Details
Description
Hi,
we're seeing an -11.1% performance drop between s9u3_01 and s9u3_02 builds in Scimark benchmark, namely its sci_14_lrg2aServer_FFT metric.
We believe it's due to the fact that Java Runtime Environment has changed between the named two builds.
In s9u3_01 JRE was:
Java(TM) 2 Runtime Environment, Standard Edition (build 1.4.0_02-b02)
Java HotSpot(TM) Server VM (build 1.4.0_02-b02, mixed mode)
In s9u3_02 JRE was:
Java(TM) 2 Runtime Environment, Standard Edition (build 1.4.1_01-b01)
Java HotSpot(TM) Server VM (build 1.4.1_01-b01, mixed mode)
Build %Change Mean %Range %Stdev Runs TTest
s81_58shwpl3 -- 10.30 2.83 0.66 20 --
s9u3_01 1.16 10.42 2.38 0.97 4 1.000
s9u3_02 -9.94 9.28 3.10 0.80 40 0.000
s9u3_03 -9.66 9.31 1.85 0.57 18 0.105
s9u3_04 -9.52 9.32 1.66 0.43 19 0.349
s9u3_05 -9.65 9.31 2.13 0.57 20 0.372
we're seeing an -11.1% performance drop between s9u3_01 and s9u3_02 builds in Scimark benchmark, namely its sci_14_lrg2aServer_FFT metric.
We believe it's due to the fact that Java Runtime Environment has changed between the named two builds.
In s9u3_01 JRE was:
Java(TM) 2 Runtime Environment, Standard Edition (build 1.4.0_02-b02)
Java HotSpot(TM) Server VM (build 1.4.0_02-b02, mixed mode)
In s9u3_02 JRE was:
Java(TM) 2 Runtime Environment, Standard Edition (build 1.4.1_01-b01)
Java HotSpot(TM) Server VM (build 1.4.1_01-b01, mixed mode)
Build %Change Mean %Range %Stdev Runs TTest
s81_58shwpl3 -- 10.30 2.83 0.66 20 --
s9u3_01 1.16 10.42 2.38 0.97 4 1.000
s9u3_02 -9.94 9.28 3.10 0.80 40 0.000
s9u3_03 -9.66 9.31 1.85 0.57 18 0.105
s9u3_04 -9.52 9.32 1.66 0.43 19 0.349
s9u3_05 -9.65 9.31 2.13 0.57 20 0.372
Attachments
Issue Links
- duplicates
-
JDK-4821582 3% regression in Scimark on Linux server compiler from mantis b15 to b16
- Closed
- relates to
-
JDK-4806453 scimark Monte metric drop of -21% between s9u3_01 and s9u3_02 due to JRE change
- Closed