This file is consumed by genmatch which produces gimple-match.cc
and generic-match.cc from it.
- Copyright (C) 2014-2023 Free Software Foundation, Inc.
+ Copyright (C) 2014-2024 Free Software Foundation, Inc.
Contributed by Richard Biener <rguenther@suse.de>
and Prathamesh Kulkarni <bilbotheelffriend@gmail.com>
TYPE_VECTOR_SUBPARTS (TREE_TYPE (@0)))
&& tree_nop_conversion_p (TREE_TYPE (type), TREE_TYPE (TREE_TYPE (@0))))))
-#if GIMPLE
/* These are used by gimple_bitwise_inverted_equal_p to simplify
detection of BIT_NOT and comparisons. */
(match (bit_not_with_nop @0)
(match (bit_not_with_nop @0)
(convert (bit_not @0))
(if (tree_nop_conversion_p (type, TREE_TYPE (@0)))))
+(match (bit_xor_cst @0 @1)
+ (bit_xor @0 uniform_integer_cst_p@1))
(for cmp (tcc_comparison)
(match (maybe_cmp @0)
(cmp@0 @1 @2))
(convert (cmp@0 @1 @2))
(if (tree_nop_conversion_p (type, TREE_TYPE (@0)))))
)
+/* `a ^ b` is another form of `a != b` when the type
+ is a 1bit precission integer. */
+(match (maybe_cmp @0)
+ (bit_xor@0 @1 @2)
+ (if (INTEGRAL_TYPE_P (type)
+ && TYPE_PRECISION (type) == 1)))
+/* maybe_bit_not is used to match what
+ is acceptable for bitwise_inverted_equal_p. */
+(match (maybe_bit_not @0)
+ (bit_not_with_nop@0 @1))
+(match (maybe_bit_not @0)
+ (INTEGER_CST@0))
+(match (maybe_bit_not @0)
+ (maybe_cmp@0 @1))
+(match (maybe_bit_not @0)
+ (bit_xor_cst@0 @1 @2))
+
+#if GIMPLE
+(match (maybe_truncate @0)
+ (convert @0)
+ (if (INTEGRAL_TYPE_P (type)
+ && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@0)))))
#endif
/* Transform likes of (char) ABS_EXPR <(int) x> into (char) ABSU_EXPR <x>
/* (x >= 0 ? x : 0) + (x <= 0 ? -x : 0) -> abs x. */
(simplify
- (plus:c (max @0 integer_zerop) (max (negate @0) integer_zerop))
- (abs @0))
+ (plus:c (max @0 integer_zerop) (max (negate @0) integer_zerop))
+ (if (ANY_INTEGRAL_TYPE_P (type) && TYPE_OVERFLOW_UNDEFINED (type))
+ (abs @0)))
/* X * 1, X / 1 -> X. */
(for op (mult trunc_div ceil_div floor_div round_div exact_div)
1 / X -> X >= -1 && X <= 1 ? X : 0 for signed integer X.
But not for 1 / 0 so that we can get proper warnings and errors,
and not for 1-bit integers as they are edge cases better handled
- elsewhere. */
+ elsewhere. Delay the conversion of the signed division until late
+ because `1 / X` is simplier to handle than the resulting COND_EXPR. */
(simplify
(trunc_div integer_onep@0 @1)
(if (INTEGRAL_TYPE_P (type)
&& (!flag_non_call_exceptions || tree_expr_nonzero_p (@1)))
(if (TYPE_UNSIGNED (type))
(convert (eq:boolean_type_node @1 { build_one_cst (type); }))
- (with { tree utype = unsigned_type_for (type); }
- (cond (le (plus (convert:utype @1) { build_one_cst (utype); })
- { build_int_cst (utype, 2); })
- @1 { build_zero_cst (type); })))))
+ (if (!canonicalize_math_p ())
+ (with { tree utype = unsigned_type_for (type); }
+ (cond (le (plus (convert:utype @1) { build_one_cst (utype); })
+ { build_int_cst (utype, 2); })
+ @1 { build_zero_cst (type); }))))))
/* Combine two successive divisions. Note that combining ceil_div
and floor_div is trickier and combining round_div even more so. */
if (TYPE_OVERFLOW_UNDEFINED (type))
{
#if GIMPLE
- value_range vr0;
+ int_range_max vr0;
if (ovf1 == wi::OVF_NONE && ovf2 == wi::OVF_NONE
&& get_global_range_query ()->range_of_expr (vr0, @4)
&& !vr0.varying_p () && !vr0.undefined_p ())
if (TYPE_OVERFLOW_UNDEFINED (type))
{
#if GIMPLE
- value_range vr0;
+ int_range_max vr0;
if (ovf1 == wi::OVF_NONE && ovf2 == wi::OVF_NONE
&& get_global_range_query ()->range_of_expr (vr0, @0)
&& !vr0.varying_p () && !vr0.undefined_p ())
(if (INTEGRAL_TYPE_P (TREE_TYPE (@0)) && TYPE_UNSIGNED (TREE_TYPE (@0)))
(bit_and @0 (negate @1))))
-/* Simplify (t * 2) / 2) -> t. */
(for div (trunc_div ceil_div floor_div round_div exact_div)
+ /* Simplify (t * u) / u -> t. */
(simplify
(div (mult:c @0 @1) @1)
(if (ANY_INTEGRAL_TYPE_P (type))
- (if (TYPE_OVERFLOW_UNDEFINED (type))
+ (if (TYPE_OVERFLOW_UNDEFINED (type) && !TYPE_OVERFLOW_SANITIZED (type))
@0
#if GIMPLE
- (with {value_range vr0, vr1;}
+ (with {int_range_max vr0, vr1;}
(if (INTEGRAL_TYPE_P (type)
&& get_range_query (cfun)->range_of_expr (vr0, @0)
&& get_range_query (cfun)->range_of_expr (vr1, @1)
&& range_op_handler (MULT_EXPR).overflow_free_p (vr0, vr1))
@0))
+#endif
+ )))
+#if GIMPLE
+ /* Simplify (t * u) / v -> t * (u / v) if u is multiple of v. */
+ (simplify
+ (div (mult @0 INTEGER_CST@1) INTEGER_CST@2)
+ (if (INTEGRAL_TYPE_P (type)
+ && wi::multiple_of_p (wi::to_widest (@1), wi::to_widest (@2), SIGNED))
+ (if (TYPE_OVERFLOW_UNDEFINED (type) && !TYPE_OVERFLOW_SANITIZED (type))
+ (mult @0 (div! @1 @2))
+ (with {int_range_max vr0, vr1;}
+ (if (get_range_query (cfun)->range_of_expr (vr0, @0)
+ && get_range_query (cfun)->range_of_expr (vr1, @1)
+ && range_op_handler (MULT_EXPR).overflow_free_p (vr0, vr1))
+ (mult @0 (div! @1 @2))))
+ )))
+#endif
+ /* Simplify (t * u) / (t * v) -> (u / v) if u is multiple of v. */
+ (simplify
+ (div (mult @0 INTEGER_CST@1) (mult @0 INTEGER_CST@2))
+ (if (INTEGRAL_TYPE_P (type)
+ && wi::multiple_of_p (wi::to_widest (@1), wi::to_widest (@2), SIGNED))
+ (if (TYPE_OVERFLOW_UNDEFINED (type) && !TYPE_OVERFLOW_SANITIZED (type))
+ (div @1 @2)
+#if GIMPLE
+ (with {int_range_max vr0, vr1, vr2;}
+ (if (get_range_query (cfun)->range_of_expr (vr0, @0)
+ && get_range_query (cfun)->range_of_expr (vr1, @1)
+ && get_range_query (cfun)->range_of_expr (vr2, @2)
+ && range_op_handler (MULT_EXPR).overflow_free_p (vr0, vr1)
+ && range_op_handler (MULT_EXPR).overflow_free_p (vr0, vr2))
+ (div @1 @2)))
#endif
))))
/* Simplify (X + M*N) / N -> X / N + M. */
(simplify
(div (plus:c@4 @0 (mult:c@3 @1 @2)) @2)
- (with {value_range vr0, vr1, vr2, vr3, vr4;}
+ (with {int_range_max vr0, vr1, vr2, vr3, vr4;}
(if (INTEGRAL_TYPE_P (type)
&& get_range_query (cfun)->range_of_expr (vr1, @1)
&& get_range_query (cfun)->range_of_expr (vr2, @2)
/* Simplify (X - M*N) / N -> X / N - M. */
(simplify
(div (minus@4 @0 (mult:c@3 @1 @2)) @2)
- (with {value_range vr0, vr1, vr2, vr3, vr4;}
+ (with {int_range_max vr0, vr1, vr2, vr3, vr4;}
(if (INTEGRAL_TYPE_P (type)
&& get_range_query (cfun)->range_of_expr (vr1, @1)
&& get_range_query (cfun)->range_of_expr (vr2, @2)
: wi::div_trunc (v, n, TYPE_SIGN (type)))
#define exact_mod(v) (shift ? wi::ctz (v) >= n.to_shwi () \
: wi::multiple_of_p (v, n, TYPE_SIGN (type)))
- value_range vr0, vr1, vr3;
+ int_range_max vr0, vr1, vr3;
}
(if (INTEGRAL_TYPE_P (type)
&& get_range_query (cfun)->range_of_expr (vr0, @0))
/* (nop_outer_cast)-(inner_cast)var -> -(outer_cast)(var)
if var is smaller in precision.
This is always safe for both doing the negative in signed or unsigned
- as the value for undefined will not show up. */
+ as the value for undefined will not show up.
+ Note the outer cast cannot be a boolean type as the only valid values
+ are 0,-1/1 (depending on the signedness of the boolean) and the negative
+ is there to get the correct value. */
(simplify
(convert (negate:s@1 (convert:s @0)))
(if (INTEGRAL_TYPE_P (type)
&& tree_nop_conversion_p (type, TREE_TYPE (@1))
- && TYPE_PRECISION (type) > TYPE_PRECISION (TREE_TYPE (@0)))
+ && TYPE_PRECISION (type) > TYPE_PRECISION (TREE_TYPE (@0))
+ && TREE_CODE (type) != BOOLEAN_TYPE)
(negate (convert @0))))
(for op (negate abs)
(hypots @0 (copysigns @1 @2))
(hypots @0 @1))))
-/* copysign(x, CST) -> abs (x). */
+/* copysign(x, CST) -> abs (x). If the target does not
+ support the copysign optab then canonicalize
+ copysign(x, -CST) -> fneg (abs (x)). */
(for copysigns (COPYSIGN_ALL)
(simplify
(copysigns @0 REAL_CST@1)
(if (!REAL_VALUE_NEGATIVE (TREE_REAL_CST (@1)))
- (abs @0))))
+ (abs @0)
+#if GIMPLE
+ (if (!direct_internal_fn_supported_p (IFN_COPYSIGN, type,
+ OPTIMIZE_FOR_BOTH))
+ (negate (abs @0)))
+#endif
+ )))
-/* Transform fneg (fabs (X)) -> copysign (X, -1). */
+#if GIMPLE
+/* Transform fneg (fabs (X)) -> copysign (X, -1) as the canonical
+ representation if the target supports the copysign optab. */
(simplify
(negate (abs @0))
- (IFN_COPYSIGN @0 { build_minus_one_cst (type); }))
-
+ (if (direct_internal_fn_supported_p (IFN_COPYSIGN, type,
+ OPTIMIZE_FOR_BOTH))
+ (IFN_COPYSIGN @0 { build_minus_one_cst (type); })))
+#endif
/* copysign(copysign(x, y), z) -> copysign(x, z). */
(for copysigns (COPYSIGN_ALL)
(simplify
&& tree_nop_conversion_p (type, TREE_TYPE (@1)))
(lshift @0 @2)))
+/* Fold a * !a into 0. */
+(simplify
+ (mult:c @0 (convert? (eq @0 integer_zerop)))
+ { build_zero_cst (type); })
+(simplify
+ (mult:c @0 (vec_cond (eq @0 integer_zerop) @1 integer_zerop))
+ { build_zero_cst (type); })
+(simplify
+ (mult:c @0 (vec_cond (ne @0 integer_zerop) integer_zerop @1))
+ { build_zero_cst (type); })
+
/* Shifts by precision or greater result in zero. */
(for shift (lshift rshift)
(simplify
/* Simplify ~X & X as zero. */
(simplify
- (bit_and (convert? @0) (convert? @1))
+ (bit_and:c (convert? @0) (convert? (maybe_bit_not @1)))
(with { bool wascmp; }
(if (types_match (TREE_TYPE (@0), TREE_TYPE (@1))
&& bitwise_inverted_equal_p (@0, @1, wascmp))
/* ~x ^ x -> -1 */
(for op (bit_ior bit_xor)
(simplify
- (op (convert? @0) (convert? @1))
+ (op:c (convert? @0) (convert? (maybe_bit_not @1)))
(with { bool wascmp; }
(if (types_match (TREE_TYPE (@0), TREE_TYPE (@1))
&& bitwise_inverted_equal_p (@0, @1, wascmp))
(if (INTEGRAL_TYPE_P (TREE_TYPE (@1))
&& (TYPE_UNSIGNED (TREE_TYPE (@1))
|| TYPE_PRECISION (TREE_TYPE (@1)) > 1)
+ && INTEGRAL_TYPE_P (type)
+ && (TYPE_UNSIGNED (type)
+ || TYPE_PRECISION (type) > 1)
&& wi::leu_p (tree_nonzero_bits (@1), 1))))
/* Transform { 0 or 1 } * { 0 or 1 } into { 0 or 1 } & { 0 or 1 }. */
(mult (convert @0) @1)))
/* Narrow integer multiplication by a zero_one_valued_p operand.
- Multiplication by [0,1] is guaranteed not to overflow. */
+ Multiplication by [0,1] is guaranteed not to overflow except for
+ 1bit signed types. */
(simplify
(convert (mult@0 zero_one_valued_p@1 INTEGER_CST@2))
(if (INTEGRAL_TYPE_P (type)
&& INTEGRAL_TYPE_P (TREE_TYPE (@0))
- && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@0)))
+ && TYPE_PRECISION (type) < TYPE_PRECISION (TREE_TYPE (@0))
+ && (TYPE_UNSIGNED (type) || TYPE_PRECISION (type) > 1))
(mult (convert @1) (convert @2))))
/* (X << C) != 0 can be simplified to X, when C is zero_one_valued_p.
{ constant_boolean_node (cmp == NE_EXPR, type); })))
/* ((X inner_op C0) outer_op C1)
- With X being a tree where value_range has reasoned certain bits to always be
+ With X being a tree where range has reasoned certain bits to always be
zero throughout its computed value range,
inner_op = {|,^}, outer_op = {|,^} and inner_op != outer_op
where zero_mask has 1's for all bits that are sure to be 0 in
|| POINTER_TYPE_P (itype))
&& wi::eq_p (wi::to_wide (int_cst), wi::max_value (itype))))))
+/* Unsigned Saturation Add */
+/* SAT_ADD = usadd_left_part_1 | usadd_right_part_1, aka:
+ SAT_ADD = (X + Y) | -((X + Y) < X) */
+(match (usadd_left_part_1 @0 @1)
+ (plus:c @0 @1)
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* SAT_ADD = usadd_left_part_2 | usadd_right_part_2, aka:
+ SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | (IMAGPART_EXPR <.ADD_OVERFLOW> != 0) */
+(match (usadd_left_part_2 @0 @1)
+ (realpart (IFN_ADD_OVERFLOW:c @0 @1))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* SAT_ADD = usadd_left_part_1 | usadd_right_part_1, aka:
+ SAT_ADD = (X + Y) | -((type)(X + Y) < X) */
+(match (usadd_right_part_1 @0 @1)
+ (negate (convert (lt (plus:c @0 @1) @0)))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* SAT_ADD = usadd_left_part_1 | usadd_right_part_1, aka:
+ SAT_ADD = (X + Y) | -(X > (X + Y)) */
+(match (usadd_right_part_1 @0 @1)
+ (negate (convert (gt @0 (plus:c @0 @1))))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* SAT_ADD = usadd_left_part_2 | usadd_right_part_2, aka:
+ SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | (IMAGPART_EXPR <.ADD_OVERFLOW> != 0) */
+(match (usadd_right_part_2 @0 @1)
+ (negate (convert (ne (imagpart (IFN_ADD_OVERFLOW:c @0 @1)) integer_zerop)))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* SAT_ADD = usadd_left_part_2 | usadd_right_part_2, aka:
+ SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | -IMAGPART_EXPR <.ADD_OVERFLOW> */
+(match (usadd_right_part_2 @0 @1)
+ (negate (imagpart (IFN_ADD_OVERFLOW:c @0 @1)))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* We cannot merge or overload usadd_left_part_1 and usadd_left_part_2
+ because the sub part of left_part_2 cannot work with right_part_1.
+ For example, left_part_2 pattern focus one .ADD_OVERFLOW but the
+ right_part_1 has nothing to do with .ADD_OVERFLOW. */
+
+/* Unsigned saturation add, case 1 (branchless):
+ SAT_U_ADD = (X + Y) | - ((X + Y) < X) or
+ SAT_U_ADD = (X + Y) | - (X > (X + Y)). */
+(match (unsigned_integer_sat_add @0 @1)
+ (bit_ior:c (usadd_left_part_1 @0 @1) (usadd_right_part_1 @0 @1)))
+
+/* Unsigned saturation add, case 2 (branchless with .ADD_OVERFLOW):
+ SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | -IMAGPART_EXPR <.ADD_OVERFLOW> or
+ SAT_ADD = REALPART_EXPR <.ADD_OVERFLOW> | (IMAGPART_EXPR <.ADD_OVERFLOW> != 0) */
+(match (unsigned_integer_sat_add @0 @1)
+ (bit_ior:c (usadd_left_part_2 @0 @1) (usadd_right_part_2 @0 @1)))
+
+/* Unsigned saturation add, case 3 (branch with ge):
+ SAT_U_ADD = (X + Y) >= x ? (X + Y) : -1. */
+(match (unsigned_integer_sat_add @0 @1)
+ (cond^ (ge (usadd_left_part_1@2 @0 @1) @0) @2 integer_minus_onep))
+
+/* Unsigned saturation add, case 4 (branch with lt):
+ SAT_U_ADD = (X + Y) < x ? -1 : (X + Y). */
+(match (unsigned_integer_sat_add @0 @1)
+ (cond^ (lt (usadd_left_part_1@2 @0 @1) @0) integer_minus_onep @2))
+
+/* Unsigned saturation add, case 5 (branch with eq .ADD_OVERFLOW):
+ SAT_U_ADD = REALPART_EXPR <.ADD_OVERFLOW> == 0 ? .ADD_OVERFLOW : -1. */
+(match (unsigned_integer_sat_add @0 @1)
+ (cond^ (eq (imagpart (IFN_ADD_OVERFLOW:c @0 @1)) integer_zerop)
+ (usadd_left_part_2 @0 @1) integer_minus_onep))
+
+/* Unsigned saturation add, case 6 (branch with ne .ADD_OVERFLOW):
+ SAT_U_ADD = REALPART_EXPR <.ADD_OVERFLOW> != 0 ? -1 : .ADD_OVERFLOW. */
+(match (unsigned_integer_sat_add @0 @1)
+ (cond^ (ne (imagpart (IFN_ADD_OVERFLOW:c @0 @1)) integer_zerop)
+ integer_minus_onep (usadd_left_part_2 @0 @1)))
+
+/* Unsigned saturation sub, case 1 (branch with gt):
+ SAT_U_SUB = X > Y ? X - Y : 0 */
+(match (unsigned_integer_sat_sub @0 @1)
+ (cond (gt @0 @1) (minus @0 @1) integer_zerop)
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* Unsigned saturation sub, case 2 (branch with ge):
+ SAT_U_SUB = X >= Y ? X - Y : 0. */
+(match (unsigned_integer_sat_sub @0 @1)
+ (cond (ge @0 @1) (minus @0 @1) integer_zerop)
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* Unsigned saturation sub, case 3 (branchless with gt):
+ SAT_U_SUB = (X - Y) * (X > Y). */
+(match (unsigned_integer_sat_sub @0 @1)
+ (mult:c (minus @0 @1) (convert (gt @0 @1)))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
+/* Unsigned saturation sub, case 4 (branchless with ge):
+ SAT_U_SUB = (X - Y) * (X >= Y). */
+(match (unsigned_integer_sat_sub @0 @1)
+ (mult:c (minus @0 @1) (convert (ge @0 @1)))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))))
+
/* x > y && x != XXX_MIN --> x > y
x > y && x == XXX_MIN --> false . */
(for eqne (eq ne)
(if (INTEGRAL_TYPE_P (TREE_TYPE (@0)) || POINTER_TYPE_P (TREE_TYPE (@0)))
(rcmp @0 @1))))
+/* (type)([0,1]@a != 0) -> (type)a
+ (type)([0,1]@a == 1) -> (type)a
+ (type)([0,1]@a == 0) -> a ^ 1
+ (type)([0,1]@a != 1) -> a ^ 1. */
+(for eqne (eq ne)
+ (simplify
+ (convert (eqne zero_one_valued_p@0 INTEGER_CST@1))
+ (if ((integer_zerop (@1) || integer_onep (@1)))
+ (if ((eqne == EQ_EXPR) ^ integer_zerop (@1))
+ (convert @0)
+ /* Only do this if the types match as (type)(a == 0) is
+ canonical form normally, while `a ^ 1` is canonical when
+ there is no type change. */
+ (if (types_match (type, TREE_TYPE (@0)))
+ (bit_xor @0 { build_one_cst (type); } ))))))
+
/* We can't reassociate at all for saturating types. */
(if (!TYPE_SATURATING (type))
= wide_int::from (wi::to_wide (@1), TYPE_PRECISION (inner_type),
TYPE_SIGN (inner_type));
- value_range vr;
+ int_range_max vr;
if (get_global_range_query ()->range_of_expr (vr, @0)
&& !vr.varying_p () && !vr.undefined_p ())
{
/* (x <= 0 ? -x : 0) -> max(-x, 0). */
(simplify
- (cond (le @0 integer_zerop@1) (negate@2 @0) integer_zerop@1)
- (max @2 @1))
+ (cond (le @0 integer_zerop@1) (negate@2 @0) integer_zerop@1)
+ (if (ANY_INTEGRAL_TYPE_P (type) && TYPE_OVERFLOW_UNDEFINED (type))
+ (max @2 @1)))
/* (zero_one == 0) ? y : z <op> y -> ((typeof(y))zero_one * z) <op> y */
(for op (bit_xor bit_ior plus)
(cond (eq @0 integer_all_onesp) @1 (op:c@2 @1 @0))
@2))
+/* a != 0 ? a / b : 0 -> a / b iff b is nonzero. */
+(for op (trunc_div ceil_div floor_div round_div exact_div)
+ (simplify
+ (cond (ne @0 integer_zerop) (op@2 @3 @1) integer_zerop )
+ (if (bitwise_equal_p (@0, @3)
+ && tree_expr_nonzero_p (@1))
+ @2)))
+
+/* Note we prefer the != case here
+ as (a != 0) * (a * b) will generate that version. */
+/* a != 0 ? a * b : 0 -> a * b */
+/* a != 0 ? a & b : 0 -> a & b */
+(for op (mult bit_and)
+ (simplify
+ (cond (ne @0 integer_zerop) (op:c@2 @1 @3) integer_zerop)
+ (if (bitwise_equal_p (@0, @3))
+ @2)))
+
/* Simplifications of shift and rotates. */
(for rotate (lrotate rrotate)
/* If we have a sign-extension of a zero-extended value, we can
replace that by a single zero-extension. Likewise if the
final conversion does not change precision we can drop the
- intermediate conversion. */
+ intermediate conversion. Similarly truncation of a sign-extension
+ can be replaced by a single sign-extension. */
(if (inside_int && inter_int && final_int
&& ((inside_prec < inter_prec && inter_prec < final_prec
&& inside_unsignedp && !inter_unsignedp)
- || final_prec == inter_prec))
+ || final_prec == inter_prec
+ || (inside_prec < inter_prec && inter_prec > final_prec
+ && !inside_unsignedp && inter_unsignedp)))
(ocvt @0))
/* Two conversions in a row are not needed unless:
(simplify
(float (fix_trunc @0))
(if (!flag_trapping_math
+ && !HONOR_SIGNED_ZEROS (type)
&& types_match (type, TREE_TYPE (@0))
&& direct_internal_fn_supported_p (IFN_TRUNC, type,
OPTIMIZE_FOR_BOTH))
/* (c ? a : b) op (c ? d : e) --> c ? (a op d) : (b op e) */
(simplify
(op (vec_cond:s @0 @1 @2) (vec_cond:s @0 @3 @4))
- (vec_cond @0 (op! @1 @3) (op! @2 @4)))
+ (if (TREE_CODE_CLASS (op) != tcc_comparison
+ || types_match (type, TREE_TYPE (@1))
+ || expand_vec_cond_expr_p (type, TREE_TYPE (@0), ERROR_MARK)
+ || (optimize_vectors_before_lowering_p ()
+ /* The following is optimistic on the side of non-support, we are
+ missing the legacy vcond{,u,eq} cases. Do this only when
+ lowering will be able to fixup.. */
+ && !expand_vec_cond_expr_p (TREE_TYPE (@1),
+ TREE_TYPE (@0), ERROR_MARK)))
+ (vec_cond @0 (op! @1 @3) (op! @2 @4))))
/* (c ? a : b) op d --> c ? (a op d) : (b op d) */
(simplify
(op (vec_cond:s @0 @1 @2) @3)
- (vec_cond @0 (op! @1 @3) (op! @2 @3)))
+ (if (TREE_CODE_CLASS (op) != tcc_comparison
+ || types_match (type, TREE_TYPE (@1))
+ || expand_vec_cond_expr_p (type, TREE_TYPE (@0), ERROR_MARK)
+ || (optimize_vectors_before_lowering_p ()
+ && !expand_vec_cond_expr_p (TREE_TYPE (@1),
+ TREE_TYPE (@0), ERROR_MARK)))
+ (vec_cond @0 (op! @1 @3) (op! @2 @3))))
(simplify
(op @3 (vec_cond:s @0 @1 @2))
- (vec_cond @0 (op! @3 @1) (op! @3 @2))))
+ (if (TREE_CODE_CLASS (op) != tcc_comparison
+ || types_match (type, TREE_TYPE (@1))
+ || expand_vec_cond_expr_p (type, TREE_TYPE (@0), ERROR_MARK)
+ || (optimize_vectors_before_lowering_p ()
+ && !expand_vec_cond_expr_p (TREE_TYPE (@1),
+ TREE_TYPE (@0), ERROR_MARK)))
+ (vec_cond @0 (op! @3 @1) (op! @3 @2)))))
#if GIMPLE
(match (nop_atomic_bit_test_and_p @0 @1 @4)
(if (optimize_vectors_before_lowering_p () && types_match (@0, @3))
(vec_cond (bit_and @0 (bit_not @3)) @2 @1)))
+/* ((VCE (a cmp b ? -1 : 0)) < 0) ? c : d is just
+ (VCE ((a cmp b) ? (VCE c) : (VCE d))) when TYPE_PRECISION of the
+ component type of the outer vec_cond is greater equal the inner one. */
+(for cmp (simple_comparison)
+ (simplify
+ (vec_cond
+ (lt (view_convert@5 (vec_cond@6 (cmp@4 @0 @1)
+ integer_all_onesp
+ integer_zerop))
+ integer_zerop) @2 @3)
+ (if (VECTOR_INTEGER_TYPE_P (TREE_TYPE (@0))
+ && VECTOR_INTEGER_TYPE_P (TREE_TYPE (@5))
+ && !TYPE_UNSIGNED (TREE_TYPE (@5))
+ && VECTOR_TYPE_P (TREE_TYPE (@6))
+ && VECTOR_TYPE_P (type)
+ && tree_int_cst_le (TYPE_SIZE (TREE_TYPE (type)),
+ TYPE_SIZE (TREE_TYPE (TREE_TYPE (@6))))
+ && TYPE_SIZE (type) == TYPE_SIZE (TREE_TYPE (@6)))
+ (with { tree vtype = TREE_TYPE (@6);}
+ (view_convert:type
+ (vec_cond @4 (view_convert:vtype @2) (view_convert:vtype @3)))))))
+
/* c1 ? c2 ? a : b : b --> (c1 & c2) ? a : b */
(simplify
(vec_cond @0 (vec_cond:s @1 @2 @3) @3)
&& (wi::to_widest (@2) + 1 == wi::to_widest (@3)
|| wi::to_widest (@2) == wi::to_widest (@3) + 1))
(with {
- value_range r;
+ int_range_max r;
get_range_query (cfun)->range_of_expr (r, @0);
if (r.undefined_p ())
r.set_varying (TREE_TYPE (@0));
(if (VECTOR_TYPE_P (type))
(view_convert @c0)
(convert @c0))))))))
+
+/* This is for VEC_COND_EXPR
+ Optimize A < B ? A : B to MIN (A, B)
+ A > B ? A : B to MAX (A, B). */
+(for cmp (lt le ungt unge gt ge unlt unle)
+ minmax (min min min min max max max max)
+ MINMAX (MIN_EXPR MIN_EXPR MIN_EXPR MIN_EXPR MAX_EXPR MAX_EXPR MAX_EXPR MAX_EXPR)
+ (simplify
+ (vec_cond (cmp @0 @1) @0 @1)
+ (if (VECTOR_INTEGER_TYPE_P (type)
+ && target_supports_op_p (type, MINMAX, optab_vector))
+ (minmax @0 @1))))
+
+(for cmp (lt le ungt unge gt ge unlt unle)
+ minmax (max max max max min min min min)
+ MINMAX (MAX_EXPR MAX_EXPR MAX_EXPR MAX_EXPR MIN_EXPR MIN_EXPR MIN_EXPR MIN_EXPR)
+ (simplify
+ (vec_cond (cmp @0 @1) @1 @0)
+ (if (VECTOR_INTEGER_TYPE_P (type)
+ && target_supports_op_p (type, MINMAX, optab_vector))
+ (minmax @0 @1))))
#endif
(for cnd (cond vec_cond)
@2)))
/* (a != b) ? (a + b) : (2 * a) -> (a + b) */
(simplify
- (cnd (ne:c @0 @1) (plus@2 @0 @1) (mult @0 uniform_integer_cst_p@3))
+ (cnd (ne:c @0 @1) (plus:c@2 @0 @1) (mult @0 uniform_integer_cst_p@3))
(if (wi::to_wide (uniform_integer_cst_p (@3)) == 2)
@2))
)
(convert (absu:utype @0)))
@3))))
+/* X > Positive ? X : ABS(X) -> ABS(X) */
+/* X >= Positive ? X : ABS(X) -> ABS(X) */
+/* X == Positive ? X : ABS(X) -> ABS(X) */
+(for cmp (eq gt ge)
+ (simplify
+ (cond (cmp:c @0 tree_expr_nonnegative_p@1) @0 (abs@3 @0))
+ (if (INTEGRAL_TYPE_P (type))
+ @3)))
+
+/* X == Positive ? Positive : ABS(X) -> ABS(X) */
+(simplify
+ (cond (eq:c @0 tree_expr_nonnegative_p@1) @1 (abs@3 @0))
+ (if (INTEGRAL_TYPE_P (type))
+ @3))
+
/* (X + 1) > Y ? -X : 1 simplifies to X >= Y ? -X : 1 when
X is unsigned, as when X + 1 overflows, X is -1, so -X == 1. */
(simplify
/* !A ? B : C -> A ? C : B. */
(simplify
(cnd (logical_inverted_value truth_valued_p@0) @1 @2)
- (cnd @0 @2 @1)))
+ /* For CONDs, don't handle signed values here. */
+ (if (cnd == VEC_COND_EXPR
+ || TYPE_UNSIGNED (TREE_TYPE (@0)))
+ (cnd @0 @2 @1))))
/* abs/negative simplifications moved from fold_cond_expr_with_comparison.
>= TYPE_PRECISION (TREE_TYPE (@10)))
&& (TYPE_UNSIGNED (TREE_TYPE (@00))
== TYPE_UNSIGNED (TREE_TYPE (@10))))
- || (TREE_CODE (@10) == INTEGER_CST
+ || (TREE_CODE (@1) == INTEGER_CST
&& INTEGRAL_TYPE_P (TREE_TYPE (@00))
- && int_fits_type_p (@10, TREE_TYPE (@00)))))
+ && int_fits_type_p (@1, TREE_TYPE (@00)))))
(cmp @00 (convert @10))
- (if (TREE_CODE (@10) == INTEGER_CST
+ (if (TREE_CODE (@1) == INTEGER_CST
&& INTEGRAL_TYPE_P (TREE_TYPE (@00))
- && !int_fits_type_p (@10, TREE_TYPE (@00)))
+ && !int_fits_type_p (@1, TREE_TYPE (@00)))
(with
{
tree min = lower_bound_in_type (TREE_TYPE (@10), TREE_TYPE (@00));
tree max = upper_bound_in_type (TREE_TYPE (@10), TREE_TYPE (@00));
- bool above = integer_nonzerop (const_binop (LT_EXPR, type, max, @10));
- bool below = integer_nonzerop (const_binop (LT_EXPR, type, @10, min));
+ bool above = integer_nonzerop (const_binop (LT_EXPR, type, max, @1));
+ bool below = integer_nonzerop (const_binop (LT_EXPR, type, @1, min));
}
(if (above || below)
(if (cmp == EQ_EXPR || cmp == NE_EXPR)
&& exact_real_truncate (TYPE_MODE (double_type_node), &orig))
type1 = double_type_node;
}
- tree newtype
- = (element_precision (TREE_TYPE (@00)) > element_precision (type1)
- ? TREE_TYPE (@00) : type1);
+ tree newtype
+ = (element_precision (TREE_TYPE (@00)) > element_precision (type1)
+ ? TREE_TYPE (@00) : type1);
}
- (if (element_precision (TREE_TYPE (@0)) > element_precision (newtype))
+ (if (element_precision (TREE_TYPE (@0)) > element_precision (newtype)
+ && (!VECTOR_TYPE_P (type) || is_truth_type_for (newtype, type)))
(cmp (convert:newtype @00) (convert:newtype @10))))))))
(cond @0 @1 @2)
(with { bool wascmp; }
(if (INTEGRAL_TYPE_P (type)
+ && TYPE_UNSIGNED (TREE_TYPE (@0))
&& bitwise_inverted_equal_p (@1, @2, wascmp)
&& (!wascmp || TYPE_PRECISION (type) == 1))
(if ((!TYPE_UNSIGNED (type) && TREE_CODE (type) == BOOLEAN_TYPE)
(simplify
(bit_insert @0 (BIT_FIELD_REF@2 @1 @rsize @rpos) @ipos)
(if (VECTOR_TYPE_P (type)
+ && (VECTOR_MODE_P (TYPE_MODE (type))
+ || optimize_vectors_before_lowering_p ())
&& types_match (@0, @1)
&& types_match (TREE_TYPE (TREE_TYPE (@0)), TREE_TYPE (@2))
- && TYPE_VECTOR_SUBPARTS (type).is_constant ())
+ && TYPE_VECTOR_SUBPARTS (type).is_constant ()
+ && multiple_p (wi::to_poly_offset (@rpos),
+ wi::to_poly_offset (TYPE_SIZE (TREE_TYPE (type)))))
(with
{
unsigned HOST_WIDE_INT elsz
/* parity(X)^parity(Y) is parity(X^Y). */
(simplify
(bit_xor (PARITY:s @0) (PARITY:s @1))
- (PARITY (bit_xor @0 @1)))
+ (if (types_match (TREE_TYPE (@0), TREE_TYPE (@1)))
+ (PARITY (bit_xor @0 @1))
+ (if (INTEGRAL_TYPE_P (TREE_TYPE (@0))
+ && INTEGRAL_TYPE_P (TREE_TYPE (@1)))
+ (with { tree utype = TREE_TYPE (@0);
+ if (TYPE_PRECISION (utype) < TYPE_PRECISION (TREE_TYPE (@1)))
+ utype = TREE_TYPE (@1); }
+ (PARITY (bit_xor (convert:utype @0) (convert:utype @1)))))))
#if GIMPLE
/* parity(zext(X)) == parity(X). */
/* Detect simplification for vector condition folding where
- c = mask1 ? (masked_op mask2 a b) : b
+ c = mask1 ? (masked_op mask2 a b els) : els
into
- c = masked_op (mask1 & mask2) a b
+ c = masked_op (mask1 & mask2) a b els
where the operation can be partially applied to one operand. */
(for cond_op (COND_BINARY)
(simplify
(vec_cond @0
- (cond_op:s @1 @2 @3 @4) @3)
+ (cond_op:s @1 @2 @3 @4) @4)
(cond_op (bit_and @1 @0) @2 @3 @4)))
/* And same for ternary expressions. */
(for cond_op (COND_TERNARY)
(simplify
(vec_cond @0
- (cond_op:s @1 @2 @3 @4 @5) @4)
+ (cond_op:s @1 @2 @3 @4 @5) @5)
(cond_op (bit_and @1 @0) @2 @3 @4 @5)))
/* For pointers @0 and @2 and nonnegative constant offset @1, look for
d = VEC_PERM_EXPR <a, b, NEW_VCST>; */
(simplify
- (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
+ (vec_perm (view_convert?@0 (vec_perm@1 @2 @3 VECTOR_CST@4)) @0 VECTOR_CST@5)
(if (TYPE_VECTOR_SUBPARTS (type).is_constant ())
(with
{
machine_mode result_mode = TYPE_MODE (type);
- machine_mode op_mode = TYPE_MODE (TREE_TYPE (@1));
+ machine_mode op_mode = TYPE_MODE (TREE_TYPE (@2));
int nelts = TYPE_VECTOR_SUBPARTS (type).to_constant ();
vec_perm_builder builder0;
vec_perm_builder builder1;
vec_perm_builder builder2 (nelts, nelts, 1);
}
- (if (tree_to_vec_perm_builder (&builder0, @3)
- && tree_to_vec_perm_builder (&builder1, @4))
+ (if (tree_to_vec_perm_builder (&builder0, @4)
+ && tree_to_vec_perm_builder (&builder1, @5)
+ && TYPE_SIZE (TREE_TYPE (TREE_TYPE (@0)))
+ == TYPE_SIZE (TREE_TYPE (TREE_TYPE (@1))))
(with
{
vec_perm_indices sel0 (builder0, 2, nelts);
? (!can_vec_perm_const_p (result_mode, op_mode, sel0, false)
|| !can_vec_perm_const_p (result_mode, op_mode, sel1, false))
: !can_vec_perm_const_p (result_mode, op_mode, sel1, false)))
- op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
+ op0 = vec_perm_indices_to_tree (TREE_TYPE (@5), sel2);
}
(if (op0)
- (vec_perm @1 @2 { op0; })))))))
+ (view_convert (vec_perm @2 @3 { op0; }))))))))
/* Merge
c = VEC_PERM_EXPR <a, b, VCST0>;
projects / thirdparty / gcc.git / blobdiff