From: Christophe Lyon <christophe.lyon@arm.com>
To: <gcc-patches@gcc.gnu.org>, <kyrylo.tkachov@arm.com>,
<richard.earnshaw@arm.com>, <richard.sandiford@arm.com>
Cc: Christophe Lyon <christophe.lyon@arm.com>
Subject: [PATCH 08/20] arm: [MVE intrinsics] rework vdupq
Date: Wed, 10 May 2023 15:30:24 +0200 [thread overview]
Message-ID: <20230510133036.596530-8-christophe.lyon@arm.com> (raw)
In-Reply-To: <20230510133036.596530-1-christophe.lyon@arm.com>
Implement vdupq using the new MVE builtins framework.
2022-10-25 Christophe Lyon <christophe.lyon@arm.com>
gcc/
* config/arm/arm-mve-builtins-base.cc (FUNCTION_ONLY_N): New.
(vdupq): New.
* config/arm/arm-mve-builtins-base.def (vdupq): New.
* config/arm/arm-mve-builtins-base.h: (vdupq): New.
* config/arm/arm_mve.h (vdupq_n): Remove.
(vdupq_m): Remove.
(vdupq_n_f16): Remove.
(vdupq_n_f32): Remove.
(vdupq_n_s8): Remove.
(vdupq_n_s16): Remove.
(vdupq_n_s32): Remove.
(vdupq_n_u8): Remove.
(vdupq_n_u16): Remove.
(vdupq_n_u32): Remove.
(vdupq_m_n_u8): Remove.
(vdupq_m_n_s8): Remove.
(vdupq_m_n_u16): Remove.
(vdupq_m_n_s16): Remove.
(vdupq_m_n_u32): Remove.
(vdupq_m_n_s32): Remove.
(vdupq_m_n_f16): Remove.
(vdupq_m_n_f32): Remove.
(vdupq_x_n_s8): Remove.
(vdupq_x_n_s16): Remove.
(vdupq_x_n_s32): Remove.
(vdupq_x_n_u8): Remove.
(vdupq_x_n_u16): Remove.
(vdupq_x_n_u32): Remove.
(vdupq_x_n_f16): Remove.
(vdupq_x_n_f32): Remove.
(__arm_vdupq_n_s8): Remove.
(__arm_vdupq_n_s16): Remove.
(__arm_vdupq_n_s32): Remove.
(__arm_vdupq_n_u8): Remove.
(__arm_vdupq_n_u16): Remove.
(__arm_vdupq_n_u32): Remove.
(__arm_vdupq_m_n_u8): Remove.
(__arm_vdupq_m_n_s8): Remove.
(__arm_vdupq_m_n_u16): Remove.
(__arm_vdupq_m_n_s16): Remove.
(__arm_vdupq_m_n_u32): Remove.
(__arm_vdupq_m_n_s32): Remove.
(__arm_vdupq_x_n_s8): Remove.
(__arm_vdupq_x_n_s16): Remove.
(__arm_vdupq_x_n_s32): Remove.
(__arm_vdupq_x_n_u8): Remove.
(__arm_vdupq_x_n_u16): Remove.
(__arm_vdupq_x_n_u32): Remove.
(__arm_vdupq_n_f16): Remove.
(__arm_vdupq_n_f32): Remove.
(__arm_vdupq_m_n_f16): Remove.
(__arm_vdupq_m_n_f32): Remove.
(__arm_vdupq_x_n_f16): Remove.
(__arm_vdupq_x_n_f32): Remove.
(__arm_vdupq_n): Remove.
(__arm_vdupq_m): Remove.
---
gcc/config/arm/arm-mve-builtins-base.cc | 10 +
gcc/config/arm/arm-mve-builtins-base.def | 2 +
gcc/config/arm/arm-mve-builtins-base.h | 1 +
gcc/config/arm/arm_mve.h | 333 -----------------------
4 files changed, 13 insertions(+), 333 deletions(-)
diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc
index 76294ddb7fb..cb572130c2b 100644
--- a/gcc/config/arm/arm-mve-builtins-base.cc
+++ b/gcc/config/arm/arm-mve-builtins-base.cc
@@ -176,6 +176,15 @@ namespace arm_mve {
UNSPEC##_M_S, UNSPEC##_M_U, UNSPEC##_M_F, \
-1, -1, -1))
+ /* Helper for builtins with only unspec codes, _m predicated
+ overrides, only _n version. */
+#define FUNCTION_ONLY_N(NAME, UNSPEC) FUNCTION \
+ (NAME, unspec_mve_function_exact_insn, \
+ (-1, -1, -1, \
+ UNSPEC##_N_S, UNSPEC##_N_U, UNSPEC##_N_F, \
+ -1, -1, -1, \
+ UNSPEC##_M_N_S, UNSPEC##_M_N_U, UNSPEC##_M_N_F))
+
/* Helper for builtins with only unspec codes, _m predicated
overrides, only _n version, no floating-point. */
#define FUNCTION_ONLY_N_NO_F(NAME, UNSPEC) FUNCTION \
@@ -247,6 +256,7 @@ 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_ONLY_N (vdupq, VDUPQ)
FUNCTION_WITH_RTX_M (veorq, XOR, VEORQ)
FUNCTION_WITH_M_N_NO_F (vhaddq, VHADDQ)
FUNCTION_WITH_M_N_NO_F (vhsubq, VHSUBQ)
diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def
index 2602cbf20e3..30e6aa1e1e6 100644
--- a/gcc/config/arm/arm-mve-builtins-base.def
+++ b/gcc/config/arm/arm-mve-builtins-base.def
@@ -33,6 +33,7 @@ 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 (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)
DEF_MVE_FUNCTION (vhsubq, binary_opt_n, all_integer, mx_or_none)
@@ -104,6 +105,7 @@ DEF_MVE_FUNCTION (vcmpleq, cmp, all_float, m_or_none)
DEF_MVE_FUNCTION (vcmpltq, cmp, all_float, m_or_none)
DEF_MVE_FUNCTION (vcmpneq, cmp, all_float, m_or_none)
DEF_MVE_FUNCTION (vcreateq, create, all_float, none)
+DEF_MVE_FUNCTION (vdupq, unary_n, all_float, mx_or_none)
DEF_MVE_FUNCTION (veorq, binary, all_float, mx_or_none)
DEF_MVE_FUNCTION (vmaxnmaq, binary, all_float, m_or_none)
DEF_MVE_FUNCTION (vmaxnmavq, binary_maxvminv, all_float, p_or_none)
diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h
index eaea466712a..3dc9114045f 100644
--- a/gcc/config/arm/arm-mve-builtins-base.h
+++ b/gcc/config/arm/arm-mve-builtins-base.h
@@ -38,6 +38,7 @@ extern const function_base *const vcmpleq;
extern const function_base *const vcmpltq;
extern const function_base *const vcmpneq;
extern const function_base *const vcreateq;
+extern const function_base *const vdupq;
extern const function_base *const veorq;
extern const function_base *const vhaddq;
extern const function_base *const vhsubq;
diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h
index 3692f600b37..c3d18e4cc6f 100644
--- a/gcc/config/arm/arm_mve.h
+++ b/gcc/config/arm/arm_mve.h
@@ -42,7 +42,6 @@
#ifndef __ARM_MVE_PRESERVE_USER_NAMESPACE
#define vst4q(__addr, __value) __arm_vst4q(__addr, __value)
-#define vdupq_n(__a) __arm_vdupq_n(__a)
#define vaddlvq(__a) __arm_vaddlvq(__a)
#define vaddvq(__a) __arm_vaddvq(__a)
#define vmovlbq(__a) __arm_vmovlbq(__a)
@@ -92,7 +91,6 @@
#define vmlaq(__a, __b, __c) __arm_vmlaq(__a, __b, __c)
#define vmladavq_p(__a, __b, __p) __arm_vmladavq_p(__a, __b, __p)
#define vmladavaq(__a, __b, __c) __arm_vmladavaq(__a, __b, __c)
-#define vdupq_m(__inactive, __a, __p) __arm_vdupq_m(__inactive, __a, __p)
#define vaddvaq_p(__a, __b, __p) __arm_vaddvaq_p(__a, __b, __p)
#define vsriq(__a, __b, __imm) __arm_vsriq(__a, __b, __imm)
#define vsliq(__a, __b, __imm) __arm_vsliq(__a, __b, __imm)
@@ -324,17 +322,12 @@
#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 vdupq_n_f16(__a) __arm_vdupq_n_f16(__a)
-#define vdupq_n_f32(__a) __arm_vdupq_n_f32(__a)
#define vcvttq_f32_f16(__a) __arm_vcvttq_f32_f16(__a)
#define vcvtbq_f32_f16(__a) __arm_vcvtbq_f32_f16(__a)
#define vcvtq_f16_s16(__a) __arm_vcvtq_f16_s16(__a)
#define vcvtq_f32_s32(__a) __arm_vcvtq_f32_s32(__a)
#define vcvtq_f16_u16(__a) __arm_vcvtq_f16_u16(__a)
#define vcvtq_f32_u32(__a) __arm_vcvtq_f32_u32(__a)
-#define vdupq_n_s8(__a) __arm_vdupq_n_s8(__a)
-#define vdupq_n_s16(__a) __arm_vdupq_n_s16(__a)
-#define vdupq_n_s32(__a) __arm_vdupq_n_s32(__a)
#define vaddlvq_s32(__a) __arm_vaddlvq_s32(__a)
#define vaddvq_s8(__a) __arm_vaddvq_s8(__a)
#define vaddvq_s16(__a) __arm_vaddvq_s16(__a)
@@ -361,9 +354,6 @@
#define vmvnq_u8(__a) __arm_vmvnq_u8(__a)
#define vmvnq_u16(__a) __arm_vmvnq_u16(__a)
#define vmvnq_u32(__a) __arm_vmvnq_u32(__a)
-#define vdupq_n_u8(__a) __arm_vdupq_n_u8(__a)
-#define vdupq_n_u16(__a) __arm_vdupq_n_u16(__a)
-#define vdupq_n_u32(__a) __arm_vdupq_n_u32(__a)
#define vaddvq_u8(__a) __arm_vaddvq_u8(__a)
#define vaddvq_u16(__a) __arm_vaddvq_u16(__a)
#define vaddvq_u32(__a) __arm_vaddvq_u32(__a)
@@ -567,7 +557,6 @@
#define vmlaq_n_u8(__a, __b, __c) __arm_vmlaq_n_u8(__a, __b, __c)
#define vmladavq_p_u8(__a, __b, __p) __arm_vmladavq_p_u8(__a, __b, __p)
#define vmladavaq_u8(__a, __b, __c) __arm_vmladavaq_u8(__a, __b, __c)
-#define vdupq_m_n_u8(__inactive, __a, __p) __arm_vdupq_m_n_u8(__inactive, __a, __p)
#define vaddvaq_p_u8(__a, __b, __p) __arm_vaddvaq_p_u8(__a, __b, __p)
#define vsriq_n_u8(__a, __b, __imm) __arm_vsriq_n_u8(__a, __b, __imm)
#define vsliq_n_u8(__a, __b, __imm) __arm_vsliq_n_u8(__a, __b, __imm)
@@ -576,7 +565,6 @@
#define vmlsdavq_p_s8(__a, __b, __p) __arm_vmlsdavq_p_s8(__a, __b, __p)
#define vmladavxq_p_s8(__a, __b, __p) __arm_vmladavxq_p_s8(__a, __b, __p)
#define vmladavq_p_s8(__a, __b, __p) __arm_vmladavq_p_s8(__a, __b, __p)
-#define vdupq_m_n_s8(__inactive, __a, __p) __arm_vdupq_m_n_s8(__inactive, __a, __p)
#define vaddvaq_p_s8(__a, __b, __p) __arm_vaddvaq_p_s8(__a, __b, __p)
#define vqrdmlsdhxq_s8(__inactive, __a, __b) __arm_vqrdmlsdhxq_s8(__inactive, __a, __b)
#define vqrdmlsdhq_s8(__inactive, __a, __b) __arm_vqrdmlsdhq_s8(__inactive, __a, __b)
@@ -605,7 +593,6 @@
#define vmlaq_n_u16(__a, __b, __c) __arm_vmlaq_n_u16(__a, __b, __c)
#define vmladavq_p_u16(__a, __b, __p) __arm_vmladavq_p_u16(__a, __b, __p)
#define vmladavaq_u16(__a, __b, __c) __arm_vmladavaq_u16(__a, __b, __c)
-#define vdupq_m_n_u16(__inactive, __a, __p) __arm_vdupq_m_n_u16(__inactive, __a, __p)
#define vaddvaq_p_u16(__a, __b, __p) __arm_vaddvaq_p_u16(__a, __b, __p)
#define vsriq_n_u16(__a, __b, __imm) __arm_vsriq_n_u16(__a, __b, __imm)
#define vsliq_n_u16(__a, __b, __imm) __arm_vsliq_n_u16(__a, __b, __imm)
@@ -614,7 +601,6 @@
#define vmlsdavq_p_s16(__a, __b, __p) __arm_vmlsdavq_p_s16(__a, __b, __p)
#define vmladavxq_p_s16(__a, __b, __p) __arm_vmladavxq_p_s16(__a, __b, __p)
#define vmladavq_p_s16(__a, __b, __p) __arm_vmladavq_p_s16(__a, __b, __p)
-#define vdupq_m_n_s16(__inactive, __a, __p) __arm_vdupq_m_n_s16(__inactive, __a, __p)
#define vaddvaq_p_s16(__a, __b, __p) __arm_vaddvaq_p_s16(__a, __b, __p)
#define vqrdmlsdhxq_s16(__inactive, __a, __b) __arm_vqrdmlsdhxq_s16(__inactive, __a, __b)
#define vqrdmlsdhq_s16(__inactive, __a, __b) __arm_vqrdmlsdhq_s16(__inactive, __a, __b)
@@ -643,7 +629,6 @@
#define vmlaq_n_u32(__a, __b, __c) __arm_vmlaq_n_u32(__a, __b, __c)
#define vmladavq_p_u32(__a, __b, __p) __arm_vmladavq_p_u32(__a, __b, __p)
#define vmladavaq_u32(__a, __b, __c) __arm_vmladavaq_u32(__a, __b, __c)
-#define vdupq_m_n_u32(__inactive, __a, __p) __arm_vdupq_m_n_u32(__inactive, __a, __p)
#define vaddvaq_p_u32(__a, __b, __p) __arm_vaddvaq_p_u32(__a, __b, __p)
#define vsriq_n_u32(__a, __b, __imm) __arm_vsriq_n_u32(__a, __b, __imm)
#define vsliq_n_u32(__a, __b, __imm) __arm_vsliq_n_u32(__a, __b, __imm)
@@ -652,7 +637,6 @@
#define vmlsdavq_p_s32(__a, __b, __p) __arm_vmlsdavq_p_s32(__a, __b, __p)
#define vmladavxq_p_s32(__a, __b, __p) __arm_vmladavxq_p_s32(__a, __b, __p)
#define vmladavq_p_s32(__a, __b, __p) __arm_vmladavq_p_s32(__a, __b, __p)
-#define vdupq_m_n_s32(__inactive, __a, __p) __arm_vdupq_m_n_s32(__inactive, __a, __p)
#define vaddvaq_p_s32(__a, __b, __p) __arm_vaddvaq_p_s32(__a, __b, __p)
#define vqrdmlsdhxq_s32(__inactive, __a, __b) __arm_vqrdmlsdhxq_s32(__inactive, __a, __b)
#define vqrdmlsdhq_s32(__inactive, __a, __b) __arm_vqrdmlsdhq_s32(__inactive, __a, __b)
@@ -707,7 +691,6 @@
#define vcvtnq_m_s16_f16(__inactive, __a, __p) __arm_vcvtnq_m_s16_f16(__inactive, __a, __p)
#define vcvtpq_m_s16_f16(__inactive, __a, __p) __arm_vcvtpq_m_s16_f16(__inactive, __a, __p)
#define vcvtq_m_s16_f16(__inactive, __a, __p) __arm_vcvtq_m_s16_f16(__inactive, __a, __p)
-#define vdupq_m_n_f16(__inactive, __a, __p) __arm_vdupq_m_n_f16(__inactive, __a, __p)
#define vmlaldavq_p_s16(__a, __b, __p) __arm_vmlaldavq_p_s16(__a, __b, __p)
#define vmlaldavxq_p_s16(__a, __b, __p) __arm_vmlaldavxq_p_s16(__a, __b, __p)
#define vmlsldavq_p_s16(__a, __b, __p) __arm_vmlsldavq_p_s16(__a, __b, __p)
@@ -741,7 +724,6 @@
#define vcvtnq_m_s32_f32(__inactive, __a, __p) __arm_vcvtnq_m_s32_f32(__inactive, __a, __p)
#define vcvtpq_m_s32_f32(__inactive, __a, __p) __arm_vcvtpq_m_s32_f32(__inactive, __a, __p)
#define vcvtq_m_s32_f32(__inactive, __a, __p) __arm_vcvtq_m_s32_f32(__inactive, __a, __p)
-#define vdupq_m_n_f32(__inactive, __a, __p) __arm_vdupq_m_n_f32(__inactive, __a, __p)
#define vmlaldavq_p_s32(__a, __b, __p) __arm_vmlaldavq_p_s32(__a, __b, __p)
#define vmlaldavxq_p_s32(__a, __b, __p) __arm_vmlaldavxq_p_s32(__a, __b, __p)
#define vmlsldavq_p_s32(__a, __b, __p) __arm_vmlsldavq_p_s32(__a, __b, __p)
@@ -1257,12 +1239,6 @@
#define viwdupq_x_wb_u8(__a, __b, __imm, __p) __arm_viwdupq_x_wb_u8(__a, __b, __imm, __p)
#define viwdupq_x_wb_u16(__a, __b, __imm, __p) __arm_viwdupq_x_wb_u16(__a, __b, __imm, __p)
#define viwdupq_x_wb_u32(__a, __b, __imm, __p) __arm_viwdupq_x_wb_u32(__a, __b, __imm, __p)
-#define vdupq_x_n_s8(__a, __p) __arm_vdupq_x_n_s8(__a, __p)
-#define vdupq_x_n_s16(__a, __p) __arm_vdupq_x_n_s16(__a, __p)
-#define vdupq_x_n_s32(__a, __p) __arm_vdupq_x_n_s32(__a, __p)
-#define vdupq_x_n_u8(__a, __p) __arm_vdupq_x_n_u8(__a, __p)
-#define vdupq_x_n_u16(__a, __p) __arm_vdupq_x_n_u16(__a, __p)
-#define vdupq_x_n_u32(__a, __p) __arm_vdupq_x_n_u32(__a, __p)
#define vmullbq_poly_x_p8(__a, __b, __p) __arm_vmullbq_poly_x_p8(__a, __b, __p)
#define vmullbq_poly_x_p16(__a, __b, __p) __arm_vmullbq_poly_x_p16(__a, __b, __p)
#define vmullbq_int_x_s8(__a, __b, __p) __arm_vmullbq_int_x_s8(__a, __b, __p)
@@ -1333,8 +1309,6 @@
#define vornq_x_u8(__a, __b, __p) __arm_vornq_x_u8(__a, __b, __p)
#define vornq_x_u16(__a, __b, __p) __arm_vornq_x_u16(__a, __b, __p)
#define vornq_x_u32(__a, __b, __p) __arm_vornq_x_u32(__a, __b, __p)
-#define vdupq_x_n_f16(__a, __p) __arm_vdupq_x_n_f16(__a, __p)
-#define vdupq_x_n_f32(__a, __p) __arm_vdupq_x_n_f32(__a, __p)
#define vcaddq_rot90_x_f16(__a, __b, __p) __arm_vcaddq_rot90_x_f16(__a, __b, __p)
#define vcaddq_rot90_x_f32(__a, __b, __p) __arm_vcaddq_rot90_x_f32(__a, __b, __p)
#define vcaddq_rot270_x_f16(__a, __b, __p) __arm_vcaddq_rot270_x_f16(__a, __b, __p)
@@ -1553,27 +1527,6 @@ __arm_vst4q_u32 (uint32_t * __addr, uint32x4x4_t __value)
__builtin_mve_vst4qv4si ((__builtin_neon_si *) __addr, __rv.__o);
}
-__extension__ extern __inline int8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_s8 (int8_t __a)
-{
- return __builtin_mve_vdupq_n_sv16qi (__a);
-}
-
-__extension__ extern __inline int16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_s16 (int16_t __a)
-{
- return __builtin_mve_vdupq_n_sv8hi (__a);
-}
-
-__extension__ extern __inline int32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_s32 (int32_t __a)
-{
- return __builtin_mve_vdupq_n_sv4si (__a);
-}
-
__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddlvq_s32 (int32x4_t __a)
@@ -1686,27 +1639,6 @@ __arm_vmvnq_u32 (uint32x4_t __a)
return __builtin_mve_vmvnq_uv4si (__a);
}
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_u8 (uint8_t __a)
-{
- return __builtin_mve_vdupq_n_uv16qi (__a);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_u16 (uint16_t __a)
-{
- return __builtin_mve_vdupq_n_uv8hi (__a);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_u32 (uint32_t __a)
-{
- return __builtin_mve_vdupq_n_uv4si (__a);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvq_u8 (uint8x16_t __a)
@@ -2824,13 +2756,6 @@ __arm_vmladavaq_u8 (uint32_t __a, uint8x16_t __b, uint8x16_t __c)
return __builtin_mve_vmladavaq_uv16qi (__a, __b, __c);
}
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_u8 (uint8x16_t __inactive, uint8_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_uv16qi (__inactive, __a, __p);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p_u8 (uint32_t __a, uint8x16_t __b, mve_pred16_t __p)
@@ -2887,13 +2812,6 @@ __arm_vmladavq_p_s8 (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
return __builtin_mve_vmladavq_p_sv16qi (__a, __b, __p);
}
-__extension__ extern __inline int8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_s8 (int8x16_t __inactive, int8_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_sv16qi (__inactive, __a, __p);
-}
-
__extension__ extern __inline int32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p_s8 (int32_t __a, int8x16_t __b, mve_pred16_t __p)
@@ -3090,13 +3008,6 @@ __arm_vmladavaq_u16 (uint32_t __a, uint16x8_t __b, uint16x8_t __c)
return __builtin_mve_vmladavaq_uv8hi (__a, __b, __c);
}
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_u16 (uint16x8_t __inactive, uint16_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_uv8hi (__inactive, __a, __p);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p_u16 (uint32_t __a, uint16x8_t __b, mve_pred16_t __p)
@@ -3153,13 +3064,6 @@ __arm_vmladavq_p_s16 (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
return __builtin_mve_vmladavq_p_sv8hi (__a, __b, __p);
}
-__extension__ extern __inline int16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_s16 (int16x8_t __inactive, int16_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_sv8hi (__inactive, __a, __p);
-}
-
__extension__ extern __inline int32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p_s16 (int32_t __a, int16x8_t __b, mve_pred16_t __p)
@@ -3356,13 +3260,6 @@ __arm_vmladavaq_u32 (uint32_t __a, uint32x4_t __b, uint32x4_t __c)
return __builtin_mve_vmladavaq_uv4si (__a, __b, __c);
}
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_u32 (uint32x4_t __inactive, uint32_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_uv4si (__inactive, __a, __p);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p_u32 (uint32_t __a, uint32x4_t __b, mve_pred16_t __p)
@@ -3419,13 +3316,6 @@ __arm_vmladavq_p_s32 (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
return __builtin_mve_vmladavq_p_sv4si (__a, __b, __p);
}
-__extension__ extern __inline int32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_s32 (int32x4_t __inactive, int32_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_sv4si (__inactive, __a, __p);
-}
-
__extension__ extern __inline int32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p_s32 (int32_t __a, int32x4_t __b, mve_pred16_t __p)
@@ -6905,48 +6795,6 @@ __arm_viwdupq_x_wb_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16
return __res;
}
-__extension__ extern __inline int8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_s8 (int8_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_sv16qi (__arm_vuninitializedq_s8 (), __a, __p);
-}
-
-__extension__ extern __inline int16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_s16 (int16_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_sv8hi (__arm_vuninitializedq_s16 (), __a, __p);
-}
-
-__extension__ extern __inline int32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_s32 (int32_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_sv4si (__arm_vuninitializedq_s32 (), __a, __p);
-}
-
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_u8 (uint8_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_uv16qi (__arm_vuninitializedq_u8 (), __a, __p);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_u16 (uint16_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_uv8hi (__arm_vuninitializedq_u16 (), __a, __p);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_u32 (uint32_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_uv4si (__arm_vuninitializedq_u32 (), __a, __p);
-}
-
__extension__ extern __inline uint16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vmullbq_poly_x_p8 (uint8x16_t __a, uint8x16_t __b, mve_pred16_t __p)
@@ -8157,20 +8005,6 @@ __arm_vst4q_f32 (float32_t * __addr, float32x4x4_t __value)
__builtin_mve_vst4qv4sf (__addr, __rv.__o);
}
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_f16 (float16_t __a)
-{
- return __builtin_mve_vdupq_n_fv8hf (__a);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n_f32 (float32_t __a)
-{
- return __builtin_mve_vdupq_n_fv4sf (__a);
-}
-
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vcvttq_f32_f16 (float16x8_t __a)
@@ -8718,13 +8552,6 @@ __arm_vcvtq_m_s16_f16 (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
return __builtin_mve_vcvtq_m_from_f_sv8hi (__inactive, __a, __p);
}
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_f16 (float16x8_t __inactive, float16_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_fv8hf (__inactive, __a, __p);
-}
-
__extension__ extern __inline float16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vpselq_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
@@ -8844,13 +8671,6 @@ __arm_vcvtq_m_s32_f32 (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
return __builtin_mve_vcvtq_m_from_f_sv4si (__inactive, __a, __p);
}
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m_n_f32 (float32x4_t __inactive, float32_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_fv4sf (__inactive, __a, __p);
-}
-
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vpselq_f32 (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
@@ -9438,20 +9258,6 @@ __arm_vstrwq_scatter_base_wb_p_f32 (uint32x4_t * __addr, const int __offset, flo
*__addr = __builtin_mve_vstrwq_scatter_base_wb_p_fv4sf (*__addr, __offset, __value, __p);
}
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_f16 (float16_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_fv8hf (__arm_vuninitializedq_f16 (), __a, __p);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_x_n_f32 (float32_t __a, mve_pred16_t __p)
-{
- return __builtin_mve_vdupq_m_n_fv4sf (__arm_vuninitializedq_f32 (), __a, __p);
-}
-
__extension__ extern __inline float16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vcaddq_rot90_x_f16 (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
@@ -9976,27 +9782,6 @@ __arm_vst4q (uint32_t * __addr, uint32x4x4_t __value)
__arm_vst4q_u32 (__addr, __value);
}
-__extension__ extern __inline int8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (int8_t __a)
-{
- return __arm_vdupq_n_s8 (__a);
-}
-
-__extension__ extern __inline int16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (int16_t __a)
-{
- return __arm_vdupq_n_s16 (__a);
-}
-
-__extension__ extern __inline int32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (int32_t __a)
-{
- return __arm_vdupq_n_s32 (__a);
-}
-
__extension__ extern __inline int64_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddlvq (int32x4_t __a)
@@ -10095,27 +9880,6 @@ __arm_vmvnq (uint32x4_t __a)
return __arm_vmvnq_u32 (__a);
}
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (uint8_t __a)
-{
- return __arm_vdupq_n_u8 (__a);
-}
-
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (uint16_t __a)
-{
- return __arm_vdupq_n_u16 (__a);
-}
-
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (uint32_t __a)
-{
- return __arm_vdupq_n_u32 (__a);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvq (uint8x16_t __a)
@@ -11138,13 +10902,6 @@ __arm_vmladavaq (uint32_t __a, uint8x16_t __b, uint8x16_t __c)
return __arm_vmladavaq_u8 (__a, __b, __c);
}
-__extension__ extern __inline uint8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (uint8x16_t __inactive, uint8_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_u8 (__inactive, __a, __p);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p (uint32_t __a, uint8x16_t __b, mve_pred16_t __p)
@@ -11201,13 +10958,6 @@ __arm_vmladavq_p (int8x16_t __a, int8x16_t __b, mve_pred16_t __p)
return __arm_vmladavq_p_s8 (__a, __b, __p);
}
-__extension__ extern __inline int8x16_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (int8x16_t __inactive, int8_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_s8 (__inactive, __a, __p);
-}
-
__extension__ extern __inline int32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p (int32_t __a, int8x16_t __b, mve_pred16_t __p)
@@ -11404,13 +11154,6 @@ __arm_vmladavaq (uint32_t __a, uint16x8_t __b, uint16x8_t __c)
return __arm_vmladavaq_u16 (__a, __b, __c);
}
-__extension__ extern __inline uint16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (uint16x8_t __inactive, uint16_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_u16 (__inactive, __a, __p);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p (uint32_t __a, uint16x8_t __b, mve_pred16_t __p)
@@ -11467,13 +11210,6 @@ __arm_vmladavq_p (int16x8_t __a, int16x8_t __b, mve_pred16_t __p)
return __arm_vmladavq_p_s16 (__a, __b, __p);
}
-__extension__ extern __inline int16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (int16x8_t __inactive, int16_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_s16 (__inactive, __a, __p);
-}
-
__extension__ extern __inline int32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p (int32_t __a, int16x8_t __b, mve_pred16_t __p)
@@ -11670,13 +11406,6 @@ __arm_vmladavaq (uint32_t __a, uint32x4_t __b, uint32x4_t __c)
return __arm_vmladavaq_u32 (__a, __b, __c);
}
-__extension__ extern __inline uint32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (uint32x4_t __inactive, uint32_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_u32 (__inactive, __a, __p);
-}
-
__extension__ extern __inline uint32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p (uint32_t __a, uint32x4_t __b, mve_pred16_t __p)
@@ -11733,13 +11462,6 @@ __arm_vmladavq_p (int32x4_t __a, int32x4_t __b, mve_pred16_t __p)
return __arm_vmladavq_p_s32 (__a, __b, __p);
}
-__extension__ extern __inline int32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (int32x4_t __inactive, int32_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_s32 (__inactive, __a, __p);
-}
-
__extension__ extern __inline int32_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vaddvaq_p (int32_t __a, int32x4_t __b, mve_pred16_t __p)
@@ -15746,20 +15468,6 @@ __arm_vst4q (float32_t * __addr, float32x4x4_t __value)
__arm_vst4q_f32 (__addr, __value);
}
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (float16_t __a)
-{
- return __arm_vdupq_n_f16 (__a);
-}
-
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_n (float32_t __a)
-{
- return __arm_vdupq_n_f32 (__a);
-}
-
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vcvttq_f32 (float16x8_t __a)
@@ -16124,13 +15832,6 @@ __arm_vcvtq_m (int16x8_t __inactive, float16x8_t __a, mve_pred16_t __p)
return __arm_vcvtq_m_s16_f16 (__inactive, __a, __p);
}
-__extension__ extern __inline float16x8_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (float16x8_t __inactive, float16_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_f16 (__inactive, __a, __p);
-}
-
__extension__ extern __inline float16x8_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vpselq (float16x8_t __a, float16x8_t __b, mve_pred16_t __p)
@@ -16250,13 +15951,6 @@ __arm_vcvtq_m (int32x4_t __inactive, float32x4_t __a, mve_pred16_t __p)
return __arm_vcvtq_m_s32_f32 (__inactive, __a, __p);
}
-__extension__ extern __inline float32x4_t
-__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
-__arm_vdupq_m (float32x4_t __inactive, float32_t __a, mve_pred16_t __p)
-{
- return __arm_vdupq_m_n_f32 (__inactive, __a, __p);
-}
-
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
__arm_vpselq (float32x4_t __a, float32x4_t __b, mve_pred16_t __p)
@@ -17337,11 +17031,6 @@ extern void *__ARM_undef;
int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce(__p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x4_t)), \
int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x4_t]: __arm_vst4q_f32 (__ARM_mve_coerce(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));})
-#define __arm_vdupq_n(p0) ({ __typeof(p0) __p0 = (p0); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
- int (*)[__ARM_mve_type_float16x8_t]: __arm_vdupq_n_f16 (__ARM_mve_coerce(__p0, float16x8_t)), \
- int (*)[__ARM_mve_type_float32x4_t]: __arm_vdupq_n_f32 (__ARM_mve_coerce(__p0, float32x4_t)));})
-
#define __arm_vcvtbq_f32(p0) ({ __typeof(p0) __p0 = (p0); \
_Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \
int (*)[__ARM_mve_type_float16x8_t]: __arm_vcvtbq_f32_f16 (__ARM_mve_coerce(__p0, float16x8_t)));})
@@ -17814,18 +17503,6 @@ extern void *__ARM_undef;
int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vcvtpq_m_u16_f16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, float16x8_t), p2), \
int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_float32x4_t]: __arm_vcvtpq_m_u32_f32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, float32x4_t), p2));})
-#define __arm_vdupq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
- __typeof(p1) __p1 = (p1); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), (int8_t) __p1, p2), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), (int16_t) __p1, p2), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), (int32_t) __p1, p2), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint8_t) __p1, p2), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint16_t) __p1, p2), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2), \
- int (*)[__ARM_mve_type_float16x8_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f16 (__ARM_mve_coerce(__p0, float16x8_t), (float16_t) __p1, p2), \
- int (*)[__ARM_mve_type_float32x4_t][__ARM_mve_type_fp_n]: __arm_vdupq_m_n_f32 (__ARM_mve_coerce(__p0, float32x4_t), (float32_t) __p1, p2));})
-
#define __arm_vfmaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
@@ -18713,16 +18390,6 @@ extern void *__ARM_undef;
int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vqdmlsdhxq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \
int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vqdmlsdhxq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t), __ARM_mve_coerce(__p2, int32x4_t)));})
-#define __arm_vdupq_m(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
- __typeof(p1) __p1 = (p1); \
- _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \
- int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s8 (__ARM_mve_coerce(__p0, int8x16_t), (int8_t) __p1, p2), \
- int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), (int16_t) __p1, p2), \
- int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), (int32_t) __p1, p2), \
- int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint8_t) __p1, p2), \
- int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint16_t) __p1, p2), \
- int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2));})
-
#define __arm_vmlaq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \
__typeof(p1) __p1 = (p1); \
__typeof(p2) __p2 = (p2); \
--
2.34.1
next prev parent reply other threads:[~2023-05-10 13:31 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-10 13:30 [PATCH 01/20] arm: [MVE intrinsics] factorize vcmp Christophe Lyon
2023-05-10 13:30 ` [PATCH 02/20] arm: [MVE intrinsics] add cmp shape Christophe Lyon
2023-05-10 13:30 ` [PATCH 03/20] arm: [MVE intrinsics] rework vcmp Christophe Lyon
2023-05-10 13:30 ` [PATCH 04/20] arm: [MVE intrinsics] factorize vrev16q vrev32q vrev64q Christophe Lyon
2023-05-10 13:30 ` [PATCH 05/20] arm: [MVE intrinsics] rework " Christophe Lyon
2023-05-10 13:30 ` [PATCH 06/20] arm: [MVE intrinsics] factorize vdupq Christophe Lyon
2023-05-10 13:30 ` [PATCH 07/20] arm: [MVE intrinsics] add unary_n shape Christophe Lyon
2023-05-10 13:30 ` Christophe Lyon [this message]
2023-05-10 13:30 ` [PATCH 09/20] arm: [MVE intrinsics] factorize vaddvq Christophe Lyon
2023-05-10 13:30 ` [PATCH 10/20] arm: [MVE intrinsics] add unary_int32 shape Christophe Lyon
2023-05-10 13:30 ` [PATCH 11/20] arm: [MVE intrinsics] rework vaddvq Christophe Lyon
2023-05-10 13:30 ` [PATCH 12/20] arm: [MVE intrinsics] factorize vaddvaq Christophe Lyon
2023-05-10 13:30 ` [PATCH 13/20] arm: [MVE intrinsics] add unary_int32_acc shape Christophe Lyon
2023-05-10 13:30 ` [PATCH 14/20] arm: [MVE intrinsics] rework vaddvaq Christophe Lyon
2023-05-10 13:30 ` [PATCH 15/20] arm: [MVE intrinsics] add unary_acc shape Christophe Lyon
2023-05-10 14:52 ` Kyrylo Tkachov
2023-05-11 8:21 ` Christophe Lyon
2023-05-11 8:23 ` Kyrylo Tkachov
2023-05-11 8:24 ` Christophe Lyon
2023-05-11 8:30 ` Richard Sandiford
2023-05-11 9:54 ` Christophe Lyon
2023-05-11 10:58 ` Richard Sandiford
2023-05-10 13:30 ` [PATCH 16/20] arm: [MVE intrinsics] factorize vaddlvq Christophe Lyon
2023-05-10 13:30 ` [PATCH 17/20] arm: [MVE intrinsics] rework vaddlvq Christophe Lyon
2023-05-10 13:30 ` [PATCH 18/20] arm: [MVE intrinsics] factorize vmovlbq vmovltq Christophe Lyon
2023-05-10 13:30 ` [PATCH 19/20] arm: [MVE intrinsics] add unary_widen shape Christophe Lyon
2023-05-10 13:30 ` [PATCH 20/20] arm: [MVE intrinsics] rework vmovlbq vmovltq Christophe Lyon
2023-05-10 16:53 ` [PATCH 01/20] arm: [MVE intrinsics] factorize vcmp Kyrylo Tkachov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230510133036.596530-8-christophe.lyon@arm.com \
--to=christophe.lyon@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=kyrylo.tkachov@arm.com \
--cc=richard.earnshaw@arm.com \
--cc=richard.sandiford@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).