The patch extends the CDCE shrink-wrapping support added for PR102202.
The existing transform handles memset calls whose length is known to be
in [0, 1]. It bypasses the call for length zero and specializes the
nonzero path to a constant length of one.
Extend this to exact two-value length ranges {0, N}, where N is a
nonzero integer constant. The zero-length path is still bypassed and
the nonzero path is specialized to the constant N. In particular, the
transform does not accept an ordinary interval [0, N] since such an
interval can contain values other than zero and N.
The range query now returns the nonzero member of either a [0, 1] range
or an exact {0, N} range. The existing [0, 1] behavior is preserved.
gcc/ChangeLog:
PR tree-optimization/102202
* tree-call-cdce.cc: Include "value-query.h" and "value-range.h".
(len_has_boolean_range_p): Remove.
(get_len_nonzero_value): New function. Return the nonzero member of
LEN's value range when it is a boolean range [0, 1] or an exact
two-value set {0, N}.
(can_shrink_wrap_len_p): Replace len_has_boolean_range_p call with
get_len_nonzero_value. Add NONZERO_LEN output parameter and set it
to the returned nonzero value on success.
(shrink_wrap_len_call): Use it to pin the length argument on the
guarded call path instead of build_one_cst.
(shrink_wrap_conditional_dead_built_in_calls): Declare local
nonzero_len and pass it to can_shrink_wrap_len_p and forward it to
shrink_wrap_len_call.
(pass_call_cdce::execute): Pass nullptr as NONZERO_LEN to
can_shrink_wrap_len_p.
gcc/testsuite/ChangeLog:
PR tree-optimization/102202
* gcc.dg/pr102202-3.c: New test.
* gcc.dg/pr102202-4.c: New test.
Signed-off-by: Naveen <[email protected]>
---
gcc/testsuite/gcc.dg/pr102202-3.c | 21 +++++++++
gcc/testsuite/gcc.dg/pr102202-4.c | 16 +++++++
gcc/tree-call-cdce.cc | 74 ++++++++++++++++++++++---------
3 files changed, 91 insertions(+), 20 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/pr102202-3.c
create mode 100644 gcc/testsuite/gcc.dg/pr102202-4.c
diff --git a/gcc/testsuite/gcc.dg/pr102202-3.c
b/gcc/testsuite/gcc.dg/pr102202-3.c
new file mode 100644
index 00000000000..1904e309fee
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr102202-3.c
@@ -0,0 +1,21 @@
+/* PR tree-optimization/102202 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-cdce-details" } */
+
+/* An exact two-value range {0, 2}. Use a PHI so that Ranger retains
+ the two singleton values at the call. */
+
+void
+g1 (unsigned int x, int c, char *d)
+{
+ __SIZE_TYPE__ len;
+
+ if (x)
+ len = 2;
+ else
+ len = 0;
+
+ __builtin_memset (d, c, len);
+}
+
+/* { dg-final { scan-tree-dump-times "function call is shrink-wrapped into
error conditions" 1 "cdce" } } */
diff --git a/gcc/testsuite/gcc.dg/pr102202-4.c
b/gcc/testsuite/gcc.dg/pr102202-4.c
new file mode 100644
index 00000000000..908256b5b2d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr102202-4.c
@@ -0,0 +1,16 @@
+/* PR tree-optimization/102202 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-cdce-details" } */
+
+/* The interval [0, 2] is not the exact two-value set {0, 2}. */
+
+void
+g1 (__SIZE_TYPE__ len, int c, char *d)
+{
+ if (len > 2)
+ __builtin_unreachable ();
+
+ __builtin_memset (d, c, len);
+}
+
+/* { dg-final { scan-tree-dump-not "function call is shrink-wrapped into error
conditions" "cdce" } } */
diff --git a/gcc/tree-call-cdce.cc b/gcc/tree-call-cdce.cc
index 144f485909c..0ec88346d25 100644
--- a/gcc/tree-call-cdce.cc
+++ b/gcc/tree-call-cdce.cc
@@ -39,6 +39,8 @@ along with GCC; see the file COPYING3. If not see
#include "tree-eh.h"
#include "tree-ssanames.h"
#include "gimple-fold.h"
+#include "value-query.h"
+#include "value-range.h"
/* This pass serves two closely-related purposes:
@@ -1257,23 +1259,49 @@ use_internal_fn (gcall *call)
is_arg_conds ? new_call : NULL);
}
-/* Return true if LEN is an SSA_NAME known to have a boolean range, i.e. its
- value is provably in [0, 1]. */
+/* Return the nonzero member of LEN's range if LEN is an SSA name with range
+ [0, 1] or the exact two-value set {0, N}. Return NULL_TREE otherwise. */
-static bool
-len_has_boolean_range_p (tree len, gimple *stmt)
+static tree
+get_len_nonzero_value (tree len, gimple *stmt)
{
if (TREE_CODE (len) != SSA_NAME || !INTEGRAL_TYPE_P (TREE_TYPE (len)))
- return false;
- return ssa_name_has_boolean_range (len, stmt);
+ return NULL_TREE;
+
+ if (ssa_name_has_boolean_range (len, stmt))
+ return build_one_cst (TREE_TYPE (len));
+
+ int_range<2> range (TREE_TYPE (len));
+ if (!get_range_query (cfun)->range_of_expr (range, len, stmt)
+ || range.num_pairs () != 2)
+ return NULL_TREE;
+
+ wide_int zero = wi::zero (TYPE_PRECISION (TREE_TYPE (len)));
+ for (unsigned i = 0; i != 2; ++i)
+ {
+ if (!wi::eq_p (range.lower_bound (i), zero)
+ || !wi::eq_p (range.upper_bound (i), zero))
+ continue;
+
+ unsigned nonzero_pair = i ^ 1;
+ wide_int nonzero = range.lower_bound (nonzero_pair);
+ if (wi::eq_p (nonzero, zero)
+ || !wi::eq_p (nonzero, range.upper_bound (nonzero_pair)))
+ return NULL_TREE;
+
+ return wide_int_to_tree (TREE_TYPE (len), nonzero);
+ }
+
+ return NULL_TREE;
}
/* Return true if CALL is a supported length-taking builtin whose length
- argument is an SSA name known to have a boolean range. On success,
- set LEN_ARG to the argument index of the length. */
+ argument is an SSA name known to have a suitable range. On success,
+ set LEN_ARG to the argument index of the length and, if NONZERO_LEN is
+ nonnull, set it to the nonzero member of the range. */
static bool
-can_shrink_wrap_len_p (gcall *call, unsigned *len_arg)
+can_shrink_wrap_len_p (gcall *call, unsigned *len_arg, tree *nonzero_len)
{
if (!gimple_call_builtin_p (call, BUILT_IN_MEMSET)
|| !gimple_vdef (call))
@@ -1284,10 +1312,13 @@ can_shrink_wrap_len_p (gcall *call, unsigned *len_arg)
return false;
tree len = gimple_call_arg (call, memset_len_arg);
- if (!len_has_boolean_range_p (len, call))
+ tree value = get_len_nonzero_value (len, call);
+ if (!value)
return false;
*len_arg = memset_len_arg;
+ if (nonzero_len)
+ *nonzero_len = value;
return true;
}
@@ -1305,13 +1336,14 @@ gen_zero_len_conditions (tree len, vec<gimple *>
&conds, unsigned *nconds)
*nconds = 1;
}
-/* Shrink-wrap CALL whose LEN_ARG argument is known to be in [0, 1].
- ZERO_LEN_RESULT is the value of the call result when its length is zero.
- On the guarded path the length is one, so pin it to a constant for
- subsequent folding. */
+/* Shrink-wrap CALL whose LEN_ARG argument is known to be in [0, 1] or
+ {0, N}. ZERO_LEN_RESULT is the value of the call result when its length
+ is zero. On the guarded path the length is NONZERO_LEN, so pin it to that
+ constant for subsequent folding. */
static void
-shrink_wrap_len_call (gcall *call, unsigned len_arg, tree zero_len_result)
+shrink_wrap_len_call (gcall *call, unsigned len_arg, tree zero_len_result,
+ tree nonzero_len)
{
tree lhs = gimple_call_lhs (call);
@@ -1341,8 +1373,8 @@ shrink_wrap_len_call (gcall *call, unsigned len_arg, tree
zero_len_result)
shrink_wrap_one_built_in_call_with_conds (call, conds, nconds);
- /* On the guarded path the length is one. */
- gimple_call_set_arg (call, len_arg, build_one_cst (TREE_TYPE (len)));
+ /* On the guarded path the length is NONZERO_LEN. */
+ gimple_call_set_arg (call, len_arg, nonzero_len);
update_stmt (call);
gimple_stmt_iterator gsi = gsi_for_stmt (call);
fold_stmt (&gsi);
@@ -1363,8 +1395,10 @@ shrink_wrap_conditional_dead_built_in_calls (const
vec<gcall *> &calls)
unsigned len_arg;
/* memset returns its destination pointer on the zero-length path. */
- if (can_shrink_wrap_len_p (bi_call, &len_arg))
- shrink_wrap_len_call (bi_call, len_arg, gimple_call_arg (bi_call, 0));
+ tree nonzero_len;
+ if (can_shrink_wrap_len_p (bi_call, &len_arg, &nonzero_len))
+ shrink_wrap_len_call (bi_call, len_arg, gimple_call_arg (bi_call, 0),
+ nonzero_len);
else if (gimple_call_lhs (bi_call))
use_internal_fn (bi_call);
else
@@ -1427,7 +1461,7 @@ pass_call_cdce::execute (function *fun)
unsigned len_arg;
if (stmt
&& gimple_call_builtin_p (stmt, BUILT_IN_NORMAL)
- && (can_shrink_wrap_len_p (stmt, &len_arg)
+ && (can_shrink_wrap_len_p (stmt, &len_arg, nullptr)
|| (gimple_call_lhs (stmt)
? can_use_internal_fn (stmt)
: can_test_argument_range (stmt)))
--
2.34.1
