404 Not Found

PATH: lib64 / llvm17 / lib / clang / 17 / include

/*===------------- avx512vlvbmi2intrin.h - VBMI2 intrinsics -----------------===
 *
 *
 * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 * See https://llvm.org/LICENSE.txt for license information.
 * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */
#ifndef __IMMINTRIN_H
#error "Never use <avx512vlvbmi2intrin.h> directly; include <immintrin.h> instead."
#endif

#ifndef __AVX512VLVBMI2INTRIN_H
#define __AVX512VLVBMI2INTRIN_H

/* Define the default attributes for the functions in this file. */
#define __DEFAULT_FN_ATTRS128 __attribute__((__always_inline__, __nodebug__, __target__("avx512vl,avx512vbmi2"), __min_vector_width__(128)))
#define __DEFAULT_FN_ATTRS256 __attribute__((__always_inline__, __nodebug__, __target__("avx512vl,avx512vbmi2"), __min_vector_width__(256)))

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_compress_epi16(__m128i __S, __mmask8 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_compresshi128_mask ((__v8hi) __D,
              (__v8hi) __S,
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_compress_epi16(__mmask8 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_compresshi128_mask ((__v8hi) __D,
              (__v8hi) _mm_setzero_si128(),
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_compress_epi8(__m128i __S, __mmask16 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_compressqi128_mask ((__v16qi) __D,
              (__v16qi) __S,
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_compress_epi8(__mmask16 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_compressqi128_mask ((__v16qi) __D,
              (__v16qi) _mm_setzero_si128(),
              __U);
}

static __inline__ void __DEFAULT_FN_ATTRS128
_mm_mask_compressstoreu_epi16(void *__P, __mmask8 __U, __m128i __D)
{
  __builtin_ia32_compressstorehi128_mask ((__v8hi *) __P, (__v8hi) __D,
              __U);
}

static __inline__ void __DEFAULT_FN_ATTRS128
_mm_mask_compressstoreu_epi8(void *__P, __mmask16 __U, __m128i __D)
{
  __builtin_ia32_compressstoreqi128_mask ((__v16qi *) __P, (__v16qi) __D,
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_expand_epi16(__m128i __S, __mmask8 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_expandhi128_mask ((__v8hi) __D,
              (__v8hi) __S,
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_expand_epi16(__mmask8 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_expandhi128_mask ((__v8hi) __D,
              (__v8hi) _mm_setzero_si128(),
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_expand_epi8(__m128i __S, __mmask16 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_expandqi128_mask ((__v16qi) __D,
              (__v16qi) __S,
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_expand_epi8(__mmask16 __U, __m128i __D)
{
  return (__m128i) __builtin_ia32_expandqi128_mask ((__v16qi) __D,
              (__v16qi) _mm_setzero_si128(),
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_expandloadu_epi16(__m128i __S, __mmask8 __U, void const *__P)
{
  return (__m128i) __builtin_ia32_expandloadhi128_mask ((const __v8hi *)__P,
              (__v8hi) __S,
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_expandloadu_epi16(__mmask8 __U, void const *__P)
{
  return (__m128i) __builtin_ia32_expandloadhi128_mask ((const __v8hi *)__P,
              (__v8hi) _mm_setzero_si128(),
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_expandloadu_epi8(__m128i __S, __mmask16 __U, void const *__P)
{
  return (__m128i) __builtin_ia32_expandloadqi128_mask ((const __v16qi *)__P,
              (__v16qi) __S,
              __U);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_expandloadu_epi8(__mmask16 __U, void const *__P)
{
  return (__m128i) __builtin_ia32_expandloadqi128_mask ((const __v16qi *)__P,
              (__v16qi) _mm_setzero_si128(),
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_compress_epi16(__m256i __S, __mmask16 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_compresshi256_mask ((__v16hi) __D,
              (__v16hi) __S,
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_compress_epi16(__mmask16 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_compresshi256_mask ((__v16hi) __D,
              (__v16hi) _mm256_setzero_si256(),
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_compress_epi8(__m256i __S, __mmask32 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_compressqi256_mask ((__v32qi) __D,
              (__v32qi) __S,
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_compress_epi8(__mmask32 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_compressqi256_mask ((__v32qi) __D,
              (__v32qi) _mm256_setzero_si256(),
              __U);
}

static __inline__ void __DEFAULT_FN_ATTRS256
_mm256_mask_compressstoreu_epi16(void *__P, __mmask16 __U, __m256i __D)
{
  __builtin_ia32_compressstorehi256_mask ((__v16hi *) __P, (__v16hi) __D,
              __U);
}

static __inline__ void __DEFAULT_FN_ATTRS256
_mm256_mask_compressstoreu_epi8(void *__P, __mmask32 __U, __m256i __D)
{
  __builtin_ia32_compressstoreqi256_mask ((__v32qi *) __P, (__v32qi) __D,
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_expand_epi16(__m256i __S, __mmask16 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_expandhi256_mask ((__v16hi) __D,
              (__v16hi) __S,
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_expand_epi16(__mmask16 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_expandhi256_mask ((__v16hi) __D,
              (__v16hi) _mm256_setzero_si256(),
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_expand_epi8(__m256i __S, __mmask32 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_expandqi256_mask ((__v32qi) __D,
              (__v32qi) __S,
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_expand_epi8(__mmask32 __U, __m256i __D)
{
  return (__m256i) __builtin_ia32_expandqi256_mask ((__v32qi) __D,
              (__v32qi) _mm256_setzero_si256(),
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_expandloadu_epi16(__m256i __S, __mmask16 __U, void const *__P)
{
  return (__m256i) __builtin_ia32_expandloadhi256_mask ((const __v16hi *)__P,
              (__v16hi) __S,
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_expandloadu_epi16(__mmask16 __U, void const *__P)
{
  return (__m256i) __builtin_ia32_expandloadhi256_mask ((const __v16hi *)__P,
              (__v16hi) _mm256_setzero_si256(),
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_expandloadu_epi8(__m256i __S, __mmask32 __U, void const *__P)
{
  return (__m256i) __builtin_ia32_expandloadqi256_mask ((const __v32qi *)__P,
              (__v32qi) __S,
              __U);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_expandloadu_epi8(__mmask32 __U, void const *__P)
{
  return (__m256i) __builtin_ia32_expandloadqi256_mask ((const __v32qi *)__P,
              (__v32qi) _mm256_setzero_si256(),
              __U);
}

#define _mm256_shldi_epi64(A, B, I) \
  ((__m256i)__builtin_ia32_vpshldq256((__v4di)(__m256i)(A), \
                                      (__v4di)(__m256i)(B), (int)(I)))

#define _mm256_mask_shldi_epi64(S, U, A, B, I) \
  ((__m256i)__builtin_ia32_selectq_256((__mmask8)(U), \
                                     (__v4di)_mm256_shldi_epi64((A), (B), (I)), \
                                     (__v4di)(__m256i)(S)))

#define _mm256_maskz_shldi_epi64(U, A, B, I) \
  ((__m256i)__builtin_ia32_selectq_256((__mmask8)(U), \
                                     (__v4di)_mm256_shldi_epi64((A), (B), (I)), \
                                     (__v4di)_mm256_setzero_si256()))

#define _mm_shldi_epi64(A, B, I) \
  ((__m128i)__builtin_ia32_vpshldq128((__v2di)(__m128i)(A), \
                                      (__v2di)(__m128i)(B), (int)(I)))

#define _mm_mask_shldi_epi64(S, U, A, B, I) \
  ((__m128i)__builtin_ia32_selectq_128((__mmask8)(U), \
                                       (__v2di)_mm_shldi_epi64((A), (B), (I)), \
                                       (__v2di)(__m128i)(S)))

#define _mm_maskz_shldi_epi64(U, A, B, I) \
  ((__m128i)__builtin_ia32_selectq_128((__mmask8)(U), \
                                       (__v2di)_mm_shldi_epi64((A), (B), (I)), \
                                       (__v2di)_mm_setzero_si128()))

#define _mm256_shldi_epi32(A, B, I) \
  ((__m256i)__builtin_ia32_vpshldd256((__v8si)(__m256i)(A), \
                                      (__v8si)(__m256i)(B), (int)(I)))

#define _mm256_mask_shldi_epi32(S, U, A, B, I) \
  ((__m256i)__builtin_ia32_selectd_256((__mmask8)(U), \
                                     (__v8si)_mm256_shldi_epi32((A), (B), (I)), \
                                     (__v8si)(__m256i)(S)))

#define _mm256_maskz_shldi_epi32(U, A, B, I) \
  ((__m256i)__builtin_ia32_selectd_256((__mmask8)(U), \
                                     (__v8si)_mm256_shldi_epi32((A), (B), (I)), \
                                     (__v8si)_mm256_setzero_si256()))

#define _mm_shldi_epi32(A, B, I) \
  ((__m128i)__builtin_ia32_vpshldd128((__v4si)(__m128i)(A), \
                                      (__v4si)(__m128i)(B), (int)(I)))

#define _mm_mask_shldi_epi32(S, U, A, B, I) \
  ((__m128i)__builtin_ia32_selectd_128((__mmask8)(U), \
                                       (__v4si)_mm_shldi_epi32((A), (B), (I)), \
                                       (__v4si)(__m128i)(S)))

#define _mm_maskz_shldi_epi32(U, A, B, I) \
  ((__m128i)__builtin_ia32_selectd_128((__mmask8)(U), \
                                       (__v4si)_mm_shldi_epi32((A), (B), (I)), \
                                       (__v4si)_mm_setzero_si128()))

#define _mm256_shldi_epi16(A, B, I) \
  ((__m256i)__builtin_ia32_vpshldw256((__v16hi)(__m256i)(A), \
                                      (__v16hi)(__m256i)(B), (int)(I)))

#define _mm256_mask_shldi_epi16(S, U, A, B, I) \
  ((__m256i)__builtin_ia32_selectw_256((__mmask16)(U), \
                                    (__v16hi)_mm256_shldi_epi16((A), (B), (I)), \
                                    (__v16hi)(__m256i)(S)))

#define _mm256_maskz_shldi_epi16(U, A, B, I) \
  ((__m256i)__builtin_ia32_selectw_256((__mmask16)(U), \
                                    (__v16hi)_mm256_shldi_epi16((A), (B), (I)), \
                                    (__v16hi)_mm256_setzero_si256()))

#define _mm_shldi_epi16(A, B, I) \
  ((__m128i)__builtin_ia32_vpshldw128((__v8hi)(__m128i)(A), \
                                      (__v8hi)(__m128i)(B), (int)(I)))

#define _mm_mask_shldi_epi16(S, U, A, B, I) \
  ((__m128i)__builtin_ia32_selectw_128((__mmask8)(U), \
                                       (__v8hi)_mm_shldi_epi16((A), (B), (I)), \
                                       (__v8hi)(__m128i)(S)))

#define _mm_maskz_shldi_epi16(U, A, B, I) \
  ((__m128i)__builtin_ia32_selectw_128((__mmask8)(U), \
                                       (__v8hi)_mm_shldi_epi16((A), (B), (I)), \
                                       (__v8hi)_mm_setzero_si128()))

#define _mm256_shrdi_epi64(A, B, I) \
  ((__m256i)__builtin_ia32_vpshrdq256((__v4di)(__m256i)(A), \
                                      (__v4di)(__m256i)(B), (int)(I)))

#define _mm256_mask_shrdi_epi64(S, U, A, B, I) \
  ((__m256i)__builtin_ia32_selectq_256((__mmask8)(U), \
                                     (__v4di)_mm256_shrdi_epi64((A), (B), (I)), \
                                     (__v4di)(__m256i)(S)))

#define _mm256_maskz_shrdi_epi64(U, A, B, I) \
  ((__m256i)__builtin_ia32_selectq_256((__mmask8)(U), \
                                     (__v4di)_mm256_shrdi_epi64((A), (B), (I)), \
                                     (__v4di)_mm256_setzero_si256()))

#define _mm_shrdi_epi64(A, B, I) \
  ((__m128i)__builtin_ia32_vpshrdq128((__v2di)(__m128i)(A), \
                                      (__v2di)(__m128i)(B), (int)(I)))

#define _mm_mask_shrdi_epi64(S, U, A, B, I) \
  ((__m128i)__builtin_ia32_selectq_128((__mmask8)(U), \
                                       (__v2di)_mm_shrdi_epi64((A), (B), (I)), \
                                       (__v2di)(__m128i)(S)))

#define _mm_maskz_shrdi_epi64(U, A, B, I) \
  ((__m128i)__builtin_ia32_selectq_128((__mmask8)(U), \
                                       (__v2di)_mm_shrdi_epi64((A), (B), (I)), \
                                       (__v2di)_mm_setzero_si128()))

#define _mm256_shrdi_epi32(A, B, I) \
  ((__m256i)__builtin_ia32_vpshrdd256((__v8si)(__m256i)(A), \
                                      (__v8si)(__m256i)(B), (int)(I)))

#define _mm256_mask_shrdi_epi32(S, U, A, B, I) \
  ((__m256i)__builtin_ia32_selectd_256((__mmask8)(U), \
                                     (__v8si)_mm256_shrdi_epi32((A), (B), (I)), \
                                     (__v8si)(__m256i)(S)))

#define _mm256_maskz_shrdi_epi32(U, A, B, I) \
  ((__m256i)__builtin_ia32_selectd_256((__mmask8)(U), \
                                     (__v8si)_mm256_shrdi_epi32((A), (B), (I)), \
                                     (__v8si)_mm256_setzero_si256()))

#define _mm_shrdi_epi32(A, B, I) \
  ((__m128i)__builtin_ia32_vpshrdd128((__v4si)(__m128i)(A), \
                                      (__v4si)(__m128i)(B), (int)(I)))

#define _mm_mask_shrdi_epi32(S, U, A, B, I) \
  ((__m128i)__builtin_ia32_selectd_128((__mmask8)(U), \
                                       (__v4si)_mm_shrdi_epi32((A), (B), (I)), \
                                       (__v4si)(__m128i)(S)))

#define _mm_maskz_shrdi_epi32(U, A, B, I) \
  ((__m128i)__builtin_ia32_selectd_128((__mmask8)(U), \
                                       (__v4si)_mm_shrdi_epi32((A), (B), (I)), \
                                       (__v4si)_mm_setzero_si128()))

#define _mm256_shrdi_epi16(A, B, I) \
  ((__m256i)__builtin_ia32_vpshrdw256((__v16hi)(__m256i)(A), \
                                      (__v16hi)(__m256i)(B), (int)(I)))

#define _mm256_mask_shrdi_epi16(S, U, A, B, I) \
  ((__m256i)__builtin_ia32_selectw_256((__mmask16)(U), \
                                    (__v16hi)_mm256_shrdi_epi16((A), (B), (I)), \
                                    (__v16hi)(__m256i)(S)))

#define _mm256_maskz_shrdi_epi16(U, A, B, I) \
  ((__m256i)__builtin_ia32_selectw_256((__mmask16)(U), \
                                    (__v16hi)_mm256_shrdi_epi16((A), (B), (I)), \
                                    (__v16hi)_mm256_setzero_si256()))

#define _mm_shrdi_epi16(A, B, I) \
  ((__m128i)__builtin_ia32_vpshrdw128((__v8hi)(__m128i)(A), \
                                      (__v8hi)(__m128i)(B), (int)(I)))

#define _mm_mask_shrdi_epi16(S, U, A, B, I) \
  ((__m128i)__builtin_ia32_selectw_128((__mmask8)(U), \
                                       (__v8hi)_mm_shrdi_epi16((A), (B), (I)), \
                                       (__v8hi)(__m128i)(S)))

#define _mm_maskz_shrdi_epi16(U, A, B, I) \
  ((__m128i)__builtin_ia32_selectw_128((__mmask8)(U), \
                                       (__v8hi)_mm_shrdi_epi16((A), (B), (I)), \
                                       (__v8hi)_mm_setzero_si128()))

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_shldv_epi64(__m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_vpshldvq256((__v4di)__A, (__v4di)__B,
                                             (__v4di)__C);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_shldv_epi64(__m256i __A, __mmask8 __U, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectq_256(__U,
                                      (__v4di)_mm256_shldv_epi64(__A, __B, __C),
                                      (__v4di)__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_shldv_epi64(__mmask8 __U, __m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectq_256(__U,
                                      (__v4di)_mm256_shldv_epi64(__A, __B, __C),
                                      (__v4di)_mm256_setzero_si256());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_shldv_epi64(__m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_vpshldvq128((__v2di)__A, (__v2di)__B,
                                             (__v2di)__C);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_shldv_epi64(__m128i __A, __mmask8 __U, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectq_128(__U,
                                         (__v2di)_mm_shldv_epi64(__A, __B, __C),
                                         (__v2di)__A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_shldv_epi64(__mmask8 __U, __m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectq_128(__U,
                                         (__v2di)_mm_shldv_epi64(__A, __B, __C),
                                         (__v2di)_mm_setzero_si128());
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_shldv_epi32(__m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_vpshldvd256((__v8si)__A, (__v8si)__B,
                                             (__v8si)__C);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_shldv_epi32(__m256i __A, __mmask8 __U, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectd_256(__U,
                                      (__v8si)_mm256_shldv_epi32(__A, __B, __C),
                                      (__v8si)__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_shldv_epi32(__mmask8 __U, __m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectd_256(__U,
                                      (__v8si)_mm256_shldv_epi32(__A, __B, __C),
                                      (__v8si)_mm256_setzero_si256());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_shldv_epi32(__m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_vpshldvd128((__v4si)__A, (__v4si)__B,
                                             (__v4si)__C);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_shldv_epi32(__m128i __A, __mmask8 __U, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectd_128(__U,
                                         (__v4si)_mm_shldv_epi32(__A, __B, __C),
                                         (__v4si)__A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_shldv_epi32(__mmask8 __U, __m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectd_128(__U,
                                         (__v4si)_mm_shldv_epi32(__A, __B, __C),
                                         (__v4si)_mm_setzero_si128());
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_shldv_epi16(__m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_vpshldvw256((__v16hi)__A, (__v16hi)__B,
                                             (__v16hi)__C);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_shldv_epi16(__m256i __A, __mmask16 __U, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectw_256(__U,
                                      (__v16hi)_mm256_shldv_epi16(__A, __B, __C),
                                      (__v16hi)__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_shldv_epi16(__mmask16 __U, __m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectw_256(__U,
                                      (__v16hi)_mm256_shldv_epi16(__A, __B, __C),
                                      (__v16hi)_mm256_setzero_si256());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_shldv_epi16(__m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_vpshldvw128((__v8hi)__A, (__v8hi)__B,
                                             (__v8hi)__C);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_shldv_epi16(__m128i __A, __mmask8 __U, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectw_128(__U,
                                         (__v8hi)_mm_shldv_epi16(__A, __B, __C),
                                         (__v8hi)__A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_shldv_epi16(__mmask8 __U, __m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectw_128(__U,
                                         (__v8hi)_mm_shldv_epi16(__A, __B, __C),
                                         (__v8hi)_mm_setzero_si128());
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_shrdv_epi64(__m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_vpshrdvq256((__v4di)__A, (__v4di)__B,
                                             (__v4di)__C);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_shrdv_epi64(__m256i __A, __mmask8 __U, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectq_256(__U,
                                      (__v4di)_mm256_shrdv_epi64(__A, __B, __C),
                                      (__v4di)__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_shrdv_epi64(__mmask8 __U, __m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectq_256(__U,
                                      (__v4di)_mm256_shrdv_epi64(__A, __B, __C),
                                      (__v4di)_mm256_setzero_si256());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_shrdv_epi64(__m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_vpshrdvq128((__v2di)__A, (__v2di)__B,
                                             (__v2di)__C);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_shrdv_epi64(__m128i __A, __mmask8 __U, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectq_128(__U,
                                         (__v2di)_mm_shrdv_epi64(__A, __B, __C),
                                         (__v2di)__A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_shrdv_epi64(__mmask8 __U, __m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectq_128(__U,
                                         (__v2di)_mm_shrdv_epi64(__A, __B, __C),
                                         (__v2di)_mm_setzero_si128());
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_shrdv_epi32(__m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_vpshrdvd256((__v8si)__A, (__v8si)__B,
                                             (__v8si)__C);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_shrdv_epi32(__m256i __A, __mmask8 __U, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectd_256(__U,
                                      (__v8si)_mm256_shrdv_epi32(__A, __B, __C),
                                      (__v8si)__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_shrdv_epi32(__mmask8 __U, __m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectd_256(__U,
                                      (__v8si)_mm256_shrdv_epi32(__A, __B, __C),
                                      (__v8si)_mm256_setzero_si256());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_shrdv_epi32(__m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_vpshrdvd128((__v4si)__A, (__v4si)__B,
                                             (__v4si)__C);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_shrdv_epi32(__m128i __A, __mmask8 __U, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectd_128(__U,
                                         (__v4si)_mm_shrdv_epi32(__A, __B, __C),
                                         (__v4si)__A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_shrdv_epi32(__mmask8 __U, __m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectd_128(__U,
                                         (__v4si)_mm_shrdv_epi32(__A, __B, __C),
                                         (__v4si)_mm_setzero_si128());
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_shrdv_epi16(__m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_vpshrdvw256((__v16hi)__A, (__v16hi)__B,
                                             (__v16hi)__C);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_mask_shrdv_epi16(__m256i __A, __mmask16 __U, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectw_256(__U,
                                     (__v16hi)_mm256_shrdv_epi16(__A, __B, __C),
                                     (__v16hi)__A);
}

static __inline__ __m256i __DEFAULT_FN_ATTRS256
_mm256_maskz_shrdv_epi16(__mmask16 __U, __m256i __A, __m256i __B, __m256i __C)
{
  return (__m256i)__builtin_ia32_selectw_256(__U,
                                     (__v16hi)_mm256_shrdv_epi16(__A, __B, __C),
                                     (__v16hi)_mm256_setzero_si256());
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_shrdv_epi16(__m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_vpshrdvw128((__v8hi)__A, (__v8hi)__B,
                                             (__v8hi)__C);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_mask_shrdv_epi16(__m128i __A, __mmask8 __U, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectw_128(__U,
                                         (__v8hi)_mm_shrdv_epi16(__A, __B, __C),
                                         (__v8hi)__A);
}

static __inline__ __m128i __DEFAULT_FN_ATTRS128
_mm_maskz_shrdv_epi16(__mmask8 __U, __m128i __A, __m128i __B, __m128i __C)
{
  return (__m128i)__builtin_ia32_selectw_128(__U,
                                         (__v8hi)_mm_shrdv_epi16(__A, __B, __C),
                                         (__v8hi)_mm_setzero_si128());
}

#undef __DEFAULT_FN_ATTRS128
#undef __DEFAULT_FN_ATTRS256

#endif

[+] ..
[-] riscv_ntlh.h [edit]
[-] avx512vlbitalgintrin.h [edit]
[-] avxifmaintrin.h [edit]
[-] mm_malloc.h [edit]
[-] avx512vlbf16intrin.h [edit]
[-] mwaitxintrin.h [edit]
[-] adxintrin.h [edit]
[-] arm_cmse.h [edit]
[-] __clang_cuda_intrinsics.h [edit]
[-] module.modulemap [edit]
[-] crc32intrin.h [edit]
[+] cuda_wrappers
[-] msa.h [edit]
[-] __clang_hip_stdlib.h [edit]
[-] arm_acle.h [edit]
[-] arm_neon_sve_bridge.h [edit]
[-] xsaveintrin.h [edit]
[-] velintrin_gen.h [edit]
[-] stdatomic.h [edit]
[-] hvx_hexagon_protos.h [edit]
[-] uintrintrin.h [edit]
[-] fxsrintrin.h [edit]
[-] sha512intrin.h [edit]
[-] __clang_cuda_texture_intrinsics.h [edit]
[-] iso646.h [edit]
[-] unwind.h [edit]
[-] avx512vlbwintrin.h [edit]
[-] avxvnniint8intrin.h [edit]
[-] avx512erintrin.h [edit]
[-] avxvnniintrin.h [edit]
[-] ia32intrin.h [edit]
[-] rdseedintrin.h [edit]
[-] prfchiintrin.h [edit]
[-] amxcomplexintrin.h [edit]
[-] clflushoptintrin.h [edit]
[-] htmxlintrin.h [edit]
[-] avx512fintrin.h [edit]
[-] gfniintrin.h [edit]
[-] arm_cde.h [edit]
[+] ppc_wrappers
[-] amxfp16intrin.h [edit]
[-] velintrin_approx.h [edit]
[-] avx512pfintrin.h [edit]
[-] stdarg.h [edit]
[-] cmpccxaddintrin.h [edit]
[-] avx512vlintrin.h [edit]
[-] __clang_hip_math.h [edit]
[-] vecintrin.h [edit]
[-] xtestintrin.h [edit]
[-] __wmmintrin_aes.h [edit]
[-] arm_neon.h [edit]
[-] immintrin.h [edit]
[-] ammintrin.h [edit]
[-] waitpkgintrin.h [edit]
[-] vpclmulqdqintrin.h [edit]
[-] fmaintrin.h [edit]
[-] tsxldtrkintrin.h [edit]
[-] prfchwintrin.h [edit]
[-] avx512bitalgintrin.h [edit]
[-] bmiintrin.h [edit]
[-] __wmmintrin_pclmul.h [edit]
[-] htmintrin.h [edit]
[-] mm3dnow.h [edit]
[-] __clang_cuda_builtin_vars.h [edit]
[-] __clang_hip_runtime_wrapper.h [edit]
[-] stdbool.h [edit]
[-] altivec.h [edit]
[-] wbnoinvdintrin.h [edit]
[-] keylockerintrin.h [edit]
[-] tgmath.h [edit]
[-] hexagon_circ_brev_intrinsics.h [edit]
[-] x86intrin.h [edit]
[-] pkuintrin.h [edit]
[-] avx512vbmivlintrin.h [edit]
[-] avxneconvertintrin.h [edit]
[-] __clang_hip_cmath.h [edit]
[-] sgxintrin.h [edit]
[-] f16cintrin.h [edit]
[-] opencl-c-base.h [edit]
[-] cpuid.h [edit]
[-] raointintrin.h [edit]
[-] builtins.h [edit]
[-] emmintrin.h [edit]
[-] smmintrin.h [edit]
[-] vaesintrin.h [edit]
[-] larchintrin.h [edit]
[-] avx512ifmaintrin.h [edit]
[-] intrin.h [edit]
[-] avx512vlvp2intersectintrin.h [edit]
[-] fma4intrin.h [edit]
[-] pmmintrin.h [edit]
[-] __clang_hip_libdevice_declares.h [edit]
[-] limits.h [edit]
[-] clwbintrin.h [edit]
[-] rtmintrin.h [edit]
[-] mmintrin.h [edit]
[-] stddef.h [edit]
[-] invpcidintrin.h [edit]
[-] avx512vp2intersectintrin.h [edit]
[-] cet.h [edit]
[-] xopintrin.h [edit]
[-] avx512vlvnniintrin.h [edit]
[-] avx512vlfp16intrin.h [edit]
[-] stdint.h [edit]
[-] arm64intr.h [edit]
[-] sm4intrin.h [edit]
[-] avx512vnniintrin.h [edit]
[-] avx2intrin.h [edit]
[-] movdirintrin.h [edit]
[-] tbmintrin.h [edit]
[-] arm_mve.h [edit]
[-] avx512ifmavlintrin.h [edit]
[-] amxintrin.h [edit]
[-] opencl-c.h [edit]
[-] stdalign.h [edit]
[-] __clang_cuda_device_functions.h [edit]
[-] pconfigintrin.h [edit]
[-] avx512fp16intrin.h [edit]
[-] inttypes.h [edit]
[-] arm_bf16.h [edit]
[-] __clang_cuda_math_forward_declares.h [edit]
[-] vadefs.h [edit]
[-] shaintrin.h [edit]
[-] hexagon_protos.h [edit]
[-] ptwriteintrin.h [edit]
[-] xsaveoptintrin.h [edit]
[-] enqcmdintrin.h [edit]
[-] x86gprintrin.h [edit]
[-] tmmintrin.h [edit]
[-] stdnoreturn.h [edit]
[-] avx512bf16intrin.h [edit]
[-] varargs.h [edit]
[-] s390intrin.h [edit]
[-] avx512vbmiintrin.h [edit]
[+] openmp_wrappers
[-] wmmintrin.h [edit]
[-] __clang_cuda_cmath.h [edit]
[-] clzerointrin.h [edit]
[-] xsavesintrin.h [edit]
[-] __clang_cuda_libdevice_declares.h [edit]
[-] nmmintrin.h [edit]
[-] wasm_simd128.h [edit]
[-] xsavecintrin.h [edit]
[-] avx512dqintrin.h [edit]
[-] lwpintrin.h [edit]
[-] serializeintrin.h [edit]
[-] arm_sme_draft_spec_subject_to_change.h [edit]
[-] avxintrin.h [edit]
[-] __stddef_max_align_t.h [edit]
[-] sm3intrin.h [edit]
[-] velintrin.h [edit]
[-] __clang_cuda_complex_builtins.h [edit]
[-] armintr.h [edit]
[-] avx512cdintrin.h [edit]
[-] float.h [edit]
[-] avx512vbmi2intrin.h [edit]
[-] lzcntintrin.h [edit]
[-] sifive_vector.h [edit]
[-] rdpruintrin.h [edit]
[-] arm_sve.h [edit]
[-] avx512vpopcntdqintrin.h [edit]
[-] xmmintrin.h [edit]
[-] hresetintrin.h [edit]
[-] bmi2intrin.h [edit]
[-] hexagon_types.h [edit]
[-] avx512bwintrin.h [edit]
[-] cetintrin.h [edit]
[-] __clang_cuda_math.h [edit]
[-] avx512vlvbmi2intrin.h [edit]
[-] arm_fp16.h [edit]
[-] avx512vpopcntdqvlintrin.h [edit]
[-] avxvnniint16intrin.h [edit]
[+] llvm_libc_wrappers
[-] __clang_cuda_runtime_wrapper.h [edit]
[-] cldemoteintrin.h [edit]
[-] avx512vldqintrin.h [edit]
[-] avx512vlcdintrin.h [edit]
[-] popcntintrin.h [edit]