https://gcc.gnu.org/bugzilla/show_bug.cgi?id=122281
--- Comment #19 from Benjamin Schulz <schulz.benjamin at googlemail dot com> --- With the latest gcc gcc (Gentoo 16.0.9999 p, commit dfcc7b24a3954a0417f7f03651f6de52d5d796e3) 16.0.0 20251115 (experimental) aaa625a51cff750b40bc98f6555adc3f3f5f297b and -fopenmp -foffload=nvptx-none -fno-stack-protector -save-temps -foffload-options=nvptx-none=-march=sm_89 (note that gcc says it does not have sm_120 which would be right for my 5060 Ti) I still get the same cuda memory error with sparsetests. Clang works fine, however.
