Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions thirdparty/simde/arm/neon/abd.h
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ simde_vabdh_f16(simde_float16_t a, simde_float16_t b) {
return r_ < 0 ? simde_float16_from_float32(-r_) : simde_float16_from_float32(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && !defined(SIMDE_ARM_NEON_FP16))
#undef vabdh_f16
#define vabdh_f16(a, b) simde_vabdh_f16((a), (b))
#endif
Expand Down Expand Up @@ -94,7 +94,7 @@ simde_vabd_f16(simde_float16x4_t a, simde_float16x4_t b) {
return simde_vabs_f16(simde_vsub_f16(a, b));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && !defined(SIMDE_ARM_NEON_FP16))
#undef vabd_f16
#define vabd_f16(a, b) simde_vabd_f16((a), (b))
#endif
Expand Down Expand Up @@ -315,7 +315,7 @@ simde_vabdq_f16(simde_float16x8_t a, simde_float16x8_t b) {
return simde_vabsq_f16(simde_vsubq_f16(a, b));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && !defined(SIMDE_ARM_NEON_FP16))
#undef vabdq_f16
#define vabdq_f16(a, b) simde_vabdq_f16((a), (b))
#endif
Expand Down
18 changes: 11 additions & 7 deletions thirdparty/simde/arm/neon/abs.h
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,8 @@ simde_vabsd_s64(int64_t a) {
return a < 0 ? -a : a;
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(!defined(HEDLEY_GCC_VERSION) || HEDLEY_GCC_VERSION_CHECK(9,1,0)))
#undef vabsd_s64
#define vabsd_s64(a) simde_vabsd_s64(a)
#endif
Expand All @@ -60,7 +61,8 @@ simde_vabsh_f16(simde_float16_t a) {
return (a_ >= 0.0f) ? simde_float16_from_float32(a_) : simde_float16_from_float32(-a_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vabsh_f16
#define vabsh_f16(a) simde_vabsh_f16(a)
#endif
Expand All @@ -87,7 +89,8 @@ simde_vabs_f16(simde_float16x4_t a) {
return simde_float16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vabs_f16
#define vabs_f16(a) simde_vabs_f16(a)
#endif
Expand Down Expand Up @@ -166,7 +169,7 @@ simde_vabs_s8(simde_int8x8_t a) {
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] < 0 ? -a_.values[i] : a_.values[i];
r_.values[i] = a_.values[i] < 0 ? HEDLEY_STATIC_CAST(int8_t, -a_.values[i]) : a_.values[i];
}
#endif

Expand Down Expand Up @@ -294,7 +297,8 @@ simde_vabsq_f16(simde_float16x8_t a) {
return simde_float16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vabsq_f16
#define vabsq_f16(a) simde_vabsq_f16(a)
#endif
Expand Down Expand Up @@ -395,7 +399,7 @@ simde_vabsq_s8(simde_int8x16_t a) {
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] < 0 ? -a_.values[i] : a_.values[i];
r_.values[i] = a_.values[i] < 0 ? HEDLEY_STATIC_CAST(int8_t, -a_.values[i]) : a_.values[i];
}
#endif

Expand Down Expand Up @@ -433,7 +437,7 @@ simde_vabsq_s16(simde_int16x8_t a) {
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] = a_.values[i] < 0 ? -a_.values[i] : a_.values[i];
r_.values[i] = a_.values[i] < 0 ? HEDLEY_STATIC_CAST(int16_t, -a_.values[i]) : a_.values[i];
}
#endif

Expand Down
33 changes: 23 additions & 10 deletions thirdparty/simde/arm/neon/add.h
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,8 @@ simde_vaddh_f16(simde_float16_t a, simde_float16_t b) {
return simde_float16_from_float32(af + bf);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vaddh_f16
#define vaddh_f16(a, b) simde_vaddh_f16((a), (b))
#endif
Expand Down Expand Up @@ -102,7 +103,8 @@ simde_vadd_f16(simde_float16x4_t a, simde_float16x4_t b) {
return simde_float16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vadd_f16
#define vadd_f16(a, b) simde_vadd_f16((a), (b))
#endif
Expand Down Expand Up @@ -437,7 +439,8 @@ simde_vaddq_f16(simde_float16x8_t a, simde_float16x8_t b) {
return simde_float16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vaddq_f16
#define vaddq_f16(a, b) simde_vaddq_f16((a), (b))
#endif
Expand Down Expand Up @@ -809,7 +812,8 @@ simde_vadd_p8(simde_poly8x8_t a, simde_poly8x8_t b) {
return simde_poly8x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
defined(_GCC_ARM_NEON_H))
#undef vadd_p8
#define vadd_p8(a, b) simde_vadd_p8((a), (b))
#endif
Expand All @@ -833,7 +837,8 @@ simde_vadd_p16(simde_poly16x4_t a, simde_poly16x4_t b) {
return simde_poly16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
defined(_GCC_ARM_NEON_H))
#undef vadd_p16
#define vadd_p16(a, b) simde_vadd_p16((a), (b))
#endif
Expand All @@ -858,7 +863,9 @@ simde_vadd_p64(simde_poly64x1_t a, simde_poly64x1_t b) {
return simde_poly64x1_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_CRYPTO) && \
!defined(_GCC_ARM_NEON_H)))
#undef vadd_p64
#define vadd_p64(a, b) simde_vadd_p64((a), (b))
#endif
Expand All @@ -882,7 +889,8 @@ simde_vaddq_p8(simde_poly8x16_t a, simde_poly8x16_t b) {
return simde_poly8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
defined(_GCC_ARM_NEON_H))
#undef vaddq_p8
#define vaddq_p8(a, b) simde_vaddq_p8((a), (b))
#endif
Expand All @@ -906,7 +914,8 @@ simde_vaddq_p16(simde_poly16x8_t a, simde_poly16x8_t b) {
return simde_poly16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
defined(_GCC_ARM_NEON_H))
#undef vaddq_p16
#define vaddq_p16(a, b) simde_vaddq_p16((a), (b))
#endif
Expand All @@ -931,7 +940,9 @@ simde_vaddq_p64(simde_poly64x2_t a, simde_poly64x2_t b) {
return simde_poly64x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_CRYPTO) && \
!defined(_GCC_ARM_NEON_H)))
#undef vaddq_p64
#define vaddq_p64(a, b) simde_vaddq_p64((a), (b))
#endif
Expand All @@ -950,7 +961,9 @@ simde_vaddq_p128(simde_poly128_t a, simde_poly128_t b) {
return b ^ ((0 ^ a) & mask);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_CRYPTO) && \
!defined(_GCC_ARM_NEON_H)))
#undef vaddq_p128
#define vaddq_p128(a, b) simde_vaddq_p128((a), (b))
#endif
Expand Down
12 changes: 8 additions & 4 deletions thirdparty/simde/arm/neon/aes.h
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,8 @@ simde_vaeseq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
return simde_uint8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARCH_ARM_AES)))
#undef vaeseq_u8
#define vaeseq_u8(data, key) simde_vaeseq_u8((data), (key))
#endif
Expand Down Expand Up @@ -132,7 +133,8 @@ simde_vaesdq_u8(simde_uint8x16_t data, simde_uint8x16_t key) {
return simde_uint8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARCH_ARM_AES)))
#undef vaesdq_u8
#define vaesdq_u8(data, key) simde_vaesdq_u8((data), (key))
#endif
Expand Down Expand Up @@ -160,7 +162,8 @@ simde_vaesmcq_u8(simde_uint8x16_t data) {
return simde_uint8x16_from_private(a_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARCH_ARM_AES)))
#undef vaesmcq_u8
#define vaesmcq_u8(data) simde_vaesmcq_u8((data))
#endif
Expand Down Expand Up @@ -207,7 +210,8 @@ simde_vaesimcq_u8(simde_uint8x16_t data) {
return simde_uint8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARCH_ARM_AES)))
#undef vaesimcq_u8
#define vaesimcq_u8(data) simde_vaesimcq_u8((data))
#endif
Expand Down
2 changes: 1 addition & 1 deletion thirdparty/simde/arm/neon/and.h
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ simde_vand_s32(simde_int32x2_t a, simde_int32x2_t b) {

#if defined(SIMDE_X86_MMX_NATIVE)
r_.m64 = _mm_and_si64(a_.m64, b_.m64);
#elif defined(SIMDE_RISCV_V_NATIVE)
#elif defined(SIMDE_RISCV_V_NATIVE)
r_.sv64 = __riscv_vand_vv_i32m1(a_.sv64, b_.sv64, 2);
#elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
r_.values = a_.values & b_.values;
Expand Down
6 changes: 4 additions & 2 deletions thirdparty/simde/arm/neon/bsl.h
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,8 @@ simde_vbsl_f16(simde_uint16x4_t a, simde_float16x4_t b, simde_float16x4_t c) {
return simde_vreinterpret_f16_u16(simde_uint16x4_from_private(r_));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vbsl_f16
#define vbsl_f16(a, b, c) simde_vbsl_f16((a), (b), (c))
#endif
Expand Down Expand Up @@ -381,7 +382,8 @@ simde_vbslq_f16(simde_uint16x8_t a, simde_float16x8_t b, simde_float16x8_t c) {
return simde_vreinterpretq_f16_u16(simde_uint16x8_from_private(r_));
#endif
}
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES)
#if defined(SIMDE_ARM_NEON_A32V7_ENABLE_NATIVE_ALIASES) || (defined(SIMDE_ENABLE_NATIVE_ALIASES) && \
!(defined(SIMDE_ARM_NEON_FP16)))
#undef vbslq_f16
#define vbslq_f16(a, b, c) simde_vbslq_f16((a), (b), (c))
#endif
Expand Down
Loading
Loading