Quelle  svml.h   Sprache: 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      Himanshi Mathur <himanshi18037@iiitd.ac.in>
 */

#if !defined(SIMDE_X86_SVML_H)
#define SIMDE_X86_SVML_H

#include "fma.h"
#include "avx2.h"
#include "avx512/abs.h"
#include "avx512/add.h"
#include "avx512/cmp.h"
#include "avx512/copysign.h"
#include "avx512/xorsign.h"
#include "avx512/div.h"
#include "avx512/fmadd.h"
#include "avx512/mov.h"
#include "avx512/mul.h"
#include "avx512/negate.h"
#include "avx512/or.h"
#include "avx512/set1.h"
#include "avx512/setone.h"
#include "avx512/setzero.h"
#include "avx512/sqrt.h"
#include "avx512/sub.h"

#include "../simde-complex.h"

#if !defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_ENABLE_NATIVE_ALIASES)
#  define SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES
#endif

HEDLEY_DIAGNOSTIC_PUSH
SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
SIMDE_BEGIN_DECLS_

#if !defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_ENABLE_NATIVE_ALIASES)
#  define SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_acos_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_acos_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_acosf4_u10(a);
    #else
      return Sleef_acosf4_u35(a);
    #endif
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_acosf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_acos_ps
  #define _mm_acos_ps(a) simde_mm_acos_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_acos_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_acos_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_acosd2_u10(a);
    #else
      return Sleef_acosd2_u35(a);
    #endif
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_acos(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_acos_pd
  #define _mm_acos_pd(a) simde_mm_acos_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_acos_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_acos_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_acosf8_u10(a);
    #else
      return Sleef_acosf8_u35(a);
    #endif
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_acos_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_acosf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_acos_ps
  #define _mm256_acos_ps(a) simde_mm256_acos_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_acos_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_acos_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_acosd4_u10(a);
    #else
      return Sleef_acosd4_u35(a);
    #endif
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_acos_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_acos(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_acos_pd
  #define _mm256_acos_pd(a) simde_mm256_acos_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_acos_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_acos_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_acosf16_u10(a);
    #else
      return Sleef_acosf16_u35(a);
    #endif
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_acos_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_acosf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_acos_ps
  #define _mm512_acos_ps(a) simde_mm512_acos_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_acos_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_acos_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_acosd8_u10(a);
    #else
      return Sleef_acosd8_u35(a);
    #endif
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_acos_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_acos(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_acos_pd
  #define _mm512_acos_pd(a) simde_mm512_acos_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_acos_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_acos_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_acos_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_acos_ps
  #define _mm512_mask_acos_ps(src, k, a) simde_mm512_mask_acos_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_acos_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_acos_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_acos_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_acos_pd
  #define _mm512_mask_acos_pd(src, k, a) simde_mm512_mask_acos_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_acosh_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_acosh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_acoshf4_u10(a);
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_acoshf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_acosh_ps
  #define _mm_acosh_ps(a) simde_mm_acosh_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_acosh_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_acosh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_acoshd2_u10(a);
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_acosh(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_acosh_pd
  #define _mm_acosh_pd(a) simde_mm_acosh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_acosh_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_acosh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_acoshf8_u10(a);
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_acosh_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_acoshf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_acosh_ps
  #define _mm256_acosh_ps(a) simde_mm256_acosh_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_acosh_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_acosh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_acoshd4_u10(a);
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_acosh_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_acosh(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_acosh_pd
  #define _mm256_acosh_pd(a) simde_mm256_acosh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_acosh_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_acosh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_acoshf16_u10(a);
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_acosh_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_acoshf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_acosh_ps
  #define _mm512_acosh_ps(a) simde_mm512_acosh_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_acosh_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_acosh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_acoshd8_u10(a);
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_acosh_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_acosh(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_acosh_pd
  #define _mm512_acosh_pd(a) simde_mm512_acosh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_acosh_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_acosh_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_acosh_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_acosh_ps
  #define _mm512_mask_acosh_ps(src, k, a) simde_mm512_mask_acosh_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_acosh_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_acosh_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_acosh_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_acosh_pd
  #define _mm512_mask_acosh_pd(src, k, a) simde_mm512_mask_acosh_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_asin_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_asin_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_asinf4_u10(a);
    #else
      return Sleef_asinf4_u35(a);
    #endif
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_asinf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_asin_ps
  #define _mm_asin_ps(a) simde_mm_asin_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_asin_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_asin_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_asind2_u10(a);
    #else
      return Sleef_asind2_u35(a);
    #endif
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_asin(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_asin_pd
  #define _mm_asin_pd(a) simde_mm_asin_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_asin_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_asin_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_asinf8_u10(a);
    #else
      return Sleef_asinf8_u35(a);
    #endif
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_asin_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_asinf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_asin_ps
  #define _mm256_asin_ps(a) simde_mm256_asin_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_asin_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_asin_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_asind4_u10(a);
    #else
      return Sleef_asind4_u35(a);
    #endif
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_asin_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_asin(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_asin_pd
  #define _mm256_asin_pd(a) simde_mm256_asin_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_asin_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_asin_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_asinf16_u10(a);
    #else
      return Sleef_asinf16_u35(a);
    #endif
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_asin_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_asinf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_asin_ps
  #define _mm512_asin_ps(a) simde_mm512_asin_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_asin_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_asin_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_asind8_u10(a);
    #else
      return Sleef_asind8_u35(a);
    #endif
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_asin_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_asin(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_asin_pd
  #define _mm512_asin_pd(a) simde_mm512_asin_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_asin_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_asin_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_asin_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_asin_ps
  #define _mm512_mask_asin_ps(src, k, a) simde_mm512_mask_asin_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_asin_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_asin_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_asin_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_asin_pd
  #define _mm512_mask_asin_pd(src, k, a) simde_mm512_mask_asin_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_asinh_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_asinh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_asinhf4_u10(a);
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_asinhf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_asinh_ps
  #define _mm_asinh_ps(a) simde_mm_asinh_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_asinh_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_asinh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_asinhd2_u10(a);
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_asinh(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_asinh_pd
  #define _mm_asinh_pd(a) simde_mm_asinh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_asinh_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_asinh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_asinhf8_u10(a);
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_asinh_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_asinhf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_asinh_ps
  #define _mm256_asinh_ps(a) simde_mm256_asinh_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_asinh_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_asinh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_asinhd4_u10(a);
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_asinh_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_asinh(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_asinh_pd
  #define _mm256_asinh_pd(a) simde_mm256_asinh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_asinh_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_asinh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_asinhf16_u10(a);
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_asinh_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_asinhf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_asinh_ps
  #define _mm512_asinh_ps(a) simde_mm512_asinh_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_asinh_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_asinh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_asinhd8_u10(a);
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_asinh_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_asinh(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_asinh_pd
  #define _mm512_asinh_pd(a) simde_mm512_asinh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_asinh_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_asinh_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_asinh_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_asinh_ps
  #define _mm512_mask_asinh_ps(src, k, a) simde_mm512_mask_asinh_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_asinh_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_asinh_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_asinh_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_asinh_pd
  #define _mm512_mask_asinh_pd(src, k, a) simde_mm512_mask_asinh_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_atan_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_atan_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atanf4_u10(a);
    #else
      return Sleef_atanf4_u35(a);
    #endif
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_atanf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_atan_ps
  #define _mm_atan_ps(a) simde_mm_atan_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_atan_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_atan_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atand2_u10(a);
    #else
      return Sleef_atand2_u35(a);
    #endif
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_atan(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_atan_pd
  #define _mm_atan_pd(a) simde_mm_atan_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_atan_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_atan_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atanf8_u10(a);
    #else
      return Sleef_atanf8_u35(a);
    #endif
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_atan_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_atanf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_atan_ps
  #define _mm256_atan_ps(a) simde_mm256_atan_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_atan_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_atan_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atand4_u10(a);
    #else
      return Sleef_atand4_u35(a);
    #endif
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_atan_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_atan(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_atan_pd
  #define _mm256_atan_pd(a) simde_mm256_atan_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_atan_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_atan_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atanf16_u10(a);
    #else
      return Sleef_atanf16_u35(a);
    #endif
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_atan_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_atanf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_atan_ps
  #define _mm512_atan_ps(a) simde_mm512_atan_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_atan_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_atan_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atand8_u10(a);
    #else
      return Sleef_atand8_u35(a);
    #endif
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_atan_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_atan(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_atan_pd
  #define _mm512_atan_pd(a) simde_mm512_atan_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_atan_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_atan_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_atan_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_atan_ps
  #define _mm512_mask_atan_ps(src, k, a) simde_mm512_mask_atan_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_atan_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_atan_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_atan_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_atan_pd
  #define _mm512_mask_atan_pd(src, k, a) simde_mm512_mask_atan_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_atan2_ps (simde__m128 a, simde__m128 b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_atan2_ps(a, b);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atan2f4_u10(a, b);
    #else
      return Sleef_atan2f4_u35(a, b);
    #endif
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a),
      b_ = simde__m128_to_private(b);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_atan2f(a_.f32[i], b_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_atan2_ps
  #define _mm_atan2_ps(a, b) simde_mm_atan2_ps(a, b)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_atan2_pd (simde__m128d a, simde__m128d b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_atan2_pd(a, b);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atan2d2_u10(a, b);
    #else
      return Sleef_atan2d2_u35(a, b);
    #endif
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a),
      b_ = simde__m128d_to_private(b);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_atan2(a_.f64[i], b_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_atan2_pd
  #define _mm_atan2_pd(a, b) simde_mm_atan2_pd(a, b)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_atan2_ps (simde__m256 a, simde__m256 b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_atan2_ps(a, b);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atan2f8_u10(a, b);
    #else
      return Sleef_atan2f8_u35(a, b);
    #endif
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a),
      b_ = simde__m256_to_private(b);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_atan2_ps(a_.m128[i], b_.m128[i]);
    }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_atan2f(a_.f32[i], b_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_atan2_ps
  #define _mm256_atan2_ps(a, b) simde_mm256_atan2_ps(a, b)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_atan2_pd (simde__m256d a, simde__m256d b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_atan2_pd(a, b);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atan2d4_u10(a, b);
    #else
      return Sleef_atan2d4_u35(a, b);
    #endif
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a),
      b_ = simde__m256d_to_private(b);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_atan2_pd(a_.m128d[i], b_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_atan2(a_.f64[i], b_.f64[i]);
      }
  #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_atan2_pd
  #define _mm256_atan2_pd(a, b) simde_mm256_atan2_pd(a, b)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_atan2_ps (simde__m512 a, simde__m512 b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_atan2_ps(a, b);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atan2f16_u10(a, b);
    #else
      return Sleef_atan2f16_u35(a, b);
    #endif
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a),
      b_ = simde__m512_to_private(b);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_atan2_ps(a_.m256[i], b_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_atan2f(a_.f32[i], b_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_atan2_ps
  #define _mm512_atan2_ps(a, b) simde_mm512_atan2_ps(a, b)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_atan2_pd (simde__m512d a, simde__m512d b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_atan2_pd(a, b);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_atan2d8_u10(a, b);
    #else
      return Sleef_atan2d8_u35(a, b);
    #endif
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a),
      b_ = simde__m512d_to_private(b);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_atan2_pd(a_.m256d[i], b_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_atan2(a_.f64[i], b_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_atan2_pd
  #define _mm512_atan2_pd(a, b) simde_mm512_atan2_pd(a, b)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_atan2_ps(simde__m512 src, simde__mmask16 k, simde__m512 a, simde__m512 b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_atan2_ps(src, k, a, b);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_atan2_ps(a, b));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_atan2_ps
  #define _mm512_mask_atan2_ps(src, k, a, b) simde_mm512_mask_atan2_ps(src, k, a, b)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_atan2_pd(simde__m512d src, simde__mmask8 k, simde__m512d a, simde__m512d b) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_atan2_pd(src, k, a, b);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_atan2_pd(a, b));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_atan2_pd
  #define _mm512_mask_atan2_pd(src, k, a, b) simde_mm512_mask_atan2_pd(src, k, a, b)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_atanh_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_atanh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_atanhf4_u10(a);
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_atanhf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_atanh_ps
  #define _mm_atanh_ps(a) simde_mm_atanh_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_atanh_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_atanh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_atanhd2_u10(a);
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_atanh(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_atanh_pd
  #define _mm_atanh_pd(a) simde_mm_atanh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_atanh_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_atanh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_atanhf8_u10(a);
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_atanh_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_atanhf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_atanh_ps
  #define _mm256_atanh_ps(a) simde_mm256_atanh_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_atanh_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_atanh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_atanhd4_u10(a);
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_atanh_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_atanh(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_atanh_pd
  #define _mm256_atanh_pd(a) simde_mm256_atanh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_atanh_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_atanh_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_atanhf16_u10(a);
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_atanh_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_atanhf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_atanh_ps
  #define _mm512_atanh_ps(a) simde_mm512_atanh_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_atanh_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_atanh_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_atanhd8_u10(a);
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_atanh_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_atanh(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_atanh_pd
  #define _mm512_atanh_pd(a) simde_mm512_atanh_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_atanh_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_atanh_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_atanh_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_atanh_ps
  #define _mm512_mask_atanh_ps(src, k, a) simde_mm512_mask_atanh_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_atanh_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_atanh_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_atanh_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_atanh_pd
  #define _mm512_mask_atanh_pd(src, k, a) simde_mm512_mask_atanh_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_cbrt_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_cbrt_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_cbrtf4_u10(a);
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_cbrtf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_cbrt_ps
  #define _mm_cbrt_ps(a) simde_mm_cbrt_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_cbrt_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_cbrt_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    return Sleef_cbrtd2_u10(a);
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_cbrt(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_cbrt_pd
  #define _mm_cbrt_pd(a) simde_mm_cbrt_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_cbrt_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_cbrt_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_cbrtf8_u10(a);
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_cbrt_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_cbrtf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_cbrt_ps
  #define _mm256_cbrt_ps(a) simde_mm256_cbrt_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_cbrt_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_cbrt_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    return Sleef_cbrtd4_u10(a);
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_cbrt_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_cbrt(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_cbrt_pd
  #define _mm256_cbrt_pd(a) simde_mm256_cbrt_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_cbrt_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_cbrt_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_cbrtf16_u10(a);
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_cbrt_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_cbrtf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_cbrt_ps
  #define _mm512_cbrt_ps(a) simde_mm512_cbrt_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_cbrt_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_cbrt_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return Sleef_cbrtd8_u10(a);
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_cbrt_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_cbrt(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_cbrt_pd
  #define _mm512_cbrt_pd(a) simde_mm512_cbrt_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_cbrt_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_cbrt_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_cbrt_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_cbrt_ps
  #define _mm512_mask_cbrt_ps(src, k, a) simde_mm512_mask_cbrt_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_cbrt_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_cbrt_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_cbrt_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_cbrt_pd
  #define _mm512_mask_cbrt_pd(src, k, a) simde_mm512_mask_cbrt_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_cexp_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_cexp_ps(a);
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i+=2) {
      simde_cfloat32 val = simde_math_cexpf(SIMDE_MATH_CMPLXF(a_.f32[i], a_.f32[i+1]));
      r_.f32[  i  ] = simde_math_crealf(val);
      r_.f32[i + 1] = simde_math_cimagf(val);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_cexp_ps
  #define _mm_cexp_ps(a) simde_mm_cexp_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_cexp_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_cexp_ps(a);
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i+=2) {
      simde_cfloat32 val = simde_math_cexpf(SIMDE_MATH_CMPLXF(a_.f32[i], a_.f32[i+1]));
      r_.f32[  i  ] = simde_math_crealf(val);
      r_.f32[i + 1] = simde_math_cimagf(val);
    }

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_cexp_ps
  #define _mm256_cexp_ps(a) simde_mm256_cexp_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_mm_cos_ps (simde__m128 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_cos_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_cosf4_u10(a);
    #else
      return Sleef_cosf4_u35(a);
    #endif
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
      r_.f32[i] = simde_math_cosf(a_.f32[i]);
    }

    return simde__m128_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_cos_ps
  #define _mm_cos_ps(a) simde_mm_cos_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_mm_cos_pd (simde__m128d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_SSE_NATIVE)
    return _mm_cos_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_SSE_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_cosd2_u10(a);
    #else
      return Sleef_cosd2_u35(a);
    #endif
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    SIMDE_VECTORIZE
    for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
      r_.f64[i] = simde_math_cos(a_.f64[i]);
    }

    return simde__m128d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm_cos_pd
  #define _mm_cos_pd(a) simde_mm_cos_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_mm256_cos_ps (simde__m256 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_cos_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_cosf8_u10(a);
    #else
      return Sleef_cosf8_u35(a);
    #endif
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_mm_cos_ps(a_.m128[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_cosf(a_.f32[i]);
      }
    #endif

    return simde__m256_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_cos_ps
  #define _mm256_cos_ps(a) simde_mm256_cos_ps(a)
#endif


SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_mm256_cos_pd (simde__m256d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX_NATIVE)
    return _mm256_cos_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_cosd4_u10(a);
    #else
      return Sleef_cosd4_u35(a);
    #endif
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_mm_cos_pd(a_.m128d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_cos(a_.f64[i]);
      }
    #endif

    return simde__m256d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm256_cos_pd
  #define _mm256_cos_pd(a) simde_mm256_cos_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_cos_ps (simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_cos_ps(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_cosf16_u10(a);
    #else
      return Sleef_cosf16_u35(a);
    #endif
  #else
    simde__m512_private
      r_,
      a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256) / sizeof(r_.m256[0])) ; i++) {
        r_.m256[i] = simde_mm256_cos_ps(a_.m256[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_cosf(a_.f32[i]);
      }
    #endif

    return simde__m512_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_cos_ps
  #define _mm512_cos_ps(a) simde_mm512_cos_ps(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_cos_pd (simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_cos_pd(a);
  #elif defined(SIMDE_MATH_SLEEF_ENABLE) && defined(SIMDE_X86_AVX512F_NATIVE)
    #if SIMDE_ACCURACY_PREFERENCE > 1
      return Sleef_cosd8_u10(a);
    #else
      return Sleef_cosd8_u35(a);
    #endif
  #else
    simde__m512d_private
      r_,
      a_ = simde__m512d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
      for (size_t i = 0 ; i < (sizeof(r_.m256d) / sizeof(r_.m256d[0])) ; i++) {
        r_.m256d[i] = simde_mm256_cos_pd(a_.m256d[i]);
      }
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_cos(a_.f64[i]);
      }
    #endif

    return simde__m512d_from_private(r_);
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_cos_pd
  #define _mm512_cos_pd(a) simde_mm512_cos_pd(a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_mm512_mask_cos_ps(simde__m512 src, simde__mmask16 k, simde__m512 a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_cos_ps(src, k, a);
  #else
    return simde_mm512_mask_mov_ps(src, k, simde_mm512_cos_ps(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_cos_ps
  #define _mm512_mask_cos_ps(src, k, a) simde_mm512_mask_cos_ps(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m512d
simde_mm512_mask_cos_pd(simde__m512d src, simde__mmask8 k, simde__m512d a) {
  #if defined(SIMDE_X86_SVML_NATIVE) && defined(SIMDE_X86_AVX512F_NATIVE)
    return _mm512_mask_cos_pd(src, k, a);
  #else
    return simde_mm512_mask_mov_pd(src, k, simde_mm512_cos_pd(a));
  #endif
}
#if defined(SIMDE_X86_SVML_ENABLE_NATIVE_ALIASES)
  #undef _mm512_mask_cos_pd
  #define _mm512_mask_cos_pd(src, k, a) simde_mm512_mask_cos_pd(src, k, a)
#endif

SIMDE_FUNCTION_ATTRIBUTES
simde__m128
simde_x_mm_deg2rad_ps(simde__m128 a) {
  #if SIMDE_NATURAL_VECTOR_SIZE_GE(128)
    return simde_mm_mul_ps(a, simde_mm_set1_ps(SIMDE_MATH_PI_OVER_180F));
  #else
    simde__m128_private
      r_,
      a_ = simde__m128_to_private(a);

    #if defined(SIMDE_ARM_NEON_A32V7_NATIVE)
      r_.neon_f32 = vmulq_n_f32(a_.neon_i32, SIMDE_MATH_PI_OVER_180F);
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && !defined(SIMDE_BUG_GCC_53784)
      r_.f32 = a_.f32 * SIMDE_MATH_PI_OVER_180F;
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
    const __typeof__(r_.f32) tmp = { SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F };
      r_.f32 = a_.f32 * tmp;
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_deg2radf(a_.f32[i]);
      }

    #endif
    return simde__m128_from_private(r_);
  #endif
}

SIMDE_FUNCTION_ATTRIBUTES
simde__m128d
simde_x_mm_deg2rad_pd(simde__m128d a) {
  #if SIMDE_NATURAL_VECTOR_SIZE_GE(128)
      return simde_mm_mul_pd(a, simde_mm_set1_pd(SIMDE_MATH_PI_OVER_180));
  #else
    simde__m128d_private
      r_,
      a_ = simde__m128d_to_private(a);

    #if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
      r_.neon_f64 = vmulq_n_f64(a_.neon_i64, SIMDE_MATH_PI_OVER_180);
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && !defined(SIMDE_BUG_GCC_53784)
    r_.f64 = a_.f64 * SIMDE_MATH_PI_OVER_180;
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
    const __typeof__(r_.f64) tmp = { SIMDE_MATH_PI_OVER_180, SIMDE_MATH_PI_OVER_180 };
      r_.f64 = a_.f64 * tmp;
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_deg2rad(a_.f64[i]);
      }

    #endif
    return simde__m128d_from_private(r_);
  #endif
}

SIMDE_FUNCTION_ATTRIBUTES
simde__m256
simde_x_mm256_deg2rad_ps(simde__m256 a) {
  #if SIMDE_NATURAL_VECTOR_SIZE_GE(256)
    return simde_mm256_mul_ps(a, simde_mm256_set1_ps(SIMDE_MATH_PI_OVER_180F));
  #else
    simde__m256_private
      r_,
      a_ = simde__m256_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128) / sizeof(r_.m128[0])) ; i++) {
        r_.m128[i] = simde_x_mm_deg2rad_ps(a_.m128[i]);
      }
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && !defined(SIMDE_BUG_GCC_53784)
    r_.f32 = a_.f32 * SIMDE_MATH_PI_OVER_180F;
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
    const __typeof__(r_.f32) tmp = {
        SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F,
        SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F, SIMDE_MATH_PI_OVER_180F
      };
      r_.f32 = a_.f32 * tmp;
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f32) / sizeof(r_.f32[0])) ; i++) {
        r_.f32[i] = simde_math_deg2radf(a_.f32[i]);
      }

    #endif
    return simde__m256_from_private(r_);
  #endif
}

SIMDE_FUNCTION_ATTRIBUTES
simde__m256d
simde_x_mm256_deg2rad_pd(simde__m256d a) {
  #if SIMDE_NATURAL_VECTOR_SIZE_GE(256)
    return simde_mm256_mul_pd(a, simde_mm256_set1_pd(SIMDE_MATH_PI_OVER_180));
  #else
    simde__m256d_private
      r_,
      a_ = simde__m256d_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(128)
      for (size_t i = 0 ; i < (sizeof(r_.m128d) / sizeof(r_.m128d[0])) ; i++) {
        r_.m128d[i] = simde_x_mm_deg2rad_pd(a_.m128d[i]);
      }
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_SCALAR) && !defined(SIMDE_BUG_GCC_53784)
    r_.f64 = a_.f64 * SIMDE_MATH_PI_OVER_180;
    #elif defined(SIMDE_VECTOR_SUBSCRIPT_OPS)
    const __typeof__(r_.f64) tmp = { SIMDE_MATH_PI_OVER_180, SIMDE_MATH_PI_OVER_180, SIMDE_MATH_PI_OVER_180, SIMDE_MATH_PI_OVER_180 };
      r_.f64 = a_.f64 * tmp;
    #else
      SIMDE_VECTORIZE
      for (size_t i = 0 ; i < (sizeof(r_.f64) / sizeof(r_.f64[0])) ; i++) {
        r_.f64[i] = simde_math_deg2rad(a_.f64[i]);
      }

    #endif
    return simde__m256d_from_private(r_);
  #endif
}

SIMDE_FUNCTION_ATTRIBUTES
simde__m512
simde_x_mm512_deg2rad_ps(simde__m512 a) {
  #if SIMDE_NATURAL_VECTOR_SIZE_GE(512)
      return simde_mm512_mul_ps(a, simde_mm512_set1_ps(SIMDE_MATH_PI_OVER_180F));
  #else
    simde__m512_private
        r_,
        a_ = simde__m512_to_private(a);

    #if SIMDE_NATURAL_VECTOR_SIZE_LE(256)
--> --------------------

--> maximum size reached

--> --------------------