On Fri, Oct 18, 2024 at 5:09 AM Jennifer Schmitz <jschm...@nvidia.com> wrote:
>
> This patch adds the following two simplifications in match.pd:
> - pow (1.0/x, y) to pow (x, -y), avoiding the division
> - pow (0.0, x) to 0.0, avoiding the call to pow.
> The patterns are guarded by flag_unsafe_math_optimizations,
> !flag_trapping_math, !flag_errno_math, !HONOR_SIGNED_ZEROS,
> and !HONOR_INFINITIES.
>
> Tests were added to confirm the application of the transform for float,
> double, and long double.
>
> The patch was bootstrapped and regtested on aarch64-linux-gnu and
> x86_64-linux-gnu, no regression.
> OK for mainline?
>
> Signed-off-by: Jennifer Schmitz <jschm...@nvidia.com>
>
> gcc/
> * match.pd: Fold pow (1.0/x, y) -> pow (x, -y) and
> pow (0.0, x) -> 0.0.
Note this is not to block this patch; it looks good to me.
We have __builtin_powi too and these seem like these simplifications
should apply for that builtin also.
Also I do think you should add a testcase for powf16 too.
Thanks,
Andrew Pinski
>
> gcc/testsuite/
> * gcc.dg/tree-ssa/pow_fold_1.c: New test.
> ---
> gcc/match.pd | 14 +++++++++
> gcc/testsuite/gcc.dg/tree-ssa/pow_fold_1.c | 34 ++++++++++++++++++++++
> 2 files changed, 48 insertions(+)
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pow_fold_1.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 12d81fcac0d..ba100b117e7 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -8203,6 +8203,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (rdiv @0 (exps:s @1))
> (mult @0 (exps (negate @1)))))
>
> + /* Simplify pow(1.0/x, y) into pow(x, -y). */
> + (if (! HONOR_INFINITIES (type)
> + && ! HONOR_SIGNED_ZEROS (type)
> + && ! flag_trapping_math
> + && ! flag_errno_math)
> + (simplify
> + (POW (rdiv:s real_onep@0 @1) @2)
> + (POW @1 (negate @2)))
> +
> + /* Simplify pow(0.0, x) into 0.0. */
> + (simplify
> + (POW real_zerop@0 @1)
> + @0))
> +
> (if (! HONOR_SIGN_DEPENDENT_ROUNDING (type)
> && ! HONOR_NANS (type) && ! HONOR_INFINITIES (type)
> && ! flag_trapping_math
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pow_fold_1.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pow_fold_1.c
> new file mode 100644
> index 00000000000..113df572661
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pow_fold_1.c
> @@ -0,0 +1,34 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -ffast-math" } */
> +/* { dg-require-effective-target c99_runtime } */
> +
> +extern void link_error (void);
> +
> +#define POW1OVER(TYPE, C_TY, TY) \
> + void \
> + pow1over_##TY (TYPE x, TYPE y) \
> + { \
> + TYPE t1 = 1.0##C_TY / x; \
> + TYPE t2 = __builtin_pow##TY (t1, y); \
> + TYPE t3 = -y; \
> + TYPE t4 = __builtin_pow##TY (x, t3); \
> + if (t2 != t4) \
> + link_error (); \
> + } \
> +
> +#define POW0(TYPE, C_TY, TY) \
> + void \
> + pow0_##TY (TYPE x) \
> + { \
> + TYPE t1 = __builtin_pow##TY (0.0##C_TY, x); \
> + if (t1 != 0.0##C_TY) \
> + link_error (); \
> + } \
> +
> +#define TEST_ALL(TYPE, C_TY, TY) \
> + POW1OVER (TYPE, C_TY, TY) \
> + POW0 (TYPE, C_TY, TY)
> +
> +TEST_ALL (double, , )
> +TEST_ALL (float, f, f)
> +TEST_ALL (long double, L, l)
> --
> 2.34.1
