[gcc r13-5195] Add c[lt]z idiom recognition

[gcc r13-5195] Add c[lt]z idiom recognition

[Andrew Carlotti]

https://gcc.gnu.org/g:4798080d4a3530d985efef68aa2e04ec7549b3c1

commit r13-5195-g4798080d4a3530d985efef68aa2e04ec7549b3c1
Author: Andrew Carlotti <andrew.carlotti@arm.com>
Date:   Thu Dec 22 02:14:06 2022 +0000

    Add c[lt]z idiom recognition
    
    This recognises the patterns of the form:
      while (n & 1) { n >>= 1 }
    
    Unfortunately there are currently two issues relating to this patch.
    
    Firstly, simplify_using_initial_conditions does not recognise that
            (n != 0) and ((n & 1) == 0) implies that ((n >> 1) != 0).
    
    This preconditions arise following the loop copy-header pass, and the
    assumptions returned by number_of_iterations_exit_assumptions then
    prevent final value replacement from using the niter result.
    
    I'm not sure what is the best way to fix this - one approach could be to
    modify simplify_using_initial_conditions to handle this sort of case,
    but it seems that it basically wants the information that ranger could
    give anway, so would something like that be a better option?
    
    The second issue arises in the vectoriser, which is able to determine
    that the niter->assumptions are always true.
    When building with -march=armv8.4-a+sve -S -O3, we get this codegen:
    
    foo (unsigned int b) {
        int c = 0;
    
        if (b == 0)
          return PREC;
    
        while (!(b & (1 << (PREC - 1)))) {
            b <<= 1;
            c++;
        }
    
        return c;
    }
    
    foo:
    .LFB0:
            .cfi_startproc
            cmp     w0, 0
            cbz     w0, .L6
            blt     .L7
            lsl     w1, w0, 1
            clz     w2, w1
            cmp     w2, 14
            bls     .L8
            mov     x0, 0
            cntw    x3
            add     w1, w2, 1
            index   z1.s, #0, #1
            whilelo p0.s, wzr, w1
    .L4:
            add     x0, x0, x3
            mov     p1.b, p0.b
            mov     z0.d, z1.d
            whilelo p0.s, w0, w1
            incw    z1.s
            b.any   .L4
            add     z0.s, z0.s, #1
            lastb   w0, p1, z0.s
            ret
            .p2align 2,,3
    .L8:
            mov     w0, 0
            b       .L3
            .p2align 2,,3
    .L13:
            lsl     w1, w1, 1
    .L3:
            add     w0, w0, 1
            tbz     w1, #31, .L13
            ret
            .p2align 2,,3
    .L6:
            mov     w0, 32
            ret
            .p2align 2,,3
    .L7:
            mov     w0, 0
            ret
            .cfi_endproc
    
    In essence, the vectoriser uses the niter information to determine
    exactly how many iterations of the loop it needs to run. It then uses
    SVE whilelo instructions to run this number of iterations. The original
    loop counter is also vectorised, despite only being used in the final
    iteration, and then the final value of this counter is used as the
    return value (which is the same as the number of iterations it computed
    in the first place).
    
    This vectorisation is obviously bad, and I think it exposes a latent
    bug in the vectoriser, rather than being an issue caused by this
    specific patch.
    
    gcc/ChangeLog:
    
            * tree-ssa-loop-niter.cc (number_of_iterations_cltz): New.
            (number_of_iterations_bitcount): Add call to the above.
            (number_of_iterations_exit_assumptions): Add EQ_EXPR case for
            c[lt]z idiom recognition.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.dg/tree-ssa/cltz-max.c: New test.
            * gcc.dg/tree-ssa/clz-char.c: New test.
            * gcc.dg/tree-ssa/clz-int.c: New test.
            * gcc.dg/tree-ssa/clz-long-long.c: New test.
            * gcc.dg/tree-ssa/clz-long.c: New test.
            * gcc.dg/tree-ssa/ctz-char.c: New test.
            * gcc.dg/tree-ssa/ctz-int.c: New test.
            * gcc.dg/tree-ssa/ctz-long-long.c: New test.
            * gcc.dg/tree-ssa/ctz-long.c: New test.

Diff:
---
 gcc/testsuite/gcc.dg/tree-ssa/cltz-max.c      |  72 +++++++++++
 gcc/testsuite/gcc.dg/tree-ssa/clz-char.c      |  34 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/clz-int.c       |  34 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/clz-long-long.c |  34 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/clz-long.c      |  34 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/ctz-char.c      |  36 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/ctz-int.c       |  36 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/ctz-long-long.c |  36 ++++++
 gcc/testsuite/gcc.dg/tree-ssa/ctz-long.c      |  36 ++++++
 gcc/tree-ssa-loop-niter.cc                    | 165 ++++++++++++++++++++++++++
 10 files changed, 517 insertions(+)

diff --git a/gcc/testsuite/gcc.dg/tree-ssa/cltz-max.c b/gcc/testsuite/gcc.dg/tree-ssa/cltz-max.c
new file mode 100644
index 00000000000..a6bea3d3389
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/cltz-max.c
@@ -0,0 +1,72 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-tree-loop-optimize -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__)
+
+int clz_count1 (unsigned char b) {
+    int c = 0;
+
+    if (b == 0)
+      return 0;
+
+    while (!(b & (1 << (PREC - 1)))) {
+	b <<= 1;
+	c++;
+    }
+    if (c <= PREC - 1)
+      return 0;
+    else
+      return 34567;
+}
+
+int clz_count2 (unsigned char b) {
+    int c = 0;
+
+    if (b == 0)
+      return 0;
+
+    while (!(b & (1 << PREC - 1))) {
+	b <<= 1;
+	c++;
+    }
+    if (c <= PREC - 2)
+      return 0;
+    else
+      return 76543;
+}
+
+int ctz_count1 (unsigned char b) {
+    int c = 0;
+
+    if (b == 0)
+      return 0;
+
+    while (!(b & 1)) {
+	b >>= 1;
+	c++;
+    }
+    if (c <= PREC - 1)
+      return 0;
+    else
+      return 23456;
+}
+
+int ctz_count2 (unsigned char b) {
+    int c = 0;
+
+    if (b == 0)
+      return 0;
+
+    while (!(b & 1)) {
+	b >>= 1;
+	c++;
+    }
+    if (c <= PREC - 2)
+      return 0;
+    else
+      return 65432;
+}
+/* { dg-final { scan-tree-dump-times "34567" 0 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "76543" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "23456" 0 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "65432" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/clz-char.c b/gcc/testsuite/gcc.dg/tree-ssa/clz-char.c
new file mode 100644
index 00000000000..4a122db95bb
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/clz-char.c
@@ -0,0 +1,34 @@
+/* { dg-do run } */
+/* { dg-require-effective-target clzl } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned char b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & (1 << (PREC - 1)))) {
+	b <<= 1;
+	c++;
+    }
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(1 << (PREC - 1)) != 0)
+    __builtin_abort ();
+  if (foo(35) != PREC - 6)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_clz|\\.CLZ" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/clz-int.c b/gcc/testsuite/gcc.dg/tree-ssa/clz-int.c
new file mode 100644
index 00000000000..96646f8e19c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/clz-int.c
@@ -0,0 +1,34 @@
+/* { dg-do run } */
+/* { dg-require-effective-target clzl } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__ * __SIZEOF_INT__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned int b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & (1 << (PREC - 1)))) {
+	b <<= 1;
+	c++;
+    }
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(1 << (PREC - 1)) != 0)
+    __builtin_abort ();
+  if (foo(35) != PREC - 6)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_clz|\\.CLZ" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/clz-long-long.c b/gcc/testsuite/gcc.dg/tree-ssa/clz-long-long.c
new file mode 100644
index 00000000000..80d3edc1dab
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/clz-long-long.c
@@ -0,0 +1,34 @@
+/* { dg-do run } */
+/* { dg-require-effective-target clzll } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__ * __SIZEOF_LONG_LONG__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned long long b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & (1LL << (PREC - 1)))) {
+	b <<= 1;
+	c++;
+    }
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(1LL << (PREC - 1)) != 0)
+    __builtin_abort ();
+  if (foo(35) != PREC - 6)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_clz|\\.CLZ" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/clz-long.c b/gcc/testsuite/gcc.dg/tree-ssa/clz-long.c
new file mode 100644
index 00000000000..1c8037f93b9
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/clz-long.c
@@ -0,0 +1,34 @@
+/* { dg-do run } */
+/* { dg-require-effective-target clzl } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__ * __SIZEOF_LONG__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned long b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & (1L << (PREC - 1)))) {
+	b <<= 1;
+	c++;
+}
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(1L << (PREC - 1)) != 0)
+    __builtin_abort ();
+  if (foo(35) != PREC - 6)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_clz|\\.CLZ" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ctz-char.c b/gcc/testsuite/gcc.dg/tree-ssa/ctz-char.c
new file mode 100644
index 00000000000..3cd166acbd4
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ctz-char.c
@@ -0,0 +1,36 @@
+/* { dg-do run } */
+/* { dg-require-effective-target ctz } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned char b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & 1)) {
+	b >>= 1;
+	c++;
+    }
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(128) != 7)
+    __builtin_abort ();
+  if (foo(96) != 5)
+    __builtin_abort ();
+  if (foo(35) != 0)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_ctz|\\.CTZ" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ctz-int.c b/gcc/testsuite/gcc.dg/tree-ssa/ctz-int.c
new file mode 100644
index 00000000000..7f63493eb73
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ctz-int.c
@@ -0,0 +1,36 @@
+/* { dg-do run } */
+/* { dg-require-effective-target ctz } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__ * __SIZEOF_INT__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned int b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & 1)) {
+	b >>= 1;
+	c++;
+    }
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(1 << (PREC - 1)) != PREC - 1)
+    __builtin_abort ();
+  if (foo(96) != 5)
+    __builtin_abort ();
+  if (foo(35) != 0)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_ctz|\\.CTZ" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ctz-long-long.c b/gcc/testsuite/gcc.dg/tree-ssa/ctz-long-long.c
new file mode 100644
index 00000000000..924f61b76f0
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ctz-long-long.c
@@ -0,0 +1,36 @@
+/* { dg-do run } */
+/* { dg-require-effective-target ctzll } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__ * __SIZEOF_LONG_LONG__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned long long b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & 1)) {
+	b >>= 1;
+	c++;
+    }
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(1LL << (PREC - 1)) != PREC - 1)
+    __builtin_abort ();
+  if (foo(96) != 5)
+    __builtin_abort ();
+  if (foo(35) != 0)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_ctz|\\.CTZ" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ctz-long.c b/gcc/testsuite/gcc.dg/tree-ssa/ctz-long.c
new file mode 100644
index 00000000000..178945daa8a
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ctz-long.c
@@ -0,0 +1,36 @@
+/* { dg-do run } */
+/* { dg-require-effective-target ctzl } */
+/* { dg-options "-O2 -fno-tree-ch -fdump-tree-optimized" } */
+
+#define PREC (__CHAR_BIT__ * __SIZEOF_LONG__)
+
+int
+__attribute__ ((noinline, noclone))
+foo (unsigned long b) {
+    int c = 0;
+
+    if (b == 0)
+      return PREC;
+
+    while (!(b & 1)) {
+	b >>= 1;
+	c++;
+    }
+
+    return c;
+}
+
+int main()
+{
+  if (foo(0) != PREC)
+    __builtin_abort ();
+  if (foo(1L << (PREC - 1)) != PREC - 1)
+    __builtin_abort ();
+  if (foo(96) != 5)
+    __builtin_abort ();
+  if (foo(35) != 0)
+    __builtin_abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_ctz|\\.CTZ" 1 "optimized" } } */
diff --git a/gcc/tree-ssa-loop-niter.cc b/gcc/tree-ssa-loop-niter.cc
index c1ca20c2926..26e39ad3a51 100644
--- a/gcc/tree-ssa-loop-niter.cc
+++ b/gcc/tree-ssa-loop-niter.cc
@@ -2304,6 +2304,167 @@ build_cltz_expr (tree src, bool leading, bool define_at_zero)
   return call;
 }
 
+/* See comment below for number_of_iterations_bitcount.
+   For c[lt]z, we have:
+
+   modify:
+   iv_2 = iv_1 << 1 OR iv_1 >> 1
+
+   test:
+   if (iv & 1 << (prec-1)) OR (iv & 1)
+
+   modification count:
+   src precision - c[lt]z (src)
+
+ */
+
+static bool
+number_of_iterations_cltz (loop_p loop, edge exit,
+			       enum tree_code code,
+			       class tree_niter_desc *niter)
+{
+  bool modify_before_test = true;
+  HOST_WIDE_INT max;
+  int checked_bit;
+  tree iv_2;
+
+  /* Check that condition for staying inside the loop is like
+     if (iv == 0).  */
+  gimple *cond_stmt = last_stmt (exit->src);
+  if (!cond_stmt
+      || gimple_code (cond_stmt) != GIMPLE_COND
+      || (code != EQ_EXPR && code != GE_EXPR)
+      || !integer_zerop (gimple_cond_rhs (cond_stmt))
+      || TREE_CODE (gimple_cond_lhs (cond_stmt)) != SSA_NAME)
+    return false;
+
+  if (code == EQ_EXPR)
+    {
+      /* Make sure we check a bitwise and with a suitable constant */
+      gimple *and_stmt = SSA_NAME_DEF_STMT (gimple_cond_lhs (cond_stmt));
+      if (!is_gimple_assign (and_stmt)
+	  || gimple_assign_rhs_code (and_stmt) != BIT_AND_EXPR
+	  || !integer_pow2p (gimple_assign_rhs2 (and_stmt)))
+	return false;
+
+      checked_bit = tree_log2 (gimple_assign_rhs2 (and_stmt));
+
+      iv_2 = gimple_assign_rhs1 (and_stmt);
+    }
+  else
+    {
+      /* We have a GE_EXPR - a signed comparison with zero is equivalent to
+	 testing the leading bit, so check for this pattern too.  */
+
+      iv_2 = gimple_cond_lhs (cond_stmt);
+      tree test_value_type = TREE_TYPE (iv_2);
+
+      if (TYPE_UNSIGNED (test_value_type))
+	return false;
+
+      gimple *test_value_stmt = SSA_NAME_DEF_STMT (iv_2);
+
+      if (is_gimple_assign (test_value_stmt)
+	  && gimple_assign_rhs_code (test_value_stmt) == NOP_EXPR)
+	{
+	  /* If the test value comes from a NOP_EXPR, then we need to unwrap
+	     this.  We conservatively require that both types have the same
+	     precision.  */
+	  iv_2 = gimple_assign_rhs1 (test_value_stmt);
+	  tree rhs_type = TREE_TYPE (iv_2);
+	  if (TREE_CODE (rhs_type) != INTEGER_TYPE
+	      || (TYPE_PRECISION (rhs_type)
+		  != TYPE_PRECISION (test_value_type)))
+	    return false;
+	}
+
+      checked_bit = TYPE_PRECISION (test_value_type) - 1;
+    }
+
+  gimple *iv_2_stmt = SSA_NAME_DEF_STMT (iv_2);
+
+  /* If the test comes before the iv modification, then these will actually be
+     iv_1 and a phi node.  */
+  if (gimple_code (iv_2_stmt) == GIMPLE_PHI
+      && gimple_bb (iv_2_stmt) == loop->header
+      && gimple_phi_num_args (iv_2_stmt) == 2
+      && (TREE_CODE (gimple_phi_arg_def (iv_2_stmt,
+					 loop_latch_edge (loop)->dest_idx))
+	  == SSA_NAME))
+    {
+      /* iv_2 is actually one of the inputs to the phi.  */
+      iv_2 = gimple_phi_arg_def (iv_2_stmt, loop_latch_edge (loop)->dest_idx);
+      iv_2_stmt = SSA_NAME_DEF_STMT (iv_2);
+      modify_before_test = false;
+    }
+
+  /* Make sure iv_2_stmt is a logical shift by one stmt:
+     iv_2 = iv_1 {<<|>>} 1  */
+  if (!is_gimple_assign (iv_2_stmt)
+      || (gimple_assign_rhs_code (iv_2_stmt) != LSHIFT_EXPR
+	  && (gimple_assign_rhs_code (iv_2_stmt) != RSHIFT_EXPR
+	      || !TYPE_UNSIGNED (TREE_TYPE (gimple_assign_lhs (iv_2_stmt)))))
+      || !integer_onep (gimple_assign_rhs2 (iv_2_stmt)))
+    return false;
+
+  bool left_shift = (gimple_assign_rhs_code (iv_2_stmt) == LSHIFT_EXPR);
+
+  tree iv_1 = gimple_assign_rhs1 (iv_2_stmt);
+
+  /* Check the recurrence.  */
+  gimple *phi = SSA_NAME_DEF_STMT (iv_1);
+  if (gimple_code (phi) != GIMPLE_PHI
+      || (gimple_bb (phi) != loop_latch_edge (loop)->dest)
+      || (iv_2 != gimple_phi_arg_def (phi, loop_latch_edge (loop)->dest_idx)))
+    return false;
+
+  /* We found a match.  */
+  tree src = gimple_phi_arg_def (phi, loop_preheader_edge (loop)->dest_idx);
+  int src_precision = TYPE_PRECISION (TREE_TYPE (src));
+
+  /* Apply any needed preprocessing to src.  */
+  int num_ignored_bits;
+  if (left_shift)
+    num_ignored_bits = src_precision - checked_bit - 1;
+  else
+    num_ignored_bits = checked_bit;
+
+  if (modify_before_test)
+    num_ignored_bits++;
+
+  if (num_ignored_bits != 0)
+    src = fold_build2 (left_shift ? LSHIFT_EXPR : RSHIFT_EXPR,
+		       TREE_TYPE (src), src,
+		       build_int_cst (integer_type_node, num_ignored_bits));
+
+  /* Get the corresponding c[lt]z builtin.  */
+  tree expr = build_cltz_expr (src, left_shift, false);
+
+  if (!expr)
+    return false;
+
+  max = src_precision - num_ignored_bits - 1;
+
+  expr = fold_convert (unsigned_type_node, expr);
+
+  tree assumptions = fold_build2 (NE_EXPR, boolean_type_node, src,
+				  build_zero_cst (TREE_TYPE (src)));
+
+  niter->assumptions = simplify_using_initial_conditions (loop, assumptions);
+  niter->may_be_zero = boolean_false_node;
+  niter->niter = simplify_using_initial_conditions (loop, expr);
+
+  if (TREE_CODE (niter->niter) == INTEGER_CST)
+    niter->max = tree_to_uhwi (niter->niter);
+  else
+    niter->max = max;
+
+  niter->bound = NULL_TREE;
+  niter->cmp = ERROR_MARK;
+
+  return true;
+}
+
 /* See comment below for number_of_iterations_bitcount.
    For c[lt]z complement, we have:
 
@@ -2464,6 +2625,7 @@ number_of_iterations_bitcount (loop_p loop, edge exit,
 			       class tree_niter_desc *niter)
 {
   return (number_of_iterations_popcount (loop, exit, code, niter)
+	  || number_of_iterations_cltz (loop, exit, code, niter)
 	  || number_of_iterations_cltz_complement (loop, exit, code, niter));
 }
 
@@ -2992,6 +3154,9 @@ number_of_iterations_exit_assumptions (class loop *loop, edge exit,
     case NE_EXPR:
       break;
 
+    case EQ_EXPR:
+      return number_of_iterations_cltz (loop, exit, code, niter);
+
     default:
       return false;
     }