@@ -236,6 +236,7 @@ static rtx arm_trampoline_adjust_address (rtx);
static rtx arm_pic_static_addr (rtx orig, rtx reg);
static bool cortex_a9_sched_adjust_cost (rtx, rtx, rtx, int *);
static bool xscale_sched_adjust_cost (rtx, rtx, rtx, int *);
+static unsigned int arm_units_per_simd_word (enum machine_mode);
/* Table of machine attributes. */
@@ -363,6 +364,8 @@ static const struct attribute_spec arm_attribute_table[] =
#define TARGET_SHIFT_TRUNCATION_MASK arm_shift_truncation_mask
#undef TARGET_VECTOR_MODE_SUPPORTED_P
#define TARGET_VECTOR_MODE_SUPPORTED_P arm_vector_mode_supported_p
+#undef TARGET_VECTORIZE_UNITS_PER_SIMD_WORD
+#define TARGET_VECTORIZE_UNITS_PER_SIMD_WORD arm_units_per_simd_word
#undef TARGET_MACHINE_DEPENDENT_REORG
#define TARGET_MACHINE_DEPENDENT_REORG arm_reorg
@@ -21869,6 +21872,17 @@ arm_vector_mode_supported_p (enum machine_mode mode)
return false;
}
+/* Use the option -mvectorize-with-neon-quad to override the use of doubleword
+ registers when autovectorizing for Neon, at least until multiple vector
+ widths are supported properly by the middle-end. */
+
+static unsigned int
+arm_units_per_simd_word (enum machine_mode mode ATTRIBUTE_UNUSED)
+{
+ return (TARGET_NEON
+ ? (TARGET_NEON_VECTORIZE_QUAD ? 16 : 8) : UNITS_PER_WORD);
+}
+
/* Implements target hook small_register_classes_for_mode_p. */
bool
arm_small_register_classes_for_mode_p (enum machine_mode mode ATTRIBUTE_UNUSED)
@@ -580,12 +580,6 @@ extern int arm_arch_hwdiv;
#define UNITS_PER_WORD 4
-/* Use the option -mvectorize-with-neon-quad to override the use of doubleword
- registers when autovectorizing for Neon, at least until multiple vector
- widths are supported properly by the middle-end. */
-#define UNITS_PER_SIMD_WORD(MODE) \
- (TARGET_NEON ? (TARGET_NEON_VECTORIZE_QUAD ? 16 : 8) : UNITS_PER_WORD)
-
/* True if natural alignment is used for doubleword types. */
#define ARM_DOUBLEWORD_ALIGN TARGET_AAPCS_BASED
@@ -50,7 +50,6 @@ extern bool x86_extended_QIreg_mentioned_p (rtx);
extern bool x86_extended_reg_mentioned_p (rtx);
extern bool x86_maybe_negate_const_int (rtx *, enum machine_mode);
extern enum machine_mode ix86_cc_mode (enum rtx_code, rtx, rtx);
-extern unsigned int ix86_units_per_simd_word (enum machine_mode);
extern int avx_vpermilp_parallel (rtx par, enum machine_mode mode);
extern int avx_vperm2f128_parallel (rtx par, enum machine_mode mode);
@@ -32341,7 +32341,7 @@ has_dispatch (rtx insn, int action)
/* ??? No autovectorization into MMX or 3DNOW until we can reliably
place emms and femms instructions. */
-unsigned int
+static unsigned int
ix86_units_per_simd_word (enum machine_mode mode)
{
/* Disable double precision vectorizer if needed. */
@@ -32609,6 +32609,9 @@ ix86_units_per_simd_word (enum machine_mode mode)
#undef TARGET_VECTORIZE_BUILTIN_VEC_PERM_OK
#define TARGET_VECTORIZE_BUILTIN_VEC_PERM_OK \
ix86_vectorize_builtin_vec_perm_ok
+#undef TARGET_VECTORIZE_UNITS_PER_SIMD_WORD
+#define TARGET_VECTORIZE_UNITS_PER_SIMD_WORD \
+ ix86_units_per_simd_word
#undef TARGET_SET_CURRENT_FUNCTION
#define TARGET_SET_CURRENT_FUNCTION ix86_set_current_function
@@ -1033,8 +1033,6 @@ enum target_cpu_default
|| (MODE) == V2SImode || (MODE) == SImode \
|| (MODE) == V4HImode || (MODE) == V8QImode)
-#define UNITS_PER_SIMD_WORD(MODE) ix86_units_per_simd_word (MODE)
-
#define VALID_DFP_MODE_P(MODE) \
((MODE) == SDmode || (MODE) == DDmode || (MODE) == TDmode)
@@ -11140,6 +11140,14 @@ mips_scalar_mode_supported_p (enum machine_mode mode)
return default_scalar_mode_supported_p (mode);
}
+/* Implement TARGET_VECTORIZE_UNITS_PER_SIMD_WORD. */
+
+static bool
+mips_units_per_simd_word (enum machine_mode mode ATTRIBUTE_UNUSED)
+{
+ return TARGET_PAIRED_SINGLE_FLOAT ? 8 : UNITS_PER_WORD;
+}
+
/* Implement TARGET_INIT_LIBFUNCS. */
#include "config/gofast.h"
@@ -16506,6 +16514,9 @@ mips_shift_truncation_mask (enum machine_mode mode)
#undef TARGET_SCALAR_MODE_SUPPORTED_P
#define TARGET_SCALAR_MODE_SUPPORTED_P mips_scalar_mode_supported_p
+#undef TARGET_VECTORIZE_UNITS_PER_SIMD_WORD
+#define TARGET_VECTORIZE_UNITS_PER_SIMD_WORD mips_units_per_simd_word
+
#undef TARGET_INIT_BUILTINS
#define TARGET_INIT_BUILTINS mips_init_builtins
#undef TARGET_EXPAND_BUILTIN
@@ -1328,9 +1328,6 @@ enum mips_code_readable_setting {
/* The number of bytes in a double. */
#define UNITS_PER_DOUBLE (TYPE_PRECISION (double_type_node) / BITS_PER_UNIT)
-#define UNITS_PER_SIMD_WORD(MODE) \
- (TARGET_PAIRED_SINGLE_FLOAT ? 8 : UNITS_PER_WORD)
-
/* Set the sizes of the core types. */
#define SHORT_TYPE_SIZE 16
#define INT_TYPE_SIZE 32
@@ -3570,6 +3570,18 @@ rs6000_builtin_vectorization_cost (enum vect_cost_for_stmt type_of_cost,
}
}
+/* Implement targetm.vectorize.units_per_simd_word. */
+
+static int
+rs6000_units_per_simd_word (enum machine_mode mode ATTRIBUTE_UNUSED)
+{
+ return (TARGET_VSX ? UNITS_PER_VSX_WORD
+ : (TARGET_ALTIVEC ? UNITS_PER_ALTIVEC_WORD
+ : (TARGET_SPE ? UNITS_PER_SPE_WORD
+ : (TARGET_PAIRED_FLOAT ? UNITS_PER_PAIRED_WORD
+ : UNITS_PER_WORD))));
+}
+
/* Handle generic options of the form -mfoo=yes/no.
NAME is the option name.
VALUE is the option value.
@@ -1150,13 +1150,6 @@ extern unsigned rs6000_pointer_size;
#define PAIRED_VECTOR_MODE(MODE) \
((MODE) == V2SFmode)
-#define UNITS_PER_SIMD_WORD(MODE) \
- (TARGET_VSX ? UNITS_PER_VSX_WORD \
- : (TARGET_ALTIVEC ? UNITS_PER_ALTIVEC_WORD \
- : (TARGET_SPE ? UNITS_PER_SPE_WORD \
- : (TARGET_PAIRED_FLOAT ? UNITS_PER_PAIRED_WORD \
- : UNITS_PER_WORD))))
-
/* Value is TRUE if hard register REGNO can hold a value of
machine-mode MODE. */
#define HARD_REGNO_MODE_OK(REGNO, MODE) \
@@ -434,6 +434,7 @@ static bool sparc_can_eliminate (const int, const int);
static const char *sparc_mangle_type (const_tree);
#endif
static void sparc_trampoline_init (rtx, tree, rtx);
+static bool sparc_units_per_simd_word (enum machine_mode);
#ifdef SUBTARGET_ATTRIBUTE_TABLE
/* Table of valid machine attributes. */
@@ -571,6 +572,9 @@ static bool fpu_option_set = false;
#undef TARGET_VECTOR_MODE_SUPPORTED_P
#define TARGET_VECTOR_MODE_SUPPORTED_P sparc_vector_mode_supported_p
+#undef TARGET_VECTORIZE_UNITS_PER_SIMD_WORD
+#define TARGET_VECTORIZE_UNITS_PER_SIMD_WORD sparc_units_per_simd_word
+
#undef TARGET_DWARF_HANDLE_FRAME_UNSPEC
#define TARGET_DWARF_HANDLE_FRAME_UNSPEC sparc_dwarf_handle_frame_unspec
@@ -6233,6 +6237,14 @@ sparc_vector_mode_supported_p (enum machine_mode mode)
return TARGET_VIS && VECTOR_MODE_P (mode) ? true : false;
}
+/* Implement the TARGET_VECTORIZE_UNITS_PER_SIMD_WORD target hook. */
+
+static bool
+sparc_units_per_simd_word (enum machine_mode mode ATTRIBUTE_UNUSED)
+{
+ return TARGET_VIS ? 8 : UNITS_PER_WORD;
+}
+
/* Return the string to output an unconditional branch to LABEL, which is
the operand number of the label.
@@ -607,8 +607,6 @@ extern struct sparc_cpu_select sparc_select[];
#define MIN_UNITS_PER_WORD 4
#endif
-#define UNITS_PER_SIMD_WORD(MODE) (TARGET_VIS ? 8 : UNITS_PER_WORD)
-
/* Now define the sizes of the C data types. */
#define SHORT_TYPE_SIZE 16
@@ -949,12 +949,6 @@ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
#define HAS_LONG_UNCOND_BRANCH 0
#endif
-/* By default, only attempt to parallelize bitwise operations, and
- possibly adds/subtracts using bit-twiddling. */
-#ifndef UNITS_PER_SIMD_WORD
-#define UNITS_PER_SIMD_WORD(MODE) UNITS_PER_WORD
-#endif
-
/* Determine whether __cxa_atexit, rather than atexit, is used to
register C++ destructors for local statics and global objects. */
#ifndef DEFAULT_USE_CXA_ATEXIT
@@ -995,13 +995,6 @@ Minimum number of units in a word. If this is undefined, the default is
smallest value that @code{UNITS_PER_WORD} can have at run-time.
@end defmac
-@defmac UNITS_PER_SIMD_WORD (@var{mode})
-Number of units in the vectors that the vectorizer can produce for
-scalar mode @var{mode}. The default is equal to @code{UNITS_PER_WORD},
-because the vectorizer can do some transformations even in absence of
-specialized @acronym{SIMD} hardware.
-@end defmac
-
@defmac POINTER_SIZE
Width of a pointer, in bits. You must specify a value no wider than the
width of @code{Pmode}. If it is not equal to the width of @code{Pmode},
@@ -5765,6 +5758,13 @@ the elements in the vectors should be of type @var{type}. @var{is_packed}
parameter is true if the memory access is defined in a packed struct.
@end deftypefn
+@deftypefn {Target Hook} {unsigned int} TARGET_VECTORIZE_UNITS_PER_SIMD_WORD (enum machine_mode @var{mode})
+This hook should return th number of units in the vectors that the
+vectorizer can produce for scalar mode @var{mode}. The default is
+equal to @code{UNITS_PER_WORD}, because the vectorizer can do some
+transformations even in absence of specialized @acronym{SIMD} hardware.
+@end deftypefn
+
@node Anchored Addresses
@section Anchored Addresses
@cindex anchored addresses
@@ -995,13 +995,6 @@ Minimum number of units in a word. If this is undefined, the default is
smallest value that @code{UNITS_PER_WORD} can have at run-time.
@end defmac
-@defmac UNITS_PER_SIMD_WORD (@var{mode})
-Number of units in the vectors that the vectorizer can produce for
-scalar mode @var{mode}. The default is equal to @code{UNITS_PER_WORD},
-because the vectorizer can do some transformations even in absence of
-specialized @acronym{SIMD} hardware.
-@end defmac
-
@defmac POINTER_SIZE
Width of a pointer, in bits. You must specify a value no wider than the
width of @code{Pmode}. If it is not equal to the width of @code{Pmode},
@@ -5765,6 +5758,13 @@ the elements in the vectors should be of type @var{type}. @var{is_packed}
parameter is true if the memory access is defined in a packed struct.
@end deftypefn
+@hook TARGET_VECTORIZE_UNITS_PER_SIMD_WORD
+This hook should return th number of units in the vectors that the
+vectorizer can produce for scalar mode @var{mode}. The default is
+equal to @code{UNITS_PER_WORD}, because the vectorizer can do some
+transformations even in absence of specialized @acronym{SIMD} hardware.
+@end deftypefn
+
@node Anchored Addresses
@section Anchored Addresses
@cindex anchored addresses
@@ -715,7 +715,7 @@ extern void fancy_abort (const char *, int, const char *) ATTRIBUTE_NORETURN;
ALLOCATE_INITIAL_VALUE LEGITIMIZE_ADDRESS FRAME_POINTER_REQUIRED \
CAN_ELIMINATE TRAMPOLINE_TEMPLATE INITIALIZE_TRAMPOLINE \
TRAMPOLINE_ADJUST_ADDRESS STATIC_CHAIN STATIC_CHAIN_INCOMING \
- RETURN_POPS_ARGS
+ RETURN_POPS_ARGS UNITS_PER_SIMD_WORD
/* Other obsolete target macros, or macros that used to be in target
headers and were not used, and may be obsolete or may never have
@@ -880,6 +880,14 @@ DEFHOOK
(enum machine_mode mode, const_tree type, int misalignment, bool is_packed),
default_builtin_support_vector_misalignment)
+/* Return units per SIMD word. */
+DEFHOOK
+(units_per_simd_word,
+ "",
+ unsigned int,
+ (enum machine_mode mode),
+ default_units_per_simd_word)
+
HOOK_VECTOR_END (vectorize)
#undef HOOK_PREFIX
@@ -984,6 +984,15 @@ default_builtin_support_vector_misalignment (enum machine_mode mode,
return false;
}
+/* By default, only attempt to parallelize bitwise operations, and
+ possibly adds/subtracts using bit-twiddling. */
+
+unsigned int
+default_units_per_simd_word (enum machine_mode mode ATTRIBUTE_UNUSED)
+{
+ return UNITS_PER_WORD;
+}
+
/* Determine whether or not a pointer mode is valid. Assume defaults
of ptr_mode or Pmode - can be overridden. */
bool
@@ -86,6 +86,7 @@ extern bool
default_builtin_support_vector_misalignment (enum machine_mode mode,
const_tree,
int, bool);
+extern unsigned int default_units_per_simd_word (enum machine_mode mode);
/* These are here, and not in hooks.[ch], because not all users of
hooks.h include tm.h, and thus we don't have CUMULATIVE_ARGS. */
@@ -126,9 +126,10 @@ along with GCC; see the file COPYING3. If not see
Target modeling:
=================
Currently the only target specific information that is used is the
- size of the vector (in bytes) - "UNITS_PER_SIMD_WORD". Targets that can
- support different sizes of vectors, for now will need to specify one value
- for "UNITS_PER_SIMD_WORD". More flexibility will be added in the future.
+ size of the vector (in bytes) - "TARGET_VECTORIZE_UNITS_PER_SIMD_WORD".
+ Targets that can support different sizes of vectors, for now will need
+ to specify one value for "TARGET_VECTORIZE_UNITS_PER_SIMD_WORD". More
+ flexibility will be added in the future.
Since we only vectorize operations which vector form can be
expressed using existing tree codes, to verify that an operation is
@@ -4675,7 +4675,8 @@ get_vectype_for_scalar_type (tree scalar_type)
int nunits;
tree vectype;
- if (nbytes == 0 || nbytes >= UNITS_PER_SIMD_WORD (inner_mode))
+ if (nbytes == 0
+ || (nbytes >= targetm.vectorize.units_per_simd_word (inner_mode)))
return NULL_TREE;
/* We can't build a vector type of elements with alignment bigger than
@@ -4691,9 +4692,9 @@ get_vectype_for_scalar_type (tree scalar_type)
&& GET_MODE_BITSIZE (inner_mode) != TYPE_PRECISION (scalar_type))
return NULL_TREE;
- /* FORNOW: Only a single vector size per mode (UNITS_PER_SIMD_WORD)
- is expected. */
- nunits = UNITS_PER_SIMD_WORD (inner_mode) / nbytes;
+ /* FORNOW: Only a single vector size per mode
+ (TARGET_VECTORIZE_UNITS_PER_SIMD_WORD) is expected. */
+ nunits = targetm.vectorize.units_per_simd_word (inner_mode) / nbytes;
vectype = build_vector_type (scalar_type, nunits);
if (vect_print_dump_info (REPORT_DETAILS))