Fujitsu
Not logged in » Login
X

Please login

Please log in with your Fujitsu Partner Account.

Login


» Forgot password

Register now

If you do not have a Fujitsu Partner Account, please register for a new account.

» Register now

Recent Discussion:

NickBown | 22.12.2018, 14:18
We have come across this issue as well, and don't seem to have found a way around it (the server is ...
NickBown | 20.12.2018, 18:40
Hi everyoneWe've got an RX2540 M1 which won't boot past the Fujitsu splash screen (which shows the i...
MarkM | 15.10.2018, 11:33
Hi there.I do not believe the Fujitsu policy on this subject has changed.So NO you can not order dri...
Apr 12 2016

FUJITSU Server PRIMERGY M2 Models Break World Records

/data/www/ctec-live/application/public/media/images/blogimages/39131_PRIMERGY_RX2540_M2_Mood_scr.jpg

Just one week and a half ago, the launch of Intel's fourth-generation Xeon® E5-2600 processor line and the accompanying refresh of our PRIMERGY dual-socket servers dominated the blogs on this page. Today, we can add relevant details that let product upgrades appear even more worthwhile: the new models have set a total of seven world records in important benchmarks like SPECint, SPECpower, TPC-E and VMmark 2.5.2 for virtualization performance, database processing and energy efficiency.

Although massive performance increases are kind of a given whenever Intel launches a new processor generation, the 'world record festival' associated with the debut of the Xeon® E5-2600 v4 family is a rather rare occurrence. Probably the most staggering news was in the sheer number of improvements: nine vendors accounted for a total of more than 25 high scores that has never been reached before. Out of those nine, Fujitsu and two other vendors make up a class of their own, as they managed to set seven or more dual-socket or general world records in one swipe. Fujitsu's record breakers were the PRIMERGY RX2540 M2 and PRIMERGY RX2560 M2, which topped the following benchmarks:

  • SPECfp_rate_base2006, measuring Technical Computing Throughput in 2-socket x86 systems – test configuration: FUJITSU Server PRIMERGY RX2540 M2 with two Intel® Xeon® processor E5-2699 v4, 256 GB memory, running SUSE Linux Enterprise Server 12, C/C++: Version 16.0.0.101 of Intel C++ Studio XE for Linux; Fortran: Version 16.0.0.101 of Intel Fortran Studio XE for Linux. Scores: SPECfp_rate_base2006 = 1100, SPECfp_rate2006 = 1130. Source: http://docs.ts.fujitsu.com/dl.aspx?id=a398416d-5599-435e-b35d-3be52ee0c467. In this specific test, the PRIMERGY RX2540 M2 reached a tie with a competing Cisco system.1
  • SAP Server Power, measuring power consumption in a SAP system environment – test configuration: FUJITSU Server PRIMERGY RX2540 M2 with two Intel® Xeon® processor E5-2699 v4, 512 GB memory, running Windows Server 2012 R2 Standard Edition, SQL Server 2012, SAP enhancement package 5 for SAP ERP 6.0. Score: 4.28 watts/kSAPS. Source: SAP Server Power Benchmark (2-tier), certification number 2016005 (PDF).2
  • VMmark V2 Performance Only, measuring virtualization capabilities with a focus on throughput – test configuration: FUJITSU Server PRIMERGY RX2540 M2, matched pair, each with two Intel® Xeon® processor E5-2699 v4, 512 GB memory, running VMware ESXi 6.0.0 U1b Build 3380124 and vCenter Server 6.0.0 Build 3018524; connected to Fibre Channel SAN storage. Benchmark: VMmark V2.5.2. Score: 34.74 @ 28 Tiles. Source: http://www.vmware.com/a/assets/vmmark/pdf/2016-03-31-Fujitsu-RX2540M2.pdf.3
  • VMmark V2 Performance with Server Power, measuring performance paired with power efficiency – test configuration: FUJITSU Server PRIMERGY RX2540 M2, matched pair, each with two Intel® Xeon® processor E5-2699 v4, 512 GB memory, running VMware ESXi 6.0.0 U1b Build 3380124 and vCenter Server 6.0.0 Build 3018524; connected to Fibre Channel SAN storage. Benchmark: VMmark V2.5.2 PPKW. Score: 38.3065 @ 28 Tiles. Source: http://www.vmware.com/a/assets/vmmark/pdf/2016-03-31-Fujitsu-RX2540M2-serverPPKW.pdf.4
  • TPC-E Price/Performance, measuring OLTP performance (more specifically the number of transactions carried out per second [tpsE] and the associated price per tpsE) – Equipped with the dual-socket, 22-core CPU Xeon® E5-2699 v4, the FUJITSU Server PRIMERGY RX2540 M2 achieved a score of 4734.87 tpsE at a price / performance ratio of $111.65/tpsE. This was the second best result of 2-socket servers submitted with TPC-E and the overall best price/performance ratio. The results mark a 26% gain over the first-generation RX2540, equipped with a dual-socket, 18-core Xeon® E5-2699 v3.5
  • SPECint_rate_base2006, measuring server throughput – test configuration: FUJITSU Server PRIMERGY RX2560 M2 with two Intel® Xeon® processor E5-2699 v4, 256 GB memory, running SUSE Linux Enterprise Server 12, C/C++: Version 16.0.0.101 of Intel C++ Studio XE for Linux. Score: SPECint_rate_base2006 = 1760, SPECint_rate2006 = 1830. Source: http://docs.ts.fujitsu.com/dl.aspx?id=35eb35f4-8dc8-479a-af16-aa8b283fceb0. This 2-socket, x86 systems world record marks another tie with competing Cisco hardware.6
  • SPECpower_ssj2008, measuring a server's general energy efficiency – test configuration: FUJITSU Server PRIMERGY RX2560 M2 with two Intel® Xeon® processor E5-2699 v4, 64 GB memory, running Microsoft Windows Server 2012 R2 Standard, JVM version: Oracle Java HotSpot™ 64-Bit Server VM (build 24.80-b11, mixed mode), version 1.7.0_80. Score: 12,079 overall ssj_ops/watt. Source: http://docs.ts.fujitsu.com/dl.aspx?id=911561d3-37fb-4869-b60a-ba547afee43b.7

Fujitsu PRIMERGY customers also enjoy reduced energy costs for system cooling thanks to Fujitsu's refreshed Cool-safe® Advanced Thermal Design, with the threshold for safe operation raised from 40°C to 45°C for most available rack, tower and scale-out systems.

To learn more, please check out this video and visit our PRIMERGY product site. For a comprehensive overview of all records set, please refer to http://docs.ts.fujitsu.com/dl.aspx?id=8e762033-d6c8-4350-81b2-c9e5d2a664f7 (closed user group, FUJITSU Partner account required).

[1] Competitive SPEC® benchmark results stated in this presentation reflect results published as of March 31, 2016. For the latest SPEC® benchmark results, visit the result pages for the different benchmarks on http://www.spec.org or http://www.fujitsu.com/fts/products/computing/servers/primergy/benchmarks/..

[2] The SAP Sales and Distribution (SD) Standard Application Benchmark performed on several dates by Fujitsu in Paderborn, Germany, was certified by SAP on behalf of the SAP Benchmark Council. Further information can be found at http://global.sap.com/solutions/benchmark/sd2tier.epx.

[3] The VMmark results were achieved by FUJITSU Server PRIMERGY systems. Full test results including system specification, further details and current results can be found at http://www.vmware.com/a/vmmark/. Comparisons reflect the status as of March 31, 2016. VMware and VMmark are trademarks or registered trademarks of VMware, Inc. VMware® VMmark® is a product of VMware, Inc. VMmark utilizes the SPEC Power and Temperature Daemon (SPECPTDaemon), which is available from the Standard Performance Evaluation Corporation (SPEC®). VMmark results are not SPEC metrics and cannot be compared to SPEC metrics in any way.

[4] Cf. fn 3.

[5] The reflected TPC-E benchmark comparisons reflect results published as of March 31, 2016. For more information and specific tested configurations as well as all results, please refer to the official TPC web pages: http://www.tpc.org/tpce/default.asp as well as http://www.tpc.org/tpce/results/tpce_results.asp and http://www.tpc.org/tpce/results/tpce_price_perf_results.asp for the respective results.

[6] Cf. fn 1.

[7] Cf. fn 1.

 
SHARE

Comments on this article

No comments yet.

Please Login to leave a comment.