https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91929
--- Comment #5 from Milian Wolff <mail at milianw dot de> --- > Note the line number program should have picked up a location from the surrounding code, at least the surrounding function, so the ?? in the backtraces look like a consumer (perf) issue to me. All major DWARF consumers get it wrong, no? addr2line from binutils / libbfd, elfutils / libdwfl and also GDB - none of them find any information for __cos_fma.
