| Server IP : 88.223.91.63 / Your IP : 216.73.217.32 Web Server : LiteSpeed System : Linux id-dci-web1986.main-hosting.eu 5.14.0-611.26.1.el9_7.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Jan 29 05:24:47 EST 2026 x86_64 User : u686484674 ( 686484674) PHP Version : 8.0.30 Disable Function : system, exec, shell_exec, passthru, mysql_list_dbs, ini_alter, dl, symlink, link, chgrp, leak, popen, apache_child_terminate, virtual, mb_send_mail MySQL : OFF | cURL : ON | WGET : ON | Perl : OFF | Python : OFF | Sudo : OFF | Pkexec : OFF Directory : /proc/./self/root/lib/clang/20/include/ |
Upload File : |
/*===-------- avxvnniint8intrin.h - AVXVNNIINT8 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 <avxvnniint8intrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __AVXVNNIINT8INTRIN_H
#define __AVXVNNIINT8INTRIN_H
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding signed 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W, and store the packed 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm_dpbssd_epi32(__m128i __W, __m128i __A, __m128i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 128-bit vector of [16 x char].
/// \param __B
/// A 128-bit vector of [16 x char].
/// \returns
/// A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// FOR j := 0 to 3
/// tmp1.word := SignExtend16(__A.byte[4*j]) * SignExtend16(__B.byte[4*j])
/// tmp2.word := SignExtend16(__A.byte[4*j+1]) * SignExtend16(__B.byte[4*j+1])
/// tmp3.word := SignExtend16(__A.byte[4*j+2]) * SignExtend16(__B.byte[4*j+2])
/// tmp4.word := SignExtend16(__A.byte[4*j+3]) * SignExtend16(__B.byte[4*j+3])
/// dst.dword[j] := __W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4
/// ENDFOR
/// dst[MAX:128] := 0
/// \endcode
#define _mm_dpbssd_epi32(__W, __A, __B) \
((__m128i)__builtin_ia32_vpdpbssd128((__v4si)(__W), (__v4si)(__A), \
(__v4si)(__B)))
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding signed 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W, and store the packed 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm256_dpbssd_epi32(__m256i __W, __m256i __A, __m256i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 256-bit vector of [32 x char].
/// \param __B
/// A 256-bit vector of [32 x char].
/// \returns
/// A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// FOR j := 0 to 7
/// tmp1.word := SignExtend16(__A.byte[4*j]) * SignExtend16(__B.byte[4*j])
/// tmp2.word := SignExtend16(__A.byte[4*j+1]) * SignExtend16(__B.byte[4*j+1])
/// tmp3.word := SignExtend16(__A.byte[4*j+2]) * SignExtend16(__B.byte[4*j+2])
/// tmp4.word := SignExtend16(__A.byte[4*j+3]) * SignExtend16(__B.byte[4*j+3])
/// dst.dword[j] := __W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4
/// ENDFOR
/// dst[MAX:256] := 0
/// \endcode
#define _mm256_dpbssd_epi32(__W, __A, __B) \
((__m256i)__builtin_ia32_vpdpbssd256((__v8si)(__W), (__v8si)(__A), \
(__v8si)(__B)))
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding signed 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W with signed saturation, and store the packed
/// 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm_dpbssds_epi32( __m128i __W, __m128i __A, __m128i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 128-bit vector of [16 x char].
/// \param __B
/// A 128-bit vector of [16 x char].
/// \returns
/// A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// FOR j := 0 to 3
/// tmp1.word := SignExtend16(__A.byte[4*j]) * SignExtend16(__B.byte[4*j])
/// tmp2.word := SignExtend16(__A.byte[4*j+1]) * SignExtend16(__B.byte[4*j+1])
/// tmp3.word := SignExtend16(__A.byte[4*j+2]) * SignExtend16(__B.byte[4*j+2])
/// tmp4.word := SignExtend16(__A.byte[4*j+3]) * SignExtend16(__B.byte[4*j+3])
/// dst.dword[j] := SIGNED_DWORD_SATURATE(__W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4)
/// ENDFOR
/// dst[MAX:128] := 0
/// \endcode
#define _mm_dpbssds_epi32(__W, __A, __B) \
((__m128i)__builtin_ia32_vpdpbssds128((__v4si)(__W), (__v4si)(__A), \
(__v4si)(__B)))
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding signed 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W with signed saturation, and store the packed
/// 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm256_dpbssds_epi32(__m256i __W, __m256i __A, __m256i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 256-bit vector of [32 x char].
/// \param __B
/// A 256-bit vector of [32 x char].
/// \returns
/// A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// FOR j := 0 to 7
/// tmp1.word := SignExtend16(__A.byte[4*j]) * SignExtend16(__B.byte[4*j])
/// tmp2.word := SignExtend16(__A.byte[4*j+1]) * SignExtend16(__B.byte[4*j+1])
/// tmp3.word := SignExtend16(__A.byte[4*j+2]) * SignExtend16(__B.byte[4*j+2])
/// tmp4.word := SignExtend16(__A.byte[4*j+3]) * SignExtend16(__B.byte[4*j+3])
/// dst.dword[j] := SIGNED_DWORD_SATURATE(__W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4)
/// ENDFOR
/// dst[MAX:256] := 0
/// \endcode
#define _mm256_dpbssds_epi32(__W, __A, __B) \
((__m256i)__builtin_ia32_vpdpbssds256((__v8si)(__W), (__v8si)(__A), \
(__v8si)(__B)))
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W, and store the packed 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm_dpbsud_epi32(__m128i __W, __m128i __A, __m128i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 128-bit vector of [16 x char].
/// \param __B
/// A 128-bit vector of [16 x unsigned char].
/// \returns
/// A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// FOR j := 0 to 3
/// tmp1.word := Signed(SignExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j]))
/// tmp2.word := Signed(SignExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1]))
/// tmp3.word := Signed(SignExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2]))
/// tmp4.word := Signed(SignExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3]))
/// dst.dword[j] := __W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4
/// ENDFOR
/// dst[MAX:128] := 0
/// \endcode
#define _mm_dpbsud_epi32(__W, __A, __B) \
((__m128i)__builtin_ia32_vpdpbsud128((__v4si)(__W), (__v4si)(__A), \
(__v4si)(__B)))
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W, and store the packed 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm256_dpbsud_epi32(__m256i __W, __m256i __A, __m256i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 256-bit vector of [32 x char].
/// \param __B
/// A 256-bit vector of [32 x unsigned char].
/// \returns
/// A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// FOR j := 0 to 7
/// tmp1.word := Signed(SignExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j]))
/// tmp2.word := Signed(SignExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1]))
/// tmp3.word := Signed(SignExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2]))
/// tmp4.word := Signed(SignExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3]))
/// dst.dword[j] := __W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4
/// ENDFOR
/// dst[MAX:256] := 0
/// \endcode
#define _mm256_dpbsud_epi32(__W, __A, __B) \
((__m256i)__builtin_ia32_vpdpbsud256((__v8si)(__W), (__v8si)(__A), \
(__v8si)(__B)))
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W with signed saturation, and store the packed
/// 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm_dpbsuds_epi32( __m128i __W, __m128i __A, __m128i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 128-bit vector of [16 x char].
/// \param __B
/// A 128-bit vector of [16 x unsigned char].
/// \returns
/// A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// FOR j := 0 to 3
/// tmp1.word := Signed(SignExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j]))
/// tmp2.word := Signed(SignExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1]))
/// tmp3.word := Signed(SignExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2]))
/// tmp4.word := Signed(SignExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3]))
/// dst.dword[j] := SIGNED_DWORD_SATURATE(__W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4)
/// ENDFOR
/// dst[MAX:128] := 0
/// \endcode
#define _mm_dpbsuds_epi32(__W, __A, __B) \
((__m128i)__builtin_ia32_vpdpbsuds128((__v4si)(__W), (__v4si)(__A), \
(__v4si)(__B)))
/// Multiply groups of 4 adjacent pairs of signed 8-bit integers in \a __A with
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W with signed saturation, and store the packed
/// 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm256_dpbsuds_epi32(__m256i __W, __m256i __A, __m256i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 256-bit vector of [32 x char].
/// \param __B
/// A 256-bit vector of [32 x unsigned char].
/// \returns
/// A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// FOR j := 0 to 7
/// tmp1.word := Signed(SignExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j]))
/// tmp2.word := Signed(SignExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1]))
/// tmp3.word := Signed(SignExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2]))
/// tmp4.word := Signed(SignExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3]))
/// dst.dword[j] := SIGNED_DWORD_SATURATE(__W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4)
/// ENDFOR
/// dst[MAX:256] := 0
/// \endcode
#define _mm256_dpbsuds_epi32(__W, __A, __B) \
((__m256i)__builtin_ia32_vpdpbsuds256((__v8si)(__W), (__v8si)(__A), \
(__v8si)(__B)))
/// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W, and store the packed 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm_dpbuud_epi32(__m128i __W, __m128i __A, __m128i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 128-bit vector of [16 x unsigned char].
/// \param __B
/// A 128-bit vector of [16 x unsigned char].
/// \returns
/// A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// FOR j := 0 to 3
/// tmp1.word := ZeroExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j])
/// tmp2.word := ZeroExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1])
/// tmp3.word := ZeroExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2])
/// tmp4.word := ZeroExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3])
/// dst.dword[j] := __W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4
/// ENDFOR
/// dst[MAX:128] := 0
/// \endcode
#define _mm_dpbuud_epi32(__W, __A, __B) \
((__m128i)__builtin_ia32_vpdpbuud128((__v4si)(__W), (__v4si)(__A), \
(__v4si)(__B)))
/// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W, and store the packed 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm256_dpbuud_epi32(__m256i __W, __m256i __A, __m256i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBSSD instruction.
///
/// \param __A
/// A 256-bit vector of [32 x unsigned char].
/// \param __B
/// A 256-bit vector of [32 x unsigned char].
/// \returns
/// A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// FOR j := 0 to 7
/// tmp1.word := ZeroExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j])
/// tmp2.word := ZeroExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1])
/// tmp3.word := ZeroExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2])
/// tmp4.word := ZeroExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3])
/// dst.dword[j] := __W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4
/// ENDFOR
/// dst[MAX:256] := 0
/// \endcode
#define _mm256_dpbuud_epi32(__W, __A, __B) \
((__m256i)__builtin_ia32_vpdpbuud256((__v8si)(__W), (__v8si)(__A), \
(__v8si)(__B)))
/// Multiply groups of 4 adjacent pairs of unsigned 8-bit integers in \a __A with
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W with signed saturation, and store the packed
/// 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm_dpbuuds_epi32( __m128i __W, __m128i __A, __m128i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBUUDS instruction.
///
/// \param __A
/// A 128-bit vector of [16 x unsigned char].
/// \param __B
/// A 128-bit vector of [16 x unsigned char].
/// \returns
/// A 128-bit vector of [4 x int].
///
/// \code{.operation}
/// FOR j := 0 to 3
/// tmp1.word := ZeroExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j])
/// tmp2.word := ZeroExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1])
/// tmp3.word := ZeroExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2])
/// tmp4.word := ZeroExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3])
/// dst.dword[j] := UNSIGNED_DWORD_SATURATE(__W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4)
/// ENDFOR
/// dst[MAX:128] := 0
/// \endcode
#define _mm_dpbuuds_epi32(__W, __A, __B) \
((__m128i)__builtin_ia32_vpdpbuuds128((__v4si)(__W), (__v4si)(__A), \
(__v4si)(__B)))
/// corresponding unsigned 8-bit integers in \a __B, producing 4 intermediate
/// signed 16-bit results. Sum these 4 results with the corresponding
/// 32-bit integer in \a __W with signed saturation, and store the packed
/// 32-bit results in \a dst.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// _mm256_dpbuuds_epi32(__m256i __W, __m256i __A, __m256i __B);
/// \endcode
///
/// This intrinsic corresponds to the \c VPDPBUUDS instruction.
///
/// \param __A
/// A 256-bit vector of [32 x unsigned char].
/// \param __B
/// A 256-bit vector of [32 x unsigned char].
/// \returns
/// A 256-bit vector of [8 x int].
///
/// \code{.operation}
/// FOR j := 0 to 7
/// tmp1.word := ZeroExtend16(__A.byte[4*j]) * ZeroExtend16(__B.byte[4*j])
/// tmp2.word := ZeroExtend16(__A.byte[4*j+1]) * ZeroExtend16(__B.byte[4*j+1])
/// tmp3.word := ZeroExtend16(__A.byte[4*j+2]) * ZeroExtend16(__B.byte[4*j+2])
/// tmp4.word := ZeroExtend16(__A.byte[4*j+3]) * ZeroExtend16(__B.byte[4*j+3])
/// dst.dword[j] := UNSIGNED_DWORD_SATURATE(__W.dword[j] + tmp1 + tmp2 + tmp3 + tmp4)
/// ENDFOR
/// dst[MAX:256] := 0
/// \endcode
#define _mm256_dpbuuds_epi32(__W, __A, __B) \
((__m256i)__builtin_ia32_vpdpbuuds256((__v8si)(__W), (__v8si)(__A), \
(__v8si)(__B)))
#endif // __AVXVNNIINT8INTRIN_H