|
Sun SPARC Enterprise T5140 and T5240 servers are the industry's first dual socket CMT platforms,
delivering the highest compute density ever, with up to 128 threads in as little as 1 RU of physical space while
maintaining maximum power efficiency to deliver outstanding levels of performance per watt. With up to 5,120
threads per rack, the Sun SPARC Enterprise T5140 server delivers 32x the compute density of the competing 4-socket
servers. Additionally, the Sun SPARC Enterprise T5140 and T5240 servers offer rich memory and disk expandability, an
embedded hypervisor at no additional cost, integrated cryptographic acceleration and high I/O bandwidth. The above
features make Sun's CMT-based servers ideally suited for efficient and secure virtualization of demanding application
services, web-based applications, as well as distributed OLTP databases and back-office applications. The Sun SPARC
Enterprise T5140 and T5240 servers couple high performance with a low cost, space and power efficient design.
Organizations can transform their web scale and enterprise application infrastructure with unsurpassed throughput,
while slashing capital and operational expense.
The Sun SPARC Enterprise T5240 server running the open source Solaris 10 OS and Oracle Database Server 10g
delivered the highest dual-socket result on SAP SD-2-tier benchmark, an industry standard measure of ERP performance.
This breakthrough score outperforms systems based on IBM Power6 and Intel Xeon processors and confirms the Sun SPARC
Enterprise T5240 server as one of the highest performing and most space efficient platforms on the planet for deploying
ERP solutions.
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.
|
|
|
|
|
Space (RU) |
2 |
4 |
4 |
2 |
Performance (Users) |
4,170 |
2,035 |
3,705 |
2,436 |
Users per Rack Unit (Higher is Better) |
2,085 |
508.8 |
926.25 |
1,218 |
|
Benchmark Outcome (7)
- The Sun SPARC Enterprise T5240 server, equipped with the new UltraSPARC T2 Plus CPUs, posted the
best dual-processor result on SAP SD 2-Tier benchmark, supporting 4,170 users. Additionally, Sun's
server is the first dual-processor system to exceed 20,000 SAPS, the hardware-independent metric
that describes the performance of a system configuration in the SAP environment, all while maintaining
the best Rack Unit to Users ratio.
- This benchmark proves that the Sun SPARC Enterprise T5240 server, running Oracle 10g Database Server
on the top of Solaris 10, which is the most reliable OS in the industry, is well-suited to act as an enterprise
class OLTP database server, providing supreme levels of comnpute density.
- The result also highlights the vertical consolidation capability of the new server that delivered world
record level of performance and space efficiency, while running both the SAP application and the Oracle database
on the same physical system. Additionally, the Sun SPARC Enterprise T5240 server with two 1.4 GHz UltraSPARC T2
Plus processors demonstrated near linear scalability with 1.9x improvement over single socket Sun SPARC Enterprise
T5120 server equipped with 1.4 GHz UltraSPARC T2 processor.
- The Sun SPARC Enterprise T5240 server delivers twice the number of SAPS in half the space, when compared to the
IBM p570 server, equipped with two dual-core 4.7GHz Power6
- processors and running AIX 5.3 OS.
The Sun SPARC Enterprise T5240 server delivers over 70% more users per RU when compared to the HP Proliant DL380 G5
server, equipped with two of the latest quad-core Intel Xeon 5460 CPUs and running Windows Server Enterprise Edition
2003 OS.
- The Sun SPARC Enterprise T5240 server delivers over 2.2x more users per RU when compared to the HP Proliant DL580
G5 server, equipped with four of the latest quad-core Intel Xeon 7350 CPUs and running Windows Server Enterprise Edition
2003 OS.
(7)
SAP and all SAP logos are trademarks or registered trademarks of SAP AG in Germany and in several other countries.
Results of two-tier SAP SD Standard Application Benchmarks as of April 9, 2008: The SPARC Enterprise Model T5240,
2 processors / 16 cores / 128 threads, UltraSPARC T2 Plus, 1.4 GHz, 8 KB(D) + 16 KB(I) L1 cache per core, 4 MB L2
cache per processor, 128 GB main memory; Number of benchmark users & comp.: 4,170 SD (Sales & Distribution); Average
dialog response time: 1.97 seconds; Throughput: Fully Processed Order Line items/hour: 418,000, Dialog steps/hour:
1,254,000; SAPS: 20,900; Average DB request time (dia/upd): 0.085 sec / 0.238 sec; CPU utilization of central server:
99%; Operating System central server: Solaris 10; RDBMS: Oracle 10g; SAP ECC Release: 6.0. The SAP certification number
was not available at press time and can be found at http://www.sap.com/benchmark. Sun SPARC Enterprise T5120 (1x1.4 GHz
UltraSPARC T2 processor, 8 cores, 64 threads) running Solaris 10, Oracle 10g and the SAP ERP application Release 6.0
(2005) 2,175 SAP SD benchmark users, Cert#200705. IBM System p570 (2 x 4.7 GHz POWER6 processors, 4 cores, 8 threads)
32 GB mem) running Oracle 10g, AIX 5L Version 5.3. SAP ECC Release 6.0 - 2035 SD benchmark users, 10180 SAPS, 1.99 sec
avg response time, Certification number 2007037. HP ProLiant DL380 G5, (2x3.16 Ghz Quad-Core Intel Xeon Processor Model
X5460, 8 cores, 8 threads) running Windows Server 2003 Enterprise Edition, SQL Server 2005 and the SAP ERP application
Release 6.0 (2005) 2,436 SAP SD benchmark users. Certification number 2007064. HP ProLiant DL580 G5, (X7350, 2.93 4x
2.93 Ghz Quad-Core Intel Xeon Processor Model X7350, 8 cores, 8 threads) running Windows Server 2003 Enterprise Edition,
SQL Server 2005 and the SAP ERP application Release 6.0 (2005) 3,705 SAP SD benchmark users, 18530 SAPS. Certification
number 2007056.
The Sun SPARC Enterprise T5240 server with two UltraSPARC T2 Plus processors was able to support 65,000
simulated email users on Lotus R6i Notes benchmark that was designed to help organizations in estimating
the performance of various hardware solutions while reducing expenses associated with internal benchmark
activities. Sun Microsystems and Lotus Software have been working together since 1989, providing best-of-breed
solutions to the messaging and groupware market. Sun Microsystems is a prominent player in the Lotus Domino market
and has been using this benchmark for many years to guide customers to more sensible solutions based on Sun's hardware.
Benchmark Description
The NotesBench R6iNotes benchmark is used for performance evaluation of hardware solutions offered by various
vendors. It simulates active e-mail users accessing their IBM Lotus Domino mailboxes via standard web browser where
each simulated user periodically sends, retrieves, and deletes a specified number of e-mail messages.
|
|
|
|
Space (RU) |
2 |
8 |
2 |
Power Consumption (Watts) |
815 |
1,820 |
498 |
Performance per Socket (Users) |
32,500 |
13,750 |
11,000 |
Performance (Users) |
65,000 |
55,000 |
22,000 |
Performance / Watt (Higher is Better) |
79.755 |
30.220 |
44.177 |
SWaP (Higher is Better) |
39.9 |
3.8 |
22.1 |
$ / User |
$2.84 |
$4.89 |
$3.47 |
|
Benchmark Outcome (6)
- The Sun SPARC Enterprise T5240 server using two 1.2 GHz UltraSPARCT2 Plus processors achieved the World Record
number of supported users among all classes of servers using the Lotus Domino 7.0.1 Messaging server on Lotus R6iNotes
benchmark.
- The Sun SPARC Enterprise T5240 server using two 1.2 GHz UltraSPARC T2 Plus processors can support 65,000 email users
with an average response time of less than 224 milliseconds and a price/performance of $2.84/user. This result signifies
the highest number of supported R6iNotes users ever reported.
- The dual-socket Sun SPARC Enterprise T5240 server running Lotus Domino 7.0.1 Messaging server under Solaris 10 OS
supported 18% more users at 42% better price per user than IBM p 560Q server with eight Power5+ processors. Notably, the
Sun SPARC Enterprise T5240 server used half the space of the 4RU IBM p 560Q server.
- Compared to the IBM p 560Q server configured with four quad core Power 5+ processors and running AIX 5.3, the dual
processor Sun SPARC Enterprise T5240 server delivers over 2x higher throughput on a per socket basis and 3.8x faster
response time. Additionally, Sun's new server has 2.5x better Performance per Watt at 58% better Price per User.
- This result demonstrates an innovative solution that utilizes the latest generation of CMT processors and allows organizations
to minimize their IT expenditures by servicing e-mail users at a lower price point. The Sun SPARC Enterprise T5240 server demonstrates
the lowest cost per user among all competitive systems from HP and IBM.
- The SWaP metric is a measure of server efficiency ratio that includes system performance, power and space consumption on a
specific benchmark. (SWaP = Perf /[ Space (RU) x Watts ] ). The Sun SPARC Enterprise T5240 server has 10x lead over IBM p 560Q
server.
- Compared to the IBM x3650 server equipped with two dual core Intel Xeon 5100 series processors and running SuSE Linux Enterprise
Server, the dual processor Sun SPARC Enterprise T5240 server delivers nearly 3x higher throughput, with over 13x faster response time.
Additionally, Sun's new server has 80% better performance per Watt at over 20% better Price per User.
- Compared to the dual-socket HP BL480C blade system equipped with Intel Xeon quad-core processors, the dual processor Sun SPARC
Enterprise T5240 server delivers 2.4x higher performance with nearly 5x better price/performance.
(6)
Sun SPARC Enterprise T5240 (2 x 1200 Mhz UltraSPARC T2 Plus, 128GB), 6 partitions, Solaris [TM] 10,Lotus[R]Domino 7.0.1,
65,000 NotesBench R6iNotes users, $2.84 per user, 55,101 NotesMark tpm, 224 ms avg. IBM x3650 (2 x 3GHz Intel Xeon 5160, 24GB),
4 partitions, SuSE Linux Enterprise Server 9.0 SP3, Lotus[R]Domino 7.0, 22,000 NotesBench R6iNotes users, $3.47 per user, 17,777
NotesMark tpm, 3.056 seconds avg. IBM p5 560Q (4 x 4 core 1.8GHz Power 5+, 64GB), 6 partitions, AIX 5L V5.3, Lotus[R] Domino 7.0.1,
5,000 NotesBench R6iNotes users, $4.89 per user, 46,193 NotesMark tpm, 848 ms avg. HP BL480C (2 x 2.66GHz Intel Xeon X5355, 8GB), 3
partitions, Windows Server 2003, Lotus[R] Domino 7.0, 27,000 users, $13.27 per user, 23,117 NotesMark tpm, 0.764 seconds avg NotesBench
R6iNotes. More info www.notesbench.org
IBM x3650 power consumption obtained from IBM Power configurator for system configured with 2 x Xeon 5160 3.0GHz processors, redundant
PSU, 12 x 2GB DIMMs, and 2 x 74GB SAS drives, on 24/8/07.
IBM p 560Q power rating of 1820W is estimated as 70% of maximum PSU rating published here on 03/26/07
Sun SPARC Enterprise T5240 power consumption taken from measurements made during the benchmark run.
The Sun SPARC Enterprise T5240 server running the Solaris 10 OS and Oracle Application Server outperformed all other
single Application servers on the SPECjAppServer2004 benchmark, including systems based on the latest IBM Power6, Intel
Xeon and Intel Itanium2 processors. In addition, the Sun SPARC Enterprise T5240 server delivered the highest Performanc
per Watt and the best Performance per Rack Unit (RU) in Java application serving.
The database tier of the benchmark was powered by a Sun SPARC Enterprise T5240 Server running Oracle Database 10g on
Solaris 10 OS. The result achieved on the Database tier of the benchmark is a single server World Record as well.
These results confirm the Sun SPARC Enterprise T5240 server as the highest performing and most efficient platform on
the planet for deployment of secure Application and OLTP database services.
Benchmark Description
The SPECjAppServer2004 is a multi-tier benchmark for measuring the performance of Java 2 Enterprise Edition (J2EE)
technology-based application servers that was developed to aid potential users in understanding the capabilities of
different solutions under a heavy load. It measures the volume of transactions a particular system configuration can
process while maintaining specified response times for 90% of the transactions. SPECjAppServer2004 is an end-to-end
pplication which exercises all parts of the underlying infrastructure that make up the application environment, including
hardware, JVM software, database software, JDBC drivers, and the system network.
|
|
|
|
|
Space (RU) |
2 |
4 |
5 |
2 |
Power Consumption (Watts) |
720 |
1,120 |
350 |
560 |
Performance (SPECjAppServer2004 JOPS@ Standard) |
3,331.31 |
1,197.51 |
652.95 |
874.17 |
Performance / Watt (Higher is Better) |
4.6 |
1.07 |
1.9 |
1.6 |
Performance / RU (Higher is Better) |
1,665 |
299 |
131 |
437 |
SWaP (Higher is Better) |
2.3 |
0.3 |
0.4 |
0.8 |
|
Benchmark Outcome (5)
- The Sun SPARC Enterprise T5240 server equipped with two 1.4GHz UltraSPARC T2 Plus processors and running the Oracle Application Server 10g under Solaris 10 Operating System obtained a new World Record score of 3,331.31 JOPS@Standard (Java Operations per Second) for all single Application servers on the SPECjAppServer2004 benchmark.
- The Sun SPARC Enterprise T5240 server configured with two 1.4GHz UltraSPARC T2 Plus processors running Oracle Database 10g supported the database tier of the benchmark.
- The new UltraSPARC T2 Plus-based server has been deployed at Application and Database layers of the benchmark demonstrating the Sun SPARC Enterprise T5240 server's ability to perform business critical operations and act as a superb J2EE Application server, as well an outstanding Oracle 10G OLTP database server.
- During benchmark execution the Sun SPARC Enterprise T5240 server in the Application tier consumed an average of 720 Watts in a 2RU space, while the same server in the Database tier consumed only 670 Watts on average.
- The SWaP metric is a measure of server efficiency ratio that includes system performance, power and space consumption on a specific benchmark. SWaP = Perf /[ Space (RU) x Watts ])
- Compared to the result of 1197.51 JOPS@Standard posted by IBM p 570, equipped with two of the latest dual core 4.7GHz Power6 processors and running AIX 5.3, the dual-socket Sun SPARC Enterprise T5240 server delivers nearly 3x more performance in 1/2 the space, while consuming less power. As a result, the Sun SPARC Enterprise T5240 server deliver 4.3x better Performance per Watt and 8x better SwaP.
- Compared to the result of 652.95 JOPS@Standard posted by Dell PowerEdge 2900, equipped with two dual core 3GHz Intel Xeon processors and running Windows Server 2003, the Sun SPARC Enterprise T5240 delivers over 5x higher throughput in half the space. As a result, the Sun SPARC Enterprise T5220 delivers 2.5x better Performance per Watt and over 6x better SwaP.
- Compared to the result of 874.17 JOPS@Standard posted by HP Integrity rx2660, equipped with two of the latest dual core Intel Itanium2 processors and running HP-UX, the Sun SPARC Enterprise T5220 delivers 3.8x higher throughput, while delivering up to 3x better Performance per Watt and SwaP
- The Sun SPARC Enterprise T5240 server with two UltraSPARC T2 Plus processors demonstrated 62% better performance than Intel Xeon-based HP BL460c blade, which has the closest competing score of of 2056.27 JOPS@Standard among all single-node results.
-
(5)
SPEC, SPECjAppServer are registered trademarks of Standard Performance Evaluation Corporation. All results from www.spec.org as of 4/5/08. SPECjAppServer2004: Sun SPARC Enterprise T5240 (16 cores, 2 chip) 3,331 JOPS@Standard. IBM p 570 (4 cores, 2 chips) 1,197.51 JOPS@Standard. Dell 2900 (4 cores, 2 chips) 652.93 JOPS@Standard. HP rx2660 (4 cores, 2 chips) 874.17 JOPS@Standard. HP BL460c (8 cores, 2 chips) of 2056.27 JOPS@Standard
IBM p 570 power rating of 1040W is estimated as 80% of maximum PSU rating published here on 4/4/2008:
Dell PE 2900 power rating of 350 W is estimated as 70% of maximum PSU rating published here on 4/4/2008:
Sun HP rx2660 power rating of 560 W is estimated as 70% of maximum PSU rating published here on 4/4/2008:
SPARC Enterprise T5240 power consumption of 720 watts reported during benchmark run.
IBM pricing of $182,103 from Sun Market Intelligence, 03/04/08. IBM p 570 configured with 2 x 2-core 4.7 GHz Power6 processors, 8 x 2 GB FBDIMMS, 2 x 146 GB SAS 15k HDD, 2 x 1GbE ports, 2 x 1600 Watt PSU, DVD-ROM, Rail kit, AIX 6.1.Sun SPARC Enterprise T5240 pricing at $41,708 configured with 2 x 1.4 GHz UltraSPARC T2 Plus 8 Core processors, 16 x 2 GB FBDIMMS, 2 x 146 10k GB SAS 2.5 HDD, RAID, 4 x 1GbE ports,2 x 1100 Watt PSU, Slim DVD RW, Rail kit, Solaris10
The Sun SPARC Enterprise T5240 server running the Solaris 10 OS and Oracle Database Server 10g outperformed all other
competitive dual-processor servers in the database tier of SPECjAppServer2004 benchmark, including systems based on the
IBM Power 5+, Intel Xeon and Intel Itanium2 processors. In addition, the Sun SPARC Enterprise T5240 server delivered the
highest overall Performance per Watt and SWaP.
The application tier of the benchmark was powered by a Sun SPARC Enterprise T5240 server running Oracle Application Server
10g on Solaris 10 OS. The result achieved on the application tier of the benchmark is a single server World Record as well.
These results confirm the Sun SPARC Enterprise T5240 server as the highest performing and most efficient platform on the plane
for deployment of secure Application and OLTP database services.
Benchmark Description
The SPECjAppServer2004 is a multi-tier benchmark for measuring the performance of Java 2 Enterprise Edition (J2EE)
technology-based application servers that was developed to aid potential users in understanding the capabilities of different
solutions under a heavy load. It measures the volume of transactions a particular system configuration can process while maintaining
specified response times for 90% of the transactions. SPECjAppServer2004 is an end-to-end application that exercises all parts of the
underlying infrastructure that make up the application environment, including hardware, JVM software, database software, JDBC drivers,
and the system network.
|
|
|
|
|
Space (RU) |
2 |
2 |
5 |
4 |
Power Consumption (Watts) |
670 |
560 |
350 |
770 |
Performance (SPECjApp JOPS) |
3,331.31 |
874.17 |
652.95 |
1,197.51 |
Performance / Watt |
5 |
1.56 |
1.9 |
1.6 |
SWaP |
2.5 |
0.8 |
0.4 |
0.4 |
|
Benchmark Outcome (4)
- The Sun SPARC Enterprise T5240 server with two 1.4GHz UltraSPARC T2 Plus processors running Solaris 10 and the
Oracle Database Server 10g was able to support another Sun SPARC Enterprise T5240 Server at the Application tier in
delivering a new single server World Record score of 3,331.31 JOPS@Standard (Java Operations per Second) on the
SPECjAppServer2004 benchmark.
- The Sun SPARC Enterprise T5240 server configured with two 1.4GHz UltraSPARC T2 Plus processors running Oracle
Database 10g supported the application tier of the benchmark.
- The new UltraSPARC T2 Plus-based server has been deployed at application and database layers of the benchmark
demonstrating the Sun SPARC Enterprise T5240 server's ability to perform business critical operations and act as an
outstanding Oracle 10G OLTP database server, as well very capable J2EE Application server.
- During benchmark execution the Sun SPARC Enterprise T5240 server in the database tier consumed only 670 Watts on
average while the same server in the application tier consumed an average of 720 Watts in a 2RU space.
- The SWaP metric is a measure of server efficiency ratio that includes system performance, power and space consumption
on a specific benchmark. SWaP = Perf /[ Space (RU) x Watts ]
- At the database tier, the Sun SPARC Enterprise T5420 server support the application tier in delivering 3.8x better
performance in half the space, when compared to the result of 874.17 JOPS@Standard posted by HP Integrity rx2660 server,
equipped with two dual-core Intel Itanium 2 processors and running HP-UX. As a result, the Sun SPARC Enterprise T5240 server
delivers over 3x better SWaP.
- At the database tier, the Sun SPARC Enterprise T5420 server support the application tier in delivering 2.8X better performance
with 3x better Performance per Watt and 6.3x higher SwaP when compared to compared to the IBM p 550, equipped with two dual-core
Power5+ processors and running AIX 5.3.
- At the database tier, the Sun SPARC Enterprise T5420 server support the application tier in delivering 1.9x higher throughput
in half the space, when compared to the result of 652.95 JOPS@Standard posted by compared to the Dell PowerEdge 2900, equipped with
two dual-core Intel Xeon processors and running Windows Server 2003 OS. As a result the Sun' new server delivers 5.7x better
Performance per Watt and 14x better SWaP.
(4)
SPEC, SPECjAppServer are registered trademarks of Standard Performance Evaluation Corporation.
All results from www.spec.org as of 4/5/08. SPECjAppServer2004:
Sun SPARC Enterprise T5240 (16 cores, 2 chip) 3,331 JOPS@Standard. IBM p 570 (4 cores, 2 chips)
1,197.51 JOPS@Standard. Dell 2900 (4 cores, 2 chips) 652.93 JOPS@Standard. HP rx2660 (4 cores, 2 chips) 874.17 JOPS@Standard.
IBM p 550 power rating of 770W is estimated as 80% of maximum PSU rating published here on 4/4/2008:
Dell PE 2900 power rating of 350 W is estimated as 70% of maximum PSU rating published here on 4/4/2008:
Sun HP rx2660 power rating of 560 W is estimated as 70% of maximum PSU rating published here on 4/4/2008:
SPARC Enterprise T5240 power consumption of 670 watts reported during benchmark run.
The Sun SPARC Enterprise T5240 server equipped with two 1.4GHz UltraSPARC T2 Plus processors delivered
a World Record dual CPU result of 373,405 SPECjbb2005 BOPS, surpassing the nearest competing 2-socket
system by more than 15% and beating most 4 processor systems. These results confirm the Sun SPARC Enterprise
T5240 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 server
in the middle tier. This 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).
|
|
|
|
|
Space (RU) |
2 |
4 |
7 |
4 |
Power Consumption (Watts) |
770 |
1,099 |
1,163 |
1,040 |
Performance (SPECjbb2005 BOPS) |
373,405 |
176,909 |
158,174 |
175,474 |
Performance / Watt (Higher is Better) |
485 |
161 |
136 |
169 |
SWaP< (Higher is Better)/div> |
242.5 |
40.2 |
19.4 |
42.2 |
|
Benchmark Outcome (3)
- The Sun SPARC Enterprise T5240 server equipped with two UltraSPARC T2 Plus processors at 1.4GHz delivered a
World Record result for all systems with two processors, achieving unprecedented scores of 373,405 SPECjbb2005
bops and 23,338 SPECjbb2005 bops/JVM in a 2U of rack space.
- The Sun HotSpot JVM sets a new standard for scalability by demonstrating near linear throughput, while fully
leveraging the 128 hardware threads of the UltraSPARC T2 Plus processor.
- Compared to 4 socket Dell PowerEdge 6950 AMD Opteron-based server, the Sun SPARC Enterprise T5240 server delivers
over 2x higher performance in half the space and with 3x higher performance per watt, allowing customers to deploy
breakaway services with higher levels of scalability and efficiency than ever before possible.
- Compared to the IBM p 570 server, equipped with two of the latest dual core 4.7GHz Power6 processors and runnin
AIX 5.3, the dual processor Sun SPARC Enterprise T5240 server delivers more than double the throughput in half the
space, while consuming 1/3rd less power.
- Compared to the IBM p 550 server, equipped with four of the latest dual core 4.2GHz Power6 processors and running
AIX 5.3, the dual processor Sun SPARC Enterprise T5240 server delivered 3.25x better SWaP and 45% better power-performance.
- The Sun SPARC Enterprise T5240 server running enterprise-proven Solaris 10 OS demonstrated 2.4X better performance over
the HP rx6600 server that uses four 1.6GHz Intel Itanium2 chips, as well as posted 12.5x better SWaP and 3.5x better power-performance
and space than aforementioned HP server.
(3)
SPEC, SPECjbb reg tm of Standard Performance Evaluation Corporation. All results as of 04/09/08 on http://www.spec.org.
Sun SPARC Enterprise T5240 results submitted to SPEC. Other results as of 04/01/08 on www.spec.org Sun SPARC Enterprise T5240 (2 chips, 16 cores) 373,405
SPECjbb2005 bops, 23,338 SPECjbb2005 bops/JVM. IBM p 550 (4x4.2GHz Power6 chips, 8 cores) 333,779 SPECjbb2005 bops, 83445 SPECjbb2005 bops/JVM. HP rx6600
(4 x1.6 GHz Intel Intanium2 chips, 8 cores) 158174 SPECjbb2005 bops, 39544 SPECjbb2005 bops/JVM. IBM p 570 (2x4.2GHz Power6 chips, 4 cores) 175,474 SPECjbb2005
bops, 87737 SPECjbb2005 bops/JVM. Dell PowerEdge 6950 (4 chips, 8 cores) 176909 SPECjbb2005 bops, 44,227 SPECjbb2005 bops/JVM.
Dell 6950 power rating of 1100W is estimated as 70% of maximum PSU rating published here on 4/4/08
IBM p 570 power rating of 1040W is estimated as 80% of maximum PSU rating published here on 06/07/07
HP rx6600 power rating of 1120W is estimated as 70% of maximum PSU rating published here on 03/23/08
Sun SPARC Enterprise T5240 power consumption taken from measurements made during the benchmark run.
The Sun SPARC Enterprise T5240 server bands together an innovative and best-in-class design with advanced features of Solaris
10 Operating System and Sun's compiler software (Sun Studio 12 and GCC for SPARC Systems V4.2) to achieve unprecedented levels
of compute performance. Sun's new CoolThreads server, powered by two UltraSPARC T2 Plus processors at 1.4GHz, produce the record-breaking
SPECint_rate2006 score of 157 and the SPECfp_rate2006 result of 119. These results are the new 2-processor World Records for Integer
and Floating Point throughput performance, respectively.
Benchmark Description
The SPEC CPU2006 benchmark provides a broader variety of workloads and better real-world applicability of the results.
It consists of two benchmark suites in which one suite measures and compares compute-intensive integer performance and the
other measures and compares floating point performance. The benchmark exercises a computer's processor, memory architecture,
and compilers on a variety of compute intensive workloads, including protein sequencing, MPEG-4 decoding, XML processing, fluid
dynamics, structural mechanics, and speech recognition.
|
|
|
|
SPECint_rate2006 |
157 |
122 |
62.8 |
SPECfp_rate2006 |
119 |
115 |
55.8 |
|
Benchmark Outcome (2)
- Surpassing the competing dual processor systems from HP and IBM, the Sun SPARC Enterprise T5240 server
equipped with two 1.4GHz UltraSPARC T2 Plus processors posted 2- processor World Records on both integer and
floating-point throughput suites of the SPEC CPU2006 benchmark.
- On the Integer-intensive throughput tests, the Sun SPARC Enterprise T5240 server delivered 29% higher performance
than the dual processor POWER6-based IBM System p 570 server, and 2.5x more performance than the HP Integrity
rx2660 server with two Itanium2 processors.
- On the Floating Point-intensive throughput tests, the Sun SPARC Enterprise T5240 server delivered 3% higher
performance than the dual processor POWER6-based IBM System p 570 server, and over 2x more performance than
the HP Integrity rx2660 server with two Itanium2 processors.
- In addition, the Sun SPARC Enterprise T5240 server delivered 2-processor World Record scores of 142 on
SPECint_rate_base2006 suite and 111 on SPECfp_rate_base2006 suite of the benchmark. The "base" scores are produced
using less optimized benchmark binaries that were compiled under stricter guidelines. Although "base" scores may not
reflect the the ultimate performance of the system, some end users, who may prefer to spend less time tuning their
compiler optimizations, may find them more appealing.
- These results demonstrate that the 3rd generation of CMT processors is capable of processing highly compute-intensive
workloads with the leading results among all dual-chip systems on the market.
- In the same amount of physical space, the Sun SPARC Enterprise T5240 server, powered by two UltraSPARC T2 Plus
processors, delivers 1.9X the floating point and integer throughput performance of the Sun SPARC Enterprise T5220
server, powered by the previous generation of CMT processors the UltraSPARC T2.
- The Sun SPARC Enterprise T5240 server demonstrates that an elegant CMT design can scale well in SMP applications
and provides an unprecedented computing capacity for this segment of the market. Enterprise T5240 server delivers
2.4x higher performance with nearly 5x better price/performance.
(2)
SPEC, SPECint, SPECfp registered trademarks of Standard Performance Evaluation Corporation. Sun SPARC Enterprise T5240
server, (2x1.4 GHz UltraSPARC T2 Plus chips, 16 cores, 128 threads) 157 SPECint_rate2006, 142 SPECint_rate_base2006,
119 SPECfp_rate2006, 111 SPECfp_rate_base2006. Sun SPARC Enterprise T5220 server, (1.4 GHz UltraSPARC T2 chip, 8 cores,
64 threads) 83.2 SPECint_rate2006, 62.3 SPECfp_rate2006. Competitive results from www.spec.org as of April 8, 2008.
IBM System p 570 (2 x4.7GHz POWER6 chips, 4 cores, 8 threads) 122 SPECint_rate2006, 115 SPECfp_rate2006. HP Integrity
rx2660 (2x1.6 GHz Intel Itanium2 chips, 4 cores, 4 threads) 62.8 SPECint_rate2006, 55.8 SPECfp_rate2006
The Sun SPARC Enterprise T5240 server, equipped with two UltraSPARC T2 Plus processors, running Solaris 10 OS and
Sun Studio 12 software delivered a world record SPECompM2001 result of 25,488 for systems with 2 or less chips.
Benchmark Description
The SPEC OMP2001 is a key benchmark that is used to compare the performance of shared memory servers executing
compute-intensive scientific applications. It represents a collection of applications that are used in high-energy
physics, weather modeling, computational chemistry, mechanical design and several other areas, and consists of medium
and large problem sets. All C/C++ and FORTRAN applications in this suite use the OpenMP programming model that provides
a portable, scalable model for developing parallel applications for platforms ranging from the desktop to the supercomputer.
The OpenMP Application Program Interface (API) supports multi-platform shared-memory parallel programming in C/C++ and Fortran
on all architectures.
|
|
|
|
|
Space (RU) |
2 |
24 |
4 |
4 |
Performance (SPECompM2001) |
25,488 |
24,632 |
20,433 |
19,983 |
|
Benchmark Outcome (1)
- The The Sun SPARC Enterprise T5240 server, equipped with dual 1.4GHz UltraSPARC T2 Plus processor delivered a 16
cores/2 chips/128 threads world record SPECompM2001 result of 25,488 for systems with 2 or less processors.
- The Sun SPARC Enterprise T5240 server, running Solaris 10 and freely available Sun Studio 12 software on two
UltraSPARC T2 Plus processors, beats the 64 cores/32 chips/64 threads SPEC OMPM2001 result of Unisys ES7000/One
server by 3.5% in 1/12 the space. Unisys used freely available gcc compilers and libriaries on this 32 socket Intel
Xeon-based system.
- The Sun SPARC Enterprise T5240 server, running Solaris 10 and Studio 12 software on two UltraSPARC T2 Plus
processors, beats the SPEC OMPM2001 4 cores/2 chips/ 8 threads result of IBM p 520 POWER6-based system by 25% in
half the space.
- Compare to the previous generation of IBM systems, the Sun SPARC Enterprise T5240 server, with two UltraSPARC
T2 Plus processors, surpasses the 4 cores/2 chips/ 8 threads SPEC OMPM2001 result of IBM p5 550 system by 27% in
half the space.
(1)
SPEC, SPEC OMPM2001 , SPEC OMPL2001 registered trademarks of Standard Performance Evaluation Corporation.
Sun SPARC Enterprise T5240 server, (2x1.4 GHz, UltraSPARC T2 Plus chips, 16 cores, 128 threads) 25,488 SPEC
OMPM2001. Competitive results from www.spec.org as of April 7, 2008. IBM System p5720 (2x4.7GHz POWER6 chips, 4
cores, 8 threads) 20,433 SPEC OMPM2001. IBM System p5 550 (2x2.1GHz POWER5+ chips, 4 cores, 8 threads) 19,983 SPEC
OMPM2001. Unisys ES7000/One (32 x3.4GHz Xeon 7140 chips , 64 cores, 64 threads) 24,632 SPEC OMPM2001.
|
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.
|
|
The NotesBench Consortium is an independent organization dedicated to providing Domino and Notes performance information to customers with the goal of reducing customers' expenses associated with internal benchmark activities as well as ensuring more rapid and optimized deployment of Domino and Notes
|
Back to top
|
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 SPECweb, SPECint, SPEComp, SPECfp, SPECjAppServer 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-H, QphH, $/QphH TM of Transaction Processing Performance Council (TPC). More info http://www.tpc.org.
|