is_rshift_by_1 previously checked TYPE_UNSIGNED on the shift statement,
preventing signed arithmetic right shifts from being optimized into CLZ
calls. However, an arithmetic right shift behaves identically to a logical
right shift when the initial operand entering the loop is non-negative.
This patch removes the strict TYPE_UNSIGNED requirement from is_rshift_by_1
and adds ranger range_on_edge non-negativity checks in number_of_iterations_cltz
and number_of_iterations_cltz_complement on the loop preheader edge.
PR tree-optimization/125734
gcc/ChangeLog:
* tree-ssa-loop-niter.cc (is_rshift_by_1): Remove TYPE_UNSIGNED
restriction.
(number_of_iterations_cltz): Use range_on_edge to check non-negativity
of
signed preheader input.
(number_of_iterations_cltz_complement): Likewise.
gcc/testsuite/ChangeLog:
* gcc.dg/tree-ssa/pr125734.c: New test.
Regression tested on arch64-unknown-linux-gnu.
Signed-off-by: Shivam Gupta <[email protected]>
---
gcc/testsuite/gcc.dg/tree-ssa/pr125734.c | 32 ++++++++++++++++++++++++
gcc/tree-ssa-loop-niter.cc | 26 +++++++++++++++++--
2 files changed, 56 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr125734.c
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr125734.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr125734.c
new file mode 100644
index 000000000..f8d76c459
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr125734.c
@@ -0,0 +1,32 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+int
+nlz32 (int b)
+{
+ int c = sizeof(b) * 8;
+ if (b < 0)
+ return -1;
+ while (b != 0)
+ {
+ b >>= 1;
+ c--;
+ }
+ return c;
+}
+
+int
+nlz32_negative (int b)
+{
+ int c = sizeof(b) * 8;
+
+ while (b != 0)
+ {
+ b >>= 1;
+ c--;
+ }
+
+ return c;
+}
+
+/* { dg-final { scan-tree-dump-times "\\.CLZ" 1 "optimized" } } */
diff --git a/gcc/tree-ssa-loop-niter.cc b/gcc/tree-ssa-loop-niter.cc
index 0c1ebd1c7..3ce3dccfa 100644
--- a/gcc/tree-ssa-loop-niter.cc
+++ b/gcc/tree-ssa-loop-niter.cc
@@ -2313,8 +2313,6 @@ is_lshift_by_1 (gassign *stmt)
static bool
is_rshift_by_1 (gassign *stmt)
{
- if (!TYPE_UNSIGNED (TREE_TYPE (gimple_assign_lhs (stmt))))
- return false;
if (gimple_assign_rhs_code (stmt) == RSHIFT_EXPR
&& integer_onep (gimple_assign_rhs2 (stmt)))
return true;
@@ -2482,6 +2480,18 @@ number_of_iterations_cltz (loop_p loop, edge exit,
/* We found a match. */
tree src = gimple_phi_arg_def (phi, loop_preheader_edge (loop)->dest_idx);
+
+ /* If the type is signed, verify via Ranger on the preheader edge
+ that the initial value entering the loop is non-negative. */
+ if (!TYPE_UNSIGNED (TREE_TYPE (src)))
+ {
+ int_range_max r (TREE_TYPE (src));
+ edge e = loop_preheader_edge (loop);
+ if (!get_range_query (cfun)->range_on_edge (r, e, src)
+ || !r.nonnegative_p ())
+ return false;
+ }
+
int src_precision = TYPE_PRECISION (TREE_TYPE (src));
/* Save the original SSA name before preprocessing for ranger queries. */
@@ -2641,6 +2651,18 @@ number_of_iterations_cltz_complement (loop_p loop, edge
exit,
/* We found a match. */
tree src = gimple_phi_arg_def (phi, loop_preheader_edge (loop)->dest_idx);
+
+ /* If the type is signed, verify via Ranger on the preheader edge
+ that the initial value entering the loop is non-negative. */
+ if (!TYPE_UNSIGNED (TREE_TYPE (src)))
+ {
+ int_range_max r (TREE_TYPE (src));
+ edge e = loop_preheader_edge (loop);
+ if (!get_range_query (cfun)->range_on_edge (r, e, src)
+ || !r.nonnegative_p ())
+ return false;
+ }
+
int src_precision = TYPE_PRECISION (TREE_TYPE (src));
/* Get the corresponding c[lt]z builtin. */
--
2.43.0
