Module core::core_arch::x86::avx512bw

source ·
🔬This is a nightly-only experimental API. (stdsimd #48556)
Available on x86 or x86-64 only.

Functions

  • _kadd_mask32Experimentalavx512bw
    Add 32-bit masks in a and b, and store the result in k.
  • _kadd_mask64Experimentalavx512bw
    Add 64-bit masks in a and b, and store the result in k.
  • _kand_mask32Experimentalavx512bw
    Compute the bitwise AND of 32-bit masks a and b, and store the result in k.
  • _kand_mask64Experimentalavx512bw
    Compute the bitwise AND of 64-bit masks a and b, and store the result in k.
  • _kandn_mask32Experimentalavx512bw
    Compute the bitwise NOT of 32-bit masks a and then AND with b, and store the result in k.
  • _kandn_mask64Experimentalavx512bw
    Compute the bitwise NOT of 64-bit masks a and then AND with b, and store the result in k.
  • _knot_mask32Experimentalavx512bw
    Compute the bitwise NOT of 32-bit mask a, and store the result in k.
  • _knot_mask64Experimentalavx512bw
    Compute the bitwise NOT of 64-bit mask a, and store the result in k.
  • _kor_mask32Experimentalavx512bw
    Compute the bitwise OR of 32-bit masks a and b, and store the result in k.
  • _kor_mask64Experimentalavx512bw
    Compute the bitwise OR of 64-bit masks a and b, and store the result in k.
  • _kxnor_mask32Experimentalavx512bw
    Compute the bitwise XNOR of 32-bit masks a and b, and store the result in k.
  • _kxnor_mask64Experimentalavx512bw
    Compute the bitwise XNOR of 64-bit masks a and b, and store the result in k.
  • _kxor_mask32Experimentalavx512bw
    Compute the bitwise XOR of 32-bit masks a and b, and store the result in k.
  • _kxor_mask64Experimentalavx512bw
    Compute the bitwise XOR of 64-bit masks a and b, and store the result in k.
  • _load_mask32Experimentalavx512bw
    Load 32-bit mask from memory into k.
  • _load_mask64Experimentalavx512bw
    Load 64-bit mask from memory into k.
  • _mm256_cmp_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm256_cmp_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm256_cmp_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm256_cmp_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm256_cmpeq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm256_cmpeq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm256_cmpeq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm256_cmpeq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm256_cmpge_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm256_cmpge_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm256_cmpge_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm256_cmpge_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm256_cmpgt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm256_cmpgt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm256_cmpgt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm256_cmpgt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm256_cmple_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm256_cmple_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm256_cmple_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm256_cmple_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm256_cmplt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm256_cmplt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm256_cmplt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm256_cmplt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm256_cmpneq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm256_cmpneq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm256_cmpneq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm256_cmpneq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm256_cvtepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
  • _mm256_cvtsepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
  • _mm256_cvtusepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
  • _mm256_dbsad_epu8Experimentalavx512bw,avx512vl
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst. Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm256_loadu_epi8Experimentalavx512bw,avx512vl
    Load 256-bits (composed of 32 packed 8-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
  • _mm256_loadu_epi16Experimentalavx512bw,avx512vl
    Load 256-bits (composed of 16 packed 16-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
  • _mm256_mask2_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
  • _mm256_mask_abs_epi8Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_abs_epi16Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_add_epi8Experimentalavx512bw,avx512vl
    Add packed 8-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_add_epi16Experimentalavx512bw,avx512vl
    Add packed 16-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_adds_epi8Experimentalavx512bw,avx512vl
    Add packed signed 8-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_adds_epi16Experimentalavx512bw,avx512vl
    Add packed signed 16-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_adds_epu8Experimentalavx512bw,avx512vl
    Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_adds_epu16Experimentalavx512bw,avx512vl
    Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_alignr_epi8Experimentalavx512bw,avx512vl
    Concatenate pairs of 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by imm8 bytes, and store the low 16 bytes in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_avg_epu8Experimentalavx512bw,avx512vl
    Average packed unsigned 8-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_avg_epu16Experimentalavx512bw,avx512vl
    Average packed unsigned 16-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_blend_epi8Experimentalavx512bw,avx512vl
    Blend packed 8-bit integers from a and b using control mask k, and store the results in dst.
  • _mm256_mask_blend_epi16Experimentalavx512bw,avx512vl
    Blend packed 16-bit integers from a and b using control mask k, and store the results in dst.
  • _mm256_mask_broadcastb_epi8Experimentalavx512bw,avx512vl
    Broadcast the low packed 8-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_broadcastw_epi16Experimentalavx512bw,avx512vl
    Broadcast the low packed 16-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_cmp_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmp_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmp_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmp_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpeq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpeq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpeq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpeq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpge_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpge_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpge_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpge_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpgt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpgt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpgt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpgt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmple_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmple_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmple_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmple_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmplt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmplt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmplt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmplt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpneq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpneq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpneq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cmpneq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_mask_cvtepi8_epi16Experimentalavx512bw,avx512vl
    Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_cvtepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_cvtepi16_storeu_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm256_mask_cvtepu8_epi16Experimentalavx512bw,avx512vl
    Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_cvtsepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_cvtsepi16_storeu_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm256_mask_cvtusepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_cvtusepi16_storeu_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm256_mask_dbsad_epu8Experimentalavx512bw,avx512vl
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm256_mask_loadu_epi8Experimentalavx512f,avx512bw,avx512vl,avx
    Load packed 8-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm256_mask_loadu_epi16Experimentalavx512f,avx512bw,avx512vl,avx
    Load packed 16-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm256_mask_madd_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_maddubs_epi16Experimentalavx512bw,avx512vl
    Multiply packed unsigned 8-bit integers in a by packed signed 8-bit integers in b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers, and pack the saturated results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_max_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_max_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_max_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_max_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_min_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_min_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_min_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_min_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_mov_epi8Experimentalavx512bw,avx512vl
    Move packed 8-bit integers from a into dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_mov_epi16Experimentalavx512bw,avx512vl
    Move packed 16-bit integers from a into dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_mulhi_epi16Experimentalavx512bw,avx512vl
    Multiply the packed signed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_mulhi_epu16Experimentalavx512bw,avx512vl
    Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_mulhrs_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_mullo_epi16Experimentalavx512bw,avx512vl
    Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_packs_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_packs_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_packus_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_packus_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
  • _mm256_mask_permutexvar_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_set1_epi8Experimentalavx512bw,avx512vl
    Broadcast 8-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_set1_epi16Experimentalavx512bw,avx512vl
    Broadcast 16-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_shuffle_epi8Experimentalavx512bw,avx512vl
    Shuffle 8-bit integers in a within 128-bit lanes using the control in the corresponding 8-bit element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_shufflehi_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the high 64 bits of 128-bit lanes of dst, with the low 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_shufflelo_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the low 64 bits of 128-bit lanes of dst, with the high 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_sll_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_slli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_sllv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_sra_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_srai_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_srav_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_srl_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_srli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_srlv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_storeu_epi8Experimentalavx512f,avx512bw,avx512vl,avx
    Store packed 8-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
  • _mm256_mask_storeu_epi16Experimentalavx512f,avx512bw,avx512vl,avx
    Store packed 16-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
  • _mm256_mask_sub_epi8Experimentalavx512bw,avx512vl
    Subtract packed 8-bit integers in b from packed 8-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_sub_epi16Experimentalavx512bw,avx512vl
    Subtract packed 16-bit integers in b from packed 16-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_subs_epi8Experimentalavx512bw,avx512vl
    Subtract packed signed 8-bit integers in b from packed 8-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_subs_epi16Experimentalavx512bw,avx512vl
    Subtract packed signed 16-bit integers in b from packed 16-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_subs_epu8Experimentalavx512bw,avx512vl
    Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_subs_epu16Experimentalavx512bw,avx512vl
    Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_test_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
  • _mm256_mask_test_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
  • _mm256_mask_testn_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
  • _mm256_mask_testn_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
  • _mm256_mask_unpackhi_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_unpackhi_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_unpacklo_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_mask_unpacklo_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_maskz_abs_epi8Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_abs_epi16Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_add_epi8Experimentalavx512bw,avx512vl
    Add packed 8-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_add_epi16Experimentalavx512bw,avx512vl
    Add packed 16-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_adds_epi8Experimentalavx512bw,avx512vl
    Add packed signed 8-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_adds_epi16Experimentalavx512bw,avx512vl
    Add packed signed 16-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_adds_epu8Experimentalavx512bw,avx512vl
    Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_adds_epu16Experimentalavx512bw,avx512vl
    Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_alignr_epi8Experimentalavx512bw,avx512vl
    Concatenate pairs of 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by imm8 bytes, and store the low 16 bytes in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_avg_epu8Experimentalavx512bw,avx512vl
    Average packed unsigned 8-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_avg_epu16Experimentalavx512bw,avx512vl
    Average packed unsigned 16-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_broadcastb_epi8Experimentalavx512bw,avx512vl
    Broadcast the low packed 8-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_broadcastw_epi16Experimentalavx512bw,avx512vl
    Broadcast the low packed 16-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_cvtepi8_epi16Experimentalavx512bw,avx512vl
    Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_cvtepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_cvtepu8_epi16Experimentalavx512bw,avx512vl
    Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_cvtsepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_cvtusepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_dbsad_epu8Experimentalavx512bw,avx512vl
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm256_maskz_loadu_epi8Experimentalavx512f,avx512bw,avx512vl,avx
    Load packed 8-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm256_maskz_loadu_epi16Experimentalavx512f,avx512bw,avx512vl,avx
    Load packed 16-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm256_maskz_madd_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_maddubs_epi16Experimentalavx512bw,avx512vl
    Multiply packed unsigned 8-bit integers in a by packed signed 8-bit integers in b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers, and pack the saturated results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_max_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_max_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_max_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_max_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_min_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_min_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_min_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_min_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_mov_epi8Experimentalavx512bw,avx512vl
    Move packed 8-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_mov_epi16Experimentalavx512bw,avx512vl
    Move packed 16-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_mulhi_epi16Experimentalavx512bw,avx512vl
    Multiply the packed signed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_mulhi_epu16Experimentalavx512bw,avx512vl
    Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_mulhrs_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_mullo_epi16Experimentalavx512bw,avx512vl
    Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_packs_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_packs_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_packus_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_packus_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_permutexvar_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_set1_epi8Experimentalavx512bw,avx512vl
    Broadcast 8-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_set1_epi16Experimentalavx512bw,avx512vl
    Broadcast the low packed 16-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_shuffle_epi8Experimentalavx512bw,avx512vl
    Shuffle packed 8-bit integers in a according to shuffle control mask in the corresponding 8-bit element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_shufflehi_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the high 64 bits of 128-bit lanes of dst, with the low 64 bits of 128-bit lanes being copied from a to dst, using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_shufflelo_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the low 64 bits of 128-bit lanes of dst, with the high 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm256_maskz_sll_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_slli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_sllv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_sra_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_srai_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_srav_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_srl_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_srli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_srlv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_sub_epi8Experimentalavx512bw,avx512vl
    Subtract packed 8-bit integers in b from packed 8-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_sub_epi16Experimentalavx512bw,avx512vl
    Subtract packed 16-bit integers in b from packed 16-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_subs_epi8Experimentalavx512bw,avx512vl
    Subtract packed signed 8-bit integers in b from packed 8-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_subs_epi16Experimentalavx512bw,avx512vl
    Subtract packed signed 16-bit integers in b from packed 16-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_subs_epu8Experimentalavx512bw,avx512vl
    Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_subs_epu16Experimentalavx512bw,avx512vl
    Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_unpackhi_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_unpackhi_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_unpacklo_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_maskz_unpacklo_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm256_movepi8_maskExperimentalavx512bw,avx512vl
    Set each bit of mask register k based on the most significant bit of the corresponding packed 8-bit integer in a.
  • _mm256_movepi16_maskExperimentalavx512bw,avx512vl
    Set each bit of mask register k based on the most significant bit of the corresponding packed 16-bit integer in a.
  • _mm256_movm_epi8Experimentalavx512bw,avx512vl
    Set each packed 8-bit integer in dst to all ones or all zeros based on the value of the corresponding bit in k.
  • _mm256_movm_epi16Experimentalavx512bw,avx512vl
    Set each packed 16-bit integer in dst to all ones or all zeros based on the value of the corresponding bit in k.
  • _mm256_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
  • _mm256_permutexvar_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst.
  • _mm256_sllv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
  • _mm256_srav_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst.
  • _mm256_srlv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
  • _mm256_storeu_epi8Experimentalavx512bw,avx512vl
    Store 256-bits (composed of 32 packed 8-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
  • _mm256_storeu_epi16Experimentalavx512bw,avx512vl
    Store 256-bits (composed of 16 packed 16-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
  • _mm256_test_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
  • _mm256_test_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
  • _mm256_testn_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
  • _mm256_testn_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
  • _mm512_abs_epi8Experimentalavx512bw
    Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst.
  • _mm512_abs_epi16Experimentalavx512bw
    Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst.
  • _mm512_add_epi8Experimentalavx512bw
    Add packed 8-bit integers in a and b, and store the results in dst.
  • _mm512_add_epi16Experimentalavx512bw
    Add packed 16-bit integers in a and b, and store the results in dst.
  • _mm512_adds_epi8Experimentalavx512bw
    Add packed signed 8-bit integers in a and b using saturation, and store the results in dst.
  • _mm512_adds_epi16Experimentalavx512bw
    Add packed signed 16-bit integers in a and b using saturation, and store the results in dst.
  • _mm512_adds_epu8Experimentalavx512bw
    Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst.
  • _mm512_adds_epu16Experimentalavx512bw
    Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst.
  • _mm512_alignr_epi8Experimentalavx512bw
    Concatenate pairs of 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by imm8 bytes, and store the low 16 bytes in dst.
  • _mm512_avg_epu8Experimentalavx512bw
    Average packed unsigned 8-bit integers in a and b, and store the results in dst.
  • _mm512_avg_epu16Experimentalavx512bw
    Average packed unsigned 16-bit integers in a and b, and store the results in dst.
  • _mm512_broadcastb_epi8Experimentalavx512bw
    Broadcast the low packed 8-bit integer from a to all elements of dst.
  • _mm512_broadcastw_epi16Experimentalavx512bw
    Broadcast the low packed 16-bit integer from a to all elements of dst.
  • _mm512_bslli_epi128Experimentalavx512bw
    Shift 128-bit lanes in a left by imm8 bytes while shifting in zeros, and store the results in dst.
  • _mm512_bsrli_epi128Experimentalavx512bw
    Shift 128-bit lanes in a right by imm8 bytes while shifting in zeros, and store the results in dst.
  • _mm512_cmp_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm512_cmp_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm512_cmp_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm512_cmp_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b based on the comparison operand specified by IMM8, and store the results in mask vector k.
  • _mm512_cmpeq_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm512_cmpeq_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm512_cmpeq_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm512_cmpeq_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm512_cmpge_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm512_cmpge_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm512_cmpge_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm512_cmpge_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm512_cmpgt_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm512_cmpgt_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm512_cmpgt_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm512_cmpgt_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm512_cmple_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm512_cmple_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm512_cmple_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm512_cmple_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm512_cmplt_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm512_cmplt_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm512_cmplt_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm512_cmplt_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm512_cmpneq_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm512_cmpneq_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm512_cmpneq_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm512_cmpneq_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm512_cvtepi8_epi16Experimentalavx512bw
    Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst.
  • _mm512_cvtepi16_epi8Experimentalavx512bw
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
  • _mm512_cvtepu8_epi16Experimentalavx512bw
    Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst.
  • _mm512_cvtsepi16_epi8Experimentalavx512bw
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
  • _mm512_cvtusepi16_epi8Experimentalavx512bw
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
  • _mm512_dbsad_epu8Experimentalavx512bw
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst. Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm512_loadu_epi8Experimentalavx512bw
    Load 512-bits (composed of 64 packed 8-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
  • _mm512_loadu_epi16Experimentalavx512bw
    Load 512-bits (composed of 32 packed 16-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
  • _mm512_madd_epi16Experimentalavx512bw
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst.
  • _mm512_maddubs_epi16Experimentalavx512bw
    Vertically multiply each unsigned 8-bit integer from a with the corresponding signed 8-bit integer from b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers, and pack the saturated results in dst.
  • _mm512_mask2_permutex2var_epi16Experimentalavx512bw
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
  • _mm512_mask_abs_epi8Experimentalavx512bw
    Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_abs_epi16Experimentalavx512bw
    Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_add_epi8Experimentalavx512bw
    Add packed 8-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_add_epi16Experimentalavx512bw
    Add packed 16-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_adds_epi8Experimentalavx512bw
    Add packed signed 8-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_adds_epi16Experimentalavx512bw
    Add packed signed 16-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_adds_epu8Experimentalavx512bw
    Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_adds_epu16Experimentalavx512bw
    Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_alignr_epi8Experimentalavx512bw
    Concatenate pairs of 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by imm8 bytes, and store the low 16 bytes in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_avg_epu8Experimentalavx512bw
    Average packed unsigned 8-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_avg_epu16Experimentalavx512bw
    Average packed unsigned 16-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_blend_epi8Experimentalavx512bw
    Blend packed 8-bit integers from a and b using control mask k, and store the results in dst.
  • _mm512_mask_blend_epi16Experimentalavx512bw
    Blend packed 16-bit integers from a and b using control mask k, and store the results in dst.
  • _mm512_mask_broadcastb_epi8Experimentalavx512bw
    Broadcast the low packed 8-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_broadcastw_epi16Experimentalavx512bw
    Broadcast the low packed 16-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_cmp_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmp_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmp_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmp_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpeq_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpeq_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpeq_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpeq_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpge_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpge_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpge_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpge_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpgt_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpgt_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpgt_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpgt_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmple_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmple_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmple_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmple_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmplt_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmplt_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmplt_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmplt_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpneq_epi8_maskExperimentalavx512bw
    Compare packed signed 8-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpneq_epi16_maskExperimentalavx512bw
    Compare packed signed 16-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpneq_epu8_maskExperimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cmpneq_epu16_maskExperimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_mask_cvtepi8_epi16Experimentalavx512bw
    Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_cvtepi16_epi8Experimentalavx512bw
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_cvtepi16_storeu_epi8Experimentalavx512bw
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm512_mask_cvtepu8_epi16Experimentalavx512bw
    Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_cvtsepi16_epi8Experimentalavx512bw
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_cvtsepi16_storeu_epi8Experimentalavx512bw
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm512_mask_cvtusepi16_epi8Experimentalavx512bw
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_cvtusepi16_storeu_epi8Experimentalavx512bw
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm512_mask_dbsad_epu8Experimentalavx512bw
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm512_mask_loadu_epi8Experimentalavx512f,avx512bw
    Load packed 8-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm512_mask_loadu_epi16Experimentalavx512f,avx512bw
    Load packed 16-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm512_mask_madd_epi16Experimentalavx512bw
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_maddubs_epi16Experimentalavx512bw
    Multiply packed unsigned 8-bit integers in a by packed signed 8-bit integers in b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers, and pack the saturated results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_max_epi8Experimentalavx512bw
    Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_max_epi16Experimentalavx512bw
    Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_max_epu8Experimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_max_epu16Experimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_min_epi8Experimentalavx512bw
    Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_min_epi16Experimentalavx512bw
    Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_min_epu8Experimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_min_epu16Experimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_mov_epi8Experimentalavx512bw
    Move packed 8-bit integers from a into dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_mov_epi16Experimentalavx512bw
    Move packed 16-bit integers from a into dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_mulhi_epi16Experimentalavx512bw
    Multiply the packed signed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_mulhi_epu16Experimentalavx512bw
    Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_mulhrs_epi16Experimentalavx512bw
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_mullo_epi16Experimentalavx512bw
    Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_packs_epi16Experimentalavx512bw
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_packs_epi32Experimentalavx512bw
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_packus_epi16Experimentalavx512bw
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_packus_epi32Experimentalavx512bw
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_permutex2var_epi16Experimentalavx512bw
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
  • _mm512_mask_permutexvar_epi16Experimentalavx512bw
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_set1_epi8Experimentalavx512bw
    Broadcast 8-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_set1_epi16Experimentalavx512bw
    Broadcast 16-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_shuffle_epi8Experimentalavx512bw
    Shuffle 8-bit integers in a within 128-bit lanes using the control in the corresponding 8-bit element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_shufflehi_epi16Experimentalavx512bw
    Shuffle 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the high 64 bits of 128-bit lanes of dst, with the low 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_shufflelo_epi16Experimentalavx512bw
    Shuffle 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the low 64 bits of 128-bit lanes of dst, with the high 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_sll_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_slli_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_sllv_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_sra_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_srai_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_srav_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_srl_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_srli_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_srlv_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_storeu_epi8Experimentalavx512f,avx512bw
    Store packed 8-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
  • _mm512_mask_storeu_epi16Experimentalavx512f,avx512bw
    Store packed 16-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
  • _mm512_mask_sub_epi8Experimentalavx512bw
    Subtract packed 8-bit integers in b from packed 8-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_sub_epi16Experimentalavx512bw
    Subtract packed 16-bit integers in b from packed 16-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_subs_epi8Experimentalavx512bw
    Subtract packed signed 8-bit integers in b from packed 8-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_subs_epi16Experimentalavx512bw
    Subtract packed signed 16-bit integers in b from packed 16-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_subs_epu8Experimentalavx512bw
    Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_subs_epu16Experimentalavx512bw
    Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_test_epi8_maskExperimentalavx512bw
    Compute the bitwise AND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
  • _mm512_mask_test_epi16_maskExperimentalavx512bw
    Compute the bitwise AND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
  • _mm512_mask_testn_epi8_maskExperimentalavx512bw
    Compute the bitwise NAND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
  • _mm512_mask_testn_epi16_maskExperimentalavx512bw
    Compute the bitwise NAND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
  • _mm512_mask_unpackhi_epi8Experimentalavx512bw
    Unpack and interleave 8-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_unpackhi_epi16Experimentalavx512bw
    Unpack and interleave 16-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_unpacklo_epi8Experimentalavx512bw
    Unpack and interleave 8-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_mask_unpacklo_epi16Experimentalavx512bw
    Unpack and interleave 16-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm512_maskz_abs_epi8Experimentalavx512bw
    Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_abs_epi16Experimentalavx512bw
    Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_add_epi8Experimentalavx512bw
    Add packed 8-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_add_epi16Experimentalavx512bw
    Add packed 16-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_adds_epi8Experimentalavx512bw
    Add packed signed 8-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_adds_epi16Experimentalavx512bw
    Add packed signed 16-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_adds_epu8Experimentalavx512bw
    Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_adds_epu16Experimentalavx512bw
    Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_alignr_epi8Experimentalavx512bw
    Concatenate pairs of 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by imm8 bytes, and store the low 16 bytes in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_avg_epu8Experimentalavx512bw
    Average packed unsigned 8-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_avg_epu16Experimentalavx512bw
    Average packed unsigned 16-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_broadcastb_epi8Experimentalavx512bw
    Broadcast the low packed 8-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_broadcastw_epi16Experimentalavx512bw
    Broadcast the low packed 16-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_cvtepi8_epi16Experimentalavx512bw
    Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_cvtepi16_epi8Experimentalavx512bw
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_cvtepu8_epi16Experimentalavx512bw
    Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_cvtsepi16_epi8Experimentalavx512bw
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_cvtusepi16_epi8Experimentalavx512bw
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_dbsad_epu8Experimentalavx512bw
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm512_maskz_loadu_epi8Experimentalavx512f,avx512bw
    Load packed 8-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm512_maskz_loadu_epi16Experimentalavx512f,avx512bw
    Load packed 16-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm512_maskz_madd_epi16Experimentalavx512bw
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_maddubs_epi16Experimentalavx512bw
    Multiply packed unsigned 8-bit integers in a by packed signed 8-bit integers in b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers, and pack the saturated results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_max_epi8Experimentalavx512bw
    Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_max_epi16Experimentalavx512bw
    Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_max_epu8Experimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_max_epu16Experimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_min_epi8Experimentalavx512bw
    Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_min_epi16Experimentalavx512bw
    Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_min_epu8Experimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_min_epu16Experimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_mov_epi8Experimentalavx512bw
    Move packed 8-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_mov_epi16Experimentalavx512bw
    Move packed 16-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_mulhi_epi16Experimentalavx512bw
    Multiply the packed signed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_mulhi_epu16Experimentalavx512bw
    Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_mulhrs_epi16Experimentalavx512bw
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_mullo_epi16Experimentalavx512bw
    Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_packs_epi16Experimentalavx512bw
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_packs_epi32Experimentalavx512bw
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_packus_epi16Experimentalavx512bw
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_packus_epi32Experimentalavx512bw
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_permutex2var_epi16Experimentalavx512bw
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_permutexvar_epi16Experimentalavx512bw
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_set1_epi8Experimentalavx512bw
    Broadcast 8-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_set1_epi16Experimentalavx512bw
    Broadcast the low packed 16-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_shuffle_epi8Experimentalavx512bw
    Shuffle packed 8-bit integers in a according to shuffle control mask in the corresponding 8-bit element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_shufflehi_epi16Experimentalavx512bw
    Shuffle 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the high 64 bits of 128-bit lanes of dst, with the low 64 bits of 128-bit lanes being copied from a to dst, using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_shufflelo_epi16Experimentalavx512bw
    Shuffle 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the low 64 bits of 128-bit lanes of dst, with the high 64 bits of 128-bit lanes being copied from a to dst, using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_sll_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_slli_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_sllv_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_sra_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_srai_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_srav_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_srl_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_srli_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_srlv_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_sub_epi8Experimentalavx512bw
    Subtract packed 8-bit integers in b from packed 8-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_sub_epi16Experimentalavx512bw
    Subtract packed 16-bit integers in b from packed 16-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_subs_epi8Experimentalavx512bw
    Subtract packed signed 8-bit integers in b from packed 8-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_subs_epi16Experimentalavx512bw
    Subtract packed signed 16-bit integers in b from packed 16-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_subs_epu8Experimentalavx512bw
    Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_subs_epu16Experimentalavx512bw
    Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_unpackhi_epi8Experimentalavx512bw
    Unpack and interleave 8-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_unpackhi_epi16Experimentalavx512bw
    Unpack and interleave 16-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_unpacklo_epi8Experimentalavx512bw
    Unpack and interleave 8-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_maskz_unpacklo_epi16Experimentalavx512bw
    Unpack and interleave 16-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm512_max_epi8Experimentalavx512bw
    Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst.
  • _mm512_max_epi16Experimentalavx512bw
    Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst.
  • _mm512_max_epu8Experimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst.
  • _mm512_max_epu16Experimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst.
  • _mm512_min_epi8Experimentalavx512bw
    Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst.
  • _mm512_min_epi16Experimentalavx512bw
    Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst.
  • _mm512_min_epu8Experimentalavx512bw
    Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst.
  • _mm512_min_epu16Experimentalavx512bw
    Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst.
  • _mm512_movepi8_maskExperimentalavx512bw
    Set each bit of mask register k based on the most significant bit of the corresponding packed 8-bit integer in a.
  • _mm512_movepi16_maskExperimentalavx512bw
    Set each bit of mask register k based on the most significant bit of the corresponding packed 16-bit integer in a.
  • _mm512_movm_epi8Experimentalavx512bw
    Set each packed 8-bit integer in dst to all ones or all zeros based on the value of the corresponding bit in k.
  • _mm512_movm_epi16Experimentalavx512bw
    Set each packed 16-bit integer in dst to all ones or all zeros based on the value of the corresponding bit in k.
  • _mm512_mulhi_epi16Experimentalavx512bw
    Multiply the packed signed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst.
  • _mm512_mulhi_epu16Experimentalavx512bw
    Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst.
  • _mm512_mulhrs_epi16Experimentalavx512bw
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst.
  • _mm512_mullo_epi16Experimentalavx512bw
    Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst.
  • _mm512_packs_epi16Experimentalavx512bw
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using signed saturation, and store the results in dst.
  • _mm512_packs_epi32Experimentalavx512bw
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using signed saturation, and store the results in dst.
  • _mm512_packus_epi16Experimentalavx512bw
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation, and store the results in dst.
  • _mm512_packus_epi32Experimentalavx512bw
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst.
  • _mm512_permutex2var_epi16Experimentalavx512bw
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
  • _mm512_permutexvar_epi16Experimentalavx512bw
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst.
  • _mm512_sad_epu8Experimentalavx512bw
    Compute the absolute differences of packed unsigned 8-bit integers in a and b, then horizontally sum each consecutive 8 differences to produce eight unsigned 16-bit integers, and pack these unsigned 16-bit integers in the low 16 bits of 64-bit elements in dst.
  • _mm512_shuffle_epi8Experimentalavx512bw
    Shuffle packed 8-bit integers in a according to shuffle control mask in the corresponding 8-bit element of b, and store the results in dst.
  • _mm512_shufflehi_epi16Experimentalavx512bw
    Shuffle 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the high 64 bits of 128-bit lanes of dst, with the low 64 bits of 128-bit lanes being copied from a to dst.
  • _mm512_shufflelo_epi16Experimentalavx512bw
    Shuffle 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the low 64 bits of 128-bit lanes of dst, with the high 64 bits of 128-bit lanes being copied from a to dst.
  • _mm512_sll_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by count while shifting in zeros, and store the results in dst.
  • _mm512_slli_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst.
  • _mm512_sllv_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
  • _mm512_sra_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by count while shifting in sign bits, and store the results in dst.
  • _mm512_srai_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst.
  • _mm512_srav_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst.
  • _mm512_srl_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by count while shifting in zeros, and store the results in dst.
  • _mm512_srli_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by imm8 while shifting in zeros, and store the results in dst.
  • _mm512_srlv_epi16Experimentalavx512bw
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
  • _mm512_storeu_epi8Experimentalavx512bw
    Store 512-bits (composed of 64 packed 8-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
  • _mm512_storeu_epi16Experimentalavx512bw
    Store 512-bits (composed of 32 packed 16-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
  • _mm512_sub_epi8Experimentalavx512bw
    Subtract packed 8-bit integers in b from packed 8-bit integers in a, and store the results in dst.
  • _mm512_sub_epi16Experimentalavx512bw
    Subtract packed 16-bit integers in b from packed 16-bit integers in a, and store the results in dst.
  • _mm512_subs_epi8Experimentalavx512bw
    Subtract packed signed 8-bit integers in b from packed 8-bit integers in a using saturation, and store the results in dst.
  • _mm512_subs_epi16Experimentalavx512bw
    Subtract packed signed 16-bit integers in b from packed 16-bit integers in a using saturation, and store the results in dst.
  • _mm512_subs_epu8Experimentalavx512bw
    Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst.
  • _mm512_subs_epu16Experimentalavx512bw
    Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation, and store the results in dst.
  • _mm512_test_epi8_maskExperimentalavx512bw
    Compute the bitwise AND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
  • _mm512_test_epi16_maskExperimentalavx512bw
    Compute the bitwise AND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
  • _mm512_testn_epi8_maskExperimentalavx512bw
    Compute the bitwise NAND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
  • _mm512_testn_epi16_maskExperimentalavx512bw
    Compute the bitwise NAND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
  • _mm512_unpackhi_epi8Experimentalavx512bw
    Unpack and interleave 8-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst.
  • _mm512_unpackhi_epi16Experimentalavx512bw
    Unpack and interleave 16-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst.
  • _mm512_unpacklo_epi8Experimentalavx512bw
    Unpack and interleave 8-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst.
  • _mm512_unpacklo_epi16Experimentalavx512bw
    Unpack and interleave 16-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst.
  • _mm_cmp_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm_cmp_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm_cmp_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm_cmp_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k.
  • _mm_cmpeq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm_cmpeq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm_cmpeq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm_cmpeq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for equality, and store the results in mask vector k.
  • _mm_cmpge_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm_cmpge_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm_cmpge_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm_cmpge_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k.
  • _mm_cmpgt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm_cmpgt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm_cmpgt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm_cmpgt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than, and store the results in mask vector k.
  • _mm_cmple_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm_cmple_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm_cmple_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm_cmple_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k.
  • _mm_cmplt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm_cmplt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm_cmplt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm_cmplt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than, and store the results in mask vector k.
  • _mm_cmpneq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm_cmpneq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm_cmpneq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm_cmpneq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for not-equal, and store the results in mask vector k.
  • _mm_cvtepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst.
  • _mm_cvtsepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst.
  • _mm_cvtusepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst.
  • _mm_dbsad_epu8Experimentalavx512bw,avx512vl
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst. Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm_loadu_epi8Experimentalavx512bw,avx512vl
    Load 128-bits (composed of 16 packed 8-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
  • _mm_loadu_epi16Experimentalavx512bw,avx512vl
    Load 128-bits (composed of 8 packed 16-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary.
  • _mm_mask2_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from idx when the corresponding mask bit is not set).
  • _mm_mask_abs_epi8Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set)
  • _mm_mask_abs_epi16Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_add_epi8Experimentalavx512bw,avx512vl
    Add packed 8-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_add_epi16Experimentalavx512bw,avx512vl
    Add packed 16-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_adds_epi8Experimentalavx512bw,avx512vl
    Add packed signed 8-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_adds_epi16Experimentalavx512bw,avx512vl
    Add packed signed 16-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_adds_epu8Experimentalavx512bw,avx512vl
    Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_adds_epu16Experimentalavx512bw,avx512vl
    Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_alignr_epi8Experimentalavx512bw,avx512vl
    Concatenate pairs of 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by imm8 bytes, and store the low 16 bytes in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_avg_epu8Experimentalavx512bw,avx512vl
    Average packed unsigned 8-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_avg_epu16Experimentalavx512bw,avx512vl
    Average packed unsigned 16-bit integers in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_blend_epi8Experimentalavx512bw,avx512vl
    Blend packed 8-bit integers from a and b using control mask k, and store the results in dst.
  • _mm_mask_blend_epi16Experimentalavx512bw,avx512vl
    Blend packed 16-bit integers from a and b using control mask k, and store the results in dst.
  • _mm_mask_broadcastb_epi8Experimentalavx512bw,avx512vl
    Broadcast the low packed 8-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_broadcastw_epi16Experimentalavx512bw,avx512vl
    Broadcast the low packed 16-bit integer from a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_cmp_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmp_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmp_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmp_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpeq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpeq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpeq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpeq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for equality, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpge_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpge_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpge_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpge_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpgt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpgt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpgt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpgt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for greater-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmple_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmple_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmple_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmple_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmplt_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmplt_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmplt_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmplt_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for less-than, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpneq_epi8_maskExperimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpneq_epi16_maskExperimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpneq_epu8_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cmpneq_epu16_maskExperimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b for not-equal, and store the results in mask vector k using zeromask k1 (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_mask_cvtepi8_epi16Experimentalavx512bw,avx512vl
    Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_cvtepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_cvtepi16_storeu_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm_mask_cvtepu8_epi16Experimentalavx512bw,avx512vl
    Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_cvtsepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_cvtsepi16_storeu_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm_mask_cvtusepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_cvtusepi16_storeu_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the active results (those with their respective bit set in writemask k) to unaligned memory at base_addr.
  • _mm_mask_dbsad_epu8Experimentalavx512bw,avx512vl
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm_mask_loadu_epi8Experimentalavx512f,avx512bw,avx512vl,avx,sse
    Load packed 8-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm_mask_loadu_epi16Experimentalavx512f,avx512bw,avx512vl,avx,sse
    Load packed 16-bit integers from memory into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm_mask_madd_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_maddubs_epi16Experimentalavx512bw,avx512vl
    Multiply packed unsigned 8-bit integers in a by packed signed 8-bit integers in b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers, and pack the saturated results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_max_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_max_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_max_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_max_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_min_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_min_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_min_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_min_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_mov_epi8Experimentalavx512bw,avx512vl
    Move packed 8-bit integers from a into dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_mov_epi16Experimentalavx512bw,avx512vl
    Move packed 16-bit integers from a into dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_mulhi_epi16Experimentalavx512bw,avx512vl
    Multiply the packed signed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_mulhi_epu16Experimentalavx512bw,avx512vl
    Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_mulhrs_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_mullo_epi16Experimentalavx512bw,avx512vl
    Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_packs_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_packs_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using signed saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_packus_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_packus_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set).
  • _mm_mask_permutexvar_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_set1_epi8Experimentalavx512bw,avx512vl
    Broadcast 8-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_set1_epi16Experimentalavx512bw,avx512vl
    Broadcast 16-bit integer a to all elements of dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_shuffle_epi8Experimentalavx512bw,avx512vl
    Shuffle 8-bit integers in a within 128-bit lanes using the control in the corresponding 8-bit element of b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_shufflehi_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the high 64 bits of 128-bit lanes of dst, with the low 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_shufflelo_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the low 64 bits of 128-bit lanes of dst, with the high 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_sll_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_slli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_sllv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_sra_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_srai_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_srav_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_srl_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_srli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_srlv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_storeu_epi8Experimentalavx512f,avx512bw,avx512vl,avx,sse
    Store packed 8-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
  • _mm_mask_storeu_epi16Experimentalavx512f,avx512bw,avx512vl,avx,sse
    Store packed 16-bit integers from a into memory using writemask k. mem_addr does not need to be aligned on any particular boundary.
  • _mm_mask_sub_epi8Experimentalavx512bw,avx512vl
    Subtract packed 8-bit integers in b from packed 8-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_sub_epi16Experimentalavx512bw,avx512vl
    Subtract packed 16-bit integers in b from packed 16-bit integers in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_subs_epi8Experimentalavx512bw,avx512vl
    Subtract packed signed 8-bit integers in b from packed 8-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_subs_epi16Experimentalavx512bw,avx512vl
    Subtract packed signed 16-bit integers in b from packed 16-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_subs_epu8Experimentalavx512bw,avx512vl
    Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_subs_epu16Experimentalavx512bw,avx512vl
    Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_test_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
  • _mm_mask_test_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is non-zero.
  • _mm_mask_testn_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
  • _mm_mask_testn_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero.
  • _mm_mask_unpackhi_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_unpackhi_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_unpacklo_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_mask_unpacklo_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_maskz_abs_epi8Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_abs_epi16Experimentalavx512bw,avx512vl
    Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_add_epi8Experimentalavx512bw,avx512vl
    Add packed 8-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_add_epi16Experimentalavx512bw,avx512vl
    Add packed 16-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_adds_epi8Experimentalavx512bw,avx512vl
    Add packed signed 8-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_adds_epi16Experimentalavx512bw,avx512vl
    Add packed signed 16-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_adds_epu8Experimentalavx512bw,avx512vl
    Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_adds_epu16Experimentalavx512bw,avx512vl
    Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_alignr_epi8Experimentalavx512bw,avx512vl
    Concatenate pairs of 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by imm8 bytes, and store the low 16 bytes in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_avg_epu8Experimentalavx512bw,avx512vl
    Average packed unsigned 8-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_avg_epu16Experimentalavx512bw,avx512vl
    Average packed unsigned 16-bit integers in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_broadcastb_epi8Experimentalavx512bw,avx512vl
    Broadcast the low packed 8-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_broadcastw_epi16Experimentalavx512bw,avx512vl
    Broadcast the low packed 16-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_cvtepi8_epi16Experimentalavx512bw,avx512vl
    Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_cvtepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_cvtepu8_epi16Experimentalavx512bw,avx512vl
    Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_cvtsepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_cvtusepi16_epi8Experimentalavx512bw,avx512vl
    Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_dbsad_epu8Experimentalavx512bw,avx512vl
    Compute the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and store the 16-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). Four SADs are performed on four 8-bit quadruplets for each 64-bit lane. The first two SADs use the lower 8-bit quadruplet of the lane from a, and the last two SADs use the uppper 8-bit quadruplet of the lane from a. Quadruplets from b are selected from within 128-bit lanes according to the control in imm8, and each SAD in each 64-bit lane uses the selected quadruplet at 8-bit offsets.
  • _mm_maskz_loadu_epi8Experimentalavx512f,avx512bw,avx512vl,avx,sse
    Load packed 8-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm_maskz_loadu_epi16Experimentalavx512f,avx512bw,avx512vl,avx,sse
    Load packed 16-bit integers from memory into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). mem_addr does not need to be aligned on any particular boundary.
  • _mm_maskz_madd_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers, and pack the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_maddubs_epi16Experimentalavx512bw,avx512vl
    Multiply packed unsigned 8-bit integers in a by packed signed 8-bit integers in b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers, and pack the saturated results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_max_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_max_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_max_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_max_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_min_epi8Experimentalavx512bw,avx512vl
    Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_min_epi16Experimentalavx512bw,avx512vl
    Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_min_epu8Experimentalavx512bw,avx512vl
    Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_min_epu16Experimentalavx512bw,avx512vl
    Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_mov_epi8Experimentalavx512bw,avx512vl
    Move packed 8-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_mov_epi16Experimentalavx512bw,avx512vl
    Move packed 16-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_mulhi_epi16Experimentalavx512bw,avx512vl
    Multiply the packed signed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_mulhi_epu16Experimentalavx512bw,avx512vl
    Multiply the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers, and store the high 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_mulhrs_epi16Experimentalavx512bw,avx512vl
    Multiply packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and store bits [16:1] to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_mullo_epi16Experimentalavx512bw,avx512vl
    Multiply the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_packs_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_packs_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using signed saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_packus_epi16Experimentalavx512bw,avx512vl
    Convert packed signed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_packus_epi32Experimentalavx512bw,avx512vl
    Convert packed signed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_permutexvar_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_set1_epi8Experimentalavx512bw,avx512vl
    Broadcast 8-bit integer a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_set1_epi16Experimentalavx512bw,avx512vl
    Broadcast the low packed 16-bit integer from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_shuffle_epi8Experimentalavx512bw,avx512vl
    Shuffle packed 8-bit integers in a according to shuffle control mask in the corresponding 8-bit element of b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_shufflehi_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the high 64 bits of 128-bit lanes of dst, with the low 64 bits of 128-bit lanes being copied from a to dst, using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_shufflelo_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. Store the results in the low 64 bits of 128-bit lanes of dst, with the high 64 bits of 128-bit lanes being copied from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set).
  • _mm_maskz_sll_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_slli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_sllv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_sra_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_srai_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_srav_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_srl_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_srli_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by imm8 while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_srlv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_sub_epi8Experimentalavx512bw,avx512vl
    Subtract packed 8-bit integers in b from packed 8-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_sub_epi16Experimentalavx512bw,avx512vl
    Subtract packed 16-bit integers in b from packed 16-bit integers in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_subs_epi8Experimentalavx512bw,avx512vl
    Subtract packed signed 8-bit integers in b from packed 8-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_subs_epi16Experimentalavx512bw,avx512vl
    Subtract packed signed 16-bit integers in b from packed 16-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_subs_epu8Experimentalavx512bw,avx512vl
    Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_subs_epu16Experimentalavx512bw,avx512vl
    Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_unpackhi_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_unpackhi_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the high half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_unpacklo_epi8Experimentalavx512bw,avx512vl
    Unpack and interleave 8-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_maskz_unpacklo_epi16Experimentalavx512bw,avx512vl
    Unpack and interleave 16-bit integers from the low half of each 128-bit lane in a and b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set).
  • _mm_movepi8_maskExperimentalavx512bw,avx512vl
    Set each bit of mask register k based on the most significant bit of the corresponding packed 8-bit integer in a.
  • _mm_movepi16_maskExperimentalavx512bw,avx512vl
    Set each bit of mask register k based on the most significant bit of the corresponding packed 16-bit integer in a.
  • _mm_movm_epi8Experimentalavx512bw,avx512vl
    Set each packed 8-bit integer in dst to all ones or all zeros based on the value of the corresponding bit in k.
  • _mm_movm_epi16Experimentalavx512bw,avx512vl
    Set each packed 16-bit integer in dst to all ones or all zeros based on the value of the corresponding bit in k.
  • _mm_permutex2var_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst.
  • _mm_permutexvar_epi16Experimentalavx512bw,avx512vl
    Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst.
  • _mm_sllv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
  • _mm_srav_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits, and store the results in dst.
  • _mm_srlv_epi16Experimentalavx512bw,avx512vl
    Shift packed 16-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros, and store the results in dst.
  • _mm_storeu_epi8Experimentalavx512bw,avx512vl
    Store 128-bits (composed of 16 packed 8-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
  • _mm_storeu_epi16Experimentalavx512bw,avx512vl
    Store 128-bits (composed of 8 packed 16-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
  • _mm_test_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
  • _mm_test_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise AND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k if the intermediate value is non-zero.
  • _mm_testn_epi8_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 8-bit integers in a and b, producing intermediate 8-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
  • _mm_testn_epi16_maskExperimentalavx512bw,avx512vl
    Compute the bitwise NAND of packed 16-bit integers in a and b, producing intermediate 16-bit values, and set the corresponding bit in result mask k if the intermediate value is zero.
  • _store_mask32Experimentalavx512bw
    Store 32-bit mask from a into memory.
  • _store_mask64Experimentalavx512bw
    Store 64-bit mask from a into memory.
  • pslliw128 🔒 Experimental
  • pslliw256 🔒 Experimental
  • psraiw128 🔒 Experimental
  • psraiw256 🔒 Experimental
  • vdbpsadbw 🔒 Experimental
  • vdbpsadbw128 🔒 Experimental
  • vdbpsadbw256 🔒 Experimental
  • vpackssdw 🔒 Experimental
  • vpacksswb 🔒 Experimental
  • vpackusdw 🔒 Experimental
  • vpackuswb 🔒 Experimental
  • vpaddsb 🔒 Experimental
  • vpaddsb128 🔒 Experimental
  • vpaddsb256 🔒 Experimental
  • vpaddsw 🔒 Experimental
  • vpaddsw128 🔒 Experimental
  • vpaddsw256 🔒 Experimental
  • vpaddusb 🔒 Experimental
  • vpaddusb128 🔒 Experimental
  • vpaddusb256 🔒 Experimental
  • vpaddusw 🔒 Experimental
  • vpaddusw128 🔒 Experimental
  • vpaddusw256 🔒 Experimental
  • vpavgb 🔒 Experimental
  • vpavgw 🔒 Experimental
  • vpcmpb 🔒 Experimental
  • vpcmpb128 🔒 Experimental
  • vpcmpb256 🔒 Experimental
  • vpcmpub 🔒 Experimental
  • vpcmpub128 🔒 Experimental
  • vpcmpub256 🔒 Experimental
  • vpcmpuw 🔒 Experimental
  • vpcmpuw128 🔒 Experimental
  • vpcmpuw256 🔒 Experimental
  • vpcmpw 🔒 Experimental
  • vpcmpw128 🔒 Experimental
  • vpcmpw256 🔒 Experimental
  • vpermi2w 🔒 Experimental
  • vpermi2w128 🔒 Experimental
  • vpermi2w256 🔒 Experimental
  • vpermw 🔒 Experimental
  • vpermw128 🔒 Experimental
  • vpermw256 🔒 Experimental
  • vpmaddubsw 🔒 Experimental
  • vpmaddwd 🔒 Experimental
  • vpmaxsb 🔒 Experimental
  • vpmaxsw 🔒 Experimental
  • vpmaxub 🔒 Experimental
  • vpmaxuw 🔒 Experimental
  • vpminsb 🔒 Experimental
  • vpminsw 🔒 Experimental
  • vpminub 🔒 Experimental
  • vpminuw 🔒 Experimental
  • vpmovswb 🔒 Experimental
  • vpmovswb128 🔒 Experimental
  • vpmovswb256 🔒 Experimental
  • vpmovswbmem 🔒 Experimental
  • vpmovswbmem128 🔒 Experimental
  • vpmovswbmem256 🔒 Experimental
  • vpmovuswb 🔒 Experimental
  • vpmovuswb128 🔒 Experimental
  • vpmovuswb256 🔒 Experimental
  • vpmovuswbmem 🔒 Experimental
  • vpmovuswbmem128 🔒 Experimental
  • vpmovuswbmem256 🔒 Experimental
  • vpmovwbmem 🔒 Experimental
  • vpmovwbmem128 🔒 Experimental
  • vpmovwbmem256 🔒 Experimental
  • vpmulhrsw 🔒 Experimental
  • vpmulhuw 🔒 Experimental
  • vpmulhw 🔒 Experimental
  • vpsadbw 🔒 Experimental
  • vpshufb 🔒 Experimental
  • vpslliw 🔒 Experimental
  • vpsllvw 🔒 Experimental
  • vpsllvw128 🔒 Experimental
  • vpsllvw256 🔒 Experimental
  • vpsllw 🔒 Experimental
  • vpsraiw 🔒 Experimental
  • vpsravw 🔒 Experimental
  • vpsravw128 🔒 Experimental
  • vpsravw256 🔒 Experimental
  • vpsraw 🔒 Experimental
  • vpsrliw 🔒 Experimental
  • vpsrlvw 🔒 Experimental
  • vpsrlvw128 🔒 Experimental
  • vpsrlvw256 🔒 Experimental
  • vpsrlw 🔒 Experimental
  • vpsubsb 🔒 Experimental
  • vpsubsb128 🔒 Experimental
  • vpsubsb256 🔒 Experimental
  • vpsubsw 🔒 Experimental
  • vpsubsw128 🔒 Experimental
  • vpsubsw256 🔒 Experimental
  • vpsubusb 🔒 Experimental
  • vpsubusb128 🔒 Experimental
  • vpsubusb256 🔒 Experimental
  • vpsubusw 🔒 Experimental
  • vpsubusw128 🔒 Experimental
  • vpsubusw256 🔒 Experimental