Sun Fire X4440 Server

Sun Fire X4440 Server

Powered by Six-Core AMD Opteron CPUs, the Sun Fire X4440 server offers a combination of performance, density, scalability and energy efficiency while lowering costs and complexity. Unlike Dell, HP, and IBM, the Sun Fire X4440 server is jam-packed with features to optimize massive virtualization and consolidation with over 2 TB of storage in half the size.


(Thu, 19 March 2009)

Sun Fire X4440 Server Breaks New Ground on SPECweb2005 Benchmark

The industry's only four-socket 2RU x64 server based on the Quad-Core AMD Opteron processor, the Sun Fire X4440 server delivered the best 16-core result, on the SPECweb2005 benchmark. With the SPECweb2005 score of 48,007 the Sun Fire X4440 server, with four 2.7 GHz Quad-Core AMD Opteron model 8384 processors, also claims the top result for all AMD-based platforms.

SPECweb2005 is the industry standard benchmark for evaluating Web Server performance. The benchmark simulates multiple user sessions accessing a Web Server and generating static and dynamic HTTP requests. The major features of SPECweb2005 are:

  • Measures simultaneous user sessions
  • Dynamic content: currently PHP and JSP implementations
  • Page images requested using 2 parallel HTTP connections
  • Multiple, standardized workloads: Banking (HTTPS), E-commerce (HTTP and HTTPS), and Support (HTTP)
  • Simulates browser caching effects
  • File accesses more accurately simulate today's disk access patterns

Competitive Comparisons Table: 16 Core SPECweb2005 Results [1]
  Sun Fire X4440 HP DL585 G5 Fujitsu RX600 HP DL580 G5
Processor AMD Opteron 8384 AMD Opteron 8356 Intel Xeon X7350 Intel Xeon X7350
Space (RU) 2 4 4 4
Power Consumption (Watts) 617 960 920 1167
Performance (Composite) 48007 43854 42783 40046
Performance/Watt
(Higher is Better)
78 45.7 46.5 34
Performance/RU
(Higher is Better)
24003 10963 10695 10011
 
Benchmark Outcome

  • The Sun Fire X4440 server outperformed competitive systems that were running Linux Operating System (OS) and were equipped with either quad-core Intel Xeon or AMD Opteron processors. These leading performance and performance per watt results confirm the Sun Fire X4440 server as the highest performing and most efficient dual-socket platform on the planet for deployment of secure web services.
  • Sun's compact server outperformed the 16-core HP DL 580 G5 server by 20 percent while consuming only 617W of power on average. In comparison, the HP DL 580 G5 server requires twice the physical space and consumes 79 percent more electricity, making the Sun Fire X4440 server an ultimate solution for power and space-constrained data centers.
  • In the Support portion of the benchmark that has the most intensive network and I/O bandwidth requirements, the Sun X4440 server shows the highest score among all 16-core submissions.
  • The Sun Fire X4440 server, running Red Hat 5.2 OS and Accoria Rock web server, was able to surpass similarly configured competing HP Proliant DL585 G5 system by 9 percent, while consuming 47 percent less power.
  • Sun continues to be the only vendor that discloses power consumption of the systems along side the performance results. In this instance the average power consumption for Sun Fire X4440 server was measured for each of the three SPECweb2005 benchmark workloads during the steady state period at peak load. The power consumption for competing systems has been calculated using vendor provided tools. The Sun Fire X4440 server has 68 percent better performance/watt than Fujitsu RX600 and 129 percent better performance/watt than HP DL 580 G5 server.
  • Sun utilized four Sun Storage J4200 arrays to reach this leading score.
  • Since SPECweb2005 benchmark is designed to measure web server performance on system under test (SUT) it does not take into consideration any other equipment (like external storage) that was used to produce benchmark results. For the large number of supported user sessions, as in the case of Sun Fire X4440 server result, storage represents a significant part of the overall solution. Sun recognizes that fact and in the spirit of complete transparency discloses the power consumption for the external storage that was used in this test. Four Sun Storage J4200 arrays used to produce the record-breaking score had an average power consumption of 1092W.
  • On the software side, Sun solution used the 'best of breed' approach by deploying Accoria Networks' Rock Web Server v1.4.7 software and Rock JSP/Servlet Container v1.3.2. script engine on top of the Red Hat Enterprise Linux 5.2 OS. The resulting performance further highlights Sun Microsystems' ability to deliver the best performing servers, regardless of operating system environments.
  • In summary, this world record 16-core benchmark clearly demonstrates that the Sun Fire X4440 server can support thousands of concurrent web server sessions and is capable of delivering the utmost performance and scalability.

[1] Sun Fire X4440 power consumption was measured during the benchmark run. HP DL 580 G5 power consumption of 1167W was calculated as 80% of system utilization for configuration disclosed with the benchmark.HP Power Calculator is located at: http://h30099.www3.hp.com/configurator/calc/Power%20Calculator%20Catalog.xls. HP DL 585 G5 power consumption of 960W was calculated as 80% of Max Rated Output Wattage Rating disclosed here: http://h18000.www1.hp.com/products/quickspecs/12770_div/12770_div.html#Power%20Specifications. Fujitsu RX600 power consumption of W was calculated as 80% of Max Rated Output Wattage Rating disclosed here: http://www.computers.us.fujitsu.com/downloads/primergy/DS_RX600_S4_PRIMERGY.pdf

(Tue, 09 December 2008)

The Sun Fire X4440 Server is the Best-Performing x86 System on SPEC OMPL2001 Benchmark

The SPEC OMP benchmark represents workloads often used in high-energy physics, weather modeling, computational chemistry and mechanical design, and consists of medium and large problem sets that stress the computer's processor, memory, compilers and OpenMP implementation.

On the large problem set, which was designed for measuring and comparing systems with high number of processing cores, the compact Sun Fire X4440 server, equipped with four quad-core AMD Opteron model 8384 processors and running the OpenSolaris 2008.11 Operating System (OS) with Sun Studio Express 11/08 compiler software, posted the best x86 result. This ground breaking result clearly showcases Sun's commitment to the Open Source movement by utilizing the freely available community-based versions of OS and compiler software that include all the latest features and capabilities.

The Sun Fire X4440 server's (16 cores/4 chips/16 threads) delivered a SPECompL2001 result of 175,648.

(Tue, 13 May 2008)

Best Java Performance with AMD Opteron Processors

Fueled by the latest version 1.6.0_06-p of Sun's Java Platform, Standard Edition software, the compact 2 RU Sun Fire X4440 server obtained a the best recorded score of 372,467 SPECjbb2005 bops (46,558 SPECjbb2005 bops/JVM) for all AMD Opteron-based systems. This result bests the previous record held by the HP ProLiant DL585 G5 server and accomplishes that in half the physical space.

Powered by Solaris, an enterprise class, mission critical UNIX OS, the Sun Fire X4450 server, equipped with four Quad-core AMD Opteron Model 8356 processors, delivered top-notch performance on SPECjbb2005 benchmark that emulates the design of real-world server-side Java applications and provides an accurate reflection of the business logic and objects, while stressing the implementation of the Java Virtual Machine (JVM) and the scalability of the system's processors and memory.

To aid customer in their choices, Sun is reporting power consumption on this critical benchmark and posting that data side-by-side with the performance numbers. The Sun Fire X4440 server had an average power consumption of only 606W measured during the steady state of the benchmark.

The table below compares Sun's result to the scores posted by the competition.

SPECjbb2005 4-Chip Results by Various Competing Platforms
  Sun Fire X4440 IBM p 570 HP ProLiant DL585 G5
Space (RU) 2 8 4
Chips/Cores 4/16 4/8 4/16
Operating System Solaris 10 AIX 5L Windows 2003
JVM Java HotSpot(TM) 1.6.0_06-p J2RE 1.5.0 BEA JRockit(R) BEA JRockit(R) P27.5.0
Performance (SPECjbb2005 bops) 372,467 346,742 368,543
Performance per JVM
(SPECjbb2005 bops/JVM)
46,558 86,686 92,136
Power Consumption (Watts) [1] 606 2240 804
Performance/Watt (Higher is Better) 615 155 458
Performance / RU (Higher is Better) 186,233 43,343 92,136
 

This table not only demonstrates the leading performance of Sun's solution, but also highlights its effectiveness in terms of power and space utilization providing customers with another sensible choice for deploying their Java applications.

[1] IBM p 570 power rating of 1120W is estimated as 80% of maximum PSU rating published here on 5/4/2008: HP ProLiant DL585 G5 power rating of 804W is estimated as 70% of maximum PSU rating published here on 5/4/2008: Sun Fire X4440 power consumption of 606 Watts was measured during benchmark run.


									
									
										
									
									
										
									
									SPEC

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.


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.