https://gcc.gnu.org/bugzilla/show_bug.cgi?id=127542
--- Comment #4 from Tobias Burnus <burnus at gcc dot gnu.org> --- (In reply to Andrew Stubbs from comment #3) > This patch fixes the reduced testcase. Please check with the real code. Works at compilation and shows at runtime: Average kernel execution time (pc1): 834.208600 (us) Success Thus: looks good!
