Hi All,
This is an updated version of my first patch which moves part of the type
conversion code
from convert.c to match.pd because match.pd is able to apply this
transformation in the
presence of intermediate temporary variables.
The previous patch was only regtested on aarch64-none-linux-gnu and I hadn't
done a
regression on x86_64-pc-linux-gnu only a bootstrap. The previous patch was
approved
here https://gcc.gnu.org/ml/gcc-patches/2018-12/msg00116.html
but before committing I ran a x86_64-pc-linux-gnu regtest to be sure and this
showed an issue with a DFP test. I Have fixed this by removing the offending
convert.
The convert was just saying "keep the type as is" but match.pd looped here as
it thinks
the match did something and would try other patterns, causing it to match
itself again.
Instead when there's nothing to update, I just don't do anything.
The second change was to merge this with the existing pattern for integer
conversion
in order to silence a warning from match.pd which though that the two patterns
overlaps
because their match conditions are similar (they have different conditions
inside the ifs
but match.pd doesn't check those of course.).
Regtested and bootstrapped on aarch64-none-linux-gnu and x86_64-pc-linux-gnu
and no issues.
Ok for trunk?
Thanks,
Tamar
Concretely it makes both these cases behave the same
float e = (float)a * (float)b;
*c = (_Float16)e;
and
*c = (_Float16)((float)a * (float)b);
Thanks,
Tamar
gcc/ChangeLog:
2019-01-04 Tamar Christina <tamar.christ...@arm.com>
* convert.c (convert_to_real_1): Move part of conversion code...
* match.pd: ...To here.
gcc/testsuite/ChangeLog:
2019-01-04 Tamar Christina <tamar.christ...@arm.com>
* gcc.dg/type-convert-var.c: New test.
--
diff --git a/gcc/convert.c b/gcc/convert.c
index 1a3353c870768a33fe22480ec97c7d3e0c504075..a16b7af0ec54693eb4f1e3a110aabc1aa18eb8df 100644
--- a/gcc/convert.c
+++ b/gcc/convert.c
@@ -295,92 +295,6 @@ convert_to_real_1 (tree type, tree expr, bool fold_p)
return build1 (TREE_CODE (expr), type, arg);
}
break;
- /* Convert (outertype)((innertype0)a+(innertype1)b)
- into ((newtype)a+(newtype)b) where newtype
- is the widest mode from all of these. */
- case PLUS_EXPR:
- case MINUS_EXPR:
- case MULT_EXPR:
- case RDIV_EXPR:
- {
- tree arg0 = strip_float_extensions (TREE_OPERAND (expr, 0));
- tree arg1 = strip_float_extensions (TREE_OPERAND (expr, 1));
-
- if (FLOAT_TYPE_P (TREE_TYPE (arg0))
- && FLOAT_TYPE_P (TREE_TYPE (arg1))
- && DECIMAL_FLOAT_TYPE_P (itype) == DECIMAL_FLOAT_TYPE_P (type))
- {
- tree newtype = type;
-
- if (TYPE_MODE (TREE_TYPE (arg0)) == SDmode
- || TYPE_MODE (TREE_TYPE (arg1)) == SDmode
- || TYPE_MODE (type) == SDmode)
- newtype = dfloat32_type_node;
- if (TYPE_MODE (TREE_TYPE (arg0)) == DDmode
- || TYPE_MODE (TREE_TYPE (arg1)) == DDmode
- || TYPE_MODE (type) == DDmode)
- newtype = dfloat64_type_node;
- if (TYPE_MODE (TREE_TYPE (arg0)) == TDmode
- || TYPE_MODE (TREE_TYPE (arg1)) == TDmode
- || TYPE_MODE (type) == TDmode)
- newtype = dfloat128_type_node;
- if (newtype == dfloat32_type_node
- || newtype == dfloat64_type_node
- || newtype == dfloat128_type_node)
- {
- expr = build2 (TREE_CODE (expr), newtype,
- convert_to_real_1 (newtype, arg0,
- fold_p),
- convert_to_real_1 (newtype, arg1,
- fold_p));
- if (newtype == type)
- return expr;
- break;
- }
-
- if (TYPE_PRECISION (TREE_TYPE (arg0)) > TYPE_PRECISION (newtype))
- newtype = TREE_TYPE (arg0);
- if (TYPE_PRECISION (TREE_TYPE (arg1)) > TYPE_PRECISION (newtype))
- newtype = TREE_TYPE (arg1);
- /* Sometimes this transformation is safe (cannot
- change results through affecting double rounding
- cases) and sometimes it is not. If NEWTYPE is
- wider than TYPE, e.g. (float)((long double)double
- + (long double)double) converted to
- (float)(double + double), the transformation is
- unsafe regardless of the details of the types
- involved; double rounding can arise if the result
- of NEWTYPE arithmetic is a NEWTYPE value half way
- between two representable TYPE values but the
- exact value is sufficiently different (in the
- right direction) for this difference to be
- visible in ITYPE arithmetic. If NEWTYPE is the
- same as TYPE, however, the transformation may be
- safe depending on the types involved: it is safe
- if the ITYPE has strictly more than twice as many
- mantissa bits as TYPE, can represent infinities
- and NaNs if the TYPE can, and has sufficient
- exponent range for the product or ratio of two
- values representable in the TYPE to be within the
- range of normal values of ITYPE. */
- if (TYPE_PRECISION (newtype) < TYPE_PRECISION (itype)
- && (flag_unsafe_math_optimizations
- || (TYPE_PRECISION (newtype) == TYPE_PRECISION (type)
- && real_can_shorten_arithmetic (TYPE_MODE (itype),
- TYPE_MODE (type))
- && !excess_precision_type (newtype))))
- {
- expr = build2 (TREE_CODE (expr), newtype,
- convert_to_real_1 (newtype, arg0,
- fold_p),
- convert_to_real_1 (newtype, arg1,
- fold_p));
- if (newtype == type)
- return expr;
- }
- }
- }
- break;
default:
break;
}
diff --git a/gcc/match.pd b/gcc/match.pd
index 97a94cd8b2f2e0fee9ffbc76c5277c97689b6f42..4e56121e75fd226fc733dfc5c239d00b690c3d03 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4758,37 +4758,115 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
the C/C++ front-ends by shorten_binary_op and shorten_compare. Long
term we want to move all that code out of the front-ends into here. */
-/* If we have a narrowing conversion of an arithmetic operation where
- both operands are widening conversions from the same type as the outer
- narrowing conversion. Then convert the innermost operands to a suitable
- unsigned type (to avoid introducing undefined behavior), perform the
- operation and convert the result to the desired type. */
-(for op (plus minus)
- (simplify
- (convert (op:s (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. */
- && 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_has_mode_precision_p (TREE_TYPE (@0))
- && type_has_mode_precision_p (TREE_TYPE (@1))
- && type_has_mode_precision_p (type)
- /* The inner conversion must be a widening conversion. */
- && TYPE_PRECISION (TREE_TYPE (@2)) > TYPE_PRECISION (TREE_TYPE (@0))
- && types_match (@0, type)
- && (types_match (@0, @1)
- /* Or the second operand is const integer or converted const
- integer from valueize. */
- || TREE_CODE (@1) == INTEGER_CST))
- (if (TYPE_OVERFLOW_WRAPS (TREE_TYPE (@0)))
- (op @0 (convert @1))
- (with { tree utype = unsigned_type_for (TREE_TYPE (@0)); }
- (convert (op (convert:utype @0)
- (convert:utype @1))))))))
+/* Convert (outertype)((innertype0)a+(innertype1)b)
+ into ((newtype)a+(newtype)b) where newtype
+ is the widest mode from all of these. */
+(for op (plus minus mult rdiv)
+ (simplify
+ (convert (op:s@0 (convert1?@3 @1) (convert2?@4 @2)))
+ (with { tree arg0 = strip_float_extensions (@1);
+ tree arg1 = strip_float_extensions (@2);
+ tree itype = TREE_TYPE (@0);
+ tree ty1 = TREE_TYPE (arg0);
+ tree ty2 = TREE_TYPE (arg1);
+ enum tree_code code = TREE_CODE (itype); }
+ (switch
+ (if (FLOAT_TYPE_P (ty1)
+ && FLOAT_TYPE_P (ty2)
+ && FLOAT_TYPE_P (type)
+ && DECIMAL_FLOAT_TYPE_P (itype) == DECIMAL_FLOAT_TYPE_P (type))
+ (with { tree newtype = type;
+ if (TYPE_MODE (ty1) == SDmode
+ || TYPE_MODE (ty2) == SDmode
+ || TYPE_MODE (type) == SDmode)
+ newtype = dfloat32_type_node;
+ if (TYPE_MODE (ty1) == DDmode
+ || TYPE_MODE (ty2) == DDmode
+ || TYPE_MODE (type) == DDmode)
+ newtype = dfloat64_type_node;
+ if (TYPE_MODE (ty1) == TDmode
+ || TYPE_MODE (ty2) == TDmode
+ || TYPE_MODE (type) == TDmode)
+ newtype = dfloat128_type_node; }
+ (if ((newtype == dfloat32_type_node
+ || newtype == dfloat64_type_node
+ || newtype == dfloat128_type_node)
+ && newtype == type)
+ (convert:newtype (op (convert:newtype @1) (convert:newtype @2)))
+ (with { if (TYPE_PRECISION (ty1) > TYPE_PRECISION (newtype))
+ newtype = ty1;
+ if (TYPE_PRECISION (ty2) > TYPE_PRECISION (newtype))
+ newtype = ty2; }
+ /* Sometimes this transformation is safe (cannot
+ change results through affecting double rounding
+ cases) and sometimes it is not. If NEWTYPE is
+ wider than TYPE, e.g. (float)((long double)double
+ + (long double)double) converted to
+ (float)(double + double), the transformation is
+ unsafe regardless of the details of the types
+ involved; double rounding can arise if the result
+ of NEWTYPE arithmetic is a NEWTYPE value half way
+ between two representable TYPE values but the
+ exact value is sufficiently different (in the
+ right direction) for this difference to be
+ visible in ITYPE arithmetic. If NEWTYPE is the
+ same as TYPE, however, the transformation may be
+ safe depending on the types involved: it is safe
+ if the ITYPE has strictly more than twice as many
+ mantissa bits as TYPE, can represent infinities
+ and NaNs if the TYPE can, and has sufficient
+ exponent range for the product or ratio of two
+ values representable in the TYPE to be within the
+ range of normal values of ITYPE. */
+ (if (TYPE_PRECISION (newtype) < TYPE_PRECISION (itype)
+ && (flag_unsafe_math_optimizations
+ || (TYPE_PRECISION (newtype) == TYPE_PRECISION (type)
+ && real_can_shorten_arithmetic (TYPE_MODE (itype),
+ TYPE_MODE (type))
+ && !excess_precision_type (newtype))))
+ (convert:newtype (op (convert:newtype @1) (convert:newtype @2)))
+ )))) )
+
+ (if (code == REAL_TYPE)
+ /* Ignore the conversion if we don't need to store intermediate
+ results and neither type is a decimal float. */
+ (if (!(flag_float_store
+ || DECIMAL_FLOAT_TYPE_P (type)
+ || DECIMAL_FLOAT_TYPE_P (itype)))
+ (nop:type (op (convert:ty1 @1) (convert:ty2 @2)))))
+
+ /* If we have a narrowing conversion of an arithmetic operation where
+ both operands are widening conversions from the same type as the outer
+ narrowing conversion. Then convert the innermost operands to a
+ suitable unsigned type (to avoid introducing undefined behavior),
+ perform the operation and convert the result to the desired type. */
+ (if (INTEGRAL_TYPE_P (type)
+ && op != MULT_EXPR
+ && op != RDIV_EXPR
+ /* We check for type compatibility between @0 and @1 below,
+ so there's no need to check that @2/@4 are integral types. */
+ && INTEGRAL_TYPE_P (TREE_TYPE (@1))
+ && INTEGRAL_TYPE_P (TREE_TYPE (@3))
+ /* The precision of the type of each operand must match the
+ precision of the mode of each operand, similarly for the
+ result. */
+ && type_has_mode_precision_p (TREE_TYPE (@1))
+ && type_has_mode_precision_p (TREE_TYPE (@2))
+ && type_has_mode_precision_p (type)
+ /* The inner conversion must be a widening conversion. */
+ && TYPE_PRECISION (TREE_TYPE (@3)) > TYPE_PRECISION (TREE_TYPE (@1))
+ && types_match (@1, type)
+ && (types_match (@1, @2)
+ /* Or the second operand is const integer or converted const
+ integer from valueize. */
+ || TREE_CODE (@2) == INTEGER_CST))
+ (if (TYPE_OVERFLOW_WRAPS (TREE_TYPE (@1)))
+ (op @1 (convert @2))
+ (with { tree utype = unsigned_type_for (TREE_TYPE (@1)); }
+ (convert (op (convert:utype @1)
+ (convert:utype @2))))))
+ )
+)))
/* 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
diff --git a/gcc/testsuite/gcc.dg/type-convert-var.c b/gcc/testsuite/gcc.dg/type-convert-var.c
new file mode 100644
index 0000000000000000000000000000000000000000..88d74e2a49d7123515b87ff64a18bd9b306d57e9
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/type-convert-var.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O1 -fdump-tree-optimized" } */
+void foo (float a, float b, float *c)
+{
+ double e = (double)a * (double)b;
+ *c = (float)e;
+}
+
+/* { dg-final { scan-tree-dump-not {double} "optimized" } } */
