(if (((TREE_CODE (@1) == INTEGER_CST
&& INTEGRAL_TYPE_P (TREE_TYPE (@0))
&& int_fits_type_p (@1, TREE_TYPE (@0)))
- || (GIMPLE && types_compatible_p (TREE_TYPE (@0), TREE_TYPE (@1)))
- || (GENERIC && TREE_TYPE (@0) == TREE_TYPE (@1)))
+ || types_match (TREE_TYPE (@0), TREE_TYPE (@1)))
/* ??? This transform conflicts with fold-const.c doing
Convert (T)(x & c) into (T)x & (T)c, if c is an integer
constants (if x has signed type, the sign bit cannot be set
/* Unordered tests if either argument is a NaN. */
(simplify
(bit_ior (unordered @0 @0) (unordered @1 @1))
- (if ((GIMPLE && types_compatible_p (TREE_TYPE (@0), TREE_TYPE (@1)))
- || (GENERIC && TREE_TYPE (@0) == TREE_TYPE (@1)))
+ (if (types_match (TREE_TYPE (@0), TREE_TYPE (@1)))
(unordered @0 @1)))
(simplify
(bit_ior:c (unordered @0 @0) (unordered:c@2 @0 @1))
operation and convert the result to the desired type. */
(for op (plus minus)
(simplify
- (convert (op (convert@2 @0) (convert@3 @1)))
+ (convert (op@4 (convert@2 @0) (convert@3 @1)))
(if (INTEGRAL_TYPE_P (type)
/* We check for type compatibility between @0 and @1 below,
so there's no need to check that @1/@3 are integral types. */
&& TYPE_PRECISION (type) == GET_MODE_PRECISION (TYPE_MODE (type))
/* The inner conversion must be a widening conversion. */
&& TYPE_PRECISION (TREE_TYPE (@2)) > TYPE_PRECISION (TREE_TYPE (@0))
- && ((GENERIC
- && (TYPE_MAIN_VARIANT (TREE_TYPE (@0))
- == TYPE_MAIN_VARIANT (TREE_TYPE (@1)))
- && (TYPE_MAIN_VARIANT (TREE_TYPE (@0))
- == TYPE_MAIN_VARIANT (type)))
- || (GIMPLE
- && types_compatible_p (TREE_TYPE (@0), TREE_TYPE (@1))
- && types_compatible_p (TREE_TYPE (@0), type))))
+ && types_match (TREE_TYPE (@0), TREE_TYPE (@1))
+ && types_match (TREE_TYPE (@0), type)
+ && single_use (@4))
(if (TYPE_OVERFLOW_WRAPS (TREE_TYPE (@0)))
(convert (op @0 @1)))
(with { tree utype = unsigned_type_for (TREE_TYPE (@0)); }
(convert (op (convert:utype @0) (convert:utype @1)))))))
+
+/* This is another case of narrowing, specifically when there's an outer
+ BIT_AND_EXPR which masks off bits outside the type of the innermost
+ operands. Like the previous case we have to convert the operands
+ to unsigned types to avoid introducing undefined behaviour for the
+ arithmetic operation. */
+(for op (minus plus)
+ (simplify
+ (bit_and (op@5 (convert@2 @0) (convert@3 @1)) INTEGER_CST@4)
+ (if (INTEGRAL_TYPE_P (type)
+ /* We check for type compatibility between @0 and @1 below,
+ so there's no need to check that @1/@3 are integral types. */
+ && INTEGRAL_TYPE_P (TREE_TYPE (@0))
+ && INTEGRAL_TYPE_P (TREE_TYPE (@2))
+ /* The precision of the type of each operand must match the
+ precision of the mode of each operand, similarly for the
+ result. */
+ && (TYPE_PRECISION (TREE_TYPE (@0))
+ == GET_MODE_PRECISION (TYPE_MODE (TREE_TYPE (@0))))
+ && (TYPE_PRECISION (TREE_TYPE (@1))
+ == GET_MODE_PRECISION (TYPE_MODE (TREE_TYPE (@1))))
+ && TYPE_PRECISION (type) == GET_MODE_PRECISION (TYPE_MODE (type))
+ /* The inner conversion must be a widening conversion. */
+ && TYPE_PRECISION (TREE_TYPE (@2)) > TYPE_PRECISION (TREE_TYPE (@0))
+ && types_match (TREE_TYPE (@0), TREE_TYPE (@1))
+ && (tree_int_cst_min_precision (@4, UNSIGNED)
+ <= TYPE_PRECISION (TREE_TYPE (@0)))
+ && single_use (@5))
+ (if (TYPE_OVERFLOW_WRAPS (TREE_TYPE (@0)))
+ (with { tree ntype = TREE_TYPE (@0); }
+ (convert (bit_and (op @0 @1) (convert:ntype @4)))))
+ (with { tree utype = unsigned_type_for (TREE_TYPE (@0)); }
+ (convert (bit_and (op (convert:utype @0) (convert:utype @1))
+ (convert:utype @4)))))))
+
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+extern const unsigned char mode_ibit[];
+extern const unsigned char mode_fbit[];
+extern const signed char smode_ibit[];
+extern const signed char smode_fbit[];
+
+/* We use bit-and rather than modulo to ensure we're actually
+ testing the desired match.pd pattern. */
+unsigned char
+muufubar (int indx)
+{
+ int ret = (mode_fbit [indx] - mode_ibit [indx]) & 3;
+ return ret;
+}
+
+signed char
+msufubar (int indx)
+{
+ int ret = (mode_fbit [indx] - mode_ibit [indx]) & 3;
+ return ret;
+}
+
+unsigned char
+musfubar (int indx)
+{
+ int ret = (smode_fbit [indx] - smode_ibit [indx]) & 3;
+ return ret;
+}
+
+signed char
+mssfubar (int indx)
+{
+ int ret = (smode_fbit [indx] - smode_ibit [indx]) & 3;
+ return ret;
+}
+
+
+unsigned char
+puufubar (int indx)
+{
+ int ret = (mode_fbit [indx] + mode_ibit [indx]) & 3;
+ return ret;
+}
+
+signed char
+psufubar (int indx)
+{
+ int ret = (mode_fbit [indx] + mode_ibit [indx]) & 3;
+ return ret;
+}
+
+unsigned char
+pusfubar (int indx)
+{
+ int ret = (smode_fbit [indx] + smode_ibit [indx]) & 3;
+ return ret;
+}
+
+signed char
+pssfubar (int indx)
+{
+ int ret = (smode_fbit [indx] + smode_ibit [indx]) & 3;
+ return ret;
+}
+
+/* The shortening patterns in match.pd should arrange to do the
+ arithmetic in char modes and thus any casts to ints should
+ have been removed. */
+/* { dg-final {scan-tree-dump-not "\\(int\\)" "optimized"} } */
+
+/* We should have casted 4 operands from signed to unsigned char types. */
+/* { dg-final {scan-tree-dump-times "\\(unsigned char\\)" 8 "optimized" } } */
+
+/* And two return values should have been casted from unsigned char to
+ a normal char. */
+/* { dg-final {scan-tree-dump-times "\\(signed char\\)" 4 "optimized" } } */
+/* { dg-final { cleanup-tree-dump "optimized" } } */