On Wed, Jul 5, 2023 at 3:42 PM Drew Ross via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> Adds a simplification for (~X | Y) ^ X to be folded into ~(X & Y).
> Tested successfully on x86_64 and x86 targets.
>
> PR middle-end/109986
>
> gcc/ChangeLog:
>
> * match.pd ((~X | Y) ^ X -> ~(X & Y)): New simplification.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.c-torture/execute/pr109986.c: New test.
> * gcc.dg/tree-ssa/pr109986.c: New test.
> ---
> gcc/match.pd | 11 ++
> .../gcc.c-torture/execute/pr109986.c | 41 ++++
> gcc/testsuite/gcc.dg/tree-ssa/pr109986.c | 177 ++++++++++++++++++
> 3 files changed, 229 insertions(+)
> create mode 100644 gcc/testsuite/gcc.c-torture/execute/pr109986.c
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr109986.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index a17d6838c14..d9d7d932881 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -1627,6 +1627,17 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (if (tree_nop_conversion_p (type, TREE_TYPE (@0)))
> (convert (bit_and @1 (bit_not @0)))))
>
> +/* (~X | Y) ^ X -> ~(X & Y). */
> +(simplify
> + (bit_xor:c (nop_convert1?
> + (bit_ior:c (nop_convert2? (bit_not (nop_convert3? @0)))
> + @1)) (nop_convert4? @0))
you want to reduce the number of nop_convert? - for example
I wonder if we can canonicalize
(T)~X and ~(T)X
for nop-conversions. The same might apply to binary bitwise operations
where we should push those to a direction where they are likely eliminated.
Usually we'd push them outwards.
The issue with the above pattern is that nop_convertN? expands to 2^N
separate patterns. Together with the two :c you get 64 out of this.
I do not see that all of the combinations can happen when X has to
match unless we fail to contract some of them like if we have
(unsigned)(~(signed)X | Y) ^ X which we could rewrite like
-> (unsigned)((signed)~X | Y) ^ X -> (~X | (unsigned) Y) ^ X
with the last step being somewhat difficult unless we do
(signed)~X | Y -> (signed)(~X | (unsigned)Y). It feels like a
propagation problem and less of a direct pattern matching one.
> + (if (types_match (type, @1))
> + (bit_not (bit_and @1 (convert @0)))
> + (if (types_match (type, @0))
> + (bit_not (bit_and (convert @1) @0))
> + (convert (bit_not (bit_and @0 (convert @1)))))))
You can elide the types_match checks and instead always emit
(convert (bit_not (bit_and @0 (convert @1)))
the conversions are elided when the types match.
Richard.
> +
> /* Convert ~X ^ ~Y to X ^ Y. */
> (simplify
> (bit_xor (convert1? (bit_not @0)) (convert2? (bit_not @1)))
> diff --git a/gcc/testsuite/gcc.c-torture/execute/pr109986.c
> b/gcc/testsuite/gcc.c-torture/execute/pr109986.c
> new file mode 100644
> index 00000000000..00ee9888539
> --- /dev/null
> +++ b/gcc/testsuite/gcc.c-torture/execute/pr109986.c
> @@ -0,0 +1,41 @@
> +/* PR middle-end/109986 */
> +
> +#include "../../gcc.dg/tree-ssa/pr109986.c"
> +
> +int
> +main ()
> +{
> + if (t1 (29789, 29477) != -28678) __builtin_abort ();
> + if (t2 (20196, -18743) != 4294965567) __builtin_abort ();
> + if (t3 (127, 99) != -100) __builtin_abort ();
> + if (t4 (100, 53) != 219) __builtin_abort ();
> + if (t5 (20100, 1283) != -1025) __builtin_abort ();
> + if (t6 (20100, 10283) != 63487) __builtin_abort ();
> + if (t7 (2136614690L, 1136698390L) != -1128276995L) __builtin_abort ();
> + if (t8 (1136698390L, 2136614690L) != -1128276995UL) __builtin_abort ();
> + if (t9 (9176690219839792930LL, 3176690219839721234LL) !=
> -3175044472123688707LL)
> + __builtin_abort ();
> + if (t10 (9176690219839792930LL, 3176690219839721234LL) !=
> 15271699601585862909ULL)
> + __builtin_abort ();
> + if (t11 (29789, 29477) != -28678) __builtin_abort ();
> + if (t12 (20196, -18743) != 4294965567) __builtin_abort ();
> + if (t13 (127, 99) != -100) __builtin_abort ();
> + if (t14 (100, 53) != 219) __builtin_abort ();
> + if (t15 (20100, 1283) != -1025) __builtin_abort ();
> + if (t16 (20100, 10283) != 63487) __builtin_abort ();
> + if (t17 (2136614690, 1136698390) != -1128276995) __builtin_abort ();
> + if (t18 (1136698390L, 2136614690L) != -1128276995UL) __builtin_abort ();
> + if (t19 (9176690219839792930LL, 3176690219839721234LL) !=
> -3175044472123688707LL)
> + __builtin_abort ();
> + if (t20 (9176690219839792930LL, 3176690219839721234LL) !=
> 15271699601585862909ULL)
> + __builtin_abort ();
> + v4si a1 = {1, 2, 3, 4};
> + v4si a2 = {6, 7, 8, 9};
> + v4si r1 = {-1, -3, -1, -1};
> + v4si b1 = t21 (a1, a2);
> + v4si b2 = t22 (a1, a2);
> + if (__builtin_memcmp (&b1, &r1, sizeof (b1) != 0)) __builtin_abort();
> + if (__builtin_memcmp (&b2, &r1, sizeof (b2) != 0)) __builtin_abort();
> + return 0;
> +}
> +
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr109986.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr109986.c
> new file mode 100644
> index 00000000000..45f099b5656
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr109986.c
> @@ -0,0 +1,177 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -fdump-tree-dse1 -Wno-psabi" } */
> +
> +typedef int v4si __attribute__((vector_size(16)));
> +
> +/* Generic */
> +__attribute__((noipa)) int
> +t1 (int a, int b)
> +{
> + return (~a | b) ^ a;
> +}
> +
> +__attribute__((noipa)) unsigned int
> +t2 (int a, int b)
> +{
> + return a ^ (~a | (unsigned int) b);
> +}
> +
> +__attribute__((noipa)) char
> +t3 (char a, char b)
> +{
> + return (b | ~a) ^ a;
> +}
> +
> +__attribute__((noipa)) unsigned char
> +t4 (char a, char b)
> +{
> + return ((unsigned char) a) ^ (b | ~a);
> +}
> +
> +__attribute__((noipa)) short
> +t5 (short a, short b)
> +{
> + return a ^ (b | ~a);
> +}
> +
> +__attribute__((noipa)) unsigned short
> +t6 (short a, short b)
> +{
> + return ((unsigned short) a) ^ (b | ~a);
> +}
> +
> +__attribute__((noipa)) long
> +t7 (long a, long b)
> +{
> + return a ^ (b | ~a);
> +}
> +
> +__attribute__((noipa)) unsigned long
> +t8 (long a, long b)
> +{
> + return ((unsigned long) a) ^ (b | ~a);
> +}
> +
> +__attribute__((noipa)) long long
> +t9 (long long a, long long b)
> +{
> + return a ^ (b | ~a);
> +}
> +
> +__attribute__((noipa)) unsigned long long
> +t10 (long long a, long long b)
> +{
> + return ((unsigned long long) a) ^ (b | ~a);
> +}
> +
> +__attribute__((noipa)) v4si
> +t21 (v4si a, v4si b)
> +{
> + return a ^ (b | ~a);
> +}
> +
> +/* Gimple */
> +__attribute__((noipa)) int
> +t11 (int a, int b)
> +{
> + int t1 = ~a;
> + int t2 = t1 | b;
> + int t3 = t2 ^ a;
> + return t3;
> +}
> +
> +__attribute__((noipa)) unsigned int
> +t12 (int a, unsigned int b)
> +{
> + int t1 = ~a;
> + unsigned int t2 = t1 | b;
> + unsigned int t3 = a ^ t2;
> + return t3;
> +}
> +
> +__attribute__((noipa)) char
> +t13 (char a, char b)
> +{
> + char t1 = ~a;
> + char t2 = b | t1;
> + char t3 = t2 ^ a;
> + return t3;
> +}
> +
> +__attribute__((noipa)) unsigned char
> +t14 (unsigned char a, char b)
> +{
> + unsigned char t1 = ~a;
> + char t2 = b | t1;
> + unsigned char t3 = a ^ t2;
> + return t3;
> +}
> +
> +__attribute__((noipa)) short
> +t15 (short a, short b)
> +{
> + short t1 = ~a;
> + short t2 = t1 | b;
> + short t3 = t2 ^ a;
> + return t3;
> +}
> +
> +__attribute__((noipa)) unsigned short
> +t16 (unsigned short a, short b)
> +{
> + short t1 = ~a;
> + short t2 = t1 | b;
> + unsigned short t3 = t2 ^ a;
> + return t3;
> +}
> +
> +__attribute__((noipa)) long
> +t17 (long a, long b)
> +{
> + long t1 = ~a;
> + long t2 = t1 | b;
> + long t3 = t2 ^ a;
> + return t3;
> +}
> +
> +__attribute__((noipa)) unsigned long
> +t18 (long a, unsigned long b)
> +{
> + long t1 = ~a;
> + unsigned long t2 = t1 | b;
> + unsigned long t3 = t2 ^ a;
> + return t3;
> +}
> +
> +__attribute__((noipa)) long long
> +t19 (long long a, long long b)
> +{
> + long long t1 = ~a;
> + long long t2 = t1 | b;
> + long long t3 = t2 ^ a;
> + return t3;
> +}
> +
> +__attribute__((noipa)) unsigned long long
> +t20 (long long a, long long b)
> +{
> + long long t1 = ~a;
> + long long t2 = t1 | b;
> + unsigned long long t3 = a ^ t2;
> + return t3;
> +}
> +
> +__attribute__((noipa)) v4si
> +t22 (v4si a, v4si b)
> +{
> + v4si t1 = ~a;
> + v4si t2 = t1 | b;
> + v4si t3 = a ^ t2;
> + return t3;
> +}
> +
> +/* { dg-final { scan-tree-dump-not " \\\| " "dse1" } } */
> +/* { dg-final { scan-tree-dump-not " \\\^ " "dse1" } } */
> +/* { dg-final { scan-tree-dump-times " ~" 22 "dse1" } } */
> +/* { dg-final { scan-tree-dump-times " & " 22 "dse1" } } */
> +
> --
> 2.39.3
>
