RFR: 8335347: GenShen: Revert change that has adaptive heuristic ignore abbreviated cycles

William Kemper wkemper at openjdk.org
Fri Jun 28 20:37:46 UTC 2024


On Fri, 28 Jun 2024 16:22:03 GMT, William Kemper <wkemper at openjdk.org> wrote:

> Additional performance testing has shown no benefit from this feature. In fact, latency is degraded on the extremem benchmark with this feature enabled.

We tried every benchmark in the pipeline (dacapo, specjvm2008, specjbb2015, heapothesys, extremem, dilluvian). I think this attempt at optimization didn't work because an application is going to either have many abbreviated cycles, in which case, the heuristic lives in ignorance and runs based on the time for the rare regular length cycle (making it too aggressive). Or, the application may have very few abbreviated cycles, in which case this optimization doesn't matter. I'm sure we could craft a workload that created a sequence of abbreviated cycles, and then caused a non-abbreviated cycle, but this seems uncommon in practice. In those situations, if a degenerated cycle did occur, the late penalties would make the heuristic more aggressive. Your idea is interesting and perhaps something we could experiment with in the fullness of time.

-------------

PR Comment: https://git.openjdk.org/shenandoah/pull/455#issuecomment-2197622038


More information about the shenandoah-dev mailing list