Compare UNIX Servers

Move Up to IBM Power Systems

Get double the performance per core, plus improved processor utilization and availability for a more dynamic infrastructure.

Compare UNIX Servers. Learn the benefits of IBM Power Systems compared to competitive UNIX servers.

IBM POWER6™ processor-based Linux, i, and UNIX servers are designed to help you implement a dynamic infrastructure. The combination of leadership performance, energy efficiency, flexible virtualization features and RAS features are designed to reduce your cost, improve service to end users and reduce risk – especially for mission critical applications and highly virtualized, consolidated operating environments.

Tab navigation

Power performance:

Compare highend servers

IT managers have to grapple with the issue of server sprawl and the accompanying high cost of management combined with the explosion in energy use in the datacenter. One solution that many clients are implementing is server consolidation. The IBM Power™ 595 server, exploiting IBM PowerVM™ technology, is the epitome of a consolidation server because of its outstanding performance and capacity.

With the fastest processor in the industry, the 5.00GHz POWER6 processor, and outstanding memory and I/O bandwidth, the Power 595 has the capacity to support huge consolidation efforts that other servers just can't handle.

We ran a variety of benchmarks, and the answer is the same for all of them. The 64-core IBM Power™ 595 server outperforms the 128-core HP Integrity Superdome. – more performance with ½ the cores. The 595 also has 90% of the performance of the 256-core Sun SPARC Enterprise M9000 – 90% of the performance with ¼ the cores.

The Power 595 server can offer you this fabulous performance for your UNIX® applications.

*Highend Systems Performance¹*
	TPC-C	SPECint_rate2006	SPECfp_rate2006	SPECjbb2005	2-tier SAP SD
64-core, 32 chip, 128 threads IBM Power 595	6,085,166	2,080	2,110	3,435,485	35,400
128-core, 64 chips, 256 threads HP Integrity Superdome	4,092,799	1,650	1,480	2,054,864	30,000
256-core, 64 chips, 512 threads Sun SPARC Enterprise M9000	No Benchmark	2,290	2,010	1,757,035	39,100

*Highend systems performance per core²*
	TPC-C	SPECint_rate2006	SPECfp_rate2006	SPECjbb2005	2-tier SAP SD
64-core, 32 chip, 128 threads IBM Power 595	95,081	32.5	33.0	53,679	553
128-core, 64 chips, 256 threads HP Integrity Superdome	31,975	12.9	11.6	16,054	234
256-core, 64 chips, 512 threads Sun SPARC Enterprise M9000	No Benchmark	8.9	7.9	6,863	153

These benchmarks show the outstanding systems performance and scalability of the Power 595, but sometimes overall systems performance is not the most important factor, especially in a consolidated environment. Some applications are more bound by memory constraints, either based on the quantity of memory available or the memory bandwidth. Others are constrained by I/O bandwidth. When we compare those characteristics, the Power 595 is equally impressive.

Memory & I/O Characteristics³	IBM Power 595	HP Superdome	Sun M9000
Cores	64	128	128
Memory (GB)	4096	2048	2048
Memory Bandwidth (GB/s)	1376	273.1	737
I/O Bandwidth (GB/s)	640	172.8	234

Memory (GB) per core	64	16	16
Memory Bandwidth (GB/s) per core	21.50	2.13	5.76
I/O Bandwidth (GB/s) per core	10.00	1.35	1.83

Besides delivering two times the processor performance per core, the Power 595 also supports 4 times the memory per core, over 3 ½ times the memory bandwidth per core and over 5 times the I/O bandwidth per core of the Integrity Superdome and the M9000 highend systems. The tremendous capacity of the IBM Power 595 server can help you run challenging applications in every partition.

The Power 595 server is the fastest system with the fastest processor, the most memory capability, and I/O bandwidth. It is no wonder that it is a prime target for highly consolidated environments.

Compare midrange servers

The workhorse UNIX® database and application servers have to deliver cost effective, reliable performance for mission-critical applications. Using advanced features like virtualization, IBM POWER6™ processor performance, and mainframe-inspired reliability, availability, and serviceability (RAS) characteristics, the IBM Power™ 570 server epitomizes what today's midrange server should be.

The POWER6 processor technology and advanced system design of the Power 570 server create a system with leadership-balanced performance. The very fast processor, up to 5.00 GHz, with system bus, I/O bandwidth, and large memory capacity that grows with the number of processors leads to the astounding performance proven by the number of leadership commercial and technical benchmarks.

The result is the very best performance for a midrange server, and the very best performance per core of a midrange server.

We compare performance because the exceptional speed of the Power 570 system is allows you to improve end user's service. And this is designed to be done with fewer cores which helps reduce your cost and improve system manageability.

The following table summarizes the best midrange server performance result for the IBM Power 570 server versus Sun and HP 32-core and 64-core midrange UNIX servers. The results show that the Power 570 server has the very best performance of any midrange server.

*Top of the Midrange Performance⁴*
	TPC-C	SPECint_rate2006	SPECfp_rate2006	SPECjbb2005	2-tier SAP SD
32-core IBM Power 570	No Benchmark	832	602	1,390,087	14,432
16-core IBM Power 570	1,616,162	542	544	867,989	8,000
32-core HP Integrity rx8640	No Benchmark	416	371	No Benchmark	No Benchmark
64-core Sun SPARC Enterprise M8000	No Benchmark	637	582	817,158	No Benchmark
32-core Sun SPARC Enterprise M8000	No Benchmark	352	333	395,989	7,300

The Power 570 server leads competitive midrange systems in capacity by far. However that is only one measure of performance. Better performance per core helps reduce cost in hardware acquisition, software licensing, and a variety of operational areas. The following table shows the Power 570 server performance per core compared to Sun and HP midrange servers.

*Top of the Midrange Systems Performance per Core⁵*
	TPC-C	SPECint_rate 2006	SPECfp_rate 2006	SPECjbb 2005	2-tier SAP SD
32-core, 16 chips, 64 threads IBM Power 570	No Benchmark	26	19	43,440	451
16-core, 8 chips, 32 threads IBM Power 570	101,010	34	34	54,249	500
32-core, 16 chips, 64 threads HP Integrity rx8640	No Benchmark	13	12	No Benchmark	No Benchmark
64-core, 16 chips, 128 threads Sun SPARC Enterprise M8000	No Benchmark	10	9	12,768	No Benchmark
32-core, 16 chip, 64 threads Sun SPARC Enterprise M8000	No Benchmark	11	10	12,375	228

With performance per core more than double the midrange competitors, the Power 570 server can enable you to reduce the number of servers and/or the size of servers you require to do your production. Consolidation using the PowerVM™ feature of the Power 570 server can also help you increase the utilization of your servers which could enable you to even further reduce cost by implementing fewer servers.

Processing power is not the only resource required by applications. Other resource is also required for consolidation. The 570 has that resource. On a per-core basis, the 5.00GHz 16-core 570 has three times the memory, over seven times the memory bandwidth, and more than two times the I/O bandwidth of HP, and four times the memory, over 5 times the memory bandwidth, and over four times the I/O bandwidth of Sun. The 4.20GHz 32-core Power 570, optimized for space and energy efficiency, still has more capacity per core than the rx8640 and M8000.

*Top of the Midrange Bandwidth⁶*
	IBM Power 570		HP rx8640	Sun M8000
Cores	16	32	32	64
Memory (GB)	768	768	512	512
Memory Bandwidth (GB/s)	256	256	68	184
I/O Bandwidth (GB/s)	66.7	56	48	61

Memory (GB) per core	48	24	16	8
Memory Bandwidth (GB/s) per core	16	8	2.13	2.88
I/O Bandwidth (GB/s) per core	3.9125	1.75	1.50	0.95

This combination of more performance per core and more I/O and memory capacity and bandwidth per core helps you to reduce the number of servers or the number of cores per server. This could have a major impact on reducing your cost of server acquisition and your total cost of ownership for your IT environment.

The midrange also has systems with less configuration and performance capability. The Power 560 Express has the same advantages in this space as the Power 570 has in its space with 45 to 80% performance per core advantage versus HP systems and 71 to 185% performance per core advantage versus Sun systems. The 560 Express also has tremendous advantage in bandwidth with 8 times the memory bandwidth of the HP Integrity rx7640 and the Sun SPARC Enterprise M5000.

*Midrange Performance⁷*
	SPECint_rate2006	SPECfp_rate2006	SPECjbb2005
16-core IBM Power 560 Express	363	263	593,904
16-core HP Integrity rx7640	201	181	No Benchmark
32-core Sun SPARC Enterprise M5000	264	223	No Benchmark
32-core Sun SPARC Enterprise T5440	301	230	692,736

*Midrange Systems Performance per core⁸*
	SPECint_rate2006	SPECfp_rate2006	SPECjbb2005
16-core IBM Power 560 Express	23	16	37,119
16-core HP Integrity rx7640	13	11	No Benchmark
32-core Sun SPARC Enterprise M5000	8	7	No Benchmark
32-core, 4 chip, 256 thread Sun SPARC Enterprise T5440	9	7	21,648

*Midrange Bandwidth⁹*
	IBM Power 560	HP rx7640	Sun M5000
Cores	16	16	32
Memory (GB)	384	256	256
Memory Bandwidth (GB/s)	128	32	64
I/O Bandwidth (GB/s)	24	23	16

Memory (GB) per core	24	16	8
Memory Bandwidth (GB/s) per core	8	2	2
I/O Bandwidth (GB/s) per core	1.5	1.4375	0.5

The IBM Power Systems midrange servers are designed to support today’s data center. They have the performance, capacity, and bandwidth to support multi-application consolidated environments to help you control cost of operation and acquisition of your environment.

Compare Entry Servers

As entry servers become faster, more customers find them the right performance for mission-critical applications. They also are often the right servers for distributed applications in stores and branch banks. The same POWER6 technology that makes the Power 570 the fastest midrange server helps make the IBM Power 550 Express system the fastest UNIX entry server. The comparison to the 8-core HP Integrity rx6600 and the 16-core Sun SPARC Enterprise M4000 servers help demonstrate this. In fact, the Power 550 Express server has such excellent performance that its result for the demanding TPC-C benchmark is even better than the best HP 9000 Superdome result ever posted¹⁰. The 4-core IBM Power Express 520 provides comparable performance to these competitive systems at a much lower price. The very affordable price of the Power 520 Express can help you reduce cost even more.

*Top of the Entry Systems Performance¹¹*
	TPC-C	SPECint_rate 2006	SPECfp_rate 2006	2-tier SAP SD
IBM Power 550 Express	629,159	263	222	3,104
HP Integrity rx6600	372,140	102	71	2,150
Sun SPARC Enterprise M4000	No Benchmark	135	112	No Benchmark
Sun SPARC Enterprise T5240	No Benchmark	157	119	4,170

Entry Systems Performance	SPECint_rate2006	SPECfp_rate2006
IBM Power 520 Express	124	106
HP Integrity rx3600	62.4	54.8
SUN SPARC Enterprise M3000	40.8	35.2

The advantage of the Power 550 and Power 520 Express servers is even more evident when you look at performance per core.

*Top of the Entry Systems Performance per core¹²*
	TPC-C	SPECint_rate 2006	SPECfp_rate 2006	2-tier SAP SD
IBM Power 550 Express (8 cores, 4chips, 16 threads)	78,645	33	28	388
HP Integrity rx6600 (8 cores, 4chips, 16 threads)	46,518	13	9	269
Sun SPARC Enterprise M4000 (16 cores, 4 chips, 32 threads)	No Benchmark	8	7	No Benchmark
Sun SPARC Enterprise T5240 (16-cores, 2chips, 128 threads)	No Benchmark	10	7	261

Entry Systems Performance per core	SPECint_rate2006	SPECfp_rate2006
IBM Power 520 Express	31	26.5
HP Integrity rx3600	15.6	13.7
SUN SPARC Enterprise M3000	10.2	8.8

Like its highend and midrange counterparts, the Power 550 Express and Power 520 Express also have significantly greater memory and I/O bandwidth per core than the HP and Sun systems. They are also designed to support consolidated environments.

*Midrange Bandwidth¹³*
	IBM Power 550	HP rx6600	Sun M4000
Cores	8	8	16
Memory (GB)	256	384	128
Memory Bandwidth (GB/s)	128	17	32
I/O Bandwidth (GB/s)	23.2	9.8	8

Memory (GB) per core	32	48	8
Memory Bandwidth (GB/s) per core	16	2.125	2
I/O Bandwidth (GB/s) per core	2.9	1.225	0.5

Compare Blade Servers

Blade servers have become increasing popular because of their outstanding performance efficiency. Performance per rack unit (u) and performance per WATT advantage of blades has caused a movement from rack servers to blades. The performance of POWER6 processors has helped the IBM BladeCenter JS23 and JS43 to be the leaders among RISC and Itanium blade servers in these metrics. This efficiency directly leads to reduced cost of energy and floor space. The superior performance per core of the JS23 and JS43 lead to a requirement for fewer blades which also reduces cost of management, and software licensing as well as additional reductions in energy and floor space.

*Throughput (SPECint_rate2006) per core, per rack unit and per WATT¹⁴*
System Name	Peak / Core	Peak / u	Peak / WATT
IBM BladeCenter JS43 (4.20GHz, 8 core)	27.38	170.33	0.53
IBM BladeCenter JS23 (4.20GHz, 4 core)	27.50	171.11	0.53
IBM BladeCenter JS12 Express (3.80GHz, 2 core, RedHat)	22.95	71.40	0.22
HP Integrity BL860c (1.60GHz/18MB Dual-Core Intel Itanium 2)	13.48	43.12	0.18
Sun Blade T6340	10.00	182.86	0.40

Close [x]

Video not available.

1. Competitive benchmark results reflect results published as of April 21, 2009. The results are the best IBM Power 595 64-core server result, the best 256-core Sun SPARC Enterprise M9000 server results and the best 128-core HP Integrity Superdome results. Cells were left blank if there is no posted result for the benchmark. The TPC-C results can be found at www.tpc.org (link resides outside of ibm.com). The SPECint_rate2006, SPECfp_rate2006 and SPECjbb2005 results can be found at www.spec.org (link resides outside of ibm.com). The SAP SD 2-tier results can be found at www.sap.com (link resides outside of ibm.com).

TPC-C results as of April 21, 2009. Source: http://www.tpc.org (link resides outside of ibm.com).

System	Chip/Core/ Thread	Systems Availability	$/tpmC	Database	OS	tpmC	tpmC/Core
IBM Power 595 (5.00 GHz POWER6)	32/64/128	12/10/08	$2.81	IBM DB2 9.5	AIX V5.3	6,085,166	95,080
HP Superdome (1.60 GHz Itanium 2)	64/128/256	08/06/07	$2.93	Oracle 10g	HP-UX 11i v3	4,092,799	31,975

SPEC® and the benchmark names SPECrate®, SPECint®, and SPECjbb® are registered trademarks of the Standard Performance Evaluation Corporation. For the latest SPEC benchmark results, visit http://www.spec.org (link resides outside of ibm.com)

*Highend SPECint_rate2006 results as of April 21, 2009*
System Name	Cores	Chips	Cores / Chip	Threads / Core	Peak
IBM Power 595 (5.00 GHz, 64 core)	64	32	2	2	2080
HP Integrity Superdome (1.60GHz/24MB Dual-Core Intel Itanium 2)	128	64	2	1	1650
Sun SPARC Enterprise M9000	256	64	4	2	2290

*Highend SPECfp_rate2006 results as of April 21, 2009*
System Name	Cores	Chips	Cores / Chip	Threads / Core	Base	Peak
IBM Power 595	64	32	2	2	1820	2110
HP Integrity Superdome	128	64	2	1	1420	1480
Sun SPARC Enterprise M9000	256	64	4	2	1860	2010

*Highend SPECjbb2005 results as of April 21, 2009*
HW System Name	JVM Instances	Cores	Chips	HW Threading	bops	bops/JVM
IBM Power 595 (5.00 GHz, 64 core)	32	64	32	Yes	3435485	107359
HP Integrity SD64B Server	32	128	64	No	2054864	64215
Sun SPARC Enterprise M9000	1	256	64	Yes	1757035	1757035

SAP performance of highend servers from IBM, Sun, and HP. All results published as of April 21, 2009.

Number of Benchmark Users	Operating System	ERP Release	Central Server	Chips	Cores	Threads	Technology	GHz	Certificate Number
35400	AIX Version 6.1	6.0 (2005)	IBM Power 595	32	64	128	POWER6	5	2008019
39100	Solaris 10	6.0 (2005)	*SPARC Enterprise Server M9000	64	256	512	SPARC64 VII	2.52	2008042
30000	HP-UX 11iV3	2005	HP Integrity SD64B	64	128	265	Dual-Core Intel Itanium 2 9050	1.60	2006089

For full details on these and other SAP benchmarks, see SAP SD Standard Application Benchmark Results, Two-Tier Internet Configuration at http://www.sap.com/solutions/benchmark/sd2tier.epx (link resides outside of ibm.com)

2. The highend systems performance per core is calculated by dividing the values in the highend systems performance table by the number of cores in each benchmarked system. The number of cores for each result is shown in the tables in footnote 1

3. Comparisons between the IBM Power™ 595 server, the HP Integrity Superdome Server and the Sun SPARC Enterprise M9000 server. System data for HP from the HP Superdome Datasheet available at www.hp.com. System data for Sun from the Sun SPARC Enterprise M9000 Datasheet available at www.sun.com (link resides outside of ibm.com). Data is current as of April 21, 2009.

4. Competitive benchmark results reflect results published as of April 21, 2009. The results are the best IBM Power 570 16-core server result, the best Sun SPARC Enterprise M8000 server 32- and 64-core results, and the best HP Integrity rx8640 server 32-core result. Cells were with a value of 'No Benchmark' indicates there is no posted result for the benchmark for that system. The TPC-C results can be found at www.tpc.org (link resides outside of ibm.com). The SPECint_rate2006, SPECfp_rate2006 and SPECjbb2005 results can be found at www.spec.org (link resides outside of ibm.com). The SAP SD 2-tier results can be found at www.sap.com (link resides outside of ibm.com).

The TPC-C results for the top of the midrange are:

* Hardware Vendor (link resides outside of ibm.com)	System (link resides outside of ibm.com)	tpmC (link resides outside of ibm.com)	Price/tpmC (link resides outside of ibm.com)	System Availability (link resides outside of ibm.com)	Date Submitted (link resides outside of ibm.com)
IBM	IBM Power 570 (link resides outside of ibm.com)	1,616,162	3.54 US $	11/21/07	05/21/07

The IBM Power 570 has 8-processor chips, 16-cores, and 2-threads per core.

TPC-C results as of April 21, 2009. Source: http://www.tpc.org (link resides outside of ibm.com)

The SPECint_rate2006 results for the top of the midrange are:

*Top of the midrange SPECint_rate2006 results as of April 21, 2009*
System Name	Cores	Chips	Cores / Chip	Threads / Core	Peak
IBM Power 570 (4.20GHz, 32 core)	32	16	2	2	832
IBM Power 570 (5.00GHz, 16 core)	16	8	2	2	542
HP Integrity rx8640 (1.60GHz/24MB Dual-Core Intel Itanium 2)	32	16	2	1	416
Sun SPARC Enterprise M8000	64	16	4	2	637
Sun SPARC Enterprise M8000	32	16	2	2	352

SPECfpRate_2006 results for the top of the midrange are:

*Top of the midrange SPECfp_rate2006 results as of April 21, 2009*
System Name	Cores	Chips	Cores / Chip	Threads / Core	Peak
IBM Power 570 (4.20GHz, 32 core)	32	16	2	2	832
IBM Power 570 (5.00GHz, 16 core)	16	8	2	2	542
HP Integrity rx8640 (1.60GHz/24MB Dual-Core Intel Itanium 2)	32	16	2	1	416
Sun SPARC Enterprise M8000	64	16	4	2	637
Sun SPARC Enterprise M8000	32	16	2	2	352

The SPECjbb2005 results for the top of the midrange are:

*Top of the midrange SPECjbb2005 results as of April 21, 2009*
HW System Name	JVM Instances	Cores	Chips	HW Threading	bops	bops/JVM
IBM Power 570 (4.20GHz, 32 core)	16	32	16	Yes	1,390,087	86,880
IBM Power 570 (5.00GHz, 16 core)	8	16	8	Yes	867,989	108,499
Sun SPARC Enterprise M8000	16	64	16	Yes	817,158	51,072
Sun SPARC Enterprise M8000	16	32	16	No	440,207	27,513

The SAP SD 2-tier results for the top of the midrange as of April 21, 2009 are:

Number of Benchmark Users	Operating System	ERP Release	Central Server	Chips	Cores	Threads	Technology	GHz
14432	AIX 6.1	16	IBM Power 570	16	32	64	POWER6	4.20	2008057
8000	AIX 5.3	6.0 (2005)	IBM Power 570	8	46	32	POWER6	4.7	2007039
7300	Solaris 10	16	Sun SPARC Enterprise M8000	16	32	65	SPARC64 VI	2.4	2007026

5 The midrange systems performance per core is calculated by dividing the values in the midrange systems performance table by the number of cores in each benchmarked system. The number of cores for each result is shown in the tables in footnote 4.

6. Comparisons between the IBM Power 570, HP rx8640, and Sun SPARC Enterprise M8000: HP rx8640 data from Intel Itanium-based midrange servers from HP—The HP Integrity (link resides outside of ibm.com) rx7640 and rx8640 Servers (link resides outside of ibm.com) white paper at http://h71028.www7.hp.com/ERC/downloads/5982-9681en.pdf?jumpid=reg_R1002_USEN (link resides outside of ibm.com) on April 21, 2009. System data for Sun from the Sun SPARC Enterprise M8000 Tech Specs available at www.sun.com. Data is current as of April 21, 2009.

7. Competitive benchmark results reflect results published as of April 21, 2009. The results are the best IBM Power 560 16-core server result, the best Sun SPARC Enterprise M5000 server 32-core results, the best Sun SPARC Enterprise T5440 result, and the best HP Integrity rx7640 server 16-core result. Cells with the entry “No Benchmark” indicate there is no posted result for the benchmark.. The SPECint_rate2006, SPECfp_rate2006 and SPECjbb2005 results can be found at www.spec.org (link resides outside of ibm.com).

SPECint_rate2006 results are:

*Midrange SPECint_rate2006 results as of April 21, 2009*
System Name	Cores	Chips	Cores / Chip	Threads / Core	Peak
IBM Power 560	16	8	2	2	363
HP Integrity rx7640 (1.60GHz/18MB Dual-Core Intel Itanium 2)	16	8	2	1	201
Sun SPARC Enterprise M5000	32	8	4	2	264
Sun SPARC Enterprise T5440	32	4	8	8	301

SPECfp_rate2006 results are:

*Midrange SPECfp_rate2006 results as of April 21, 2009*
System Name	Cores	Chips	Cores / Chip	Threads / Core	Peak
IBM Power 560	16	8	2	2	263
HP Integrity rx7640 (1.60GHz/18MB Dual-Core Intel Itanium 2)	16	8	2	1	181
Sun SPARC Enterprise M5000	32	8	4	2	223
Sun SPARC Enterprise T5440	32	4	8	8	230

SPECjbb2005 results are:

*Midrange SPECjbb2005 results as of April 21, 2009*
HW System Name	JVM Instances	Cores	Chips	HW Threading	bops	bops/JVM
IBM Power 560	8	32	16	Yes	593,904	74,238
Sun SPARC Enterprise T5440	32	32	4	Yes	692736	21648

8. The midrange systems performance per core is calculated by dividing the values in the midrange systems performance table by the number of cores in each benchmarked system. The number of cores for each result is shown in the tables in footnote 7.

9. Comparisons between the IBM Power 560, HP rx7640, and Sun SPARC Enterprise M5000: HP rx7640 data from Intel Itanium-based midrange servers from HP—The HP Integrity rx7640 and rx8640 Servers (link resides outside of ibm.com) white paper at http://h71028.www7.hp.com/ERC/downloads/5982-9681en.pdf?jumpid=reg_R1002_USEN (link resides outside of ibm.com) on April 21, 2009. System data for Sun from the Sun SPARC Enterprise M5000 Tech Specs available at www.sun.com. Data is current as of April 21, 2009.

10. Comparison of IBM Power 550 Express and HP 9000 Superdome.

TPC-C results are:

*TPC-C Benchmark results*
System (link resides outside of ibm.com)	Processor Chips	Cores	Threads	tpmC (link resides outside of ibm.com)	Price/tpmC (link resides outside of ibm.com)	System Availability (link resides outside of ibm.com)	Date Submitted (link resides outside of ibm.com)
HP Superdome – PA-RISC/875 MHz	64	64	64	541,674	11.66 US $	01/30/04	07/30/03
IBM Power 550 Express (link resides outside of ibm.com)	4	8	16	629,159	2.49 US $	4/20/2008	03/20/08

TPC-C results as of April 21, 2009. Source: http://www.tpc.org (link resides outside of ibm.com)

11. Competitive benchmark results reflect results published as of April 21, 2009. The results are the best IBM Power 550 Express 8-core server result, the best IBM Power 520 Express 4-core result, the best Sun SPARC Enterprise M4000 server 16-core result, the best Sun SPARC Enterprise T5240 result, and the best HP Integrity rx6600 server 8-core result. Cells with “No Benchmark” in dicate there is no posted result for the benchmark.. The SPECint_rate2006, SPECfp_rate2006 and SPECjbb2005 results can be found at www.spec.org (link resides outside of ibm.com). midrange

TPC-C results for entry systems are:

*TPC-C Benchmark results*
System (link resides outside of ibm.com)	Processor Chips	Cores	Threads	tpmC (link resides outside of ibm.com)	Price/tpmC (link resides outside of ibm.com)	System Availability (link resides outside of ibm.com)	Date Submitted (link resides outside of ibm.com)
HP Integrity rx6600 (link resides outside of ibm.com)	4	8	16	372,140	1.81 US $	6/11/2007	06/11/07
IBM Power 550 Express (link resides outside of ibm.com)	4	8	16	629,159	2.49 US $	4/20/2008	03/20/08

TPC-C results as of April 21, 2009. Source: http://www.tpc.org (link resides outside of ibm.com)

SPECint_rate2006 results are:

Top of the Entry System Name	Enabled Cores	Enabled Chips	Cores / Chip	Threads / Core	Peak Result	Peak / Core
IBM Power 550 Express	8	4	2	2	263	32.9
HP Integrity rx6600	8	4	2	1	102	12.8
Sun SPARC Enterprise M4000	16	4	4	2	135	8.4
Sun SPARC Enterprise T5240	16	2	8	8	157	9.8

Entry System Name	Enabled Cores	Enabled Chips	Cores / Chip	Threads / Core	Peak Result	Peak / Core
IBM Power 520 Express	4	2	2	2	124	31.0
HP Integrity rx3600	4	2	2	2	62.4	15.6
Sun SPARC Enterprise M3000	4	1	4	2	40.8	10.2

All results posted on www.spec.org (link resides outside of ibm.com) except IBM Power 550 and IBM Power 520 results which were submitted to SPEC on April 28, 2009.

SPECfp_rate2006 results are:

Top of the Entry System Name	Enabled Cores	Enabled Chips	Cores / Chip	Threads / Core	Peak Result	Peak / Core
IBM Power 550 Express	8	4	2	2	222	27.8
HP Integrity rx6600	8	4	2	1	71.4	8.9
Sun SPARC Enterprise M4000	16	4	4	2	135	8.4
Sun SPARC Enterprise T5240	16	2	8	8	119	7.4

Entry System Name	Enabled Cores	Enabled Chips	Cores / Chip	Threads / Core	Peak Result	Peak / Core
IBM Power 520 Express	4	2	2	2	106	26.5
HP Integrity rx3600	4	2	2	2	54.8	13.7
Sun SPRC Enterprise M3000	4	1	4	2	35.2	8.8

All results posted on www.spec.org (link resides outside of ibm.com) except IBM Power 550 and IBM Power 520 results which were submitted to SPEC on April 28, 2009.

SAP SD 2-tier results are:

Number of Benchmark Users	Operating System	ERP Release	Central Server	Chips	Cores	Threads	Technology	GHz	Certificate Number
3104	RedHat Enterprise Linux 5	6.0 (2005)	IBM Power 550	4	8	16	POWER6	4.20	2008002
2150	HP-UX 11iV3	2005	HP Integrity rx6600	4	8	16	Dual-Core Intel Itanium 2 9050	1.60	2006083
4170	Solaris 10	6.0 (2005)	Sun SPARC Enterprise Model T5240	2	16	128	UltraSPARC T2 Plus	1.4	2008021

12. The entry systems performance per core is calculated by dividing the values in the entry systems performance table by the number of cores in each benchmarked system. The number of cores for each result is shown in the tables in footnote 11.

13. Comparisons between the IBM Power 550, HP rx6600, and Sun SPARC Enterprise M4000: HP rx6600 data from HP Integrity rx6600 Server Specifications at http://h20341.www2.hp.com/integrity/cache/392325-0-0-0-121.html?jumpid=reg_R1002_USEN (link resides outside of ibm.com) on April 21, 2009. System data for Sun from the Sun SPARC Enterprise M4000 Tech Specs available at www.sun.com. Data is current as of April 21, 2009.

14. Competitive benchmark results reflect results published as of April 21, 2009. The results are the best IBM BladeCenter JS43, JS23 and JS12 results, the best Sun Blade server results using SPARC based blade servers, and the best HP Blade Server results using Itanium based blade servers.. The SPECint_rate2006 results which can also be found at www.spec.org (link resides outside of ibm.com). are:

*SPECint_rate2006 results for blades as of April 21, 2009*
System Name	Enabled Cores	Enabled Chips	Cores / Chip	Threads / Core	Peak Result
IBM Bladecenter JS43	8	4	2	2	219
IBM Bladecenter JS23	4	2	2	2	110
IBM BladeCenter JS12 Express (3.8 GHz, 2 core, RedHat)	2	1	2	2	45.9
HP Integrity BL860c (1.60GHz/18MB Dual-Core Intel Itanium 2)	4	2	2	1	53.9
Sun Blade T6340	16	2	8	8	160

All results posted on www.spec.org (link resides outside of ibm.com) except IBM BladeCenter JS43 and IBM BladeCenter JS23 results which were submitted to SPEC on April 28, 2009.

Peak per u calculated based on SPECint_rate2006 peak divided by the number of u (1.75”) of rack space used by a blade server in a full IBM BladeCenter H for IBM blades, full HP BladeSystem c7000 Enclosure for HP, and full Sun Blade 6048 Modular System for Sun blades. Peak per WATT calculated by dividing SPECint_rate2006 by maximum power requirement supplied by the blade enclosure (2900 WATTs for the BladeCenter H, 2400 WATTs for the c7000 Enclosure and 8400 WATTs for the 6048 Modular system.)