Elisabeth Stahl on Benchmarking and IT Optimization

And the Oscar Goes to . . . IBM

with 3 comments

It seems as if just a few years ago I actually used to get excited about the big night. The big night that was last night, the 87th Academy Awards. I used to watch with friends, with family. I even went to an awards party once.

In the past I even saw the movies that won — before they won.

And I think that’s how some of us have been feeling lately about industry standard performance benchmarks. Remember the good old days of leapfrogging? Of vicious ads and blogs? Of fights over TPC-C?

But recently I was super impressed with a brand new IBM publish last week of the SPECjEnterprise2010 benchmark. SPECjEnterprise2010 emulates an automobile dealership, manufacturing, supply chain management and order/inventory system and was designed to stress the Java EE application server. It’s an excellent measure of middleware.

The new IBM result running WebSphere and DB2 was the best Intel “Haswell” EP result, over 31% greater per core than the just published Oracle result with WebLogic.(1) And of course, the flagship IBM POWER8 result is the #1 per core result in the industry, over 79% greater per core than the new Oracle x86 result.(2)

At least I still have the passion for benchmarks. Because nowadays my interest in the Academy Awards pretty much revolves around a few dresses on the red carpet. And I can get that not by staying up all night but with a couple of photos online the next morning.


The postings on this site solely reflect the personal views of the author and do not necessarily represent the views, positions, strategies or opinions of IBM or IBM management.

(1) 36-core(2×18-core Processor) Oracle Server X5-2, WL 12.1.3 – 18800.76 SPECjEnterprise2010 EjOPS, 522.24 EjOPS per app core. 28-core(2×14-core processors) IBM System x3650 M5 Lenovo Server, WAS, DB2 10.5 – 19282.14 EjOPS, 688.65 EjOPS/core.
(2) 24-core IBM Power S824 (3.52 GHz) db running DB2 10.5 / 24-core IBM Power S824 (3.52 GHz) app running WebSphere 8.5, SPECjEnterprise2010 (22,543 Enterprise jAppServer Operations Per Second (EjOPS), 939EjOPS/core) .

Source: All results current as of 2/23/15.

Oracle and Java are registered trademarks of Oracle and/or its affiliates. Other names may be trademarks of their respective owners.

SPEC, SPECint, SPECfp, SPECjbb, SPECweb, SPECjAppServer, SPECjEnterprise, SPECjvm, SPECvirt, SPECompM, SPECompL, SPECsfs, SPECpower, SPEC MPI and SPECpower_ssj are trademarks of the Standard Performance Evaluation Corporation (SPEC).

TPC-C ,TPC-H, and TPC-E are trademarks of the Transaction Performance Processing Council (TPPC).

technorati tags: , , ,,,,,,,,,



Written by benchmarkingblog

February 23, 2015 at 9:41 am

3 Responses

Subscribe to comments with RSS.

  1. Reblogged this on Mirv in the 'Burgh and commented:
    This is news!


    March 9, 2015 at 2:50 pm

  2. So, the same two results show that the Oracle database has a 62% better result than the IBM DB2 database (19,282.14 for 60 cores with IBM DB2, vs. 18,800.76 for 36 cores with the Oracle database).


    March 23, 2015 at 4:56 am

    • Hi Olivier – Thanks for your comment ! Per SPEC, this benchmark really is designed for stressing the application. Many configurations merely use what happens to be available on the floor for the database – ie. note the hardware for this one.


      March 23, 2015 at 8:00 am

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: