Re: [PATCH v3 3/3] ivopts: Adjust reg pressure estimate for spilling invariants compared to iv cands.

On Wed, Jul 29, 2026 at 4:01 PM Jovan Dmitrovic
<[email protected]> wrote:
>
> Currently, ivopt calculates register pressure cost so that the cost of
> spilling induction variables is exactly double the cost of spilling
> loop invariants, which is not exactly right.
> When invariants are spilled, only loading the invariant back to
> registers should be taken into account, as we don't need to save them
> more than once. This isn't the case for IV candidates which have to
> be both loaded and stored for each iteration of the loop.

OK.

Thanks,
Richard.

> gcc/ChangeLog:
>
>         * tree-ssa-loop-ivopts.cc (ivopts_estimate_reg_pressure):
>         Change register pressure estimate in order to respect
>         the impact of spilling induction variables, compared
>         to spilling loop invariants.
>
> Co-authored-by: Radosav Krunić <[email protected]>
> Signed-off-by: Djordje Todorović <[email protected]>
> Signed-off-by: Chao-Ying Fu <[email protected]>
> Signed-off-by: Jovan Dmitrović <[email protected]>
> Signed-off-by: Radosav Krunić <[email protected]>
> ---
>  gcc/tree-ssa-loop-ivopts.cc | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
>
> diff --git a/gcc/tree-ssa-loop-ivopts.cc b/gcc/tree-ssa-loop-ivopts.cc
> index ca06592190e0..40413c46f1b2 100644
> --- a/gcc/tree-ssa-loop-ivopts.cc
> +++ b/gcc/tree-ssa-loop-ivopts.cc
> @@ -6096,15 +6096,17 @@ ivopts_estimate_reg_pressure (struct ivopts_data *data, unsigned n_invs,
>    if (regs_needed <= available_regs)
>      cost = 0;
>    /* If we run out of available registers but the number of candidates
> -     does not, we penalize extra registers using target_spill_cost.  */
> +     does not, we penalize extra registers using target_spill_cost.
> +     As we tend to spill invariants here, only take loading the
> +     invariant into account, because the invariant won't change for the
> +     duration of the loop and storing it every iteration is unnecessary. */
>    else if (n_cands <= available_regs)
> -    cost = target_spill_cost [speed] * (regs_needed - available_regs);
> -  /* If the number of candidates runs out available registers, we penalize
> -     extra candidate registers using target_spill_cost * 2.  Because it is
> -     more expensive to spill induction variable than invariant.  */
> +    cost = target_spill_cost [speed] * (regs_needed - available_regs) / 2;
> +  /* If both IV cands and invariants spill, calculate additional cost for
> +     having to store spilled candidates. */
>    else
> -    cost = target_spill_cost [speed] * (n_cands - available_regs) * 2
> -          + target_spill_cost [speed] * (regs_needed - n_cands);
> +    cost = target_spill_cost [speed] * (regs_needed - available_regs) / 2;
> +               + target_spill_cost[speed] * (n_cands - available_regs) / 2;
>
>    return cost;
>  }
> --
> 2.34.1