[aarch64-port-dev ] aarch64 and arm64 jdk benchmarks result sharing

Andrew Haley aph at redhat.com
Wed Apr 19 11:44:49 UTC 2017


On 19/04/17 12:30, Andrew Haley wrote:
> The results for Partner B's hardware on Dacapo are so weird that I
> think there must be something wrong.  lusearch didn't work at all, so
> there must be a code generation problem somewhere.

... in addition, the score for sunflow on Partner B openjdk-arm64
looks deeply suspect.  It has a relative score of 37.88% and a
standard deviation of zero.  These results are so strange, and so
difficult for me to verify, that I'm going to have to ignore them
until I can get suitable hardware.

Andrew.



More information about the aarch64-port-dev mailing list