https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97030
--- Comment #1 from Tom de Vries <vries at gcc dot gnu.org> --- (In reply to Tom de Vries from comment #0) > ATM, we have the following in the nvptx.c source code: > ... > #define WORKAROUND_PTXJIT_BUG 1 > #define WORKAROUND_PTXJIT_BUG_2 1 > #define WORKAROUND_PTXJIT_BUG_3 1 > ... > > Having the workaround hardcoded in the sources has the benefit that when > people report a problem with a certain gcc version, you can reasonably > assume that you know which workarounds were applied. > > OTOH, it might unnecessarily slow down real apps on JIT versions that are > fixed. > > So, it could be good to have these runtime switchable. > OTOH, some of these may not have been acknowledged as JIT bug by nvidia, and actually be PTX ISA documentation bugs. In which case it's probably a bad idea to expose the possibility to disable the workaround.
