Date: 26-Nov-2009 URL: www.sun.com/servers/coolthreads/t5120/performance.xml

Sun SPARC Enterprise T5120 Server

The Sun SPARC Enterprise T5120 server with Chip Multithreading (CMT) technology delivers breakthrough levels of performance with dramatic power and space savings, as demonstrated by a range of World Record benchmark results.

These world record results span many commercial and technical workloads common across all IT infrastructure. When the Space, Watts and Performance (SWaP) metric is applied, it is easy to see why these servers are the most efficient in the market, uniquely enabling customers to consolidate space and energy consumption, without sacrificing performance.

No other servers on the planet better empower organizations to build for web scale and push the boundaries of network participation through the combination of world record performance, performance per watt and price / performance. The next generation CoolThreads servers based on the UltraSPARC T2 processor enables organizations to securely, reliably and eco-efficiently serve millions of new customers and communities, all while saving millions of dollars in operational costs, through a virtualized, environmentally responsible data centre infrastructure.

(Tue, 12 February 2008)

The Sun SPARC Enterprise T5120 Server Sets a New World Record Single Chip SPECint_rate2006 Performance with gccfss Compiler

The Sun SPARC Enterprise T5120 Server, based on the innovative UltraSPARC T2 processor, achieved the highest ever single-chip integer throughput result on SPEC CPU2006 benchmark, while outperforming IBM systems based on the fastest 4.7GHz POWER6 processor by 38% and beating the best published results for Intel Xeon-based systems by up to 15%.

Benchmark Description

SPEC CPU2006 is a CPU-intensive benchmark suite, stressing a system's processor, memory subsystem and compiler. SPEC designed CPU2006 to provide a comparative measure of compute-intensive performance across the widest practical range of hardware.

The gccfs compiler allows one to use the optimal Sun SPARC optimization tools along with the popular gcc coding conventions and deliver performance that has not been possible before without time-consuming code changes.

Competitive Comparisons Table

	Sun SPARC Enterprise T5120	IBM System p570	HP ProLiant DL360 G5
SPECint_rate2006	83.9	60.9	73.0

Benchmark Outcome [1]

The Sun SPARC Enterprise T5120 server, equipped with the 1.4GHz UltraSPARC T2 processor, achieved world record integer throughput performance on the SPEC CPU2006 benchmark.
On the integer-intensive tests, the Sun SPARC Enterprise T5220 server delivered 38% higher performance than the 4.7GHz dual core POWER6-based IBM System p570 server and 15% more performance than the 3.16 GHz quad-core Intel Xeon-based HP Proliant DL360 G5 server.
These results demonstrate that the UltraSPARC T2 processor provides more integer computing capacity than any other chip on the market.
The Operating System (OS) and compiler software often help to deliver the best performance by providing optimizations tailored to a specific hardware platform or microprocessor architecture. The advanced optimization techniques used in freely available Sun Studio 12 compiler software in combination with the popular gcc coding conventions, allowed the Sun SPARC Enterprise T5120 server module to successfully claim the top spot on the industry-standard SPECint_rate2006 benchmark suite.

[1] SPEC, SPECint registered trademarks of Standard Performance Evaluation Corporation. Sun SPARC Enterprise T5120 server (1xUltraSPARC T2 1.4GHz) (1 chip, 8 cores, 64 threads) 83.9 SPECint_rate2006. Competitive results from www.spec.org as of February 12, 2008. IBM System p570 (4.7GHz POWER6 processor, 1 chip, 2 cores, 4 threads) 60.9 SPECint_rate2006. HP Proliant DL360 G5 (3.16 GHz, Intel Xeon processor X5460,1 chip, 4 cores, 4 threads) 73.0 SPECint_rate2006.

(Fri, 04 January 2008)

Sun SPARC Enterprise T5120 and T5220 Servers Support 10,000 Concurrent Users Running Siebel CRM R8 and Oracle 10G R2 Database

The benchmark demonstrates that the Sun SPARC Enterprise T5120 and T5220 Servers provide the highest performing and the most cost-effective business solution for Siebel CRM applications. This is achieved through a powerful combination of Oracle's Siebel CRM Release 8.0 architecture with Oracle 10g R2 database running on a 8-core / 64 threads UltraSPARC T2 processor, Sun Java System Web Server, and the industry leading, free and open Solaris 10 OS.

All tiers of the Siebel CRM Release 8.0 architecture ran on the UltraSPARC T2 chip multithreading (CMT) processor with Solaris 10 8/07. The Multithreading capability of the UltraSPARC T2 processor allowed each of the active Object Manager (OM) processes to run hundreds of Light Weight Processes (LWP), thus utilizing the available resources very effectively. A total number of 30 object managers serviced the work load of 10,000 concurrent users.
Scalability — The Solaris 10 OS and CMT based servers proves once again to be the best combination for scalability and resource utilization in the datacenter, giving users a consistent response time and future growth on critical applications.
Low network utilization — The Siebel CRM Release 8.0 Smart Web Architecture and Smart Network Architecture efficiently managed the network, consuming only 7.17 kilobits per second per user.
Efficient use of the database server — Siebel CRM Release 8.0 Smart Database Connection Pooling and Multiplexing allowed the database to service 10,000 concurrent users and the supporting Siebel CRM Release 8.0 server application services with only 357 database connections using a Siebel database pooling ratio of 25:1.
Energy efficiency — While supporting 10,000 concurrent Siebel users, the entire Sun Solution based on Sun SPARC Enterprise T5120/T5220 servers running Siebel CRM Release 8.0 and Oracle 10g R2 on top of Solaris 10 consumed 1202 watts in a 6U rack space. As a result the T5210/T5220 supports 8.3 users per watt of energy consumed and supports 1666 users per rack unit.

Click here for a full copy of the benchmark report

(Wed, 21 November 2007)

Cluster of Sun SPARC Enterprise T5120 Servers Running Java Enterprise Edition Application Server Software Posts the Best Performance and Efficiency Result for all Open Source Submissions

A cluster of six Sun SPARC Enterprise T5120 servers running the Solaris 10 OS and the Sun Java System Application Server 9.1 (Glassfish) delivered the highest results ever recorded for open source application servers on the industry standard measure of application server performance. What is more, when viewing performance and data center efficiency, these results beat those submitted on HP Itanium 2 servers running proprietary HP-UX operating systems and application servers.

These results confirm Sun SPARC Enterprise T5120 servers running the open source Solaris 10 OS and Glassfish application server as one of the highest performing and most efficient platforms on the planet for deployment of secure Java-based application services.

Benchmark Description

SPECjAppServer2004 Multi-Node is a recognized industry standard benchmark that is used to measure performance of Java EE application server tier. The benchmark provides a factual demonstration of the performance capabilities of the complete environment that is powering critical applications and web based services.It is the only industry-standard benchmark used for Java Enterprise Edition application servers. It measures the the number of Java Operations per second (JOPS) a particular system configuration (hardware and software) can deliver while maintaining acceptable response times for 90% of the transactions.

Competitive Comparisons Table

	Sun SPARC Enterprise T5120	HP BL860c	HP rx6600
Space (RU)	1	8 blades per 10U chassis	7
Power per Server Chassis	444	4,272	998
Total Number of JEE Nodes	6	12	6
Total Space (RU)	6	20	42
Total Watts	2,664	8,544	5,988
Performance (SPECjAppServer 2004 JOPs)	8,439.36	10,519.43	7,269.45
Performance / Watt (Higher is Better)	3.2	1.2	1.2
SWaP (Higher is Better)	0.53	0.06	0.03

Benchmark Outcome [1]

A cluster of six Sun SPARC Enterprise T5120 servers obtained a result of of 8,439.36 SPECjAppServer2004 JOPS@Standard in just 6U of rack space while consuming 444 watts of power per node. A single Sun Fire E6900 equipped with 24 x UltraSPARC IV+ processors, 96GB of memory and Solaris 10 powered the database tier of the configuration.
This clustered results demonstrates the scalability of the entire apllication tier solution built upon Sun SPARC Enterprise T5120 servers and the open source Solaris OS, and Sun Java System Application Server software.
A cluster of 12 x HP BL860c blade servers equipped with the latest Itanium 2 9100 processors required 2x the number of server nodes consuming over 3x more space and power to delivered a result that was only 20% higher than the Sun submission. Also, the HP configuration used two Superdome servers at the database tier, with 2/3rd more processors and 3.4x more memory than the Sun solution. As a result, the HP configuration is considerably more expensive to purchase and operate.
Compared to a cluster of 6 x HP rx6600 servers equipped with four dual core Itanium 2 processors and running HP-UX, the Sun SPARC Enterprise T5120 cluster delivered nearly 16% higher performance while consuming 2x less power and 7x less space. As a result, the Sun SPARC Enterprise T5120 cluster delivers 2.6x higher Performance per Watt and 18x better SWaP (server efficiency) score.

[1] SPEC, SPECjbb reg tm of Standard Performance Evaluation Corporation. 6 Sun SPARC Enterprise T5120's (48 cores, 6 chips) and 1 Sun Fire E6900 (48 cores, 24 chips ) 8439.36 JOPS@Standard. 12 HP BL860c servers (48 cores, 24 chips) and 2 HP Superdomes (80 cores, 40 chips) 10519.43 JOPS@Standard. 6 HP rx6600 (48 cores, 24 chips) and HP Superdome (64 cores, 32 chips) 7269.45 JOPS@Standard.
HP blade power from: http://h71019.www7.hp.com/ActiveAnswers/cache/347628-0-0-0-121.html. HP blades configured with 1.6GHz Itanium 2 9040 processors with 18MB Cache, 24GB per blade via 6 x 4GB DIMMs, 1 x 73GB SAS drive and 80% utilisation HP rx6600 power from Typical Power Consumption, reported 11/30/07: http://h18000.www1.hp.com/products/quickspecs/12596_div/12596_div.HTML#Technical%20Specifications Sun SPARC Enterprise T5120 power consumption taken from measurements made during the benchmark run

(Wed, 10 October 2007)

The Sun SPARC Enterprise T5120 Sets World Record Single JVM Performance for 4- Rack Unit Servers and Less on SPECjbb2005 Benchmark

The Sun SPARC Enterprise T5120 server running Solaris 10 delivered the highest ever single JVM results recorded for 1 Rack Unit servers on the industry standard measure of JVM performance. These results were higher than 2 and 4 Rack Unit high servers based on competitive processors and operating systems.

These results confirm the Sun SPARC Enterprise T5120 server as one of the highest performing and most efficient platforms on the planet for deployment of secure Java-based B2B Enterprise applications.

Benchmark Description

SPECjbb2005 (Java Business Benchmark) measures the performance of a Java implemented application tier (server-side Java). The benchmark is based on the order processing of a wholesale supplier application. The metrics given are number of SPECjbb2005 bops (Business Operations per Second) and SPECjbb2005 bops/JVM (bops per JVM instance).

Competitive Comparisons Table

	Sun SPARC Enterprise T5120	IBM p6 570	HP 2660	Dell 2950
Space (RU)	1	4	2	2
Power Consumption (Watts)	464	560	563	300
Performance (BOPS/JVM)	170,153	87,737	80,884	74,218
Performance / Watt	366.7	156.7	143.7	247.4
SWaP	366.7	39.2	71.8	123.7

Benchmark Outcome [1]

The Sun SPARC Enterprise T5120 server obtained a result of of 170,153 Business Operations per Second in just 1U of rack space, running a single JVM.
The Sun HotSpot JVM sets a new standard for scalability by demonstrating near linear throughput and fully leveraging the 64 hardware threads of the UltraSPARC T2 processor, and running up to 8x more threads than the competition.
The Sun SPARC Enterprise T5120 server's single-JVM 64-bitSPECjbb2005 result is within 11% of the performance of the multi-JVM result of 192,055 SPECjbb2005 bops, 24007 SPECjbb2005 bops/JVM, highlighting the flexibility of the Ultra SPARC T2 processor and Sun HotSpot JVM technology.
Compared to the IBM p570, equipped with four of the latest dual core 4.7GHz Power6 processors and running AIX 5.3, the single processor Sun SPARC Enterprise T5120 delivers nearly 2x higher throughput per JVM, while consuming less power and 4x less space. As a result, the Sun SPARC Enterprise T5120 delivers 2.3x higher Performance per Watt and nearly 9.5x SWaP (server efficiency).
Compared to the HP rx2660, equipped with two of the latest dual core Itanium 2 processors and running HP-UX, the Sun SPARC Enterprise T5120 delivers over 2x higher throughput per JVM, while consuming 1.2x less power and half the space. As a result the Sun SPARC Enterprise T5120 delivers over 2.5x higher Performance per Watt and over 5x SWaP (server efficiency).
Compared to the Dell PowerEdge 2950, equipped with two of the latest 1.6GHz quad core Intel Xeon processors and running Windows Server 2003, the Sun SPARC Enterprise T5120 delivers over 2x higher throughput per JVM, while consuming half space. As a result the Sun SPARC Enterprise T5120 delivers 1.5x higher Performance per Watt and 3x SWaP (server efficiency).

[1] SPEC, SPECjbb reg tm of Standard Performance Evaluation Corporation. All results as of 10/09/07 on www.spec.org. Sun SPARC Enterprise T5120 results submitted to SPEC. Other results as of 10/09/07 on www.spec.org Sun SPARC Enterprise T5120 (1 chip, 8 cores) 170,153 SPECjbb2005 bops, 170,153 SPECjbb2005 bops/JVM. Sun SPARC Enterprise T5120 (1 chip, 8 cores) 192,055 SPECjbb2005 bops, 24,007 SPECjbb2005 bops/JVM IBM p570 (2 chips, 4 cores) SPECjbb2005 bops = 175474, SPECjbb2005 bops/JVM = 87737. Dell 2950 (2 chips, 8 cores) SPECjbb2005 bops = 148,436, SPECjbb2005 bops/JVM = 74,218. HP rx2660 (2 chips, 4 cores) SPECjbb2005 bops = 80884, SPECjbb2005 bops/JVM = 80884 IBM p6 570 power specifications from 40% of maximum report power consumption published here, 10/10/07, posted at ftp://ftp.software.ibm.com/common/ssi/rep_sp/n/PSB01628USEN/PSB01628USEN.PDF HP rx2600 power consumption estimated by taking 70% of the maximum reported power dissipation, documented here on 03/23/07: Actual HP power specs http://h18004.www1.hp.com/products/quickspecs/12698_div/12698_div.HTML#Technical%20Specifications: http://h20341.www2.hp.com/integrity/cache/387834-0-0-225-121.html. Dell power specifications from 40% of PSU ratings published here, 10/10/07, posted at http://www.dell.com/content/products/productdetails.aspx/pedge_2950?c=us&cs=555&l=en&s=biz&~section=specs#tabtop Sun SPARC Enterprise T5120 power consumption taken from measurements made during the benchmark run

(Wed, 10 October 2007)

The Sun SPARC Enterprise T5120 Sets World Record for Performance & Efficiency on the Database Tier of the SPECjAppServer2004 2-Node Benchmark

The Sun SPARC Enterprise T5120 server running the Solaris 10 OS and Oracle Database Server 10g outperformed all other competitive servers in the database tier of 2-Node SPECjAppServer2004 benchmark, including systems based on the latest IBM Power 5+, Intel Xeon and Intel Itanium 2 processors. In addition, the Sun SPARC Enterprise T5120 server delivered the highest overall Performance per Watt and the best per-socket performance in OLTP database serving.

The application tier of the benchmark was powered by a Sun SPARC Enterprise T5220 Server running Oracle Application Server 10g on Solaris 10. The result achieved in the application tier are also world records.

These results confirm the Sun SPARC Enterprise T5x20 servers as the highest performing and most efficient platforms on the planet for deployment of secure application and OLTP database services.

Benchmark Description

SPECjAppServer2004 is the only industry-standard benchmark used for Java Enterprise Edition application servers. In addition to testing application server performance, it also tests the database performance of servers deployed to support the application tier.

Database Tier, SPECjAppServer2004 2-Node Comparison Table

	Sun SPARC Enterprise T5120	HPrx2660	Dell 2900	IBMp5+550
Space (RU)	1	2	5	4
Power Consumption (Watts)	338	559	350	770
Performance (SPECjApp JOPS)	2,000.92	874.17	652.95	1,197.51
Performance / Watt	5.2	1.6	1.9	1.6
SWaP	5.2	0.8	0.4	0.4

Benchmark Outcome [1]

A single Sun SPARC Enterprise T5120 Server configured with just a single, 8 Core UltraSPARC T2 processor running Oracle Database Server 10g was able to support a Sun SPARC Enterprise T5220 Server in delivering 2000.92 JOPS for the SPECjAppServer2004 Benchmark in the Standard category.
Compared to the HP Integrity rx2660, equipped with two of the latest dual core Intel Itanium 2 processors and running HP-UX, the Sun SPARC Enterprise T5120 delivers 2.3x higher throughput, while consuming nearly 1.5x less power in half the space. As a result the Sun SPARC Enterprise T5120 delivers over 3.3x higher Performance per Watt and 6.6x SWaP (server efficiency)
Compared to the IBM p5+ 550, equipped with two of the latest dual core 2.1GHz Power 5+ processors and running AIX 5.3, the single processor Sun SPARC Enterprise T5120 delivers nearly 1.7x higher throughput, while consuming 2x less power and nearly 13.5x higher SWaP (server efficiency)
Compared to the Dell PowerEdge 2900, equipped with two of the latest dual core 3GHz Intel Xeon 5100 "WoodCrest" processors and running Windows Server 2003, the Sun SPARC Enterprise T5120 delivers over 3x higher throughput in 5x less space. As a result the Sun SPARC Enterprise T5120 delivers 2.8x higher Performance per Watt and nearly 14x SWaP (server efficiency)

[1] SPECjAppServer2004 Sun SPARC Enterprise T5220 (8 cores, 1 chip) and Sun SPARC Enterprise 5120 (8 cores, 1 chip) 2000.92 JOPS@Standard. SPECjAppServer2004 IBM p570 (4 cores, 2 chips) and IBM p5+ 550 (4 cores, 2 chips) 1,197.51 JOPS@Standard. SPECjAppServer2004 2 x Dell 2900 (4 cores, 2 chips) 652.93 JOPS@Standard. SPECjAppServer2004 2 x HP rx2660 (4 cores, 2 chips) 618.38 JOPS@Standard. IBM p5 power specifications calculated by applying 70% of the power numbers published in "Facts and Features Report", 3/10/06, posted at http://www-03.ibm.com/servers/eserver/pseries/hardware/factsfeatures.html
Dell power rating 08/24/07 from Dell DataCenter Capacity Planner, System configured with 2 x Xeon 5160 processors, 8 x 2GB DIMMs, 1 x Disk, 1 x HBA & Redundant PSU HP rx2660 power calculated as 70% of max input power reported 07/17/07: http://h18004.www1.hp.com/products/quickspecs/12698_div/12698_div.HTML#Technical%20Specifications Sun SPARC Enterprise T5120 server power consumption taken from measurements made during the benchmark run.
All results from www.spec.org as of 10/10/07.

(Tue, 09 October 2007)

The Sun SPARC Enterprise T5120 Server, Equipped with a Single UltraSPARC T2 Processor, Claims Two World Records for SPEC CPU2006

The Sun SPARC Enterprise T5120 Server, based on the innovative UltraSPARC T2 processor, achieved world record integer and floating point throughput performance with the highest ever per-chip results on the SPEC CPU2006 benchmark , outperforming the latest 4.7GHz POWER6 processor from IBM by up to 29% and the latest quad core Intel Xeon x5365 3GHz processor by up to 61%

Benchmark Description

CPU-intensive benchmark suite, stressing a system's processor, memory subsystem and compiler. SPEC designed CPU2006 to provide a comparative measure of compute-intensive performance across the widest practical range of hardware.

Competitive Comparisons Table

	Sun SPARC Enterprise T5120	IBM System p570	HP ProLiant DL360 G5
SPECint_rate2006	78.5	60.9	61.3
SPECfp_rate2006	62.3	58	38.8

Benchmark Outcome [1]

These results demonstrate that the UltraSPARC T2 processor provides more computing capacity than any other chip on the market
The Sun SPARC Enterprise T5120 server, equipped with the 1.4GHz UltraSPARC T2 processor achieved world record Integer and Floating Point performance throughput on the SPEC CPU2006 benchmark.
On the Integer tests, the Sun SPARC Enterprise T5120 server delivered 29% higher performance than the 4.7GHz dual core POWER6-based IBM System p570 server and 28% more performance that the 3GHz quad-core Intel Xeon-based HP Proliant DL36 0G5 server.
On the Floating Point tests, the Sun SPARC Enterprise T5120 server delivered 7% higher performance than the 4.7GHz dual core IBM POWER6-based IBM System p570 server and 61% more performance that the 3GHz quad core Intel Xeon-based HP ProLiant DL360 G5 server.
These results demonstrate that the UltraSPARC T2 processor provides more computing capacity than any other chip on the market.

[1] SPEC, SPECint, SPECfp registered trademarks of Standard Performance Evaluation Corporation.Sun SPARC Enterprise T5120 server, (1xUltraSPARC T2, 1.4GHz ) (1 chip, 8 cores, 64 threads) 78.5. SPECint_rate2006, 62.3 SPECfp_rate2006. Competitive results from www.spec.org as of October 8, 2007. IBM System p570 (4.7GHz POWER6 processor)4.7GHz (1 chip, 2 cores, 4 threads) 60.9. SPECint_rate2006, 58.0 SPECfp_rate2006. HP Proliant DL360 G5 (3.0 GHz, Intel Xeon processor X5365) (1 chip, 4 cores, 4 threads) 61.3 SPECint_rate2006, 38.8 SPECfp_rate2006.

(Tue, 09 October 2007)

The Sun SPARC Enterprise T5120 Sets Single-Socket Performance World Record and Leading Efficiency on Server-Side Java Benchmark

The Sun SPARC Enterprise T5120 server running Solaris 10 delivered the highest ever single socket server results on the industry standard measure of JVM performance This was also the highest result achieved by comparable UNIX servers, outperforming the latest Power6 system from IBM and Itanium 2 system from HP, all while consuming less space and power.

These results confirm the Sun SPARC Enterprise T5120 server as one of the highest performing and most efficient platform on the planet for deployment of secure Java-based B2B Enterprise applications.

Benchmark Description

Competitive Comparisons Table

	Sun SPARC Enterprise T5120	IBM Power 6 570	IBM p5+ 505Q	HP rx2660
Space (RU)	1	4	1	2
Power Consumption (Watts)	464	1,040	320	563
Performance (BOPS)	192,055	175,474	63,544	80,884
Performance / Watt (Higher is Better)	413.9	168.7	198.6	143.7
SWaP (Higher is Better)	413.9	42.2	198.6	71.8

Benchmark Outcome [1]

The Sun SPARC Enterprise T5120 server obtained a single socket world record result of 192,055 Business Operations per Second
Compared to the IBM p570, equipped with two of the latest dual core 4.7GHz Power6 processors and running AIX 5.3, the single processor Sun SPARC Enterprise T5120 delivers 9% higher throughput, while consuming over 2x less power and 4x less space. As a result the T5120 delivers 2.5X higher Performance per Watt and over 9.5x SWaP (server efficiency)
Compared to a 4-way IBM p505Q, equipped with the latest quad core Power 5+ processor and running AIX 5.3, the Sun SPARC Enterprise T5120 delivers 3x higher throughput and over 2X higher Performance per Watt and SWaP (server efficiency)
Compared to the HP Integrity rx2660, equipped with the latest dual core Itanium 2 processors and running HP-UX, the Sun SPARC Enterprise T5120 delivers nearly 2.5x higher throughput while consuming 1.2x less power and 2x less space. As a result the T5120 delivers nearly nearly 3X higher Performance per Watt and 5.7x SWaP (server efficiency)
The Sun HotSpot JVM sets a new standard for scalability by demonstrating near linear scalability and fully leveraging the 64 hardware threads of the UltraSPARC T2 processor, and running up to 8x more threads than the competition.

[1] SPEC, SPECjbb reg tm of Standard Performance Evaluation Corporation. Sun SPARC Enterprise T5120 results submitted to SPEC. Other results as of 09/28/07 on www.spec.org Sun SPARC Enterprise T5120 (1 chip, 8 cores) 192,055 SPECjbb2005 bops, 24,007 SPECjbb2005 bops/JVM. IBM p570 (2 chips, 4 cores) SPECjbb2005 bops = 175474, SPECjbb2005 bops/JVM = 87737. IBM p505Q (1 chip, 4 cores) SPECjbb2005 bops = 63544, SPECjbb2005 bops/JVM = 31772. HP rx2660 (2 chips, 4 cores) SPECjbb2005 bops = 80884, SPECjbb2005 bops/JVM = 80884 IBM p6 570 power specifications from 80% of maximum report power consumption published here, 06/07/07, posted at ftp://ftp.software.ibm.com/common/ssi/rep_sp/n/PSB01628USEN/PSB01628USEN.PDF
IBM p505 power specifications from 80% of maximum report power consumption published in "Facts and Features Report", 03/27/06, posted at ftp://ftp.software.ibm.com/common/ssi/rep_sp/n/PSB01628USEN/PSB01628USEN.PDF HP rx2600 power consumption estimated by taking 70% of the maximum reported power dissipation, documented here on 03/23/07: Actual HP power specs http://h18004.www1.hp.com/products/quickspecs/12698_div/12698_div.HTML#Technical%20Specifications: http://h20341.www2.hp.com/integrity/cache/387834-0-0-225-121.html Sun SPARC Enterprise T5120 power consumption taken from measurements made during the benchmark run

(Tue, 09 October 2007)

The Sun SPARC Enterprise T5120 Sets World Record for Single Socket Performance on SAP SD 2-Tier Benchmark

The Sun SPARC Enterprise T5120 server running Solaris 10 OS, SAP and Oracle Database Server 10g delivered the highest ever single socket server results on an industry standard measure of ERP performance This result was achieved while outperforming systems based on IBM Power6, Intel Xeon and Itanium 2 processors, all while consuming less space.

These results confirm the Sun SPARC Enterprise T5120 server as one of the highest performing and most space efficient platforms on the planet for deployment of secure ERP and database services.

Benchmark Description

The SAP Standard Application SD (Sales and Distribution) Benchmark is a two-tier ERP business test that represents full business workloads of order processing and invoice processing, while demonstrating the ability to run both the application and database software on a single system. The SAP Standard Application SD Benchmark represents the critical tasks performed in real-world ERP business environments.

SAP is one of the premier world-wide ERP application providers, and maintains a suite of benchmark tests to demonstrate the performance of competitive systems on the various SAP products.

Competitive Comparisons Table

	Sun SPARC Enterprise T5120	IBM Power 6 570	HP DL380G5	HP rx6600
Space (RU)	1	4	2	7
Performance (Users)	2,175	2,035	2,080	1,725
Users per Rack Unit (Higher is Better)	2175	508.8	1040	246.4

Benchmark Outcome [1]

The Sun SPARC Enterprise T5120 Server posted the best SAP SD 2-Tier benchmark result for single processor servers, along with the best performance per Rack Unit of all servers in its class. The benchmark demonstrates the the T5120 and Solaris Operating System can support over two thousand concurrent users accessing an SAP application server.
This benchmark proves that the Sun SPARC Enterprise T5120 server, running Oracle 10g Database Server on the top of Solaris 10, the most reliable OS in the industry, is well-suited to act as an enterprise class OLTP database server.
The result also demonstrates vertical consolidation through the ability to deliver world record levels of performance and space efficiency while running both the SAP application and the Oracle database on the same system.
Compared to the IBM p570, equipped with two of the latest dual core 4.7GHz Power6 processors and running AIX 5.3, the single processor Sun SPARC Enterprise T5120 delivers 7% higher throughput with faster response times, while consuming 4x less space. As a result the T5120 delivers over 4X higher Performance per Rack Unit.
Compared to the HP Proliant DL380 G5, equipped with two of the latest quad-core Intel Xeon 5300 Series "Clovertown" processors and running Windows Server Enterprise Edition 2003, the Sun SPARC Enterprise T5120 delivers 5% higher throughput, in half the space.
Compared to the HP Integrity rx6600, equipped with four of the latest dual core Intel Itanium 2 processors and running Windows Server Enterprise Edition 2003, the Sun SPARC Enterprise T5120 delivers 1.26x higher throughput, in 7x less space. As a result the Sun SPARC Enterprise T5120 delivers nearly 9x higher Performance per Rack Unit.

[1] SAP, R/3, mySAP reg TM of SAP AG in Germany and other countries. More info http://www50.sap.com/benchmarkdata/sd2tier.asp Two-tier SAP Sales and Distribution (SD) standard SAP ERP 2005 application benchmark: Sun SPARC Enterprise T5120, 1 processor / 8 cores / 64 threads, UltraSPARC T2, 1.4 GHz, Number of benchmark users & comp.: 2,175 SD (Sales & Distribution); Average dialog response time: 1.91 seconds; Certificate #2007059. Operating System central server: Solaris 10; RDBMS: Oracle 10g; SAP ECC Release: 6.0. IBM System p570 (2 processors, 4 cores, 8 threads) 4.7 GHz POWER6, 32 GB mem, 2035 SD benchmark users, 1.99 sec avg response time, Cert#2007037, Oracle 10g, AIX 5L Version 5.3. HP ProLiant DL380 G5 (2 processors / 8 cores / 8 threads) 3GHz Intel Xeon Processor X5365, 32 GB main, 2080 SD benchmark users, 1.95 sec avg response time, Cert#2007057, Windows Server 2003 Enterprise Edition, SQL Server 2005 HP Integrity rx6600 (4 processors / 8 cores / 16 threads) Intel Itanium 2 9050, 1.6 GHz, 64 GB main memory, 1725 SD benchmark users, 1.93 sec avg response time, Certification Number. 2007040, Windows Server 2003 Enterprise Edition, SQL Server 2005

The Standard Performance Evaluation Corporation (SPEC) is a non-profit corporation formed to establish, maintain and endorse a standardized set of relevant benchmarks that can be applied to the newest generation of high-performance computers. SPEC develops suites of benchmarks and also reviews and publishes submitted results from their member organizations and other benchmark licensees.

SAP Standard Application Benchmarks test and prove the scalability of mySAP Business Suite. The benchmark results provide basic sizing recommendations for customers by testing new hardware, system software components, and Relational Database Management Systems (RDBMS). They also allow for the comparison of different system configurations. The benchmarking procedure is standardized and well defined. It is monitored by the SAP Benchmark Council made up of representatives of SAP and technology partners involved in benchmarking. The SAP Standard Application Benchmarks can also be used to test and verify scalability, concurrency and multi-user behavior of system software components, RDBMS, and business applications. All performance data relevant to system, user, and business applications are monitored during a benchmark run and can be used to compare platforms and as basic input for sizing recommendations.

Sun, Sun Microsystems, the Sun logo, Java, J2EE, Sun Fire and The Network Is The Computer are trademarks or registered trademarks of Sun Microsystems, Inc. in the United States and other countries. SPEC and the benchmark names SPECviewperf, SPECweb, SPECint, SPEComp, SPECfp, SPECjAppServer, SPECjvm, SPECpower, SPECmail, SPECsfs and SPECjbb are registered trademarks of the Standard Performance Evaluation Corporation. Sun's results have been submitted to SPEC. Competitive data obtained from http://www.spec.org as of the date located next to the respective claim. See the website for latest results. For comparison purposes, the terms CPU, chip and processor are used interchangeably. Each socket can accommodate one chip. SAP, R/3, mySAP reg TM of SAP AG in Germany and other countries. For the latest results and additional information visit www.sap.com/benchmark. TPC Benchmark C, tpmC, TPC-C, TPC Benchmark H, TPC-H, QphH are trademarks of the Transaction Performance Processing Council (TPC). More info http://www.tpc.org.