On Mon, Jul 31, 2023 at 7:35 AM Andrew Pinski via Gcc-patches
<[email protected]> wrote:
>
> Even though these are done by combine_comparisons, we can add them to match
> to allow simplifcations during match rather than just during
> reassoc/ifcombine.
>
> OK? Bootstrapped and tested on x86_64-linux-gnu with no regressions.
OK. Note we want to get rid of the GENERIC folding parts of
maybe_fold_{and,or}_comparisons which is what those passes rely on.
Richard.
> gcc/ChangeLog:
>
> PR tree-optimization/106164
> * match.pd (`a != b & a <= b`, `a != b & a >= b`,
> `a == b | a < b`, `a == b | a > b`): Handle these cases
> too.
>
> gcc/testsuite/ChangeLog:
>
> PR tree-optimization/106164
> * gcc.dg/tree-ssa/cmpbit-2.c: New test.
> ---
> gcc/match.pd | 32 +++++++++++++++++--
> gcc/testsuite/gcc.dg/tree-ssa/cmpbit-2.c | 39 ++++++++++++++++++++++++
> 2 files changed, 69 insertions(+), 2 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/cmpbit-2.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 00af5d99119..cf8057701ea 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -2832,7 +2832,21 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (switch
> (if (code1 == EQ_EXPR && val) @3)
> (if (code1 == EQ_EXPR && !val) { constant_boolean_node (false, type);
> })
> - (if (code1 == NE_EXPR && !val) @4)))))))
> + (if (code1 == NE_EXPR && !val) @4)
> + (if (code1 == NE_EXPR
> + && code2 == GE_EXPR
> + && cmp == 0)
> + (gt @0 @1))
> + (if (code1 == NE_EXPR
> + && code2 == LE_EXPR
> + && cmp == 0)
> + (lt @0 @1))
> + )
> + )
> + )
> + )
> + )
> +)
>
> /* Convert (X OP1 CST1) && (X OP2 CST2).
> Convert (X OP1 Y) && (X OP2 Y). */
> @@ -2917,7 +2931,21 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (switch
> (if (code1 == EQ_EXPR && val) @4)
> (if (code1 == NE_EXPR && val) { constant_boolean_node (true, type); })
> - (if (code1 == NE_EXPR && !val) @3)))))))
> + (if (code1 == NE_EXPR && !val) @3)
> + (if (code1 == EQ_EXPR
> + && code2 == GT_EXPR
> + && cmp == 0)
> + (ge @0 @1))
> + (if (code1 == EQ_EXPR
> + && code2 == LT_EXPR
> + && cmp == 0)
> + (le @0 @1))
> + )
> + )
> + )
> + )
> + )
> +)
>
> /* Convert (X OP1 CST1) || (X OP2 CST2).
> Convert (X OP1 Y) || (X OP2 Y). */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-2.c
> b/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-2.c
> new file mode 100644
> index 00000000000..c4226ef01af
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-2.c
> @@ -0,0 +1,39 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O1 -fno-tree-reassoc -fdump-tree-optimized-raw" } */
> +
> +_Bool f(int a, int b)
> +{
> + _Bool c = a == b;
> + _Bool d = a > b;
> + return c | d;
> +}
> +
> +_Bool f1(int a, int b)
> +{
> + _Bool c = a != b;
> + _Bool d = a >= b;
> + return c & d;
> +}
> +
> +_Bool g(int a, int b)
> +{
> + _Bool c = a == b;
> + _Bool d = a < b;
> + return c | d;
> +}
> +
> +_Bool g1(int a, int b)
> +{
> + _Bool c = a != b;
> + _Bool d = a <= b;
> + return c & d;
> +}
> +
> +
> +/* We should be able to optimize these without reassociation too. */
> +/* { dg-final { scan-tree-dump-not "bit_and_expr," "optimized" } } */
> +/* { dg-final { scan-tree-dump-not "bit_ior_expr," "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "gt_expr," 1 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "ge_expr," 1 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "lt_expr," 1 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "le_expr," 1 "optimized" } } */
> --
> 2.31.1
>
