stk-code_catmod/lib/simd_wrapper/simde/arm/neon/orr.h
2022-04-29 11:02:25 +08:00

553 lines
16 KiB
C

/* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy,
* modify, merge, publish, distribute, sublicense, and/or sell copies
* of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
* Copyright:
* 2020 Evan Nemerson <evan@nemerson.com>
* 2020 Christopher Moore <moore@free.fr>
*/
#if !defined(SIMDE_ARM_NEON_ORR_H)
#define SIMDE_ARM_NEON_ORR_H
#include "types.h"
HEDLEY_DIAGNOSTIC_PUSH
SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
SIMDE_BEGIN_DECLS_
SIMDE_FUNCTION_ATTRIBUTES
simde_int8x8_t
simde_vorr_s8(simde_int8x8_t a, simde_int8x8_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_s8(a, b);
#else
simde_int8x8_private
r_,
a_ = simde_int8x8_to_private(a),
b_ = simde_int8x8_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int8x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_s8
#define vorr_s8(a, b) simde_vorr_s8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int16x4_t
simde_vorr_s16(simde_int16x4_t a, simde_int16x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_s16(a, b);
#else
simde_int16x4_private
r_,
a_ = simde_int16x4_to_private(a),
b_ = simde_int16x4_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_s16
#define vorr_s16(a, b) simde_vorr_s16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int32x2_t
simde_vorr_s32(simde_int32x2_t a, simde_int32x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_s32(a, b);
#else
simde_int32x2_private
r_,
a_ = simde_int32x2_to_private(a),
b_ = simde_int32x2_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int32x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_s32
#define vorr_s32(a, b) simde_vorr_s32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int64x1_t
simde_vorr_s64(simde_int64x1_t a, simde_int64x1_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_s64(a, b);
#else
simde_int64x1_private
r_,
a_ = simde_int64x1_to_private(a),
b_ = simde_int64x1_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int64x1_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_s64
#define vorr_s64(a, b) simde_vorr_s64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint8x8_t
simde_vorr_u8(simde_uint8x8_t a, simde_uint8x8_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_u8(a, b);
#else
simde_uint8x8_private
r_,
a_ = simde_uint8x8_to_private(a),
b_ = simde_uint8x8_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint8x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_u8
#define vorr_u8(a, b) simde_vorr_u8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint16x4_t
simde_vorr_u16(simde_uint16x4_t a, simde_uint16x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_u16(a, b);
#else
simde_uint16x4_private
r_,
a_ = simde_uint16x4_to_private(a),
b_ = simde_uint16x4_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_u16
#define vorr_u16(a, b) simde_vorr_u16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint32x2_t
simde_vorr_u32(simde_uint32x2_t a, simde_uint32x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_u32(a, b);
#else
simde_uint32x2_private
r_,
a_ = simde_uint32x2_to_private(a),
b_ = simde_uint32x2_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint32x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_u32
#define vorr_u32(a, b) simde_vorr_u32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint64x1_t
simde_vorr_u64(simde_uint64x1_t a, simde_uint64x1_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorr_u64(a, b);
#else
simde_uint64x1_private
r_,
a_ = simde_uint64x1_to_private(a),
b_ = simde_uint64x1_to_private(b);
#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_or_si64(a_.m64, b_.m64);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint64x1_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorr_u64
#define vorr_u64(a, b) simde_vorr_u64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int8x16_t
simde_vorrq_s8(simde_int8x16_t a, simde_int8x16_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_s8(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P6_NATIVE)
return vec_or(a, b);
#else
simde_int8x16_private
r_,
a_ = simde_int8x16_to_private(a),
b_ = simde_int8x16_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_s8
#define vorrq_s8(a, b) simde_vorrq_s8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int16x8_t
simde_vorrq_s16(simde_int16x8_t a, simde_int16x8_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_s16(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P6_NATIVE)
return vec_or(a, b);
#else
simde_int16x8_private
r_,
a_ = simde_int16x8_to_private(a),
b_ = simde_int16x8_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_s16
#define vorrq_s16(a, b) simde_vorrq_s16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int32x4_t
simde_vorrq_s32(simde_int32x4_t a, simde_int32x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_s32(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P6_NATIVE)
return vec_or(a, b);
#else
simde_int32x4_private
r_,
a_ = simde_int32x4_to_private(a),
b_ = simde_int32x4_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int32x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_s32
#define vorrq_s32(a, b) simde_vorrq_s32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int64x2_t
simde_vorrq_s64(simde_int64x2_t a, simde_int64x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_s64(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P7_NATIVE)
return vec_or(a, b);
#else
simde_int64x2_private
r_,
a_ = simde_int64x2_to_private(a),
b_ = simde_int64x2_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_int64x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_s64
#define vorrq_s64(a, b) simde_vorrq_s64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint8x16_t
simde_vorrq_u8(simde_uint8x16_t a, simde_uint8x16_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_u8(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P6_NATIVE)
return vec_or(a, b);
#else
simde_uint8x16_private
r_,
a_ = simde_uint8x16_to_private(a),
b_ = simde_uint8x16_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_u8
#define vorrq_u8(a, b) simde_vorrq_u8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint16x8_t
simde_vorrq_u16(simde_uint16x8_t a, simde_uint16x8_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_u16(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P6_NATIVE)
return vec_or(a, b);
#else
simde_uint16x8_private
r_,
a_ = simde_uint16x8_to_private(a),
b_ = simde_uint16x8_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_u16
#define vorrq_u16(a, b) simde_vorrq_u16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint32x4_t
simde_vorrq_u32(simde_uint32x4_t a, simde_uint32x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_u32(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P6_NATIVE)
return vec_or(a, b);
#else
simde_uint32x4_private
r_,
a_ = simde_uint32x4_to_private(a),
b_ = simde_uint32x4_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint32x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_u32
#define vorrq_u32(a, b) simde_vorrq_u32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint64x2_t
simde_vorrq_u64(simde_uint64x2_t a, simde_uint64x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
return vorrq_u64(a, b);
#elif defined(SIMDE_POWER_ALTIVEC_P7_NATIVE)
return vec_or(a, b);
#else
simde_uint64x2_private
r_,
a_ = simde_uint64x2_to_private(a),
b_ = simde_uint64x2_to_private(b);
#if defined(SIMDE_X86_SSE2_NATIVE)
r_.m128i = _mm_or_si128(a_.m128i, b_.m128i);
#elif defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_v128_or(a_.v128, b_.v128);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values | b_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] | b_.values[i];
}
#endif
return simde_uint64x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#undef vorrq_u64
#define vorrq_u64(a, b) simde_vorrq_u64((a), (b))
#endif
SIMDE_END_DECLS_
HEDLEY_DIAGNOSTIC_POP
#endif /* !defined(SIMDE_ARM_NEON_ORR_H) */