MATCH: [PR111109] Fix bit_ior(cond,cond) when comparisons are fp

The patterns that were added in r13-4620-g4d9db4bdd458, missed that
(a > b) and (a <= b) are not inverse of each other for floating point
comparisons (if NaNs are supported). Even though there was a check for
intergal types, it was only for the result of the cond rather for the
type of what is being compared. The fix is to check to see if cmp and
icmp are inverse of each other by using the invert_tree_comparison function.

OK for trunk and GCC 13 branch? Bootstrapped and tested on x86_64-linux-gnu with no regressions.

I added the testcase to execute/ieee as it requires support for NAN.

	PR tree-optimization/111109

gcc/ChangeLog:

	* match.pd (ior(cond,cond), ior(vec_cond,vec_cond)):
	Add check to make sure cmp and icmp are inverse.

gcc/testsuite/ChangeLog:

	* gcc.c-torture/execute/ieee/fp-cmp-cond-1.c: New test.

2 files changed, 86 insertions, 3 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index 890f050..cf0bb3a 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -2087,6 +2087,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
    (bit_and:c (convert? (cmp@0  @01 @02)) @3)
    (bit_and:c (convert? (icmp@4 @01 @02)) @5))
     (if (INTEGRAL_TYPE_P (type)
+	 && invert_tree_comparison (cmp, HONOR_NANS (@01)) == icmp
 	 /* The scalar version has to be canonicalized after vectorization
 	    because it makes unconditional loads conditional ones, which
 	    means we lose vectorization because the loads may trap.  */
@@ -2101,6 +2102,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
    (cond (cmp@0  @01 @02) @3 zerop)
    (cond (icmp@4 @01 @02) @5 zerop))
     (if (INTEGRAL_TYPE_P (type)
+	 && invert_tree_comparison (cmp, HONOR_NANS (@01)) == icmp
 	 /* The scalar version has to be canonicalized after vectorization
 	    because it makes unconditional loads conditional ones, which
 	    means we lose vectorization because the loads may trap.  */
@@ -2113,13 +2115,15 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   (bit_ior
    (bit_and:c (vec_cond:s (cmp@0 @6 @7) @4 @5) @2)
    (bit_and:c (vec_cond:s (icmp@1 @6 @7) @4 @5) @3))
-    (if (integer_zerop (@5))
+    (if (integer_zerop (@5)
+	 && invert_tree_comparison (cmp, HONOR_NANS (@6)) == icmp)
      (switch
       (if (integer_onep (@4))
        (bit_and (vec_cond @0 @2 @3) @4))
 	(if (integer_minus_onep (@4))
 	 (vec_cond @0 @2 @3)))
-    (if (integer_zerop (@4))
+    (if (integer_zerop (@4)
+	 && invert_tree_comparison (cmp, HONOR_NANS (@6)) == icmp)
      (switch
       (if (integer_onep (@5))
        (bit_and (vec_cond @0 @3 @2) @5))
@@ -2132,7 +2136,8 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   (bit_ior
    (vec_cond:s (cmp@0 @4 @5) @2 integer_zerop)
    (vec_cond:s (icmp@1 @4 @5) @3 integer_zerop))
-    (vec_cond @0 @2 @3)))
+  (if (invert_tree_comparison (cmp, HONOR_NANS (@4)) == icmp)
+   (vec_cond @0 @2 @3))))
 
 /* Transform X & -Y into X * Y when Y is { 0 or 1 }.  */
 (simplify
diff --git a/gcc/testsuite/gcc.c-torture/execute/ieee/fp-cmp-cond-1.c b/gcc/testsuite/gcc.c-torture/execute/ieee/fp-cmp-cond-1.c
new file mode 100644
index 0000000..4a3c4b0
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/ieee/fp-cmp-cond-1.c
@@ -0,0 +1,78 @@
+/* PR tree-optimization/111109 */
+
+/*
+   f should return 0 if either fa and fb are a nan.
+   Rather than the value of a or b.
+*/
+__attribute__((noipa))
+int f(int a, int b, float fa, float fb) {
+  const _Bool c = fa < fb;
+  const _Bool c1 = fa >= fb;
+  return (c * a) | (c1 * b);
+}
+
+/*
+   f1 should return 0 if either fa and fb are a nan.
+   Rather than the value of a&1 or b&1.
+*/
+__attribute__((noipa))
+int f1(int a, int b, float fa, float fb) {
+  const _Bool c = fa < fb;
+  const _Bool c1 = fa >= fb;
+  return (c & a) | (c1 & b);
+}
+
+#if __SIZEOF_INT__ == __SIZEOF_FLOAT__
+typedef int v4si __attribute__ ((vector_size (1*sizeof(int))));
+typedef float v4sf __attribute__ ((vector_size (1*sizeof(float))));
+/*
+   fvf0 should return {0} if either fa and fb are a nan.
+   Rather than the value of a or b.
+*/
+__attribute__((noipa))
+v4si vf0(v4si a, v4si b, v4sf fa, v4sf fb) {
+  const v4si c = fa < fb;
+  const v4si c1 = fa >= fb;
+  return (c & a) | (c1 & b);
+}
+
+
+#endif
+
+int main(void)
+{
+  float a = __builtin_nan("");
+
+  if (f(-1,-1, a, a) != 0)
+    __builtin_abort();
+  if (f(-1,-1, a, 0) != 0)
+    __builtin_abort();
+  if (f(-1,-1, 0, a) != 0)
+    __builtin_abort();
+  if (f(-1,-1, 0, 0) != -1)
+    __builtin_abort();
+
+
+  if (f1(1,1, a, a) != 0)
+    __builtin_abort();
+  if (f1(1,1, a, 0) != 0)
+    __builtin_abort();
+  if (f1(1,1, 0, a) != 0)
+    __builtin_abort();
+  if (f1(1,1, 0, 0) != 1)
+        __builtin_abort();
+
+#if __SIZEOF_INT__ == __SIZEOF_FLOAT__
+  v4si b = {-1};
+  v4sf c = {a};
+  v4sf d = {0.0};
+  if (vf0(b,b, c, c)[0] != 0)
+    __builtin_abort();
+  if (vf0(b,b, c, d)[0] != 0)
+    __builtin_abort();
+  if (vf0(b,b, d, c)[0] != 0)
+    __builtin_abort();
+  if (vf0(b,b, d, d)[0] != b[0])
+        __builtin_abort();
+#endif
+}