tree-optimization/102131 - fix niter analysis wrt overflow

This fixes the overflow issues seen with analyzing
BASE0 + STEP0 cmp BASE1 + STEP1 as BASE0 + STEP0 - STEP1 cmp BASE1
by following the logic we have when simplifying comparisons.

2022-01-24  Richard Biener  <rguenther@suse.de>
	    Jiufu Guo  <guojiufu@linux.ibm.com>

	PR tree-optimization/100740
	PR tree-optimization/101508
	PR tree-optimization/101972
	PR tree-optimization/102131
	* tree-ssa-loop-niter.cc (number_of_iterations_cond): Properly
	constrain BASE0 + STEP0 cmp BASE1 + STEP1 to
	BASE0 + STEP0 - STEP1 cmp BASE1 transform.

	* gcc.dg/torture/pr100740.c: New testcase.
	* gcc.dg/torture/pr101508.c: Likewise.
	* gcc.dg/torture/pr101972.c: Likewise.
	* gcc.dg/torture/pr102131-1.c: Likewise.
	* gcc.dg/torture/pr102131-2.c: Likewise.
	* gcc.dg/torture/pr102131-3.c: Likewise.
	* gcc.dg/torture/pr102131-4.c: Likewise.

8 files changed, 143 insertions, 10 deletions

diff --git a/gcc/testsuite/gcc.dg/torture/pr100740.c b/gcc/testsuite/gcc.dg/torture/pr100740.c
new file mode 100644
index 0000000..a85855e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr100740.c
@@ -0,0 +1,12 @@
+/* { dg-do run } */
+
+unsigned a, b;
+int main()
+{
+  unsigned c = 0;
+  for (a = 0; a < 2; a++)
+    for (b = 0; b < 2; b++)
+      if (++c < a)
+	__builtin_abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr101508.c b/gcc/testsuite/gcc.dg/torture/pr101508.c
new file mode 100644
index 0000000..e1cb264
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr101508.c
@@ -0,0 +1,13 @@
+/* { dg-do run } */
+
+int
+main ()
+{
+  unsigned i;
+  for (i = 0; i < 3; ++i)
+    {
+      if (i > i * 2)
+        __builtin_abort ();
+    }
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr101972.c b/gcc/testsuite/gcc.dg/torture/pr101972.c
new file mode 100644
index 0000000..3adb482
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr101972.c
@@ -0,0 +1,39 @@
+/* { dg-do run  } */
+/* { dg-require-effective-target int32plus } */
+
+int a, b, c, d, f;
+static short e = 63891;
+char g = 30;
+unsigned h(int i, int j) { return i << j; }
+int *l(int *);
+void m()
+{
+  a = 0;
+  for (; a >= 0; a--)
+    {
+      int *k = &b;
+      *k = e < 0;
+    }
+  c = b;
+  l(&c);
+}
+int *l(int *i)
+{
+  d = 2;
+  for (; d <= 6; d++)
+    {
+      if (h(d, *i) <= d)
+	;
+      else
+	continue;
+      g = 0;
+      return &f;
+    }
+  return (void *)0;
+}
+int main()
+{
+  m();
+  if (g != 30)
+    __builtin_abort ();
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr102131-1.c b/gcc/testsuite/gcc.dg/torture/pr102131-1.c
new file mode 100644
index 0000000..5ff576d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr102131-1.c
@@ -0,0 +1,16 @@
+/* { dg-do run } */
+
+int a;
+int main()
+{
+  unsigned b = 0;
+  int c = 1;
+  for (; b < 3; b++)
+    {
+      while (c < b)
+	__builtin_abort ();
+      for (a = 0; a < 3; a++)
+	c++;
+    }
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr102131-2.c b/gcc/testsuite/gcc.dg/torture/pr102131-2.c
new file mode 100644
index 0000000..830c72c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr102131-2.c
@@ -0,0 +1,15 @@
+/* { dg-do run } */
+
+int a;
+int main()
+{
+  unsigned b = 0;
+  int c = 1;
+  for (;b < 3; b++)
+    {
+      if (c < b)
+	__builtin_abort ();
+      c+=3;
+    }
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr102131-3.c b/gcc/testsuite/gcc.dg/torture/pr102131-3.c
new file mode 100644
index 0000000..aed10c9
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr102131-3.c
@@ -0,0 +1,11 @@
+/* { dg-do run } */
+
+int a;
+int main()
+{
+  unsigned b = 0;
+  for (a = 2; a < 8; a += 2)
+    if (++b > a)
+      __builtin_abort();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr102131-4.c b/gcc/testsuite/gcc.dg/torture/pr102131-4.c
new file mode 100644
index 0000000..c63c08b
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr102131-4.c
@@ -0,0 +1,15 @@
+/* { dg-do run } */
+/* { dg-require-effective-target int32plus } */
+
+unsigned a;
+int main()
+{
+  unsigned b = 1;
+  for (; b < 4; b++) {
+      a = (a ^ 2000000000) * -b;
+      if (b > a)
+	__builtin_abort ();
+      a = 3000000000;
+  }
+  return 0;
+}
diff --git a/gcc/tree-ssa-loop-niter.cc b/gcc/tree-ssa-loop-niter.cc
index 21cc257..04c2095 100644
--- a/gcc/tree-ssa-loop-niter.cc
+++ b/gcc/tree-ssa-loop-niter.cc
@@ -1894,7 +1894,8 @@ number_of_iterations_cond (class loop *loop,
      provided that either below condition is satisfied:
 
        a) the test is NE_EXPR;
-       b) iv0.step - iv1.step is integer and iv0/iv1 don't overflow.
+       b) iv0 and iv1 do not overflow and iv0.step - iv1.step is of
+	  the same sign and of less or equal magnitude than iv0.step
 
      This rarely occurs in practice, but it is simple enough to manage.  */
   if (!integer_zerop (iv0->step) && !integer_zerop (iv1->step))
@@ -1903,17 +1904,28 @@ number_of_iterations_cond (class loop *loop,
       tree step = fold_binary_to_constant (MINUS_EXPR, step_type,
 					   iv0->step, iv1->step);
 
-      /* No need to check sign of the new step since below code takes care
-	 of this well.  */
-      if (code != NE_EXPR
-	  && (TREE_CODE (step) != INTEGER_CST
-	      || !iv0->no_overflow || !iv1->no_overflow))
-	return false;
+      /* For code other than NE_EXPR we have to ensure moving the evolution
+	 of IV1 to that of IV0 does not introduce overflow.  */
+      if (TREE_CODE (step) != INTEGER_CST
+	  || !iv0->no_overflow || !iv1->no_overflow)
+	{
+	  if (code != NE_EXPR)
+	    return false;
+	  iv0->no_overflow = false;
+	}
+      /* If the new step of IV0 has changed sign or is of greater
+	 magnitude then we do not know whether IV0 does overflow
+	 and thus the transform is not valid for code other than NE_EXPR  */
+      else if (tree_int_cst_sign_bit (step) != tree_int_cst_sign_bit (iv0->step)
+	       || wi::gtu_p (wi::abs (wi::to_widest (step)),
+			     wi::abs (wi::to_widest (iv0->step))))
+	{
+	  if (code != NE_EXPR)
+	    return false;
+	  iv0->no_overflow = false;
+	}
 
       iv0->step = step;
-      if (!POINTER_TYPE_P (type))
-	iv0->no_overflow = false;
-
       iv1->step = build_int_cst (step_type, 0);
       iv1->no_overflow = true;
     }