We had: if (vec_outside_cost <= 0) min_profitable_iters = 0; else { min_profitable_iters = ((vec_outside_cost - scalar_outside_cost) * assumed_vf - vec_inside_cost * peel_iters_prologue - vec_inside_cost * peel_iters_epilogue) / ((scalar_single_iter_cost * assumed_vf) - vec_inside_cost);
which can lead to negative min_profitable_iters when the *_outside_costs are the same and peel_iters_epilogue is nonzero (e.g. if we're peeling for gaps). This is tested as part of the patch that adds support for fully-predicated loops. Tested on aarch64-linux-gnu (both with and without SVE), x86_64-linux-gnu and powerpc64le-linux-gnu. OK to install? Thanks, Richard 2017-11-08 Richard Sandiford <richard.sandif...@linaro.org> Alan Hayward <alan.hayw...@arm.com> David Sherwood <david.sherw...@arm.com> gcc/ * tree-vect-loop.c (vect_estimate_min_profitable_iters): Make sure min_profitable_iters doesn't go negative. Index: gcc/tree-vect-loop.c =================================================================== --- gcc/tree-vect-loop.c 2017-11-08 16:35:04.770241799 +0000 +++ gcc/tree-vect-loop.c 2017-11-08 16:47:06.386264822 +0000 @@ -3651,23 +3651,24 @@ vect_estimate_min_profitable_iters (loop if ((scalar_single_iter_cost * assumed_vf) > (int) vec_inside_cost) { - if (vec_outside_cost <= 0) + min_profitable_iters = ((vec_outside_cost - scalar_outside_cost) + * assumed_vf + - vec_inside_cost * peel_iters_prologue + - vec_inside_cost * peel_iters_epilogue); + + if (min_profitable_iters <= 0) min_profitable_iters = 0; else - { - min_profitable_iters = ((vec_outside_cost - scalar_outside_cost) - * assumed_vf - - vec_inside_cost * peel_iters_prologue - - vec_inside_cost * peel_iters_epilogue) - / ((scalar_single_iter_cost * assumed_vf) - - vec_inside_cost); + { + min_profitable_iters /= ((scalar_single_iter_cost * assumed_vf) + - vec_inside_cost); if ((scalar_single_iter_cost * assumed_vf * min_profitable_iters) <= (((int) vec_inside_cost * min_profitable_iters) + (((int) vec_outside_cost - scalar_outside_cost) * assumed_vf))) min_profitable_iters++; - } + } } /* vector version will never be profitable. */ else