html.

Technical Computing: Floating-point throughput performance using SPECfp*_rate_base2006

Comparison based on all server systems published at www.spec.org as of 6 March 2012. SPECfp* is a trademark of the Standard Performance Evaluation Corp. (SPEC). See http://www.spec.org/cpu2006 for more information.

World record result: SGI Altix* UV1000 server platform with 128 Intel Xeon processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI), 4TB memory, Intel® C++ and Fortran Compiler XE2011, SUSE* Linux Enterprise Server 11 SP1 (x86_64). Referenced as published base score of 20,500. Source: http://www.spec.org/cpu2006/results/res2011q2/cpu2006-20110326-15189.html.
(+28%) in comparison to SGI Altix* UV1000 server platform with 128 Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published baseline score of 16000. Source: http://www.spec.org/cpu2006/results/res2010q3/cpu2006-20100629-12035.html.

Server-side Java* middleware: Java* middle-tier performance on SPECjbb*2005 benchmark

Comparison based on all server systems published at www.spec.org as of 6 March 2012. SPECjbb* is a trademark of the Standard Performance Evaluation Corp. (SPEC). See http://www.spec.org/jbb2005 for more information. World Record SPECjbb*2005 claim based on published result using SGI Altix* UV1000 server compared with all other results.

World record details: SGI Altix* UV1000 server platform with 64 Intel Xeon processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QPI), 2TB memory, Oracle Java* 6 Update 24 JVM, SUSE* LINUX Enterprise Server 11 SP1. Referenced as published score of 32,643,008 bops and 510,047 bops / JVM. Source: http://www.spec.org/osg/jbb2005/results/res2011q2/jbb2005-20110322-00960.html.
(+24%) in comparison to SGI Altix* UV1000 server platform with 128 Intel Xeon processors X7560 (24M cache, 2.26GHz, 6.40GT/s Intel® QPI). Referenced as published score of 26,328,087 bops and 411,376 bops / JVM. Source: http://www.spec.org/osg/jbb2005/results/res2010q3/jbb2005-20100907-00923.html.

High-Performance Computing: Memory Bandwidth performance on STREAM TRIAD benchmark

Comparison based on best performing server systems published at www.cs.virginia.edu as of 6 March 2012. World Record STREAM benchmark result claim based on published result using SGI Altix* UV1000 server compared with all other published results at http://www.cs.virginia.edu/stream/standard/Bandwidth.html.

Citations:

McCalpin, John D., 1995: "Memory Bandwidth and Machine Balance in Current High Performance Computers", IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter, December 1995.
McCalpin, John D.: "STREAM: Sustainable Memory Bandwidth in High Performance Computers", a continually updated technical report (1991-2007), available at: "http://www.cs.virginia.edu/stream/".
World record result: SGI Altix* UV1000 server platform with 192x Intel Xeon processors E7-4870 (30M cache, 2.40GHz, 6.40GT/s Intel® QuickPath Interconnect (Intel® QPI)) and 64x Intel Xeon processors E7-8837 (24M cache, 2.66GHz, 6.40GT/s Intel® QPI), 8TB memory, Intel® C++ Compiler XE2011, SUSE* Linux Enterprise Server 11 SP1 (x86_64). Referenced as published STREAM Triad result of 5.8TB/s. Source: http://www.cs.virginia.edu/stream/top20/Bandwidth.html.

Additional information: ² ³ ⁴ ⁵ ⁶ ⁷ ⁸

Videos

Red Hat and Intel: Rock-Solid Mission-Critical Computing
Pauline Nist (Intel) and Jim Totton (Red Hat) discuss their collaborative value to enterprise computing. (1:50)
Intel and Isilon at VM World 2009
Nicholas Kirsch, Isilon Systems, gives a virtualization chalk talk at VMWorld 2009. (8:12)
Jasper Forest From Intel Animation
Introducing Jasper Forest: the newest addition to the Intel® Xeon® processor family. (1:23)
Intel® Architecture: Powering a World of Storage
Video shows storage possibilities powered by Intel® Architecture (2:06)

Intel® Intelligent Power Node Manager Enables Server Power Capping
Intel® Intelligent Power Node Manager enables server power capping to increase rack density, and facilitate load balancing. (2:27)
SGI and Intel Video: Altix UV* Technology Overview
Dr. Eng Lim Goh, CTO, SGI, describes features of SGI Altix UV* compared to standard rack mounted and clustered solutions. (6:59)
Cisco and Intel Video: Leading Server Innovation with Cisco UCS*
Leading server innovation with the Intel® Xeon® processor E7 family for higher speed and capacity. (8:30)
Ethernet Power Management Technology
DMA coalescing and built-in intelligence enables increased performance per watt and consolidation.

Intel® Server Continuity Suite: Power of Integration
Business continuity software interface demo shows easy-to-use, cost-effective, unified management.
Intel® RAID: The Perfect Fit
Video: importance of matching Intel® RAID embedded, integrated, and add-in products to the correct server. (3:54)
Intel® RAID: World Class Performance
Video: Intel® 6Gb/s RAID controllers features, benefits, and technical specs outlined. (2:56)
Plum Tree Mortgage Upgrades to Intel® Xeon® Processors: Testimonial
Video: Intel IT Tune Up contest winner discusses their upgrade to an Intel® Xeon® processor-based server. (2:47)

Intel® Xeon® Processor E3 Family-Based Servers: Better Security
Learn how the Intel® Xeon® Processor E3 Family compares to a 4 year old desktop. (1:04)
Intel® Xeon® Processor E3 Family-Based Servers vs. Desktops: Great Performance for SMB
The Tech Show: Intel® Xeon® processor E3 family-based server delivers business compute performance. (1:07)
Intel® Xeon® Processor 7400 Series: Product Brief Video
Diane Bryant, Intel CIO, and VMware executive Brian Byun discuss the Intel® Xeon® Processor 7400 Series. (1:52)

Product and Performance Information

1. 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.

2. Relative performance for each benchmark is calculated by taking the actual benchmark result for the first platform tested and assigning it a value of 1.0 as a baseline. Relative performance for the remaining platforms tested was calculated by 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.

3. Enhanced Intel SpeedStep® Technology: See the Processor Spec Finder at http://ark.intel.com or contact your Intel representative for more information.

4. Requires a system with Intel® Turbo Boost Technology. Intel Turbo Boost Technology and Intel Turbo Boost Technology 2.0 are only available on select Intel® processors. Consult your PC manufacturer. Performance varies depending on hardware, software, and system configuration. For more information, visit http://www.intel.com/go/turbo.

5. Intel® Hyper-Threading Technology (Intel® HT Technology) requires a computer system with a processor supporting Intel HT Technology and an Intel HT Technology-enabled chipset, BIOS, and operating system. Performance will vary depending on the specific hardware and software used. For more information including details on which processors support Intel HT Technology, visit http://www.intel.com/info/hyperthreading.

6. Intel® processor numbers are not a measure of performance. Processor numbers differentiate features within each processor family, not across different processor families. See www.intel.com/products/processor_number/ for details.

7. Intel® products are not intended for use in medical, life-saving, life-sustaining, critical control, or safety systems, or in nuclear facility applications. All dates and products specified are for planning purposes only and are subject to change without notice.

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

Best Match

Did You Mean?

Intel® Xeon® Processor E7 Family

World Record Benchmark Performance