move the (a-b) CMP 0 ? (a-b) : (b-a) optimization from fold_cond_expr_with_comparison to match

This patch moves the `(a-b) CMP 0 ? (a-b) : (b-a)` optimization
from fold_cond_expr_with_comparison to match.

Bootstrapped and tested on x86_64-linux-gnu.

Changes in:
v2: Removes `(a == b) ? 0 : (b - a)` handling since it was handled
    via r14-3606-g3d86e7f4a8ae
    Change zerop to integer_zerop for `(a - b) == 0 ? 0 : (b - a)`,
    Add `(a - b) != 0 ? (a - b) : 0` handling.

gcc/ChangeLog:

	* match.pd (`(A - B) CMP 0 ? (A - B) : (B - A)`):
	New patterns.

gcc/testsuite/ChangeLog:

	* gcc.dg/tree-ssa/phi-opt-38.c: New test.

2 files changed, 88 insertions, 3 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index a56838f..ce8d159 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -5650,9 +5650,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   (cnd (logical_inverted_value truth_valued_p@0) @1 @2)
   (cnd @0 @2 @1)))
 
-/* abs/negative simplifications moved from fold_cond_expr_with_comparison,
-   Need to handle (A - B) case as fold_cond_expr_with_comparison does.
-   Need to handle UN* comparisons.
+/* abs/negative simplifications moved from fold_cond_expr_with_comparison.
 
    None of these transformations work for modes with signed
    zeros.  If A is +/-0, the first two transformations will
@@ -5717,6 +5715,48 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
        (convert (negate (absu:utype @0))))
        (negate (abs @0)))))
  )
+
+ /* (A - B) == 0 ? (A - B) : (B - A)    same as (B - A) */
+ (for cmp (eq uneq)
+  (simplify
+   (cnd (cmp (minus@0 @1 @2) zerop) @0 (minus@3 @2 @1))
+   (if (!HONOR_SIGNED_ZEROS (type))
+    @3))
+  (simplify
+   (cnd (cmp (minus@0 @1 @2) integer_zerop) integer_zerop (minus@3 @2 @1))
+   @3)
+ )
+ /* (A - B) != 0 ? (A - B) : (B - A)    same as (A - B) */
+ (for cmp (ne ltgt)
+  (simplify
+   (cnd (cmp (minus@0 @1 @2) zerop) @0 (minus @2 @1))
+   (if (!HONOR_SIGNED_ZEROS (type))
+    @0))
+  (simplify
+   (cnd (cmp (minus@0 @1 @2) integer_zerop) @0 integer_zerop)
+   @0)
+ )
+ /* (A - B) >=/> 0 ? (A - B) : (B - A)    same as abs (A - B) */
+ (for cmp (ge gt)
+  (simplify
+   (cnd (cmp (minus@0 @1 @2) zerop) @0 (minus @2 @1))
+   (if (!HONOR_SIGNED_ZEROS (type)
+	&& !TYPE_UNSIGNED (type))
+    (abs @0))))
+ /* (A - B) <=/< 0 ? (A - B) : (B - A)    same as -abs (A - B) */
+ (for cmp (le lt)
+  (simplify
+   (cnd (cmp (minus@0 @1 @2) zerop) @0 (minus @2 @1))
+   (if (!HONOR_SIGNED_ZEROS (type)
+	&& !TYPE_UNSIGNED (type))
+    (if (ANY_INTEGRAL_TYPE_P (type)
+	 && !TYPE_OVERFLOW_WRAPS (type))
+     (with {
+        tree utype = unsigned_type_for (type);
+      }
+      (convert (negate (absu:utype @0))))
+      (negate (abs @0)))))
+ )
 )
 
 /* -(type)!A -> (type)A - 1.  */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-38.c b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-38.c
new file mode 100644
index 0000000..0f0e317
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-38.c
@@ -0,0 +1,45 @@
+/* { dg-options "-O2 -fno-signed-zeros -fdump-tree-phiopt" } */
+int minus1(int a, int b)
+{
+  int c = a - b;
+  if (c == 0) c = b - a;
+  return c;
+}
+int minus2(int a, int b)
+{
+  int c = a - b;
+  if (c != 0) c = b - a;
+  return c;
+}
+int minus3(int a, int b)
+{
+  int c = a - b;
+  if (c == 0) c = 0;
+  else c = b - a;
+  return c;
+}
+int minus4(int a, int b)
+{
+  int c;
+  if (a == b) c = 0;
+  else
+    c = b - a;
+  return c;
+}
+int abs0(int a, int b)
+{
+  int c = a - b;
+  if (c <= 0) c = b - a;
+  return c;
+}
+int negabs(int a, int b)
+{
+  int c = a - b;
+  if (c >= 0) c = b - a;
+  return c;
+}
+
+/* The above should be optimized at phiopt1 except for negabs which has to wait
+  until phiopt2 as -abs is not acceptable in early phiopt.  */
+/* { dg-final { scan-tree-dump-times "if" 1  "phiopt1"  } } */
+/* { dg-final { scan-tree-dump-not "if" "phiopt2" } } */