Jonathan Wright <jonathan.wri...@arm.com> writes:
> Hi,
>
> As subject, this patch declares the Neon vector-tuple types inside the
> compiler instead of in the arm_neon.h header. This is a necessary first
> step before adding corresponding machine modes to the AArch64
> backend.
>
> The vector-tuple types are implemented using a #pragma. This means
> initialization of builtin functions that have vector-tuple types as
> arguments or return values has to be delayed until the #pragma is
> handled.
>
> Bootstrapped and regression tested on aarch64-none-linux-gnu - no
> issues.
>
> Note that this patch series cannot be merged until the following has
> been accepted:
> https://gcc.gnu.org/pipermail/gcc-patches/2021-October/581948.html
>
> Ok for master with this proviso?
>
> Thanks,
> Jonathan
>
> ---
>
> gcc/ChangeLog:
>
> 2021-09-10 Jonathan Wright <jonathan.wri...@arm.com>
>
> * config/aarch64/aarch64-builtins.c (aarch64_init_simd_builtins):
> Factor out main loop to...
> (aarch64_init_simd_builtin_functions): This new function.
> (register_tuple_type): Define.
> (aarch64_scalar_builtin_type_p): Define.
> (handle_arm_neon_h): Define.
> * config/aarch64/aarch64-c.c (aarch64_pragma_aarch64): Handle
> pragma for arm_neon.h.
> * config/aarch64/aarch64-protos.h (aarch64_advsimd_struct_mode_p):
> Declare.
> (handle_arm_neon_h): Likewise.
> * config/aarch64/aarch64.c (aarch64_advsimd_struct_mode_p):
> Remove static modifier.
> * config/aarch64/arm_neon.h (target): Remove Neon vector
> structure type definitions.
OK when the prerequisite you mention is applied, thanks.
Richard
> diff --git a/gcc/config/aarch64/aarch64-builtins.c
> b/gcc/config/aarch64/aarch64-builtins.c
> index
> 1a507ea59142d0b5977b0167abfe9a58a567adf7..27f2dc5ea4337da80f3b84b6a798263e7bd9012e
> 100644
> --- a/gcc/config/aarch64/aarch64-builtins.c
> +++ b/gcc/config/aarch64/aarch64-builtins.c
> @@ -1045,32 +1045,22 @@ aarch64_init_fcmla_laneq_builtins (void)
> }
>
> void
> -aarch64_init_simd_builtins (void)
> +aarch64_init_simd_builtin_functions (bool called_from_pragma)
> {
> unsigned int i, fcode = AARCH64_SIMD_PATTERN_START;
>
> - if (aarch64_simd_builtins_initialized_p)
> - return;
> -
> - aarch64_simd_builtins_initialized_p = true;
> -
> - aarch64_init_simd_builtin_types ();
> -
> - /* Strong-typing hasn't been implemented for all AdvSIMD builtin
> intrinsics.
> - Therefore we need to preserve the old __builtin scalar types. It can be
> - removed once all the intrinsics become strongly typed using the
> qualifier
> - system. */
> - aarch64_init_simd_builtin_scalar_types ();
> -
> - tree lane_check_fpr = build_function_type_list (void_type_node,
> - size_type_node,
> - size_type_node,
> - intSI_type_node,
> - NULL);
> - aarch64_builtin_decls[AARCH64_SIMD_BUILTIN_LANE_CHECK]
> - = aarch64_general_add_builtin ("__builtin_aarch64_im_lane_boundsi",
> - lane_check_fpr,
> - AARCH64_SIMD_BUILTIN_LANE_CHECK);
> + if (!called_from_pragma)
> + {
> + tree lane_check_fpr = build_function_type_list (void_type_node,
> + size_type_node,
> + size_type_node,
> + intSI_type_node,
> + NULL);
> + aarch64_builtin_decls[AARCH64_SIMD_BUILTIN_LANE_CHECK]
> + = aarch64_general_add_builtin ("__builtin_aarch64_im_lane_boundsi",
> + lane_check_fpr,
> + AARCH64_SIMD_BUILTIN_LANE_CHECK);
> + }
>
> for (i = 0; i < ARRAY_SIZE (aarch64_simd_builtin_data); i++, fcode++)
> {
> @@ -1100,6 +1090,18 @@ aarch64_init_simd_builtins (void)
> tree return_type = void_type_node, args = void_list_node;
> tree eltype;
>
> + int struct_mode_args = 0;
> + for (int j = op_num; j >= 0; j--)
> + {
> + machine_mode op_mode = insn_data[d->code].operand[j].mode;
> + if (aarch64_advsimd_struct_mode_p (op_mode))
> + struct_mode_args++;
> + }
> +
> + if ((called_from_pragma && struct_mode_args == 0)
> + || (!called_from_pragma && struct_mode_args > 0))
> + continue;
> +
> /* Build a function type directly from the insn_data for this
> builtin. The build_function_type () function takes care of
> removing duplicates for us. */
> @@ -1173,9 +1175,82 @@ aarch64_init_simd_builtins (void)
> fndecl = aarch64_general_add_builtin (namebuf, ftype, fcode, attrs);
> aarch64_builtin_decls[fcode] = fndecl;
> }
> +}
> +
> +/* Register the tuple type that contains NUM_VECTORS of the AdvSIMD type
> + indexed by TYPE_INDEX. */
> +static void
> +register_tuple_type (unsigned int num_vectors, unsigned int type_index)
> +{
> + aarch64_simd_type_info *type = &aarch64_simd_types[type_index];
> +
> + /* Synthesize the name of the user-visible vector tuple type. */
> + const char *vector_type_name = type->name;
> + char tuple_type_name[sizeof ("bfloat16x4x2_t")];
> + snprintf (tuple_type_name, sizeof (tuple_type_name), "%.*sx%d_t",
> + (int) strlen (vector_type_name) - 4, vector_type_name + 2,
> + num_vectors);
> + tuple_type_name[0] = TOLOWER (tuple_type_name[0]);
> +
> + tree vector_type = type->itype;
> + tree array_type = build_array_type_nelts (vector_type, num_vectors);
> + unsigned int alignment
> + = (known_eq (GET_MODE_SIZE (type->mode), 16) ? 128 : 64);
> + gcc_assert (TYPE_MODE_RAW (array_type) == TYPE_MODE (array_type)
> + && TYPE_ALIGN (array_type) == alignment);
> +
> + tree field = build_decl (input_location, FIELD_DECL,
> + get_identifier ("val"), array_type);
> +
> + tree t = lang_hooks.types.simulate_record_decl (input_location,
> + tuple_type_name,
> + make_array_slice (&field,
> + 1));
> + gcc_assert (TYPE_MODE_RAW (t) == TYPE_MODE (t)
> + && TYPE_ALIGN (t) == alignment);
> +}
> +
> +static bool
> +aarch64_scalar_builtin_type_p (aarch64_simd_type t)
> +{
> + return (t == Poly8_t || t == Poly16_t || t == Poly64_t || t == Poly128_t);
> +}
> +
> +/* Implement #pragma GCC aarch64 "arm_neon.h". */
> +void
> +handle_arm_neon_h (void)
> +{
> + /* Register the AdvSIMD vector tuple types. */
> + for (unsigned int i = 0; i < ARM_NEON_H_TYPES_LAST; i++)
> + for (unsigned int count = 2; count <= 4; ++count)
> + if (!aarch64_scalar_builtin_type_p (aarch64_simd_types[i].type))
> + register_tuple_type (count, i);
> +
> + aarch64_init_simd_builtin_functions (true);
> +}
> +
> +void
> +aarch64_init_simd_builtins (void)
> +{
> + if (aarch64_simd_builtins_initialized_p)
> + return;
> +
> + aarch64_simd_builtins_initialized_p = true;
> +
> + aarch64_init_simd_builtin_types ();
> +
> + /* Strong-typing hasn't been implemented for all AdvSIMD builtin
> intrinsics.
> + Therefore we need to preserve the old __builtin scalar types. It can be
> + removed once all the intrinsics become strongly typed using the
> qualifier
> + system. */
> + aarch64_init_simd_builtin_scalar_types ();
> +
> + aarch64_init_simd_builtin_functions (false);
> + if (in_lto_p)
> + handle_arm_neon_h ();
>
> - /* Initialize the remaining fcmla_laneq intrinsics. */
> - aarch64_init_fcmla_laneq_builtins ();
> + /* Initialize the remaining fcmla_laneq intrinsics. */
> + aarch64_init_fcmla_laneq_builtins ();
> }
>
> static void
> diff --git a/gcc/config/aarch64/aarch64-c.c b/gcc/config/aarch64/aarch64-c.c
> index
> f9ddffa007818a42710cfc0d60af580dd6c76f95..d6653e474dec9bcddde2106f36ceb22f1d43375c
> 100644
> --- a/gcc/config/aarch64/aarch64-c.c
> +++ b/gcc/config/aarch64/aarch64-c.c
> @@ -296,6 +296,8 @@ aarch64_pragma_aarch64 (cpp_reader *)
> const char *name = TREE_STRING_POINTER (x);
> if (strcmp (name, "arm_sve.h") == 0)
> aarch64_sve::handle_arm_sve_h ();
> + else if (strcmp (name, "arm_neon.h") == 0)
> + handle_arm_neon_h ();
> else
> error ("unknown %<#pragma GCC aarch64%> option %qs", name);
> }
> diff --git a/gcc/config/aarch64/aarch64-protos.h
> b/gcc/config/aarch64/aarch64-protos.h
> index
> b91eeeba1012ef830f8bb3535c7c81c29afccc17..c6a83d57c8ede53053cdd852b7d7e6e8a4a08514
> 100644
> --- a/gcc/config/aarch64/aarch64-protos.h
> +++ b/gcc/config/aarch64/aarch64-protos.h
> @@ -743,6 +743,7 @@ unsigned HOST_WIDE_INT aarch64_and_split_imm2
> (HOST_WIDE_INT val_in);
> bool aarch64_and_bitmask_imm (unsigned HOST_WIDE_INT val_in, machine_mode
> mode);
> int aarch64_branch_cost (bool, bool);
> enum aarch64_symbol_type aarch64_classify_symbolic_expression (rtx);
> +bool aarch64_advsimd_struct_mode_p (machine_mode mode);
> opt_machine_mode aarch64_vq_mode (scalar_mode);
> opt_machine_mode aarch64_full_sve_mode (scalar_mode);
> bool aarch64_can_const_movi_rtx_p (rtx x, machine_mode mode);
> @@ -967,6 +968,7 @@ rtx aarch64_general_expand_builtin (unsigned int, tree,
> rtx, int);
> tree aarch64_general_builtin_decl (unsigned, bool);
> tree aarch64_general_builtin_rsqrt (unsigned int);
> tree aarch64_builtin_vectorized_function (unsigned int, tree, tree);
> +void handle_arm_neon_h (void);
>
> namespace aarch64_sve {
> void init_builtins ();
> diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
> index
> a9a1800af53b18306465e382e9dd149d0e335b09..fe09e36710b9b082ea6fe86b1c3a937b9e3bd9b6
> 100644
> --- a/gcc/config/aarch64/aarch64.c
> +++ b/gcc/config/aarch64/aarch64.c
> @@ -2785,7 +2785,7 @@ aarch64_estimated_sve_vq ()
> }
>
> /* Return true if MODE is any of the Advanced SIMD structure modes. */
> -static bool
> +bool
> aarch64_advsimd_struct_mode_p (machine_mode mode)
> {
> return (TARGET_SIMD
> diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
> index
> 2d5bf34b698a88ed934c522cc9f14f125c604a39..b638854c32460ccfbc0cdd24ccbdbf18ccb2df44
> 100644
> --- a/gcc/config/aarch64/arm_neon.h
> +++ b/gcc/config/aarch64/arm_neon.h
> @@ -30,6 +30,8 @@
> #pragma GCC push_options
> #pragma GCC target ("+nothing+simd")
>
> +#pragma GCC aarch64 "arm_neon.h"
> +
> #include <stdint.h>
>
> #define __AARCH64_UINT64_C(__C) ((uint64_t) __C)
> @@ -76,456 +78,6 @@ typedef double float64_t;
> typedef __Bfloat16x4_t bfloat16x4_t;
> typedef __Bfloat16x8_t bfloat16x8_t;
>
> -typedef struct bfloat16x4x2_t
> -{
> - bfloat16x4_t val[2];
> -} bfloat16x4x2_t;
> -
> -typedef struct bfloat16x8x2_t
> -{
> - bfloat16x8_t val[2];
> -} bfloat16x8x2_t;
> -
> -typedef struct bfloat16x4x3_t
> -{
> - bfloat16x4_t val[3];
> -} bfloat16x4x3_t;
> -
> -typedef struct bfloat16x8x3_t
> -{
> - bfloat16x8_t val[3];
> -} bfloat16x8x3_t;
> -
> -typedef struct bfloat16x4x4_t
> -{
> - bfloat16x4_t val[4];
> -} bfloat16x4x4_t;
> -
> -typedef struct bfloat16x8x4_t
> -{
> - bfloat16x8_t val[4];
> -} bfloat16x8x4_t;
> -
> -typedef struct int8x8x2_t
> -{
> - int8x8_t val[2];
> -} int8x8x2_t;
> -
> -typedef struct int8x16x2_t
> -{
> - int8x16_t val[2];
> -} int8x16x2_t;
> -
> -typedef struct int16x4x2_t
> -{
> - int16x4_t val[2];
> -} int16x4x2_t;
> -
> -typedef struct int16x8x2_t
> -{
> - int16x8_t val[2];
> -} int16x8x2_t;
> -
> -typedef struct int32x2x2_t
> -{
> - int32x2_t val[2];
> -} int32x2x2_t;
> -
> -typedef struct int32x4x2_t
> -{
> - int32x4_t val[2];
> -} int32x4x2_t;
> -
> -typedef struct int64x1x2_t
> -{
> - int64x1_t val[2];
> -} int64x1x2_t;
> -
> -typedef struct int64x2x2_t
> -{
> - int64x2_t val[2];
> -} int64x2x2_t;
> -
> -typedef struct uint8x8x2_t
> -{
> - uint8x8_t val[2];
> -} uint8x8x2_t;
> -
> -typedef struct uint8x16x2_t
> -{
> - uint8x16_t val[2];
> -} uint8x16x2_t;
> -
> -typedef struct uint16x4x2_t
> -{
> - uint16x4_t val[2];
> -} uint16x4x2_t;
> -
> -typedef struct uint16x8x2_t
> -{
> - uint16x8_t val[2];
> -} uint16x8x2_t;
> -
> -typedef struct uint32x2x2_t
> -{
> - uint32x2_t val[2];
> -} uint32x2x2_t;
> -
> -typedef struct uint32x4x2_t
> -{
> - uint32x4_t val[2];
> -} uint32x4x2_t;
> -
> -typedef struct uint64x1x2_t
> -{
> - uint64x1_t val[2];
> -} uint64x1x2_t;
> -
> -typedef struct uint64x2x2_t
> -{
> - uint64x2_t val[2];
> -} uint64x2x2_t;
> -
> -typedef struct float16x4x2_t
> -{
> - float16x4_t val[2];
> -} float16x4x2_t;
> -
> -typedef struct float16x8x2_t
> -{
> - float16x8_t val[2];
> -} float16x8x2_t;
> -
> -typedef struct float32x2x2_t
> -{
> - float32x2_t val[2];
> -} float32x2x2_t;
> -
> -typedef struct float32x4x2_t
> -{
> - float32x4_t val[2];
> -} float32x4x2_t;
> -
> -typedef struct float64x2x2_t
> -{
> - float64x2_t val[2];
> -} float64x2x2_t;
> -
> -typedef struct float64x1x2_t
> -{
> - float64x1_t val[2];
> -} float64x1x2_t;
> -
> -typedef struct poly8x8x2_t
> -{
> - poly8x8_t val[2];
> -} poly8x8x2_t;
> -
> -typedef struct poly8x16x2_t
> -{
> - poly8x16_t val[2];
> -} poly8x16x2_t;
> -
> -typedef struct poly16x4x2_t
> -{
> - poly16x4_t val[2];
> -} poly16x4x2_t;
> -
> -typedef struct poly16x8x2_t
> -{
> - poly16x8_t val[2];
> -} poly16x8x2_t;
> -
> -typedef struct poly64x1x2_t
> -{
> - poly64x1_t val[2];
> -} poly64x1x2_t;
> -
> -typedef struct poly64x1x3_t
> -{
> - poly64x1_t val[3];
> -} poly64x1x3_t;
> -
> -typedef struct poly64x1x4_t
> -{
> - poly64x1_t val[4];
> -} poly64x1x4_t;
> -
> -typedef struct poly64x2x2_t
> -{
> - poly64x2_t val[2];
> -} poly64x2x2_t;
> -
> -typedef struct poly64x2x3_t
> -{
> - poly64x2_t val[3];
> -} poly64x2x3_t;
> -
> -typedef struct poly64x2x4_t
> -{
> - poly64x2_t val[4];
> -} poly64x2x4_t;
> -
> -typedef struct int8x8x3_t
> -{
> - int8x8_t val[3];
> -} int8x8x3_t;
> -
> -typedef struct int8x16x3_t
> -{
> - int8x16_t val[3];
> -} int8x16x3_t;
> -
> -typedef struct int16x4x3_t
> -{
> - int16x4_t val[3];
> -} int16x4x3_t;
> -
> -typedef struct int16x8x3_t
> -{
> - int16x8_t val[3];
> -} int16x8x3_t;
> -
> -typedef struct int32x2x3_t
> -{
> - int32x2_t val[3];
> -} int32x2x3_t;
> -
> -typedef struct int32x4x3_t
> -{
> - int32x4_t val[3];
> -} int32x4x3_t;
> -
> -typedef struct int64x1x3_t
> -{
> - int64x1_t val[3];
> -} int64x1x3_t;
> -
> -typedef struct int64x2x3_t
> -{
> - int64x2_t val[3];
> -} int64x2x3_t;
> -
> -typedef struct uint8x8x3_t
> -{
> - uint8x8_t val[3];
> -} uint8x8x3_t;
> -
> -typedef struct uint8x16x3_t
> -{
> - uint8x16_t val[3];
> -} uint8x16x3_t;
> -
> -typedef struct uint16x4x3_t
> -{
> - uint16x4_t val[3];
> -} uint16x4x3_t;
> -
> -typedef struct uint16x8x3_t
> -{
> - uint16x8_t val[3];
> -} uint16x8x3_t;
> -
> -typedef struct uint32x2x3_t
> -{
> - uint32x2_t val[3];
> -} uint32x2x3_t;
> -
> -typedef struct uint32x4x3_t
> -{
> - uint32x4_t val[3];
> -} uint32x4x3_t;
> -
> -typedef struct uint64x1x3_t
> -{
> - uint64x1_t val[3];
> -} uint64x1x3_t;
> -
> -typedef struct uint64x2x3_t
> -{
> - uint64x2_t val[3];
> -} uint64x2x3_t;
> -
> -typedef struct float16x4x3_t
> -{
> - float16x4_t val[3];
> -} float16x4x3_t;
> -
> -typedef struct float16x8x3_t
> -{
> - float16x8_t val[3];
> -} float16x8x3_t;
> -
> -typedef struct float32x2x3_t
> -{
> - float32x2_t val[3];
> -} float32x2x3_t;
> -
> -typedef struct float32x4x3_t
> -{
> - float32x4_t val[3];
> -} float32x4x3_t;
> -
> -typedef struct float64x2x3_t
> -{
> - float64x2_t val[3];
> -} float64x2x3_t;
> -
> -typedef struct float64x1x3_t
> -{
> - float64x1_t val[3];
> -} float64x1x3_t;
> -
> -typedef struct poly8x8x3_t
> -{
> - poly8x8_t val[3];
> -} poly8x8x3_t;
> -
> -typedef struct poly8x16x3_t
> -{
> - poly8x16_t val[3];
> -} poly8x16x3_t;
> -
> -typedef struct poly16x4x3_t
> -{
> - poly16x4_t val[3];
> -} poly16x4x3_t;
> -
> -typedef struct poly16x8x3_t
> -{
> - poly16x8_t val[3];
> -} poly16x8x3_t;
> -
> -typedef struct int8x8x4_t
> -{
> - int8x8_t val[4];
> -} int8x8x4_t;
> -
> -typedef struct int8x16x4_t
> -{
> - int8x16_t val[4];
> -} int8x16x4_t;
> -
> -typedef struct int16x4x4_t
> -{
> - int16x4_t val[4];
> -} int16x4x4_t;
> -
> -typedef struct int16x8x4_t
> -{
> - int16x8_t val[4];
> -} int16x8x4_t;
> -
> -typedef struct int32x2x4_t
> -{
> - int32x2_t val[4];
> -} int32x2x4_t;
> -
> -typedef struct int32x4x4_t
> -{
> - int32x4_t val[4];
> -} int32x4x4_t;
> -
> -typedef struct int64x1x4_t
> -{
> - int64x1_t val[4];
> -} int64x1x4_t;
> -
> -typedef struct int64x2x4_t
> -{
> - int64x2_t val[4];
> -} int64x2x4_t;
> -
> -typedef struct uint8x8x4_t
> -{
> - uint8x8_t val[4];
> -} uint8x8x4_t;
> -
> -typedef struct uint8x16x4_t
> -{
> - uint8x16_t val[4];
> -} uint8x16x4_t;
> -
> -typedef struct uint16x4x4_t
> -{
> - uint16x4_t val[4];
> -} uint16x4x4_t;
> -
> -typedef struct uint16x8x4_t
> -{
> - uint16x8_t val[4];
> -} uint16x8x4_t;
> -
> -typedef struct uint32x2x4_t
> -{
> - uint32x2_t val[4];
> -} uint32x2x4_t;
> -
> -typedef struct uint32x4x4_t
> -{
> - uint32x4_t val[4];
> -} uint32x4x4_t;
> -
> -typedef struct uint64x1x4_t
> -{
> - uint64x1_t val[4];
> -} uint64x1x4_t;
> -
> -typedef struct uint64x2x4_t
> -{
> - uint64x2_t val[4];
> -} uint64x2x4_t;
> -
> -typedef struct float16x4x4_t
> -{
> - float16x4_t val[4];
> -} float16x4x4_t;
> -
> -typedef struct float16x8x4_t
> -{
> - float16x8_t val[4];
> -} float16x8x4_t;
> -
> -typedef struct float32x2x4_t
> -{
> - float32x2_t val[4];
> -} float32x2x4_t;
> -
> -typedef struct float32x4x4_t
> -{
> - float32x4_t val[4];
> -} float32x4x4_t;
> -
> -typedef struct float64x2x4_t
> -{
> - float64x2_t val[4];
> -} float64x2x4_t;
> -
> -typedef struct float64x1x4_t
> -{
> - float64x1_t val[4];
> -} float64x1x4_t;
> -
> -typedef struct poly8x8x4_t
> -{
> - poly8x8_t val[4];
> -} poly8x8x4_t;
> -
> -typedef struct poly8x16x4_t
> -{
> - poly8x16_t val[4];
> -} poly8x16x4_t;
> -
> -typedef struct poly16x4x4_t
> -{
> - poly16x4_t val[4];
> -} poly16x4x4_t;
> -
> -typedef struct poly16x8x4_t
> -{
> - poly16x8_t val[4];
> -} poly16x8x4_t;
> -
> /* __aarch64_vdup_lane internal macros. */
> #define __aarch64_vdup_lane_any(__size, __q, __a, __b) \
> vdup##__q##_n_##__size (__aarch64_vget_lane_any (__a, __b))
