December 9, 2014 - SPEC has identified a defect in its SPECjbb®2013 benchmark suite. SPEC has suspended sales of the benchmark software and is no longer accepting new submissions of SPECjbb®2013 results for publication on SPEC's website. Current SPECjbb®2013 licensees will receive a free copy of the new version of the benchmark when it becomes available.
SPEC is advising SPECjbb®2013 licensees and users of the SPECjbb®2013 metrics that the recently discovered defect impacts the comparability of results. This defect can significantly impact the amount of work done during the measurement period, resulting in an inflated SPECjbb®2013 metric. SPEC recommends that users not utilize these results for system comparisons without a full understanding of the impact of these defects on each benchmark result.
Additional information is available here.
SPECjbb2013 is a new benchmark designed to show modern Java server performance. Oracle's SPARC T5-2 set a world record as the fastest two-chip system beating just introduced two-chip x86-based servers. Oracle, using Oracle Solaris and Oracle JDK, delivered this two-chip world record result on the MultiJVM SPECjbb2013 metric. SPECjbb2013 is the replacement for SPECjbb2005 (SPECjbb2005 will soon be retired by SPEC). Oracle's SPARC T5-2 server achieved 81,084 SPECjbb2013-MultiJVM max-jOPS and 39,129 SPECjbb2013-MultiJVM critical-jOPS on the SPECjbb2013 benchmark. This result is a two chip world record. There are no IBM POWER7 or POWER7+ based server results on the SPECjbb2013 benchmark. IBM has published IBM POWER7+ based servers on the SPECjbb2005 which will soon be retired by SPEC. The 2-chip SPARC T5-2 server running SPECjbb2013 is 30% faster than the 2-chip Cisco UCS B200 M3 server (2.7 GHz E5-2697 v2 Ivy Bridge-based) based on SPECjbb2013-MultiJVM max-jOPS. The 2-chip SPARC T5-2 server running SPECjbb2013 is 66% faster than the 2-chip Cisco UCS B200 M3 server (2.7 GHz E5-2697 v2 Ivy Bridge-based) based on SPECjbb2013-MultiJVM critical-jOPS. These results were obtained using Oracle Solaris 11 along with Java Platform, Standard Edition, JDK 7 Update 40 on the SPARC T5-2 server.
From SPEC's press release, "SPECjbb2013 replaces SPECjbb2005. The new benchmark has been developed from the ground up to measure performance based on the latest Java application features. It is expected to be used widely by all those interested in Java server performance, including JVM vendors, hardware developers, Java application developers, researchers and members of the academic community."
Results of SPECjbb2013 from www.spec.org as of September 22, 2013 and this report. The above table represents all of the published results on www.spec.org. SPEC allows for self publication of SPECjbb2013 results. See below for locations where full reports were made available.
System Under Test:
The SPECjbb2013 benchmark has been developed from the ground up to measure performance based on the latest Java application features. It is relevant to all audiences who are interested in Java server performance, including JVM vendors, hardware developers, Java application developers, researchers and members of the academic community.
SPECjbb2013 replaces SPECjbb2005. New features include:
SPEC and the benchmark name SPECjbb are registered trademarks of Standard Performance Evaluation Corporation (SPEC).
Results as of 9/23/2013, see http://www.spec.org for more information. SPARC T5-2 81,084 SPECjbb2013-MultiJVM max-jOPS, 39,129 SPECjbb2013-MultiJVM critical-jOPS, result from https://blogs.oracle.com/BestPerf/resource/jbb2013/sparct5-922.pdf Cisco UCS B200 M3 62,393 SPECjbb2013-MultiJVM max-jOPS, 23,505 SPECjbb2013-MultiJVM critical-jOPS, result from http://www.cisco.com/en/US/prod/collateral/ps10265/le_41704_pb_specjbb2013b200.pdf; Sun Server X4-2 52,664 SPECjbb2013-MultiJVM max-jOPS, 20,553 SPECjbb2013-MultiJVM critical-jOPS, result from https://blogs.oracle.com/BestPerf/entry/20130918_x4_2_specjbb2013; Cisco UCS C220 M3 41,954 SPECjbb2013-MultiJVM max-jOPS, 16,545 SPECjbb2013-MultiJVM critical-jOPS result from www.spec.org.