> For -fwrapv I don't see why you'd get into trouble ever, the VRP computation
> should be well aware of the -fwrapv semantics and the value ranges should
> reflect that.
>
> For -fno-strict-overflow, I have no idea since it is very weirdly defined.
>
> In any case, for your example above, the loop is always well defined,
> because for char/short a++ is performed as:
> a = (short) ((int) a + 1)
> So, if the patch turns it into infinite loop, with -Os -fno-strict-overflow
> or -Os, it is simply a problem with the patch. VR [1, 32768] looks correct,
> a++ is performed only if a is >= 0, therefore before addition [0, 32767].
> But from VR [1, 32768] you can't optimize away the sign extension, make sure
> you don't have there off-by-one?
>
> It would be nice if the patch contained some testcases, it is easy
> to construct testcases where you have arbitrary VRs on some SSA_NAMEs,
> you just need something to stick the VR on, so you can do something like:
> type foo (type a)
> {
> if (a < VR_min + 1 || a > VR_max + 1) return; // If VR_min is type minimum
> or VR_max type maximum this needs to be adjusted of course.
> a = a + 1;
> // now you can try some cast that your optimization would try to optimize
> return a;
> }
> Or void bar (type a) { a = (a & mask) + bias; (or similarly) }
> Make sure to cover the boundary cases, where VR minimum or maximum still
> allow optimizing away zero and/or sign extensions, and another case where
> they are +- 1 and already don't allow it.
Hi Jakub,
For -fwrapv, it is due to how PROMOTE_MODE is defined in arm back-end.
In the test-case, a function (which has signed char return type) returns
-1 in one of the paths. ARM PROMOTE_MODE changes that to 255 and relies
on zero/sign extension generated by RTL again for the correct value. I
saw some other targets also defining similar think. I am therefore
skipping removing zero/sign extension if the ssa variable can be set to
negative integer constants.
As for the -fno-strict-overflow case, if the variables overflows, in VRP
dumps, I see +INF(OVF), but the value range stored in ssa has TYPE_MAX.
We therefore should limit the comparison to (TYPE_MIN < VR_MIN && VR_MAX
< TYPE_MAX) instead of (TYPE_MIN <= VR_MIN && VR_MAX <= TYPE_MAX) when
checking to be sure that this is not the overflowing case. Attached
patch changes this.
I have bootstrapped on x86_64-unknown-linux-gnu and regression tested
for x86_64-unknown-linux-gnu, arm-none-linux-gnueabi (using qemu),
aarch64_be-none-elf (Foundation model), aarch64-none-elf
--with-abi=ilp32 (Foundation model) and s390x-ibm-linux (64bit, using
qemu) with no new regression.
Is this OK?
Thanks,
Kugan
gcc/
2014-07-07 Kugan Vivekanandarajah <[email protected]>
* calls.c (precompute_arguments): Check is_promoted_for_type
and set the promoted mode.
(is_promoted_for_type): New function.
(expand_expr_real_1): Check is_promoted_for_type
and set the promoted mode.
* expr.h (is_promoted_for_type): New function definition.
* cfgexpand.c (expand_gimple_stmt_1): Call emit_move_insn if
SUBREG is promoted with SRP_SIGNED_AND_UNSIGNED.
gcc/testsuite
2014-07-07 Kugan Vivekanandarajah <[email protected]>
* gcc.dg/zero_sign_ext_test.c: New test.
diff --git a/gcc/calls.c b/gcc/calls.c
index a3e6faa..eac512f 100644
--- a/gcc/calls.c
+++ b/gcc/calls.c
@@ -1484,7 +1484,10 @@ precompute_arguments (int num_actuals, struct arg_data
*args)
args[i].initial_value
= gen_lowpart_SUBREG (mode, args[i].value);
SUBREG_PROMOTED_VAR_P (args[i].initial_value) = 1;
- SUBREG_PROMOTED_SET (args[i].initial_value, args[i].unsignedp);
+ if (is_promoted_for_type (args[i].tree_value, mode,
!args[i].unsignedp))
+ SUBREG_PROMOTED_SET (args[i].initial_value,
SRP_SIGNED_AND_UNSIGNED);
+ else
+ SUBREG_PROMOTED_SET (args[i].initial_value, args[i].unsignedp);
}
}
}
diff --git a/gcc/cfgexpand.c b/gcc/cfgexpand.c
index b7a34a2..ac6776d 100644
--- a/gcc/cfgexpand.c
+++ b/gcc/cfgexpand.c
@@ -3309,7 +3309,13 @@ expand_gimple_stmt_1 (gimple stmt)
GET_MODE (target), temp, unsignedp);
}
- convert_move (SUBREG_REG (target), temp, unsignedp);
+ if ((SUBREG_PROMOTED_GET (target) == SRP_SIGNED_AND_UNSIGNED)
+ && (GET_CODE (temp) == SUBREG)
+ && (GET_MODE (target) == GET_MODE (temp))
+ && (GET_MODE (SUBREG_REG (target)) == GET_MODE (SUBREG_REG
(temp))))
+ emit_move_insn (SUBREG_REG (target), SUBREG_REG (temp));
+ else
+ convert_move (SUBREG_REG (target), temp, unsignedp);
}
else if (nontemporal && emit_storent_insn (target, temp))
;
diff --git a/gcc/expr.c b/gcc/expr.c
index 10f4a96..68708c1 100644
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -68,6 +68,7 @@ along with GCC; see the file COPYING3. If not see
#include "tree-ssa-address.h"
#include "cfgexpand.h"
#include "builtins.h"
+#include "tree-ssa.h"
#ifndef STACK_PUSH_CODE
#ifdef STACK_GROWS_DOWNWARD
@@ -9210,6 +9211,88 @@ expand_expr_real_2 (sepops ops, rtx target, enum
machine_mode tmode,
}
#undef REDUCE_BIT_FIELD
+/* Return TRUE if value in SSA is already zero/sign extended for lhs type
+ (type here is the combination of LHS_MODE and LHS_UNS) using value range
+ information stored. Return FALSE otherwise. */
+bool
+is_promoted_for_type (tree ssa, enum machine_mode lhs_mode, bool lhs_uns)
+{
+ wide_int type_min, type_max;
+ wide_int min, max, limit;
+ unsigned int prec;
+ tree lhs_type;
+ bool rhs_uns;
+ gimple stmt;
+
+ if (ssa == NULL_TREE
+ || TREE_CODE (ssa) != SSA_NAME
+ || !INTEGRAL_TYPE_P (TREE_TYPE (ssa)))
+ return false;
+
+ /* Return FALSE if value_range is not recorded for SSA. */
+ if (get_range_info (ssa, &min, &max) != VR_RANGE)
+ return false;
+ stmt = SSA_NAME_DEF_STMT (ssa);
+
+ /* In some architectures, negative integer constants are truncated and
+ sign changed with target defined PROMOTE_MODE macro. This will impact
+ the value range seen here and produce wrong code if zero/sign extensions
+ are eliminated. Therefore, return false if this SSA can have negative
+ integers. */
+ if (is_gimple_assign (stmt)
+ && (TREE_CODE_CLASS (gimple_assign_rhs_code (stmt)) == tcc_unary))
+ {
+ tree rhs1 = gimple_assign_rhs1 (stmt);
+ if (TREE_CODE (rhs1) == INTEGER_CST
+ && !TYPE_UNSIGNED (TREE_TYPE (ssa))
+ && tree_int_cst_compare (rhs1, integer_zero_node) == -1)
+ return false;
+ }
+ else if (gimple_code (stmt) == GIMPLE_PHI)
+ {
+ unsigned int i;
+ for (i = 0; i < gimple_phi_num_args (stmt); ++i)
+ {
+ tree arg = gimple_phi_arg_def (stmt, i);
+ if (TREE_CODE (arg) == INTEGER_CST
+ && !TYPE_UNSIGNED (TREE_TYPE (ssa))
+ && tree_int_cst_compare (arg, integer_zero_node) == -1)
+ return false;
+ }
+ }
+
+ lhs_type = lang_hooks.types.type_for_mode (lhs_mode, lhs_uns);
+ rhs_uns = TYPE_UNSIGNED (TREE_TYPE (ssa));
+ prec = min.get_precision ();
+
+ /* Signed maximum value. */
+ limit = wide_int::from (TYPE_MAX_VALUE (TREE_TYPE (ssa)), prec, SIGNED);
+
+ /* Signedness of LHS and RHS differs but values in range. */
+ if ((rhs_uns != lhs_uns)
+ && ((!lhs_uns && !wi::neg_p (min, TYPE_SIGN (lhs_type)))
+ || (lhs_uns && (wi::cmp (max, limit, TYPE_SIGN (TREE_TYPE (ssa))) ==
-1))))
+ lhs_uns = !lhs_uns;
+
+ /* Signedness of LHS and RHS should match. */
+ if (rhs_uns != lhs_uns)
+ return false;
+
+ type_min = wide_int::from (TYPE_MIN_VALUE (lhs_type), prec,
+ TYPE_SIGN (TREE_TYPE (ssa)));
+ type_max = wide_int::from (TYPE_MAX_VALUE (lhs_type), prec,
+ TYPE_SIGN (TREE_TYPE (ssa)));
+
+ /* Check if values lies in-between the type range. */
+ if ((wi::neg_p (max, TYPE_SIGN (TREE_TYPE (ssa)))
+ || (wi::cmp (max, type_max, TYPE_SIGN (TREE_TYPE (ssa))) == -1))
+ && (!wi::neg_p (min, TYPE_SIGN (TREE_TYPE (ssa)))
+ || (wi::cmp (min, 0, TYPE_SIGN (TREE_TYPE (ssa))) == 0)
+ || (wi::cmp (type_min, min, TYPE_SIGN (TREE_TYPE (ssa))) == -1)))
+ return true;
+
+ return false;
+}
/* Return TRUE if expression STMT is suitable for replacement.
Never consider memory loads as replaceable, because those don't ever lead
@@ -9513,7 +9596,10 @@ expand_expr_real_1 (tree exp, rtx target, enum
machine_mode tmode,
temp = gen_lowpart_SUBREG (mode, decl_rtl);
SUBREG_PROMOTED_VAR_P (temp) = 1;
- SUBREG_PROMOTED_SET (temp, unsignedp);
+ if (is_promoted_for_type (ssa_name, mode, !unsignedp))
+ SUBREG_PROMOTED_SET (temp, SRP_SIGNED_AND_UNSIGNED);
+ else
+ SUBREG_PROMOTED_SET (temp, unsignedp);
return temp;
}
diff --git a/gcc/expr.h b/gcc/expr.h
index 6a1d3ab..e99d000 100644
--- a/gcc/expr.h
+++ b/gcc/expr.h
@@ -440,6 +440,7 @@ extern rtx expand_expr_real_1 (tree, rtx, enum machine_mode,
enum expand_modifier, rtx *, bool);
extern rtx expand_expr_real_2 (sepops, rtx, enum machine_mode,
enum expand_modifier);
+extern bool is_promoted_for_type (tree, enum machine_mode, bool);
/* Generate code for computing expression EXP.
An rtx for the computed value is returned. The value is never null.
diff --git a/gcc/testsuite/gcc.dg/zero_sign_ext_test.c
b/gcc/testsuite/gcc.dg/zero_sign_ext_test.c
index e69de29..ef37612 100644
--- a/gcc/testsuite/gcc.dg/zero_sign_ext_test.c
+++ b/gcc/testsuite/gcc.dg/zero_sign_ext_test.c
@@ -0,0 +1,135 @@
+extern void abort (void);
+
+/* { dg-options "-O2" } */
+/* { dg-do run } */
+
+#define TYPE_MAX(type, sign) \
+ ((!sign) ? ((1 << (sizeof (type) * 8 - 1)) - 1) : \
+ ((1 << (sizeof (type) * 8)) - 1))
+#define TYPE_MIN(type, sign) \
+ ((!sign) ? -(1 << (sizeof (type) * 8 - 1)) : 0)
+
+#define TEST_FN(NAME, ARG_TYPE, RET_TYPE, CAST_TYPE, VAL, VR_MIN,
VR_MAX)\
+ __attribute__((noinline, noclone)) RET_TYPE \
+ NAME (ARG_TYPE arg){ \
+ RET_TYPE ret = VAL; \
+ if (arg + 1 < VR_MIN || arg + 1 > VR_MAX) return ret; \
+ /* Value Range of arg at this point will be [VR_min, VR_max]. */\
+ arg = arg + VAL; \
+ ret = (CAST_TYPE)arg; \
+ return arg; \
+ }
+
+/* Signed to signed conversion with value in-range. */
+TEST_FN (foo1, short, short, char, 1, TYPE_MIN (char, 0), TYPE_MAX (char, 0));
+TEST_FN (foo2, short, short, char, 1, TYPE_MIN (char, 0) + 1,\
+ TYPE_MAX (char, 0) - 1);
+
+/* Signed to signed conversion with value not in-range. */
+TEST_FN (foo3, short, short, char, -1, TYPE_MIN (short, 0) + 1, 100);
+TEST_FN (foo4, short, short, char, 1, 12, TYPE_MAX (short, 0) + 1);
+
+/* Unsigned to unsigned conversion with value in-range. */
+TEST_FN (foo5, unsigned short, unsigned short, unsigned char, 1,\
+ TYPE_MIN (char, 1) + 1, TYPE_MAX (char, 1) - 1);
+TEST_FN (foo6, unsigned short, unsigned short, unsigned char, 1,\
+ TYPE_MIN (char, 1), TYPE_MAX (char, 1));
+
+/* Unsigned to unsigned conversion with value not in-range. */
+TEST_FN (foo7, unsigned short, unsigned short, unsigned char, 1,\
+ TYPE_MIN (short, 1) + 1, TYPE_MAX (short, 1) - 1);
+TEST_FN (foo8, unsigned short, unsigned short, unsigned char, 1,\
+ TYPE_MIN (short, 1), TYPE_MAX (short, 1));
+
+/* Signed to unsigned conversion with value range positive. */
+TEST_FN (foo9, short, short, unsigned char, -1, 1,\
+ TYPE_MAX (char, 1) - 1);
+TEST_FN (foo10, short, short, unsigned char, 1, 0,\
+ TYPE_MAX (char, 1));
+
+/* Signed to unsigned conversion with value range negative. */
+TEST_FN (foo11, short, short, unsigned char, 1,\
+ TYPE_MIN (char, 0) + 1, TYPE_MAX (char, 0) - 1);
+TEST_FN (foo12, short, short, unsigned char, 1,\
+ TYPE_MIN (char, 0), TYPE_MAX (char, 0));
+
+/* Unsigned to Signed conversion with value range in signed equiv range */
+TEST_FN (foo13, unsigned short, unsigned short, char, 1,\
+ TYPE_MIN (char, 1) + 1, TYPE_MAX (char, 0) - 1);
+TEST_FN (foo14, unsigned short, unsigned short, char, 1,\
+ TYPE_MIN (char, 1), TYPE_MAX (char, 0));
+
+/* Unsigned to Signed conversion with value range not-in signed range */
+TEST_FN (foo15, unsigned short, unsigned short, char, 1,\
+ TYPE_MIN (char, 1) + 1, TYPE_MAX (char, 1) - 1);
+TEST_FN (foo16, unsigned short, unsigned short, char, 1,\
+ TYPE_MIN (char, 1), TYPE_MAX (char, 1));
+
+int main ()
+{
+ /* Signed to signed conversion with value in-range. */
+ /* arg + 1 */
+ if (foo1 (-32) != -31)
+ abort ();
+ /* arg + 1 */
+ if (foo2 (32) != 33)
+ abort ();
+
+ /* Signed to signed conversion with value not in-range. */
+ /* arg - 1 */
+ if (foo3 (-512) != -513)
+ abort ();
+ /* arg + 1 */
+ if (foo4 (512) != 513)
+ abort ();
+
+ /* Unsigned to unsigned conversion with value in-range. */
+ /* arg + 1 */
+ if (foo5 (64) != 65)
+ abort ();
+ /* arg + 1 */
+ if (foo6 (64) != 65)
+ abort ();
+
+ /* Unigned to unsigned conversion with value not in-range. */
+ /* arg + 1 */
+ if (foo7 (512) != 513)
+ abort ();
+ /* arg + 1 */
+ if (foo8 (512) != 513)
+ abort ();
+
+ /* Signed to unsigned conversion with value range positive. */
+ /* arg - 1 */
+ if (foo9 (2) != 1)
+ abort ();
+ /* arg + 1 */
+ if (foo10 (2) != 3)
+ abort ();
+
+ /* Signed to unsigned conversion with value range negative. */
+ /* arg + 1 */
+ if (foo11 (-125) != -124)
+ abort ();
+ /* arg + 1 */
+ if (foo12 (-125) != -124)
+ abort ();
+
+ /* Unsigned to Signed conversion with value range in signed equiv range */
+ /* arg + 1 */
+ if (foo13 (125) != 126)
+ abort ();
+ /* arg + 1 */
+ if (foo14 (125) != 126)
+ abort ();
+
+ /* Unsigned to Signed conversion with value range not-in signed range */
+ /* arg + 1 */
+ if (foo15 (250) != 251)
+ abort ();
+ /* arg + 1 */
+ if (foo16 (250) != 251)
+ abort ();
+
+ return 0;
+}
