Re: Implement more rtx vector folds on variable-length vectors
On 7/15/19 9:30 AM, Richard Sandiford wrote: > Richard Sandiford writes: >> This patch extends the tree-level folding of variable-length vectors >> so that it can also be used on rtxes. The first step is to move >> the tree_vector_builder new_unary/binary_operator routines to the >> parent vector_builder class (which in turn means adding a new >> template parameter). The second step is to make simplify-rtx.c >> use a direct rtx analogue of the VECTOR_CST handling in fold-const.c. >> >> Tested on aarch64-linux-gnu, aarch64_be-elf and x86_64-linux-gnu. >> OK to install? >> >> Richard > > Here's a version updated for the earlier patch, so that we take > both HONOR_NANS and HONOR_SNANS into account. Tested on > aarch64-linux-gnu to far. > > Thanks, > Richard > > > 2019-07-15 Richard Sandiford > > gcc/ > * rtl.h (bit_and_conditions, bit_ior_conditions): Declare. > * jump.c (flags_to_condition): Add an honor_nans_p argument. > (bit_ior_conditions, bit_and_conditions): New functions. > * simplify-rtx.c (simplify_binary_operation_1): Try to fold an > AND or IOR of two comparisons into a single comparison. > (simplify_ternary_operation): Try to fold an if_then_else involving > two conditions into an AND of two conditions. > (test_merged_comparisons): New function. > (simplify_rtx_c_tests): Call it. This is fine once the prereqs are approved. jeff
Re: Implement more rtx vector folds on variable-length vectors
Richard Sandiford writes:
> This patch extends the tree-level folding of variable-length vectors
> so that it can also be used on rtxes. The first step is to move
> the tree_vector_builder new_unary/binary_operator routines to the
> parent vector_builder class (which in turn means adding a new
> template parameter). The second step is to make simplify-rtx.c
> use a direct rtx analogue of the VECTOR_CST handling in fold-const.c.
>
> Tested on aarch64-linux-gnu, aarch64_be-elf and x86_64-linux-gnu.
> OK to install?
>
> Richard
Here's a version updated for the earlier patch, so that we take
both HONOR_NANS and HONOR_SNANS into account. Tested on
aarch64-linux-gnu to far.
Thanks,
Richard
2019-07-15 Richard Sandiford
gcc/
* rtl.h (bit_and_conditions, bit_ior_conditions): Declare.
* jump.c (flags_to_condition): Add an honor_nans_p argument.
(bit_ior_conditions, bit_and_conditions): New functions.
* simplify-rtx.c (simplify_binary_operation_1): Try to fold an
AND or IOR of two comparisons into a single comparison.
(simplify_ternary_operation): Try to fold an if_then_else involving
two conditions into an AND of two conditions.
(test_merged_comparisons): New function.
(simplify_rtx_c_tests): Call it.
Index: gcc/rtl.h
===
--- gcc/rtl.h 2019-07-12 09:14:06.0 +0100
+++ gcc/rtl.h 2019-07-15 16:24:30.685937855 +0100
@@ -3315,6 +3315,8 @@ extern enum rtx_code reverse_condition_m
extern enum rtx_code swap_condition (enum rtx_code);
extern enum rtx_code unsigned_condition (enum rtx_code);
extern enum rtx_code signed_condition (enum rtx_code);
+extern rtx_code bit_and_conditions (rtx_code, rtx_code, machine_mode);
+extern rtx_code bit_ior_conditions (rtx_code, rtx_code, machine_mode);
extern void mark_jump_label (rtx, rtx_insn *, int);
/* Return true if integer comparison operator CODE interprets its operands
Index: gcc/jump.c
===
--- gcc/jump.c 2019-07-15 16:22:55.342699887 +0100
+++ gcc/jump.c 2019-07-15 16:24:30.685937855 +0100
@@ -138,13 +138,28 @@ #define CASE(CODE, ORDER, SIGNEDNESS, TR
}
/* Return the comparison code that implements FLAGS_* bitmask FLAGS.
+ If MODE is not VOIDmode, it gives the mode of the values being compared.
+
Assert on failure if FORCE, otherwise return UNKNOWN. */
static rtx_code
-flags_to_condition (unsigned int flags, bool force)
+flags_to_condition (unsigned int flags, bool force,
+ machine_mode mode = VOIDmode)
{
+ unsigned int order_mask = FLAGS_ORDER;
+ if (mode != VOIDmode)
+{
+ if (!HONOR_NANS (mode))
+ {
+ flags |= FLAGS_TRAP_NANS;
+ order_mask &= ~FLAGS_UNORDERED;
+ }
+ else if (!HONOR_SNANS (mode))
+ flags |= FLAGS_TRAP_SNANS;
+}
+
#define TEST(CODE, ORDER, SIGNEDNESS, TRAPS) \
- if (((flags ^ (ORDER)) & FLAGS_ORDER) == 0 \
+ if (((flags ^ (ORDER)) & order_mask) == 0\
&& (FLAGS_##SIGNEDNESS == 0 \
|| ((FLAGS_##SIGNEDNESS ^ flags) & FLAGS_SIGNEDNESS) == 0)\
&& (FLAGS_##TRAPS & ~flags & FLAGS_TRAPS) == 0) \
@@ -722,6 +737,33 @@ comparison_dominates_p (enum rtx_code co
return (((flags1 | flags2) & FLAGS_SIGNEDNESS) != FLAGS_SIGNEDNESS
&& (flags1 & ~flags2 & FLAGS_ORDER) == 0);
}
+
+/* Return the comparison code that tests whether CODE1 | CODE2 is
+ true for mode MODE. Return UNKNOWN if no such comparison exists.
+ The result can trap whenever either CODE1 or CODE2 traps. */
+
+rtx_code
+bit_ior_conditions (rtx_code code1, rtx_code code2, machine_mode mode)
+{
+ unsigned int flags1 = condition_to_flags (code1);
+ unsigned int flags2 = condition_to_flags (code2);
+ unsigned int flags = flags1 | flags2;
+ return flags_to_condition (flags, false, mode);
+}
+
+/* Return the comparison code that tests whether CODE1 & CODE2 is
+ true for mode MODE. Return UNKNOWN if no such comparison exists.
+ The result can trap whenever either CODE1 or CODE2 traps. */
+
+rtx_code
+bit_and_conditions (rtx_code code1, rtx_code code2, machine_mode mode)
+{
+ unsigned int flags1 = condition_to_flags (code1);
+ unsigned int flags2 = condition_to_flags (code2);
+ unsigned int flags = ((flags1 & flags2 & FLAGS_ORDER)
+ | ((flags1 | flags2) & ~FLAGS_ORDER));
+ return flags_to_condition (flags, false, mode);
+}
/* Return 1 if INSN is an unconditional jump and nothing else. */
Index: gcc/simplify-rtx.c
===
--- gcc/simplify-rtx.c 2019-07-12 09:14:06.0 +0100
+++ gcc/simplify-rtx.c 2019-07-15 16:24:30.689937823 +0100
@@ -2889,6 +2889,20 @@ simplify_binary_operation_1 (enum rtx_co
}
}
+
Implement more rtx vector folds on variable-length vectors
This patch extends the tree-level folding of variable-length vectors
so that it can also be used on rtxes. The first step is to move
the tree_vector_builder new_unary/binary_operator routines to the
parent vector_builder class (which in turn means adding a new
template parameter). The second step is to make simplify-rtx.c
use a direct rtx analogue of the VECTOR_CST handling in fold-const.c.
Tested on aarch64-linux-gnu, aarch64_be-elf and x86_64-linux-gnu.
OK to install?
Richard
2019-07-11 Richard Sandiford
gcc/
* vector-builder.h (vector_builder): Add a shape template parameter.
(vector_builder::new_unary_operation): New function, generalizing
the old tree_vector_builder function.
(vector_builder::new_binary_operation): Likewise.
(vector_builder::binary_encoded_nelts): Likewise.
* int-vector-builder.h (int_vector_builder): Update template
parameters to vector_builder.
(int_vector_builder::shape_nelts): New function.
* rtx-vector-builder.h (rtx_vector_builder): Update template
parameters to vector_builder.
(rtx_vector_builder::shape_nelts): New function.
(rtx_vector_builder::nelts_of): Likewise.
(rtx_vector_builder::npatterns_of): Likewise.
(rtx_vector_builder::nelts_per_pattern_of): Likewise.
* tree-vector-builder.h (tree_vector_builder): Update template
parameters to vector_builder.
(tree_vector_builder::shape_nelts): New function.
(tree_vector_builder::nelts_of): Likewise.
(tree_vector_builder::npatterns_of): Likewise.
(tree_vector_builder::nelts_per_pattern_of): Likewise.
* tree-vector-builder.c (tree_vector_builder::new_unary_operation)
(tree_vector_builder::new_binary_operation): Delete.
(tree_vector_builder::binary_encoded_nelts): Likewise.
* simplify-rtx.c (distributes_over_addition_p): New function.
(simplify_const_unary_operation)
(simplify_const_binary_operation): Generalize handling of vector
constants to include variable-length vectors.
(test_vector_ops_series): Add more tests.
Index: gcc/vector-builder.h
===
--- gcc/vector-builder.h2019-06-07 08:39:43.126344672 +0100
+++ gcc/vector-builder.h2019-07-11 08:55:03.187049079 +0100
@@ -45,8 +45,11 @@ #define GCC_VECTOR_BUILDER_H
variable-length vectors. finalize () then canonicalizes the encoding
to a simpler form if possible.
- The derived class Derived provides this functionality for specific Ts.
- Derived needs to provide the following interface:
+ Shape is the type that specifies the number of elements in the vector
+ and (where relevant) the type of each element.
+
+ The derived class Derived provides the functionality of this class
+ for specific Ts. Derived needs to provide the following interface:
bool equal_p (T elt1, T elt2) const;
@@ -82,9 +85,30 @@ #define GCC_VECTOR_BUILDER_H
Record that ELT2 is being elided, given that ELT1_PTR points to
the last encoded element for the containing pattern. This is
- again provided for TREE_OVERFLOW handling. */
+ again provided for TREE_OVERFLOW handling.
+
+ static poly_uint64 shape_nelts (Shape shape);
+
+ Return the number of elements in SHAPE.
+
+The class provides additional functionality for the case in which
+T can describe a vector constant as well as an individual element.
+This functionality requires:
+
+ static poly_uint64 nelts_of (T x);
+
+ Return the number of elements in vector constant X.
+
+ static unsigned int npatterns_of (T x);
+
+ Return the number of patterns used to encode vector constant X.
+
+ static unsigned int nelts_per_pattern_of (T x);
-template
+ Return the number of elements used to encode each pattern
+ in vector constant X. */
+
+template
class vector_builder : public auto_vec
{
public:
@@ -101,8 +125,13 @@ #define GCC_VECTOR_BUILDER_H
bool operator == (const Derived &) const;
bool operator != (const Derived &x) const { return !operator == (x); }
+ bool new_unary_operation (Shape, T, bool);
+ bool new_binary_operation (Shape, T, T, bool);
+
void finalize ();
+ static unsigned int binary_encoded_nelts (T, T);
+
protected:
void new_vector (poly_uint64, unsigned int, unsigned int);
void reshape (unsigned int, unsigned int);
@@ -121,16 +150,16 @@ #define GCC_VECTOR_BUILDER_H
unsigned int m_nelts_per_pattern;
};
-template
+template
inline const Derived *
-vector_builder::derived () const
+vector_builder::derived () const
{
return static_cast (this);
}
-template
+template
inline
-vector_builder::vector_builder ()
+vector_builder::vector_builder ()
: m_full_nelts (0),
m_npatterns (0),
m_nelts_per_pattern (0)
@@ -140,18 +169,18 @@ vector_builder::vector_build
