Adds a simplification for (~X | Y) ^ X to be folded into ~(X & Y).
Also adds the macro bitwise_equal_p for generic and gimple which
returns true iff EXPR1 and EXPR2 have the same value. This helps
to reduce the number of nop_converts necessary to match the pattern.
Tested successfully on x86_64 and x86 targets.
PR middle-end/109986
gcc/ChangeLog:
* generic-match-head.cc (bitwise_equal_p): New macro.
* gimple-match-head.cc (bitwise_equal_p): New macro.
(gimple_nop_convert): Declare.
(gimple_bitwise_equal_p): Helper for bitwise_equal_p.
* 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.
Co-authored-by: Jakub Jelinek <ja...@redhat.com>
---
gcc/generic-match-head.cc | 17 ++
gcc/gimple-match-head.cc | 36 ++++
gcc/match.pd | 6 +
.../gcc.c-torture/execute/pr109986.c | 41 ++++
gcc/testsuite/gcc.dg/tree-ssa/pr109986.c | 177 ++++++++++++++++++
5 files changed, 277 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/generic-match-head.cc b/gcc/generic-match-head.cc
index f011204c5be..b4b5bc88f4b 100644
--- a/gcc/generic-match-head.cc
+++ b/gcc/generic-match-head.cc
@@ -102,3 +102,20 @@ optimize_successive_divisions_p (tree, tree)
{
return false;
}
+
+/* Return true if EXPR1 and EXPR2 have the same value, but not necessarily
+ same type. The types can differ through nop conversions. */
+
+static inline bool
+bitwise_equal_p (tree expr1, tree expr2)
+{
+ STRIP_NOPS (expr1);
+ STRIP_NOPS (expr2);
+ if (expr1 == expr2)
+ return true;
+ if (!tree_nop_conversion_p (TREE_TYPE (expr1), TREE_TYPE (expr2)))
+ return false;
+ if (TREE_CODE (expr1) == INTEGER_CST && TREE_CODE (expr2) == INTEGER_CST)
+ return wi::to_wide (expr1) == wi::to_wide (expr2);
+ return operand_equal_p (expr1, expr2, 0);
+}
diff --git a/gcc/gimple-match-head.cc b/gcc/gimple-match-head.cc
index b08cd891a13..f960d6cf0b9 100644
--- a/gcc/gimple-match-head.cc
+++ b/gcc/gimple-match-head.cc
@@ -224,3 +224,39 @@ optimize_successive_divisions_p (tree divisor, tree
inner_div)
}
return true;
}
+
+/* Return true if EXPR1 and EXPR2 have the same value, but not necessarily
+ same type. The types can differ through nop conversions. */
+#define bitwise_equal_p(expr1, expr2) gimple_bitwise_equal_p (expr1, expr2,
valueize)
+
+bool gimple_nop_convert (tree, tree *, tree (*)(tree));
+
+/* Helper function for bitwise_equal_p macro. */
+
+static inline bool
+gimple_bitwise_equal_p (tree expr1, tree expr2, tree (*valueize) (tree))
+{
+ if (expr1 == expr2)
+ return true;
+ if (!tree_nop_conversion_p (TREE_TYPE (expr1), TREE_TYPE (expr2)))
+ return false;
+ if (TREE_CODE (expr1) == INTEGER_CST && TREE_CODE (expr2) == INTEGER_CST)
+ return wi::to_wide (expr1) == wi::to_wide (expr2);
+ if (operand_equal_p (expr1, expr2, 0))
+ return true;
+ tree expr3, expr4;
+ if (!gimple_nop_convert (expr1, &expr3, valueize))
+ expr3 = expr1;
+ if (!gimple_nop_convert (expr2, &expr4, valueize))
+ expr4 = expr2;
+ if (expr1 != expr3)
+ {
+ if (operand_equal_p (expr3, expr2, 0))
+ return true;
+ if (expr2 != expr4 && operand_equal_p (expr3, expr4, 0))
+ return true;
+ }
+ if (expr2 != expr4 && operand_equal_p (expr1, expr4, 0))
+ return true;
+ return false;
+}
diff --git a/gcc/match.pd b/gcc/match.pd
index a17d6838c14..367e4fc5517 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -1627,6 +1627,12 @@ 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 @0)) @1)) @2)
+ (if (bitwise_equal_p (@0, @2))
+ (convert (bit_not (bit_and @0 (convert @1))))))
+
/* 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
