• <More on Intel.com

Intel® Xeon® Processor 5000 Sequence - Summary

Server Performance Summary

IT cost optimization starts with server performance

New x86 two socket server world recordsΔ

Highlights on Intel® Xeon® processor 5600 series-based server (April 2011 )
Segment - Benchmark Platform/Partner Software Details Result (gain over
Intel® Xeon® processor X5570)
Importance
Database - TPC
Benchmark* H
Hewlett-Packard
ProLiant DL380 G7*
SQL Server 2008* database R2,
Windows Server 2008 R2*
73,975 QphH @
$0.58/QphH @ 100GB
(+38%)
Number one non-clustered two-socket SQL server result @ 100GB
Database - TPC
Benchmark* H
Dell PowerEdge
R710*
EXASOL EXASolution* 4.0,
EXASOL EXACluster* OS 4.0
1,112,402 QphH @
$0.12/QphH @ 100GB
Number one clustered result @ 100GB
Database - TPC
Benchmark* E
Fujitsu PRIMERGY
RX300 S6*
SQL Server 2008* database R2,
Windows Server 2008 R2*
1,268.30 TpsE @
$183.94/TpsE (+55%)
Number one two-socket result
Scientific Computing -
SPECfp*_base2006
Fujitsu PRIMERGY RX300 S6* &
Fujitsu PRIMERGY TX300 S6*
Intel® C++ Compiler 12.0, SUSE Linux Enterprise Server* (SLES) 11 SP1 62 (+14%) Number one two-socket server result
Virtualization -
VMmark* v1.1.1
Fujitsu BX924 S2* VMware ESX 4.0 U2* 40.86@30 tiles (+62%) Number one two-socket result
Virtualization -
VMmark* v2.0
Fujitsu PRIMERGY RX200 S6* VMware ESX* 4.1 7.02@7 tiles Excellent two-socket result
Database - TPC
Benchmark* C
Hewlett-Packard ProLiant DL380 G7* SQL Server 2005* Enterprise x64 SP3 database, Windows Server 2008 R2* 803,068 TpmC @ $0.68/TpmC (+27%) Number one two-socket x86 result
Energy Efficiency - SPECpower*_ssj2008
(Single Node Server)
HP ProLiant DL380 G7* IBM* J9 JVM 3,197 overall ssj_ops/watt (+55%) Number one two-socket single node server result
Energy Efficiency - SPECpower*_ssj2008
(Multi-Node Server)
Hewlett-Packard ProLiant DL170e G6* IBM* J9 JVM 3,212 overall ssj_ops/watt (+36%) (gain over Intel® Xeon® processor L5530) Number one two-socket multi-node server result
Energy Efficiency –
SAP* Server Power Benchmark (2-tier)
Fujitsu PRIMERGY RX300 S6* SAP enhancement package 4 for SAP ERP 6.0, Windows Server 2008 R2* Datacenter Edition 18.3 watts / kilo SAPS Number one server result
eCommerce - SPECjbb*2005
(Single JVM)
Sun Fire X4270 M2* Java HotSpot 1.6.0_21*, Oracle Solaris 10* 812,358 SPECjbb2005 bops (+59%) Number one two-socket single JVM result
Web Server - SPECWeb*2005 Fujitsu PRIMERGY TX300 S6* Rock Web Server* v1.4.7, Red Hat* Enterprise Linux* 5.3 104,422(+25%) Number one two-socket x86 server result
HPC - SPEComp*Mbase
2001
Cisco UCS B200 M2* SUSE Linux Enterprise Server* (SLES), Intel® C/C++ Compiler 11.1.059 52,986 (+21%) Number one two-socket x86 server result
HPC – SPEComp*Lbase2001 Cisco UCS B200 M2* SUSE Linux Enterprise Server* (SLES), Intel® C/C++ Compiler 11.1.059 282,771 (+18%) Number one two-socket server result
HPC - SPECMPI*
2007
Intel® result server cluster SUSE Linux Enterprise Server* (SLES) Excellent cluster scaling Number one two-socket cluster result
Integer Single Task
- SPECint*_
base2006
Fujitsu PRIMERGY RX300 S6* &
Fujitsu PRIMERGY TX300 S6*
Intel® C++ Compiler 12.0, SUSE Linux Enterprise Server* (SLES) 11 SP1 45.3 (+16%) Number one two-socket server result
Energy-Efficiency-Performance/watt
using SPECint*_rate
_base2006
Fujitsu PRIMERGY RX300 S6* Intel® C++ Compiler 11.1, SLES 11 Intel® Xeon® processor L5640 uses 30% lower power than Intel® Xeon® processor X5570 at SPECint*_rate_base2006 score of 250 Same performance as Intel® Xeon® processor X5570 with 30% lower power results for

RX3000 S5

File Type/Size:  ZIP 97.3KB

results for

RX3000 S6

File Type/Size:  ZIP 101KB

HPC - Black-Scholes*
(Financial Services)
Supermicro* Black-Scholes 1.63x speed up over X5570 Exceptional gain over previous generation
Java – SPECjEnterprise*2010 IBM BladeCenter HS22* (application server) & IBM x3850 X5* (database server) IBM WebSphere Application Server V7*, IBM DB2* 2752.06 Enterprise jEnterprise operations per second (+52%) Number one two socket x86 server result
General Purpose
Computing - SPECint*_
rate_base2006
Cisco UCS B200 M2* Intel® C++ Compiler 12.0, SUSE Linux Enterprise Server* (SLES) 11 SP1 390 (+47%) Number one two socket x86 server result
Scientific Computing
- SPECfp*_rate_
base2006
Fujitsu PRIMERGY BX922 S2* Intel® C++ Compiler 12.0, SUSE Linux Enterprise Server* (SLES) 11 SP1 267 (+30%) 30% gain over Intel® Xeon® processor X5570
eCommerce -
SPECjbb*2005
Sun Blade X6270 M2* Windows Server 2008 Enterprise Edition R2* (64-bit), Oracle Java Hotspot* VM (JDK 6 Update 25) 975,257 SPECjbb2005 bops (+54%)
(487,629 SPECjbb2005 bops/JVM)
54% gain over Intel® Xeon® processor X5570
Computer Aided Engineering -
ANSYS FLUENT*
(single node truck_14m)
Sun Fire X2270 M2* SUSE Linux Enterprise Server* (SLES) 94.8 rating (+32%) Number one two-socket single node result
Application Server -
SPECjAppServer*
2004 (Single Node Server)
Cisco UCS C250 M2* Oracle WebLogic Server*, Oracle 11g Database*, Oracle Enterprise Linux* 5,185 JOPS (+30%) 30% gain over Intel® Xeon® processor X5570