On Thu, 22 Oct 2020 14:01:05 GMT, Paul Murphy <github.com+12972156+p...@openjdk.org> wrote:
>> CoreyAshford has updated the pull request incrementally with one additional >> commit since the last revision: >> >> TestBase64.java: remove jdk.test.lib.Utils from @build which was causing >> Tier3 failures. > > src/hotspot/cpu/ppc/stubGenerator_ppc.cpp line 3820: > >> 3818: __ vcmpequb_(eq_special_case_char, input, >> vec_special_case_char); >> 3819: // >> 3820: // There's a (63/64)^16 = 77.7% chance that there are no >> special > > I think that assumes uniformly randomized data, is that a good assumption? > Is it measurably faster to skip around the xxsel instead of doing it > unconditionally? Thanks for this question. I also stumbled over it when reviewing. I guess a branch which gets mispredicted in ~22% of the cases leads to a big performance loss. (In addition, the branch target is not aligned.) ------------- PR: https://git.openjdk.java.net/jdk/pull/293
