Em qua., 19 de jun. de 2024 às 20:52, Tom Lane <t...@sss.pgh.pa.us> escreveu:
> I wrote: > > I hypothesize that the reason we're not seeing equivalent failures > > on x86_64 is one of > > > 1. x86_64 valgrind is stupider than aarch64, and fails to track that > > the contents of the SIMD registers are only partially defined. > > > 2. x86_64 valgrind is smarter than aarch64, and is able to see > > that the "mask off invalid entries" step removes all the > > potentially-uninitialized bits. > > Hah: it's the second case. If I patch radixtree.h as attached, > then x86_64 valgrind complains about > > ==00:00:00:32.759 247596== Conditional jump or move depends on > uninitialised value(s) > ==00:00:00:32.759 247596== at 0x52F668: local_ts_node_16_search_eq > (radixtree.h:1018) > > showing that it knows that the result of vector8_highbit_mask is > only partly defined. I wouldn't be surprised if *RT_NODE_16_GET_INSERTPOS* (src/include/lib/radixtree.h), does not suffer from the same problem? Even with Assert trying to protect. Does the fix not apply here too? best regards, Ranier Vilela
