On 04/09/2024 14:26, Christophe Lyon wrote:
> Implement vctp using the new MVE builtins framework.
>
> 2024-08-21 Christophe Lyon <christophe.l...@linaro.org>
>
> gcc/ChangeLog:
>
> * config/arm/arm-mve-builtins-base.cc (class vctpq_impl): New.
> (vctp16q): New.
> (vctp32q): New.
> (vctp64q): New.
> (vctp8q): New.
> * config/arm/arm-mve-builtins-base.def (vctp16q): New.
> (vctp32q): New.
> (vctp64q): New.
> (vctp8q): New.
> * config/arm/arm-mve-builtins-base.h (vctp16q): New.
> (vctp32q): New.
> (vctp64q): New.
> (vctp8q): New.
> * config/arm/arm-mve-builtins-shapes.cc (vctp): New.
> * config/arm/arm-mve-builtins-shapes.h (vctp): New.
> * config/arm/arm-mve-builtins.cc
> (function_instance::has_inactive_argument): Add support for vctp.
> * config/arm/arm_mve.h (vctp16q): Delete.
> (vctp32q): Delete.
> (vctp64q): Delete.
> (vctp8q): Delete.
> (vctp8q_m): Delete.
> (vctp64q_m): Delete.
> (vctp32q_m): Delete.
> (vctp16q_m): Delete.
> (__arm_vctp16q): Delete.
> (__arm_vctp32q): Delete.
> (__arm_vctp64q): Delete.
> (__arm_vctp8q): Delete.
> (__arm_vctp8q_m): Delete.
> (__arm_vctp64q_m): Delete.
> (__arm_vctp32q_m): Delete.
> (__arm_vctp16q_m): Delete.
> * config/arm/mve.md (mve_vctp<MVE_vctp>q<MVE_vpred>): Add '@'
> prefix.
> (mve_vctp<MVE_vctp>q_m<MVE_vpred>): Likewise.
OK.
R.
> ---
> gcc/config/arm/arm-mve-builtins-base.cc | 48 +++++++++++++++++
> gcc/config/arm/arm-mve-builtins-base.def | 4 ++
> gcc/config/arm/arm-mve-builtins-base.h | 4 ++
> gcc/config/arm/arm-mve-builtins-shapes.cc | 16 ++++++
> gcc/config/arm/arm-mve-builtins-shapes.h | 1 +
> gcc/config/arm/arm-mve-builtins.cc | 4 ++
> gcc/config/arm/arm_mve.h | 64 -----------------------
> gcc/config/arm/mve.md | 4 +-
> 8 files changed, 79 insertions(+), 66 deletions(-)
>
> diff --git a/gcc/config/arm/arm-mve-builtins-base.cc
> b/gcc/config/arm/arm-mve-builtins-base.cc
> index f8260f5f483..89724320d43 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.cc
> +++ b/gcc/config/arm/arm-mve-builtins-base.cc
> @@ -139,6 +139,50 @@ public:
> }
> };
>
> + /* Implements vctp8q, vctp16q, vctp32q and vctp64q intrinsics. */
> +class vctpq_impl : public function_base
> +{
> +public:
> + CONSTEXPR vctpq_impl (machine_mode mode)
> + : m_mode (mode)
> + {}
> +
> + /* Mode this intrinsic operates on. */
> + machine_mode m_mode;
> +
> + rtx
> + expand (function_expander &e) const override
> + {
> + insn_code code;
> + rtx target;
> +
> + if (e.mode_suffix_id != MODE_none)
> + gcc_unreachable ();
> +
> + switch (e.pred)
> + {
> + case PRED_none:
> + /* No predicate, no suffix. */
> + code = code_for_mve_vctpq (m_mode, m_mode);
> + target = e.use_exact_insn (code);
> + break;
> +
> + case PRED_m:
> + /* No suffix, "m" predicate. */
> + code = code_for_mve_vctpq_m (m_mode, m_mode);
> + target = e.use_cond_insn (code, 0);
> + break;
> +
> + default:
> + gcc_unreachable ();
> + }
> +
> + rtx HItarget = gen_reg_rtx (HImode);
> + emit_move_insn (HItarget, gen_lowpart (HImode, target));
> + return HItarget;
> + }
> +};
> +
> /* Implements vcvtq intrinsics. */
> class vcvtq_impl : public function_base
> {
> @@ -506,6 +550,10 @@ FUNCTION (vcmpltq,
> unspec_based_mve_function_exact_insn_vcmp, (LT, UNKNOWN, LT,
> FUNCTION (vcmpcsq, unspec_based_mve_function_exact_insn_vcmp, (UNKNOWN, GEU,
> UNKNOWN, UNKNOWN, VCMPCSQ_M_U, UNKNOWN, UNKNOWN, VCMPCSQ_M_N_U, UNKNOWN))
> FUNCTION (vcmphiq, unspec_based_mve_function_exact_insn_vcmp, (UNKNOWN, GTU,
> UNKNOWN, UNKNOWN, VCMPHIQ_M_U, UNKNOWN, UNKNOWN, VCMPHIQ_M_N_U, UNKNOWN))
> FUNCTION_WITHOUT_M_N (vcreateq, VCREATEQ)
> +FUNCTION (vctp8q, vctpq_impl, (V16BImode))
> +FUNCTION (vctp16q, vctpq_impl, (V8BImode))
> +FUNCTION (vctp32q, vctpq_impl, (V4BImode))
> +FUNCTION (vctp64q, vctpq_impl, (V2QImode))
> FUNCTION (vcvtq, vcvtq_impl,)
> FUNCTION_WITHOUT_N_NO_F (vcvtaq, VCVTAQ)
> FUNCTION_WITHOUT_N_NO_F (vcvtmq, VCVTMQ)
> diff --git a/gcc/config/arm/arm-mve-builtins-base.def
> b/gcc/config/arm/arm-mve-builtins-base.def
> index cc76db3e0b9..dd46d882882 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.def
> +++ b/gcc/config/arm/arm-mve-builtins-base.def
> @@ -42,6 +42,10 @@ DEF_MVE_FUNCTION (vcmpleq, cmp, all_signed, m_or_none)
> DEF_MVE_FUNCTION (vcmpltq, cmp, all_signed, m_or_none)
> DEF_MVE_FUNCTION (vcmpneq, cmp, all_integer, m_or_none)
> DEF_MVE_FUNCTION (vcreateq, create, all_integer_with_64, none)
> +DEF_MVE_FUNCTION (vctp16q, vctp, none, m_or_none)
> +DEF_MVE_FUNCTION (vctp32q, vctp, none, m_or_none)
> +DEF_MVE_FUNCTION (vctp64q, vctp, none, m_or_none)
> +DEF_MVE_FUNCTION (vctp8q, vctp, none, m_or_none)
> DEF_MVE_FUNCTION (vdupq, unary_n, all_integer, mx_or_none)
> DEF_MVE_FUNCTION (veorq, binary, all_integer, mx_or_none)
> DEF_MVE_FUNCTION (vhaddq, binary_opt_n, all_integer, mx_or_none)
> diff --git a/gcc/config/arm/arm-mve-builtins-base.h
> b/gcc/config/arm/arm-mve-builtins-base.h
> index ad2647b6758..41fcf666b11 100644
> --- a/gcc/config/arm/arm-mve-builtins-base.h
> +++ b/gcc/config/arm/arm-mve-builtins-base.h
> @@ -55,6 +55,10 @@ extern const function_base *const vcmulq_rot180;
> extern const function_base *const vcmulq_rot270;
> extern const function_base *const vcmulq_rot90;
> extern const function_base *const vcreateq;
> +extern const function_base *const vctp16q;
> +extern const function_base *const vctp32q;
> +extern const function_base *const vctp64q;
> +extern const function_base *const vctp8q;
> extern const function_base *const vcvtaq;
> extern const function_base *const vcvtbq;
> extern const function_base *const vcvtmq;
> diff --git a/gcc/config/arm/arm-mve-builtins-shapes.cc
> b/gcc/config/arm/arm-mve-builtins-shapes.cc
> index 6632ee49067..8a849c2bc02 100644
> --- a/gcc/config/arm/arm-mve-builtins-shapes.cc
> +++ b/gcc/config/arm/arm-mve-builtins-shapes.cc
> @@ -1981,6 +1981,22 @@ struct unary_widen_acc_def : public overloaded_base<0>
> };
> SHAPE (unary_widen_acc)
>
> +/* mve_pred16_t foo_t0(uint32_t)
> +
> + Example: vctp16q.
> + mve_pred16_t [__arm_]vctp16q(uint32_t a)
> + mve_pred16_t [__arm_]vctp16q_m(uint32_t a, mve_pred16_t p) */
> +struct vctp_def : public nonoverloaded_base
> +{
> + void
> + build (function_builder &b, const function_group_info &group,
> + bool preserve_user_namespace) const override
> + {
> + build_all (b, "p,su32", group, MODE_none, preserve_user_namespace);
> + }
> +};
> +SHAPE (vctp)
> +
> /* <T0>_t foo_t0[_t1](<T1>_t)
> <T0>_t foo_t0_n[_t1](<T1>_t, const int)
>
> diff --git a/gcc/config/arm/arm-mve-builtins-shapes.h
> b/gcc/config/arm/arm-mve-builtins-shapes.h
> index ef497b6c97a..80340dc33ec 100644
> --- a/gcc/config/arm/arm-mve-builtins-shapes.h
> +++ b/gcc/config/arm/arm-mve-builtins-shapes.h
> @@ -77,6 +77,7 @@ namespace arm_mve
> extern const function_shape *const unary_n;
> extern const function_shape *const unary_widen;
> extern const function_shape *const unary_widen_acc;
> + extern const function_shape *const vctp;
> extern const function_shape *const vcvt;
> extern const function_shape *const vcvt_f16_f32;
> extern const function_shape *const vcvt_f32_f16;
> diff --git a/gcc/config/arm/arm-mve-builtins.cc
> b/gcc/config/arm/arm-mve-builtins.cc
> index 13c666b8f6a..84d94bb634f 100644
> --- a/gcc/config/arm/arm-mve-builtins.cc
> +++ b/gcc/config/arm/arm-mve-builtins.cc
> @@ -750,6 +750,10 @@ function_instance::has_inactive_argument () const
> || base == functions::vcmpltq
> || base == functions::vcmpcsq
> || base == functions::vcmphiq
> + || base == functions::vctp16q
> + || base == functions::vctp32q
> + || base == functions::vctp64q
> + || base == functions::vctp8q
> || (base == functions::vcvtbq && type_suffix (0).element_bits == 16)
> || (base == functions::vcvttq && type_suffix (0).element_bits == 16)
> || base == functions::vfmaq
> diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
> index 7aa61103a7d..49c4ea9afee 100644
> --- a/gcc/config/arm/arm_mve.h
> +++ b/gcc/config/arm/arm_mve.h
> @@ -140,15 +140,7 @@
> #define vst4q_u32( __addr, __value) __arm_vst4q_u32( __addr, __value)
> #define vst4q_f16( __addr, __value) __arm_vst4q_f16( __addr, __value)
> #define vst4q_f32( __addr, __value) __arm_vst4q_f32( __addr, __value)
> -#define vctp16q(__a) __arm_vctp16q(__a)
> -#define vctp32q(__a) __arm_vctp32q(__a)
> -#define vctp64q(__a) __arm_vctp64q(__a)
> -#define vctp8q(__a) __arm_vctp8q(__a)
> #define vpnot(__a) __arm_vpnot(__a)
> -#define vctp8q_m(__a, __p) __arm_vctp8q_m(__a, __p)
> -#define vctp64q_m(__a, __p) __arm_vctp64q_m(__a, __p)
> -#define vctp32q_m(__a, __p) __arm_vctp32q_m(__a, __p)
> -#define vctp16q_m(__a, __p) __arm_vctp16q_m(__a, __p)
> #define vshlcq_s8(__a, __b, __imm) __arm_vshlcq_s8(__a, __b, __imm)
> #define vshlcq_u8(__a, __b, __imm) __arm_vshlcq_u8(__a, __b, __imm)
> #define vshlcq_s16(__a, __b, __imm) __arm_vshlcq_s16(__a, __b, __imm)
> @@ -603,34 +595,6 @@ __arm_vst4q_u32 (uint32_t * __addr, uint32x4x4_t __value)
> __builtin_mve_vst4qv4si ((__builtin_neon_si *) __addr, __rv.__o);
> }
>
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp16q (uint32_t __a)
> -{
> - return __builtin_mve_vctp16qv8bi (__a);
> -}
> -
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp32q (uint32_t __a)
> -{
> - return __builtin_mve_vctp32qv4bi (__a);
> -}
> -
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp64q (uint32_t __a)
> -{
> - return __builtin_mve_vctp64qv2qi (__a);
> -}
> -
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp8q (uint32_t __a)
> -{
> - return __builtin_mve_vctp8qv16bi (__a);
> -}
> -
> __extension__ extern __inline mve_pred16_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> __arm_vpnot (mve_pred16_t __a)
> @@ -638,34 +602,6 @@ __arm_vpnot (mve_pred16_t __a)
> return __builtin_mve_vpnotv16bi (__a);
> }
>
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp8q_m (uint32_t __a, mve_pred16_t __p)
> -{
> - return __builtin_mve_vctp8q_mv16bi (__a, __p);
> -}
> -
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp64q_m (uint32_t __a, mve_pred16_t __p)
> -{
> - return __builtin_mve_vctp64q_mv2qi (__a, __p);
> -}
> -
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp32q_m (uint32_t __a, mve_pred16_t __p)
> -{
> - return __builtin_mve_vctp32q_mv4bi (__a, __p);
> -}
> -
> -__extension__ extern __inline mve_pred16_t
> -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> -__arm_vctp16q_m (uint32_t __a, mve_pred16_t __p)
> -{
> - return __builtin_mve_vctp16q_mv8bi (__a, __p);
> -}
> -
> __extension__ extern __inline int8x16_t
> __attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
> __arm_vshlcq_s8 (int8x16_t __a, uint32_t * __b, const int __imm)
> diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
> index 3d8b199d9d6..62cffebd6ed 100644
> --- a/gcc/config/arm/mve.md
> +++ b/gcc/config/arm/mve.md
> @@ -482,7 +482,7 @@ (define_insn "@mve_<mve_insn>q_<supf>v4si"
> ;;
> ;; [vctp8q vctp16q vctp32q vctp64q])
> ;;
> -(define_insn "mve_vctp<MVE_vctp>q<MVE_vpred>"
> +(define_insn "@mve_vctp<MVE_vctp>q<MVE_vpred>"
> [
> (set (match_operand:MVE_7 0 "vpr_register_operand" "=Up")
> (unspec:MVE_7 [(match_operand:SI 1 "s_register_operand" "r")]
> @@ -1272,7 +1272,7 @@ (define_insn "@mve_vcmp<mve_cmp_op>q_n_f<mode>"
> ;;
> ;; [vctp8q_m vctp16q_m vctp32q_m vctp64q_m])
> ;;
> -(define_insn "mve_vctp<MVE_vctp>q_m<MVE_vpred>"
> +(define_insn "@mve_vctp<MVE_vctp>q_m<MVE_vpred>"
> [
> (set (match_operand:MVE_7 0 "vpr_register_operand" "=Up")
> (unspec:MVE_7 [(match_operand:SI 1 "s_register_operand" "r")
