Hi,
the recent changes that allowed multi-step conversions for
"non-packing/unpacking", i.e. modifier == NONE targets included
promoting to-float and demoting to-int variants. This patch
adds demoting to-float and promoting to-int handling.
Bootstrapped and regtested on x86 and aarch64.
A question that seems related: Why do we require !flag_trapping_math
for the "NONE" multistep conversion but not for the "NARROW_DST"
case when both seem to handle float -> int and there are float
values that do not have an int representation? If a backend
can guarantee that the conversion traps, should it just implement
a multistep conversion in a matching expander?
Regards
Robin
gcc/ChangeLog:
* tree-vect-stmts.cc (vectorizable_conversion): Handle
more demotion/promotion for modifier == NONE.
---
gcc/tree-vect-stmts.cc | 40 +++++++++++++++++++++++++++++-----------
1 file changed, 29 insertions(+), 11 deletions(-)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 10e71178ce7..78e0510be7e 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -5324,28 +5324,46 @@ vectorizable_conversion (vec_info *vinfo,
break;
}
- /* For conversions between float and smaller integer types try whether we
- can use intermediate signed integer types to support the
+ /* For conversions between float and larger integer types try whether
+ we can use intermediate signed integer types to support the
conversion. */
if ((code == FLOAT_EXPR
- && GET_MODE_SIZE (lhs_mode) > GET_MODE_SIZE (rhs_mode))
+ && GET_MODE_SIZE (lhs_mode) != GET_MODE_SIZE (rhs_mode))
|| (code == FIX_TRUNC_EXPR
- && GET_MODE_SIZE (rhs_mode) > GET_MODE_SIZE (lhs_mode)
- && !flag_trapping_math))
+ && ((GET_MODE_SIZE (rhs_mode) > GET_MODE_SIZE (lhs_mode)
+ && !flag_trapping_math)
+ || GET_MODE_SIZE (rhs_mode) < GET_MODE_SIZE (lhs_mode))))
{
+ bool demotion = GET_MODE_SIZE (rhs_mode) > GET_MODE_SIZE (lhs_mode);
bool float_expr_p = code == FLOAT_EXPR;
- scalar_mode imode = float_expr_p ? rhs_mode : lhs_mode;
- fltsz = GET_MODE_SIZE (float_expr_p ? lhs_mode : rhs_mode);
+ unsigned short target_size;
+ scalar_mode intermediate_mode;
+ if (demotion)
+ {
+ intermediate_mode = lhs_mode;
+ target_size = GET_MODE_SIZE (rhs_mode);
+ }
+ else
+ {
+ target_size = GET_MODE_SIZE (lhs_mode);
+ tree itype
+ = build_nonstandard_integer_type (GET_MODE_BITSIZE
+ (rhs_mode), 0);
+ intermediate_mode = SCALAR_TYPE_MODE (itype);
+ }
code1 = float_expr_p ? code : NOP_EXPR;
codecvt1 = float_expr_p ? NOP_EXPR : code;
- FOR_EACH_2XWIDER_MODE (rhs_mode_iter, imode)
+ opt_scalar_mode mode_iter;
+ FOR_EACH_2XWIDER_MODE (mode_iter, intermediate_mode)
{
- imode = rhs_mode_iter.require ();
- if (GET_MODE_SIZE (imode) > fltsz)
+ intermediate_mode = mode_iter.require ();
+
+ if (GET_MODE_SIZE (intermediate_mode) > target_size)
break;
cvt_type
- = build_nonstandard_integer_type (GET_MODE_BITSIZE (imode),
+ = build_nonstandard_integer_type (GET_MODE_BITSIZE
+ (intermediate_mode),
0);
cvt_type = get_vectype_for_scalar_type (vinfo, cvt_type,
slp_node);
--
2.41.0
