From 2f482a07365d9f4a94a56edd13b7f01b8f78b5a0 Mon Sep 17 00:00:00 2001
From: Andre Vieira <andre.simoesdiasvieira@arm.com>
Date: Mon, 5 Jun 2023 17:53:10 +0100
Subject: [PATCH] internal-fn,vect: Refactor widen_plus as internal_fn
DEF_INTERNAL_WIDENING_OPTAB_FN and DEF_INTERNAL_NARROWING_OPTAB_FN
are like DEF_INTERNAL_SIGNED_OPTAB_FN and DEF_INTERNAL_OPTAB_FN
respectively. With the exception that they provide convenience wrappers
for a single vector to vector conversion, a hi/lo split or an even/odd
split. Each definition for <NAME> will require either signed optabs
named <UOPTAB> and <SOPTAB> (for widening) or a single <OPTAB> (for
narrowing) for each of the five functions it creates.
For example, for widening addition the
DEF_INTERNAL_WIDENING_OPTAB_FN will create five internal functions:
IFN_VEC_WIDEN_PLUS, IFN_VEC_WIDEN_PLUS_HI, IFN_VEC_WIDEN_PLUS_LO,
IFN_VEC_WIDEN_PLUS_EVEN and IFN_VEC_WIDEN_PLUS_ODD. Each requiring two
optabs, one for signed and one for unsigned.
Aarch64 implements the hi/lo split optabs:
IFN_VEC_WIDEN_PLUS_HI -> vec_widen_<su>add_hi_<mode> -> (u/s)addl2
IFN_VEC_WIDEN_PLUS_LO -> vec_widen_<su>add_lo_<mode> -> (u/s)addl
This gives the same functionality as the previous
WIDEN_PLUS/WIDEN_MINUS tree codes which are expanded into
VEC_WIDEN_PLUS_LO, VEC_WIDEN_PLUS_HI.
2023-06-05 Andre Vieira <andre.simoesdiasvieira@arm.com>
Joel Hutton <joel.hutton@arm.com>
Tamar Christina <tamar.christina@arm.com>
gcc/ChangeLog:
* config/aarch64/aarch64-simd.md (vec_widen_<su>addl_lo_<mode>): Rename
this ...
(vec_widen_<su>add_lo_<mode>): ... to this.
(vec_widen_<su>addl_hi_<mode>): Rename this ...
(vec_widen_<su>add_hi_<mode>): ... to this.
(vec_widen_<su>subl_lo_<mode>): Rename this ...
(vec_widen_<su>sub_lo_<mode>): ... to this.
(vec_widen_<su>subl_hi_<mode>): Rename this ...
(vec_widen_<su>sub_hi_<mode>): ...to this.
* doc/generic.texi: Document new IFN codes.
* internal-fn.cc (lookup_hilo_internal_fn): Add lookup function.
(commutative_binary_fn_p): Add widen_plus fn's.
(widening_fn_p): New function.
(narrowing_fn_p): New function.
(direct_internal_fn_optab): Change visibility.
* internal-fn.def (DEF_INTERNAL_WIDENING_OPTAB_FN): Macro to define an
internal_fn that expands into multiple internal_fns for widening.
(IFN_VEC_WIDEN_PLUS, IFN_VEC_WIDEN_PLUS_HI, IFN_VEC_WIDEN_PLUS_LO,
IFN_VEC_WIDEN_PLUS_EVEN, IFN_VEC_WIDEN_PLUS_ODD,
IFN_VEC_WIDEN_MINUS, IFN_VEC_WIDEN_MINUS_HI,
IFN_VEC_WIDEN_MINUS_LO, IFN_VEC_WIDEN_MINUS_ODD,
IFN_VEC_WIDEN_MINUS_EVEN): Define widening plus,minus functions.
* internal-fn.h (direct_internal_fn_optab): Declare new prototype.
(lookup_hilo_internal_fn): Likewise.
(widening_fn_p): Likewise.
(Narrowing_fn_p): Likewise.
* optabs.cc (commutative_optab_p): Add widening plus optabs.
* optabs.def (OPTAB_D): Define widen add, sub optabs.
* tree-vect-patterns.cc (vect_recog_widen_op_pattern): Support
patterns with a hi/lo or even/odd split.
(vect_recog_sad_pattern): Refactor to use new IFN codes.
(vect_recog_widen_plus_pattern): Likewise.
(vect_recog_widen_minus_pattern): Likewise.
(vect_recog_average_pattern): Likewise.
* tree-vect-stmts.cc (vectorizable_conversion): Add support for
_HILO IFNs.
(supportable_widening_operation): Likewise.
* tree.def (WIDEN_SUM_EXPR): Update example to use new IFNs.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/vect-widen-add.c: Test that new
IFN_VEC_WIDEN_PLUS is being used.
* gcc.target/aarch64/vect-widen-sub.c: Test that new
IFN_VEC_WIDEN_MINUS is being used.
---
gcc/config/aarch64/aarch64-simd.md | 8 +-
gcc/doc/generic.texi | 90 +++++++++++++++++-
gcc/internal-fn.cc | 95 ++++++++++++++++++-
gcc/internal-fn.def | 34 +++++++
gcc/internal-fn.h | 9 ++
gcc/optabs.cc | 12 ++-
gcc/optabs.def | 20 ++++
.../gcc.target/aarch64/vect-widen-add.c | 4 +-
.../gcc.target/aarch64/vect-widen-sub.c | 4 +-
gcc/tree-vect-patterns.cc | 65 +++++++++----
gcc/tree-vect-stmts.cc | 70 +++++++++++---
gcc/tree.def | 11 ++-
12 files changed, 375 insertions(+), 47 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 9307a573cefd..a567f016b354 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -4698,7 +4698,7 @@
[(set_attr "type" "neon_<ADDSUB:optab>_long")]
)
-(define_expand "vec_widen_<su>addl_lo_<mode>"
+(define_expand "vec_widen_<su>add_lo_<mode>"
[(match_operand:<VWIDE> 0 "register_operand")
(ANY_EXTEND:<VWIDE> (match_operand:VQW 1 "register_operand"))
(ANY_EXTEND:<VWIDE> (match_operand:VQW 2 "register_operand"))]
@@ -4710,7 +4710,7 @@
DONE;
})
-(define_expand "vec_widen_<su>addl_hi_<mode>"
+(define_expand "vec_widen_<su>add_hi_<mode>"
[(match_operand:<VWIDE> 0 "register_operand")
(ANY_EXTEND:<VWIDE> (match_operand:VQW 1 "register_operand"))
(ANY_EXTEND:<VWIDE> (match_operand:VQW 2 "register_operand"))]
@@ -4722,7 +4722,7 @@
DONE;
})
-(define_expand "vec_widen_<su>subl_lo_<mode>"
+(define_expand "vec_widen_<su>sub_lo_<mode>"
[(match_operand:<VWIDE> 0 "register_operand")
(ANY_EXTEND:<VWIDE> (match_operand:VQW 1 "register_operand"))
(ANY_EXTEND:<VWIDE> (match_operand:VQW 2 "register_operand"))]
@@ -4734,7 +4734,7 @@
DONE;
})
-(define_expand "vec_widen_<su>subl_hi_<mode>"
+(define_expand "vec_widen_<su>sub_hi_<mode>"
[(match_operand:<VWIDE> 0 "register_operand")
(ANY_EXTEND:<VWIDE> (match_operand:VQW 1 "register_operand"))
(ANY_EXTEND:<VWIDE> (match_operand:VQW 2 "register_operand"))]
diff --git a/gcc/doc/generic.texi b/gcc/doc/generic.texi
index 8b2882da4fe7..5e36dac2b1a1 100644
--- a/gcc/doc/generic.texi
+++ b/gcc/doc/generic.texi
@@ -1811,10 +1811,16 @@ a value from @code{enum annot_expr_kind}, the third is an @code{INTEGER_CST}.
@tindex VEC_RSHIFT_EXPR
@tindex VEC_WIDEN_MULT_HI_EXPR
@tindex VEC_WIDEN_MULT_LO_EXPR
-@tindex VEC_WIDEN_PLUS_HI_EXPR
-@tindex VEC_WIDEN_PLUS_LO_EXPR
-@tindex VEC_WIDEN_MINUS_HI_EXPR
-@tindex VEC_WIDEN_MINUS_LO_EXPR
+@tindex IFN_VEC_WIDEN_PLUS
+@tindex IFN_VEC_WIDEN_PLUS_HI
+@tindex IFN_VEC_WIDEN_PLUS_LO
+@tindex IFN_VEC_WIDEN_PLUS_EVEN
+@tindex IFN_VEC_WIDEN_PLUS_ODD
+@tindex IFN_VEC_WIDEN_MINUS
+@tindex IFN_VEC_WIDEN_MINUS_HI
+@tindex IFN_VEC_WIDEN_MINUS_LO
+@tindex IFN_VEC_WIDEN_MINUS_EVEN
+@tindex IFN_VEC_WIDEN_MINUS_ODD
@tindex VEC_UNPACK_HI_EXPR
@tindex VEC_UNPACK_LO_EXPR
@tindex VEC_UNPACK_FLOAT_HI_EXPR
@@ -1861,6 +1867,82 @@ vector of @code{N/2} products. In the case of @code{VEC_WIDEN_MULT_LO_EXPR} the
low @code{N/2} elements of the two vector are multiplied to produce the
vector of @code{N/2} products.
+@item IFN_VEC_WIDEN_PLUS
+This internal function represents widening vector addition of two input
+vectors. Its operands are vectors that contain the same number of elements
+(@code{N}) of the same integral type. The result is a vector that contains
+the same amount (@code{N}) of elements, of an integral type whose size is twice
+as wide, as the input vectors. If the current target does not implement the
+corresponding optabs the vectorizer may choose to split it into either a pair
+of @code{IFN_VEC_WIDEN_PLUS_HI} and @code{IFN_VEC_WIDEN_PLUS_LO} or
+@code{IFN_VEC_WIDEN_PLUS_EVEN} and @code{IFN_VEC_WIDEN_PLUS_ODD}, depending
+on what optabs the target implements.
+
+@item IFN_VEC_WIDEN_PLUS_HI
+@itemx IFN_VEC_WIDEN_PLUS_LO
+These internal functions represent widening vector addition of the high and low
+parts of the two input vectors, respectively. Their operands are vectors that
+contain the same number of elements (@code{N}) of the same integral type. The
+result is a vector that contains half as many elements, of an integral type
+whose size is twice as wide. In the case of @code{IFN_VEC_WIDEN_PLUS_HI} the
+high @code{N/2} elements of the two vectors are added to produce the vector of
+@code{N/2} additions. In the case of @code{IFN_VEC_WIDEN_PLUS_LO} the low
+@code{N/2} elements of the two vectors are added to produce the vector of
+@code{N/2} additions.
+
+@item IFN_VEC_WIDEN_PLUS_EVEN
+@itemx IFN_VEC_WIDEN_PLUS_ODD
+These internal functions represent widening vector addition of the even and odd
+elements of the two input vectors, respectively. Their operands are vectors
+that contain the same number of elements (@code{N}) of the same integral type.
+The result is a vector that contains half as many elements, of an integral type
+whose size is twice as wide. In the case of @code{IFN_VEC_WIDEN_PLUS_EVEN} the
+even @code{N/2} elements of the two vectors are added to produce the vector of
+@code{N/2} additions. In the case of @code{IFN_VEC_WIDEN_PLUS_ODD} the odd
+@code{N/2} elements of the two vectors are added to produce the vector of
+@code{N/2} additions.
+
+@item IFN_VEC_WIDEN_MINUS
+This internal function represents widening vector subtraction of two input
+vectors. Its operands are vectors that contain the same number of elements
+(@code{N}) of the same integral type. The result is a vector that contains
+the same amount (@code{N}) of elements, of an integral type whose size is twice
+as wide, as the input vectors. If the current target does not implement the
+corresponding optabs the vectorizer may choose to split it into either a pair
+of @code{IFN_VEC_WIDEN_MINUS_HI} and @code{IFN_VEC_WIDEN_MINUS_LO} or
+@code{IFN_VEC_WIDEN_MINUS_EVEN} and @code{IFN_VEC_WIDEN_MINUS_ODD}, depending
+on what optabs the target implements.
+
+@item IFN_VEC_WIDEN_MINUS_HI
+@itemx IFN_VEC_WIDEN_MINUS_LO
+These internal functions represent widening vector subtraction of the high and
+low parts of the two input vectors, respectively. Their operands are vectors
+that contain the same number of elements (@code{N}) of the same integral type.
+The high/low elements of the second vector are subtracted from the high/low
+elements of the first. The result is a vector that contains half as many
+elements, of an integral type whose size is twice as wide. In the case of
+@code{IFN_VEC_WIDEN_MINUS_HI} the high @code{N/2} elements of the second
+vector are subtracted from the high @code{N/2} of the first to produce the
+vector of @code{N/2} subtractions. In the case of
+@code{IFN_VEC_WIDEN_MINUS_LO} the low @code{N/2} elements of the second
+vector are subtracted from the low @code{N/2} of the first to produce the
+vector of @code{N/2} subtractions.
+
+@item IFN_VEC_WIDEN_MINUS_EVEN
+@itemx IFN_VEC_WIDEN_MINUS_ODD
+These internal functions represent widening vector subtraction of the even and
+odd parts of the two input vectors, respectively. Their operands are vectors
+that contain the same number of elements (@code{N}) of the same integral type.
+The even/odd elements of the second vector are subtracted from the even/odd
+elements of the first. The result is a vector that contains half as many
+elements, of an integral type whose size is twice as wide. In the case of
+@code{IFN_VEC_WIDEN_MINUS_EVEN} the even @code{N/2} elements of the second
+vector are subtracted from the even @code{N/2} of the first to produce the
+vector of @code{N/2} subtractions. In the case of
+@code{IFN_VEC_WIDEN_MINUS_ODD} the odd @code{N/2} elements of the second
+vector are subtracted from the odd @code{N/2} of the first to produce the
+vector of @code{N/2} subtractions.
+
@item VEC_WIDEN_PLUS_HI_EXPR
@itemx VEC_WIDEN_PLUS_LO_EXPR
These nodes represent widening vector addition of the high and low parts of
diff --git a/gcc/internal-fn.cc b/gcc/internal-fn.cc
index 5c9da73ea11f..da9b944dd5d9 100644
--- a/gcc/internal-fn.cc
+++ b/gcc/internal-fn.cc
@@ -90,6 +90,60 @@ lookup_internal_fn (const char *name)
return entry ? *entry : IFN_LAST;
}
+/* Geven an internal_fn IFN that is a widening function, return its
+ corresponding LO and HI internal_fns. */
+
+extern void
+lookup_hilo_internal_fn (internal_fn ifn, internal_fn *lo, internal_fn *hi)
+{
+ gcc_assert (widening_fn_p (ifn));
+
+ switch (ifn)
+ {
+ default:
+ gcc_unreachable ();
+#undef DEF_INTERNAL_FN
+#undef DEF_INTERNAL_WIDENING_OPTAB_FN
+#define DEF_INTERNAL_FN(NAME, FLAGS, TYPE)
+#define DEF_INTERNAL_WIDENING_OPTAB_FN(NAME, F, S, SO, UO, T) \
+ case IFN_##NAME: \
+ *lo = internal_fn (IFN_##NAME##_LO); \
+ *hi = internal_fn (IFN_##NAME##_HI); \
+ break;
+#include "internal-fn.def"
+#undef DEF_INTERNAL_FN
+#undef DEF_INTERNAL_WIDENING_OPTAB_FN
+ }
+}
+
+/* Given an internal_fn IFN that is a widening function, return its
+ corresponding _EVEN and _ODD internal_fns in *EVEN and *ODD. */
+
+extern void
+lookup_evenodd_internal_fn (internal_fn ifn, internal_fn *even,
+ internal_fn *odd)
+{
+ gcc_assert (widening_fn_p (ifn));
+
+ switch (ifn)
+ {
+ default:
+ gcc_unreachable ();
+#undef DEF_INTERNAL_FN
+#undef DEF_INTERNAL_WIDENING_OPTAB_FN
+#define DEF_INTERNAL_FN(NAME, FLAGS, TYPE)
+#define DEF_INTERNAL_WIDENING_OPTAB_FN(NAME, F, S, SO, UO, T) \
+ case IFN_##NAME: \
+ *even = internal_fn (IFN_##NAME##_EVEN); \
+ *odd = internal_fn (IFN_##NAME##_ODD); \
+ break;
+#include "internal-fn.def"
+#undef DEF_INTERNAL_FN
+#undef DEF_INTERNAL_WIDENING_OPTAB_FN
+ }
+}
+
+
/* Fnspec of each internal function, indexed by function number. */
const_tree internal_fn_fnspec_array[IFN_LAST + 1];
@@ -3852,7 +3906,7 @@ multi_vector_optab_supported_p (convert_optab optab, tree_pair types,
/* Return the optab used by internal function FN. */
-static optab
+optab
direct_internal_fn_optab (internal_fn fn, tree_pair types)
{
switch (fn)
@@ -3971,6 +4025,11 @@ commutative_binary_fn_p (internal_fn fn)
case IFN_UBSAN_CHECK_MUL:
case IFN_ADD_OVERFLOW:
case IFN_MUL_OVERFLOW:
+ case IFN_VEC_WIDEN_PLUS:
+ case IFN_VEC_WIDEN_PLUS_LO:
+ case IFN_VEC_WIDEN_PLUS_HI:
+ case IFN_VEC_WIDEN_PLUS_EVEN:
+ case IFN_VEC_WIDEN_PLUS_ODD:
return true;
default:
@@ -4044,6 +4103,37 @@ first_commutative_argument (internal_fn fn)
}
}
+/* Return true if this CODE describes an internal_fn that returns a vector with
+ elements twice as wide as the element size of the input vectors. */
+
+bool
+widening_fn_p (code_helper code)
+{
+ if (!code.is_fn_code ())
+ return false;
+
+ if (!internal_fn_p ((combined_fn) code))
+ return false;
+
+ internal_fn fn = as_internal_fn ((combined_fn) code);
+ switch (fn)
+ {
+ #undef DEF_INTERNAL_WIDENING_OPTAB_FN
+ #define DEF_INTERNAL_WIDENING_OPTAB_FN(NAME, F, S, SO, UO, T) \
+ case IFN_##NAME: \
+ case IFN_##NAME##_HI: \
+ case IFN_##NAME##_LO: \
+ case IFN_##NAME##_EVEN: \
+ case IFN_##NAME##_ODD: \
+ return true;
+ #include "internal-fn.def"
+ #undef DEF_INTERNAL_WIDENING_OPTAB_FN
+
+ default:
+ return false;
+ }
+}
+
/* Return true if IFN_SET_EDOM is supported. */
bool
@@ -4072,6 +4162,8 @@ set_edom_supported_p (void)
expand_##TYPE##_optab_fn (fn, stmt, which_optab); \
}
#include "internal-fn.def"
+#undef DEF_INTERNAL_OPTAB_FN
+#undef DEF_INTERNAL_SIGNED_OPTAB_FN
/* Routines to expand each internal function, indexed by function number.
Each routine has the prototype:
@@ -4080,6 +4172,7 @@ set_edom_supported_p (void)
where STMT is the statement that performs the call. */
static void (*const internal_fn_expanders[]) (internal_fn, gcall *) = {
+
#define DEF_INTERNAL_FN(CODE, FLAGS, FNSPEC) expand_##CODE,
#include "internal-fn.def"
0
diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
index 7fe742c2ae71..3ac9d82aace3 100644
--- a/gcc/internal-fn.def
+++ b/gcc/internal-fn.def
@@ -85,6 +85,21 @@ along with GCC; see the file COPYING3. If not see
says that the function extends the C-level BUILT_IN_<NAME>{,L,LL,IMAX}
group of functions to any integral mode (including vector modes).
+ DEF_INTERNAL_WIDENING_OPTAB_FN is a wrapper that defines five internal
+ functions with DEF_INTERNAL_SIGNED_OPTAB_FN:
+ - one that describes a widening operation with the same number of elements
+ in the output and input vectors,
+ - two that describe a pair of high-low widening operations where the output
+ vectors each have half the number of elements of the input vectors,
+ corresponding to the result of the widening operation on the top half and
+ bottom half, these have the suffixes _HI and _LO,
+ - and two that describe a pair of even-odd widening operations where the
+ output vectors each have half the number of elements of the input vectors,
+ corresponding to the result of the widening operation on the even and odd
+ elements, these have the suffixes _EVEN and _ODD.
+ These five internal functions will require two optabs each, a SIGNED_OPTAB
+ and an UNSIGNED_OTPAB.
+
Each entry must have a corresponding expander of the form:
void expand_NAME (gimple_call stmt)
@@ -123,6 +138,15 @@ along with GCC; see the file COPYING3. If not see
DEF_INTERNAL_OPTAB_FN (NAME, FLAGS, OPTAB, TYPE)
#endif
+#ifndef DEF_INTERNAL_WIDENING_OPTAB_FN
+#define DEF_INTERNAL_WIDENING_OPTAB_FN(NAME, FLAGS, SELECTOR, SOPTAB, UOPTAB, TYPE) \
+ DEF_INTERNAL_SIGNED_OPTAB_FN (NAME, FLAGS, SELECTOR, SOPTAB, UOPTAB, TYPE) \
+ DEF_INTERNAL_SIGNED_OPTAB_FN (NAME ## _LO, FLAGS, SELECTOR, SOPTAB##_lo, UOPTAB##_lo, TYPE) \
+ DEF_INTERNAL_SIGNED_OPTAB_FN (NAME ## _HI, FLAGS, SELECTOR, SOPTAB##_hi, UOPTAB##_hi, TYPE) \
+ DEF_INTERNAL_SIGNED_OPTAB_FN (NAME ## _EVEN, FLAGS, SELECTOR, SOPTAB##_even, UOPTAB##_even, TYPE) \
+ DEF_INTERNAL_SIGNED_OPTAB_FN (NAME ## _ODD, FLAGS, SELECTOR, SOPTAB##_odd, UOPTAB##_odd, TYPE)
+#endif
+
DEF_INTERNAL_OPTAB_FN (MASK_LOAD, ECF_PURE, maskload, mask_load)
DEF_INTERNAL_OPTAB_FN (LOAD_LANES, ECF_CONST, vec_load_lanes, load_lanes)
DEF_INTERNAL_OPTAB_FN (MASK_LOAD_LANES, ECF_PURE,
@@ -315,6 +339,16 @@ DEF_INTERNAL_OPTAB_FN (COMPLEX_ADD_ROT270, ECF_CONST, cadd270, binary)
DEF_INTERNAL_OPTAB_FN (COMPLEX_MUL, ECF_CONST, cmul, binary)
DEF_INTERNAL_OPTAB_FN (COMPLEX_MUL_CONJ, ECF_CONST, cmul_conj, binary)
DEF_INTERNAL_OPTAB_FN (VEC_ADDSUB, ECF_CONST, vec_addsub, binary)
+DEF_INTERNAL_WIDENING_OPTAB_FN (VEC_WIDEN_PLUS,
+ ECF_CONST | ECF_NOTHROW,
+ first,
+ vec_widen_sadd, vec_widen_uadd,
+ binary)
+DEF_INTERNAL_WIDENING_OPTAB_FN (VEC_WIDEN_MINUS,
+ ECF_CONST | ECF_NOTHROW,
+ first,
+ vec_widen_ssub, vec_widen_usub,
+ binary)
DEF_INTERNAL_OPTAB_FN (VEC_FMADDSUB, ECF_CONST, vec_fmaddsub, ternary)
DEF_INTERNAL_OPTAB_FN (VEC_FMSUBADD, ECF_CONST, vec_fmsubadd, ternary)
diff --git a/gcc/internal-fn.h b/gcc/internal-fn.h
index 08922ed42548..8f21068e300d 100644
--- a/gcc/internal-fn.h
+++ b/gcc/internal-fn.h
@@ -20,6 +20,10 @@ along with GCC; see the file COPYING3. If not see
#ifndef GCC_INTERNAL_FN_H
#define GCC_INTERNAL_FN_H
+#include "insn-codes.h"
+#include "insn-opinit.h"
+
+
/* INTEGER_CST values for IFN_UNIQUE function arg-0.
UNSPEC: Undifferentiated UNIQUE.
@@ -112,6 +116,10 @@ internal_fn_name (enum internal_fn fn)
}
extern internal_fn lookup_internal_fn (const char *);
+extern void lookup_hilo_internal_fn (internal_fn, internal_fn *, internal_fn *);
+extern void lookup_evenodd_internal_fn (internal_fn, internal_fn *,
+ internal_fn *);
+extern optab direct_internal_fn_optab (internal_fn, tree_pair);
/* Return the ECF_* flags for function FN. */
@@ -210,6 +218,7 @@ extern bool commutative_binary_fn_p (internal_fn);
extern bool commutative_ternary_fn_p (internal_fn);
extern int first_commutative_argument (internal_fn);
extern bool associative_binary_fn_p (internal_fn);
+extern bool widening_fn_p (code_helper);
extern bool set_edom_supported_p (void);
diff --git a/gcc/optabs.cc b/gcc/optabs.cc
index a12333c7169f..aab6ab6faf24 100644
--- a/gcc/optabs.cc
+++ b/gcc/optabs.cc
@@ -1314,7 +1314,17 @@ commutative_optab_p (optab binoptab)
|| binoptab == smul_widen_optab
|| binoptab == umul_widen_optab
|| binoptab == smul_highpart_optab
- || binoptab == umul_highpart_optab);
+ || binoptab == umul_highpart_optab
+ || binoptab == vec_widen_sadd_optab
+ || binoptab == vec_widen_uadd_optab
+ || binoptab == vec_widen_sadd_hi_optab
+ || binoptab == vec_widen_sadd_lo_optab
+ || binoptab == vec_widen_uadd_hi_optab
+ || binoptab == vec_widen_uadd_lo_optab
+ || binoptab == vec_widen_sadd_even_optab
+ || binoptab == vec_widen_sadd_odd_optab
+ || binoptab == vec_widen_uadd_even_optab
+ || binoptab == vec_widen_uadd_odd_optab);
}
/* X is to be used in mode MODE as operand OPN to BINOPTAB. If we're
diff --git a/gcc/optabs.def b/gcc/optabs.def
index 695f5911b300..d41ed6e1afad 100644
--- a/gcc/optabs.def
+++ b/gcc/optabs.def
@@ -410,6 +410,16 @@ OPTAB_D (vec_widen_ssubl_hi_optab, "vec_widen_ssubl_hi_$a")
OPTAB_D (vec_widen_ssubl_lo_optab, "vec_widen_ssubl_lo_$a")
OPTAB_D (vec_widen_saddl_hi_optab, "vec_widen_saddl_hi_$a")
OPTAB_D (vec_widen_saddl_lo_optab, "vec_widen_saddl_lo_$a")
+OPTAB_D (vec_widen_ssub_optab, "vec_widen_ssub_$a")
+OPTAB_D (vec_widen_ssub_hi_optab, "vec_widen_ssub_hi_$a")
+OPTAB_D (vec_widen_ssub_lo_optab, "vec_widen_ssub_lo_$a")
+OPTAB_D (vec_widen_ssub_odd_optab, "vec_widen_ssub_odd_$a")
+OPTAB_D (vec_widen_ssub_even_optab, "vec_widen_ssub_even_$a")
+OPTAB_D (vec_widen_sadd_optab, "vec_widen_sadd_$a")
+OPTAB_D (vec_widen_sadd_hi_optab, "vec_widen_sadd_hi_$a")
+OPTAB_D (vec_widen_sadd_lo_optab, "vec_widen_sadd_lo_$a")
+OPTAB_D (vec_widen_sadd_odd_optab, "vec_widen_sadd_odd_$a")
+OPTAB_D (vec_widen_sadd_even_optab, "vec_widen_sadd_even_$a")
OPTAB_D (vec_widen_sshiftl_hi_optab, "vec_widen_sshiftl_hi_$a")
OPTAB_D (vec_widen_sshiftl_lo_optab, "vec_widen_sshiftl_lo_$a")
OPTAB_D (vec_widen_umult_even_optab, "vec_widen_umult_even_$a")
@@ -422,6 +432,16 @@ OPTAB_D (vec_widen_usubl_hi_optab, "vec_widen_usubl_hi_$a")
OPTAB_D (vec_widen_usubl_lo_optab, "vec_widen_usubl_lo_$a")
OPTAB_D (vec_widen_uaddl_hi_optab, "vec_widen_uaddl_hi_$a")
OPTAB_D (vec_widen_uaddl_lo_optab, "vec_widen_uaddl_lo_$a")
+OPTAB_D (vec_widen_usub_optab, "vec_widen_usub_$a")
+OPTAB_D (vec_widen_usub_hi_optab, "vec_widen_usub_hi_$a")
+OPTAB_D (vec_widen_usub_lo_optab, "vec_widen_usub_lo_$a")
+OPTAB_D (vec_widen_usub_odd_optab, "vec_widen_usub_odd_$a")
+OPTAB_D (vec_widen_usub_even_optab, "vec_widen_usub_even_$a")
+OPTAB_D (vec_widen_uadd_optab, "vec_widen_uadd_$a")
+OPTAB_D (vec_widen_uadd_hi_optab, "vec_widen_uadd_hi_$a")
+OPTAB_D (vec_widen_uadd_lo_optab, "vec_widen_uadd_lo_$a")
+OPTAB_D (vec_widen_uadd_odd_optab, "vec_widen_uadd_odd_$a")
+OPTAB_D (vec_widen_uadd_even_optab, "vec_widen_uadd_even_$a")
OPTAB_D (vec_addsub_optab, "vec_addsub$a3")
OPTAB_D (vec_fmaddsub_optab, "vec_fmaddsub$a4")
OPTAB_D (vec_fmsubadd_optab, "vec_fmsubadd$a4")
diff --git a/gcc/testsuite/gcc.target/aarch64/vect-widen-add.c b/gcc/testsuite/gcc.target/aarch64/vect-widen-add.c
index 220bd9352a4c..b5a73867e44e 100644
--- a/gcc/testsuite/gcc.target/aarch64/vect-widen-add.c
+++ b/gcc/testsuite/gcc.target/aarch64/vect-widen-add.c
@@ -1,5 +1,5 @@
/* { dg-do run } */
-/* { dg-options "-O3 -save-temps" } */
+/* { dg-options "-O3 -save-temps -fdump-tree-vect-details" } */
#include <stdint.h>
#include <string.h>
@@ -86,6 +86,8 @@ main()
return 0;
}
+/* { dg-final { scan-tree-dump "add new stmt.*VEC_WIDEN_PLUS_LO" "vect" } } */
+/* { dg-final { scan-tree-dump "add new stmt.*VEC_WIDEN_PLUS_HI" "vect" } } */
/* { dg-final { scan-assembler-times {\tuaddl\t} 1} } */
/* { dg-final { scan-assembler-times {\tuaddl2\t} 1} } */
/* { dg-final { scan-assembler-times {\tsaddl\t} 1} } */
diff --git a/gcc/testsuite/gcc.target/aarch64/vect-widen-sub.c b/gcc/testsuite/gcc.target/aarch64/vect-widen-sub.c
index a2bed63affbd..1686c3f2f344 100644
--- a/gcc/testsuite/gcc.target/aarch64/vect-widen-sub.c
+++ b/gcc/testsuite/gcc.target/aarch64/vect-widen-sub.c
@@ -1,5 +1,5 @@
/* { dg-do run } */
-/* { dg-options "-O3 -save-temps" } */
+/* { dg-options "-O3 -save-temps -fdump-tree-vect-details" } */
#include <stdint.h>
#include <string.h>
@@ -86,6 +86,8 @@ main()
return 0;
}
+/* { dg-final { scan-tree-dump "add new stmt.*VEC_WIDEN_MINUS_LO" "vect" } } */
+/* { dg-final { scan-tree-dump "add new stmt.*VEC_WIDEN_MINUS_HI" "vect" } } */
/* { dg-final { scan-assembler-times {\tusubl\t} 1} } */
/* { dg-final { scan-assembler-times {\tusubl2\t} 1} } */
/* { dg-final { scan-assembler-times {\tssubl\t} 1} } */
diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc
index 635ea6ae017e..dc102c919352 100644
--- a/gcc/tree-vect-patterns.cc
+++ b/gcc/tree-vect-patterns.cc
@@ -562,21 +562,30 @@ vect_joust_widened_type (tree type, tree new_type, tree *common_type)
static unsigned int
vect_widened_op_tree (vec_info *vinfo, stmt_vec_info stmt_info, tree_code code,
- tree_code widened_code, bool shift_p,
+ code_helper widened_code, bool shift_p,
unsigned int max_nops,
vect_unpromoted_value *unprom, tree *common_type,
enum optab_subtype *subtype = NULL)
{
/* Check for an integer operation with the right code. */
- gassign *assign = dyn_cast <gassign *> (stmt_info->stmt);
- if (!assign)
+ gimple* stmt = stmt_info->stmt;
+ if (!(is_gimple_assign (stmt) || is_gimple_call (stmt)))
+ return 0;
+
+ code_helper rhs_code;
+ if (is_gimple_assign (stmt))
+ rhs_code = gimple_assign_rhs_code (stmt);
+ else if (is_gimple_call (stmt))
+ rhs_code = gimple_call_combined_fn (stmt);
+ else
return 0;
- tree_code rhs_code = gimple_assign_rhs_code (assign);
- if (rhs_code != code && rhs_code != widened_code)
+ if (rhs_code != code
+ && rhs_code != widened_code)
return 0;
- tree type = TREE_TYPE (gimple_assign_lhs (assign));
+ tree lhs = gimple_get_lhs (stmt);
+ tree type = TREE_TYPE (lhs);
if (!INTEGRAL_TYPE_P (type))
return 0;
@@ -589,7 +598,7 @@ vect_widened_op_tree (vec_info *vinfo, stmt_vec_info stmt_info, tree_code code,
{
vect_unpromoted_value *this_unprom = &unprom[next_op];
unsigned int nops = 1;
- tree op = gimple_op (assign, i + 1);
+ tree op = gimple_arg (stmt, i);
if (i == 1 && TREE_CODE (op) == INTEGER_CST)
{
/* We already have a common type from earlier operands.
@@ -1343,7 +1352,8 @@ vect_recog_sad_pattern (vec_info *vinfo,
/* FORNOW. Can continue analyzing the def-use chain when this stmt in a phi
inside the loop (in case we are analyzing an outer-loop). */
vect_unpromoted_value unprom[2];
- if (!vect_widened_op_tree (vinfo, diff_stmt_vinfo, MINUS_EXPR, WIDEN_MINUS_EXPR,
+ if (!vect_widened_op_tree (vinfo, diff_stmt_vinfo, MINUS_EXPR,
+ IFN_VEC_WIDEN_MINUS,
false, 2, unprom, &half_type))
return NULL;
@@ -1395,14 +1405,16 @@ static gimple *
vect_recog_widen_op_pattern (vec_info *vinfo,
stmt_vec_info last_stmt_info, tree *type_out,
tree_code orig_code, code_helper wide_code,
- bool shift_p, const char *name)
+ bool shift_p, const char *name,
+ optab_subtype *subtype = NULL)
{
gimple *last_stmt = last_stmt_info->stmt;
vect_unpromoted_value unprom[2];
tree half_type;
if (!vect_widened_op_tree (vinfo, last_stmt_info, orig_code, orig_code,
- shift_p, 2, unprom, &half_type))
+ shift_p, 2, unprom, &half_type, subtype))
+
return NULL;
/* Pattern detected. */
@@ -1468,6 +1480,20 @@ vect_recog_widen_op_pattern (vec_info *vinfo,
type, pattern_stmt, vecctype);
}
+static gimple *
+vect_recog_widen_op_pattern (vec_info *vinfo,
+ stmt_vec_info last_stmt_info, tree *type_out,
+ tree_code orig_code, internal_fn wide_ifn,
+ bool shift_p, const char *name,
+ optab_subtype *subtype = NULL)
+{
+ combined_fn ifn = as_combined_fn (wide_ifn);
+ return vect_recog_widen_op_pattern (vinfo, last_stmt_info, type_out,
+ orig_code, ifn, shift_p, name,
+ subtype);
+}
+
+
/* Try to detect multiplication on widened inputs, converting MULT_EXPR
to WIDEN_MULT_EXPR. See vect_recog_widen_op_pattern for details. */
@@ -1481,26 +1507,30 @@ vect_recog_widen_mult_pattern (vec_info *vinfo, stmt_vec_info last_stmt_info,
}
/* Try to detect addition on widened inputs, converting PLUS_EXPR
- to WIDEN_PLUS_EXPR. See vect_recog_widen_op_pattern for details. */
+ to IFN_VEC_WIDEN_PLUS. See vect_recog_widen_op_pattern for details. */
static gimple *
vect_recog_widen_plus_pattern (vec_info *vinfo, stmt_vec_info last_stmt_info,
tree *type_out)
{
+ optab_subtype subtype;
return vect_recog_widen_op_pattern (vinfo, last_stmt_info, type_out,
- PLUS_EXPR, WIDEN_PLUS_EXPR, false,
- "vect_recog_widen_plus_pattern");
+ PLUS_EXPR, IFN_VEC_WIDEN_PLUS,
+ false, "vect_recog_widen_plus_pattern",
+ &subtype);
}
/* Try to detect subtraction on widened inputs, converting MINUS_EXPR
- to WIDEN_MINUS_EXPR. See vect_recog_widen_op_pattern for details. */
+ to IFN_VEC_WIDEN_MINUS. See vect_recog_widen_op_pattern for details. */
static gimple *
vect_recog_widen_minus_pattern (vec_info *vinfo, stmt_vec_info last_stmt_info,
tree *type_out)
{
+ optab_subtype subtype;
return vect_recog_widen_op_pattern (vinfo, last_stmt_info, type_out,
- MINUS_EXPR, WIDEN_MINUS_EXPR, false,
- "vect_recog_widen_minus_pattern");
+ MINUS_EXPR, IFN_VEC_WIDEN_MINUS,
+ false, "vect_recog_widen_minus_pattern",
+ &subtype);
}
/* Function vect_recog_ctz_ffs_pattern
@@ -3078,7 +3108,7 @@ vect_recog_average_pattern (vec_info *vinfo,
vect_unpromoted_value unprom[3];
tree new_type;
unsigned int nops = vect_widened_op_tree (vinfo, plus_stmt_info, PLUS_EXPR,
- WIDEN_PLUS_EXPR, false, 3,
+ IFN_VEC_WIDEN_PLUS, false, 3,
unprom, &new_type);
if (nops == 0)
return NULL;
@@ -6469,6 +6499,7 @@ static vect_recog_func vect_vect_recog_func_ptrs[] = {
{ vect_recog_mask_conversion_pattern, "mask_conversion" },
{ vect_recog_widen_plus_pattern, "widen_plus" },
{ vect_recog_widen_minus_pattern, "widen_minus" },
+ /* These must come after the double widening ones. */
};
const unsigned int NUM_PATTERNS = ARRAY_SIZE (vect_vect_recog_func_ptrs);
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 0fe0d4e7ccb2..7a6b031a9059 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -5051,7 +5051,8 @@ vectorizable_conversion (vec_info *vinfo,
bool widen_arith = (code == WIDEN_PLUS_EXPR
|| code == WIDEN_MINUS_EXPR
|| code == WIDEN_MULT_EXPR
- || code == WIDEN_LSHIFT_EXPR);
+ || code == WIDEN_LSHIFT_EXPR
+ || widening_fn_p (code));
if (!widen_arith
&& !CONVERT_EXPR_CODE_P (code)
@@ -5101,8 +5102,8 @@ vectorizable_conversion (vec_info *vinfo,
gcc_assert (code == WIDEN_MULT_EXPR
|| code == WIDEN_LSHIFT_EXPR
|| code == WIDEN_PLUS_EXPR
- || code == WIDEN_MINUS_EXPR);
-
+ || code == WIDEN_MINUS_EXPR
+ || widening_fn_p (code));
op1 = is_gimple_assign (stmt) ? gimple_assign_rhs2 (stmt) :
gimple_call_arg (stmt, 0);
@@ -12574,26 +12575,69 @@ supportable_widening_operation (vec_info *vinfo,
optab1 = vec_unpacks_sbool_lo_optab;
optab2 = vec_unpacks_sbool_hi_optab;
}
- else
+
+ vec_mode = TYPE_MODE (vectype);
+ if (widening_fn_p (code))
+ {
+ /* If this is an internal fn then we must check whether the target
+ supports either a low-high split or an even-odd split. */
+ internal_fn ifn = as_internal_fn ((combined_fn) code);
+
+ internal_fn lo, hi, even, odd;
+ lookup_hilo_internal_fn (ifn, &lo, &hi);
+ *code1 = as_combined_fn (lo);
+ *code2 = as_combined_fn (hi);
+ optab1 = direct_internal_fn_optab (lo, {vectype, vectype});
+ optab2 = direct_internal_fn_optab (hi, {vectype, vectype});
+
+ /* If we don't support low-high, then check for even-odd. */
+ if (!optab1
+ || (icode1 = optab_handler (optab1, vec_mode)) == CODE_FOR_nothing
+ || !optab2
+ || (icode2 = optab_handler (optab2, vec_mode)) == CODE_FOR_nothing)
+ {
+ lookup_evenodd_internal_fn (ifn, &even, &odd);
+ *code1 = as_combined_fn (even);
+ *code2 = as_combined_fn (odd);
+ optab1 = direct_internal_fn_optab (even, {vectype, vectype});
+ optab2 = direct_internal_fn_optab (odd, {vectype, vectype});
+ }
+ }
+ else if (code.is_tree_code ())
{
- optab1 = optab_for_tree_code (c1, vectype, optab_default);
- optab2 = optab_for_tree_code (c2, vectype, optab_default);
+ if (code == FIX_TRUNC_EXPR)
+ {
+ /* The signedness is determined from output operand. */
+ optab1 = optab_for_tree_code (c1, vectype_out, optab_default);
+ optab2 = optab_for_tree_code (c2, vectype_out, optab_default);
+ }
+ else if (CONVERT_EXPR_CODE_P ((tree_code) code.safe_as_tree_code ())
+ && VECTOR_BOOLEAN_TYPE_P (wide_vectype)
+ && VECTOR_BOOLEAN_TYPE_P (vectype)
+ && TYPE_MODE (wide_vectype) == TYPE_MODE (vectype)
+ && SCALAR_INT_MODE_P (TYPE_MODE (vectype)))
+ {
+ /* If the input and result modes are the same, a different optab
+ is needed where we pass in the number of units in vectype. */
+ optab1 = vec_unpacks_sbool_lo_optab;
+ optab2 = vec_unpacks_sbool_hi_optab;
+ }
+ else
+ {
+ optab1 = optab_for_tree_code (c1, vectype, optab_default);
+ optab2 = optab_for_tree_code (c2, vectype, optab_default);
+ }
+ *code1 = c1;
+ *code2 = c2;
}
if (!optab1 || !optab2)
return false;
- vec_mode = TYPE_MODE (vectype);
if ((icode1 = optab_handler (optab1, vec_mode)) == CODE_FOR_nothing
|| (icode2 = optab_handler (optab2, vec_mode)) == CODE_FOR_nothing)
return false;
- if (code.is_tree_code ())
- {
- *code1 = c1;
- *code2 = c2;
- }
-
if (insn_data[icode1].operand[0].mode == TYPE_MODE (wide_vectype)
&& insn_data[icode2].operand[0].mode == TYPE_MODE (wide_vectype))
diff --git a/gcc/tree.def b/gcc/tree.def
index 90ceeec0b512..b37b0b35927b 100644
--- a/gcc/tree.def
+++ b/gcc/tree.def
@@ -1374,15 +1374,16 @@ DEFTREECODE (DOT_PROD_EXPR, "dot_prod_expr", tcc_expression, 3)
DEFTREECODE (WIDEN_SUM_EXPR, "widen_sum_expr", tcc_binary, 2)
/* Widening sad (sum of absolute differences).
- The first two arguments are of type t1 which should be integer.
- The third argument and the result are of type t2, such that t2 is at least
- twice the size of t1. Like DOT_PROD_EXPR, SAD_EXPR (arg1,arg2,arg3) is
+ The first two arguments are of type t1 which should be a vector of integers.
+ The third argument and the result are of type t2, such that the size of
+ the elements of t2 is at least twice the size of the elements of t1.
+ Like DOT_PROD_EXPR, SAD_EXPR (arg1,arg2,arg3) is
equivalent to:
- tmp = WIDEN_MINUS_EXPR (arg1, arg2)
+ tmp = IFN_VEC_WIDEN_MINUS_EXPR (arg1, arg2)
tmp2 = ABS_EXPR (tmp)
arg3 = PLUS_EXPR (tmp2, arg3)
or:
- tmp = WIDEN_MINUS_EXPR (arg1, arg2)
+ tmp = IFN_VEC_WIDEN_MINUS_EXPR (arg1, arg2)
tmp2 = ABS_EXPR (tmp)
arg3 = WIDEN_SUM_EXPR (tmp2, arg3)
*/
--
GitLab