Module core::arch::x86_64 1.27.0[−][src]
Platform-specific intrinsics for the x86_64
platform.
See the module documentation for more details.
Structs
__m512 | Experimental 512-bit wide set of sixteen |
__m512d | Experimental 512-bit wide set of eight |
__m512i | Experimental 512-bit wide integer vector type, x86-specific |
CpuidResult | Result of the |
__m128 | 128-bit wide set of four |
__m128d | 128-bit wide set of two |
__m128i | 128-bit wide integer vector type, x86-specific |
__m256 | 256-bit wide set of eight |
__m256d | 256-bit wide set of four |
__m256i | 256-bit wide integer vector type, x86-specific |
Constants
_MM_CMPINT_EQ | Experimental Equal |
_MM_CMPINT_FALSE | Experimental False |
_MM_CMPINT_LE | Experimental Less-than-or-equal |
_MM_CMPINT_LT | Experimental Less-than |
_MM_CMPINT_NE | Experimental Not-equal |
_MM_CMPINT_NLE | Experimental Not less-than-or-equal |
_MM_CMPINT_NLT | Experimental Not less-than |
_MM_CMPINT_TRUE | Experimental True |
_MM_MANT_NORM_1_2 | Experimental interval [1, 2) |
_MM_MANT_NORM_P5_1 | Experimental interval [0.5, 1) |
_MM_MANT_NORM_P5_2 | Experimental interval [0.5, 2) |
_MM_MANT_NORM_P75_1P5 | Experimental interval [0.75, 1.5) |
_MM_MANT_SIGN_NAN | Experimental DEST = NaN if sign(SRC) = 1 |
_MM_MANT_SIGN_SRC | Experimental sign = sign(SRC) |
_MM_MANT_SIGN_ZERO | Experimental sign = 0 |
_MM_PERM_AAAA | Experimental |
_MM_PERM_AAAB | Experimental |
_MM_PERM_AAAC | Experimental |
_MM_PERM_AAAD | Experimental |
_MM_PERM_AABA | Experimental |
_MM_PERM_AABB | Experimental |
_MM_PERM_AABC | Experimental |
_MM_PERM_AABD | Experimental |
_MM_PERM_AACA | Experimental |
_MM_PERM_AACB | Experimental |
_MM_PERM_AACC | Experimental |
_MM_PERM_AACD | Experimental |
_MM_PERM_AADA | Experimental |
_MM_PERM_AADB | Experimental |
_MM_PERM_AADC | Experimental |
_MM_PERM_AADD | Experimental |
_MM_PERM_ABAA | Experimental |
_MM_PERM_ABAB | Experimental |
_MM_PERM_ABAC | Experimental |
_MM_PERM_ABAD | Experimental |
_MM_PERM_ABBA | Experimental |
_MM_PERM_ABBB | Experimental |
_MM_PERM_ABBC | Experimental |
_MM_PERM_ABBD | Experimental |
_MM_PERM_ABCA | Experimental |
_MM_PERM_ABCB | Experimental |
_MM_PERM_ABCC | Experimental |
_MM_PERM_ABCD | Experimental |
_MM_PERM_ABDA | Experimental |
_MM_PERM_ABDB | Experimental |
_MM_PERM_ABDC | Experimental |
_MM_PERM_ABDD | Experimental |
_MM_PERM_ACAA | Experimental |
_MM_PERM_ACAB | Experimental |
_MM_PERM_ACAC | Experimental |
_MM_PERM_ACAD | Experimental |
_MM_PERM_ACBA | Experimental |
_MM_PERM_ACBB | Experimental |
_MM_PERM_ACBC | Experimental |
_MM_PERM_ACBD | Experimental |
_MM_PERM_ACCA | Experimental |
_MM_PERM_ACCB | Experimental |
_MM_PERM_ACCC | Experimental |
_MM_PERM_ACCD | Experimental |
_MM_PERM_ACDA | Experimental |
_MM_PERM_ACDB | Experimental |
_MM_PERM_ACDC | Experimental |
_MM_PERM_ACDD | Experimental |
_MM_PERM_ADAA | Experimental |
_MM_PERM_ADAB | Experimental |
_MM_PERM_ADAC | Experimental |
_MM_PERM_ADAD | Experimental |
_MM_PERM_ADBA | Experimental |
_MM_PERM_ADBB | Experimental |
_MM_PERM_ADBC | Experimental |
_MM_PERM_ADBD | Experimental |
_MM_PERM_ADCA | Experimental |
_MM_PERM_ADCB | Experimental |
_MM_PERM_ADCC | Experimental |
_MM_PERM_ADCD | Experimental |
_MM_PERM_ADDA | Experimental |
_MM_PERM_ADDB | Experimental |
_MM_PERM_ADDC | Experimental |
_MM_PERM_ADDD | Experimental |
_MM_PERM_BAAA | Experimental |
_MM_PERM_BAAB | Experimental |
_MM_PERM_BAAC | Experimental |
_MM_PERM_BAAD | Experimental |
_MM_PERM_BABA | Experimental |
_MM_PERM_BABB | Experimental |
_MM_PERM_BABC | Experimental |
_MM_PERM_BABD | Experimental |
_MM_PERM_BACA | Experimental |
_MM_PERM_BACB | Experimental |
_MM_PERM_BACC | Experimental |
_MM_PERM_BACD | Experimental |
_MM_PERM_BADA | Experimental |
_MM_PERM_BADB | Experimental |
_MM_PERM_BADC | Experimental |
_MM_PERM_BADD | Experimental |
_MM_PERM_BBAA | Experimental |
_MM_PERM_BBAB | Experimental |
_MM_PERM_BBAC | Experimental |
_MM_PERM_BBAD | Experimental |
_MM_PERM_BBBA | Experimental |
_MM_PERM_BBBB | Experimental |
_MM_PERM_BBBC | Experimental |
_MM_PERM_BBBD | Experimental |
_MM_PERM_BBCA | Experimental |
_MM_PERM_BBCB | Experimental |
_MM_PERM_BBCC | Experimental |
_MM_PERM_BBCD | Experimental |
_MM_PERM_BBDA | Experimental |
_MM_PERM_BBDB | Experimental |
_MM_PERM_BBDC | Experimental |
_MM_PERM_BBDD | Experimental |
_MM_PERM_BCAA | Experimental |
_MM_PERM_BCAB | Experimental |
_MM_PERM_BCAC | Experimental |
_MM_PERM_BCAD | Experimental |
_MM_PERM_BCBA | Experimental |
_MM_PERM_BCBB | Experimental |
_MM_PERM_BCBC | Experimental |
_MM_PERM_BCBD | Experimental |
_MM_PERM_BCCA | Experimental |
_MM_PERM_BCCB | Experimental |
_MM_PERM_BCCC | Experimental |
_MM_PERM_BCCD | Experimental |
_MM_PERM_BCDA | Experimental |
_MM_PERM_BCDB | Experimental |
_MM_PERM_BCDC | Experimental |
_MM_PERM_BCDD | Experimental |
_MM_PERM_BDAA | Experimental |
_MM_PERM_BDAB | Experimental |
_MM_PERM_BDAC | Experimental |
_MM_PERM_BDAD | Experimental |
_MM_PERM_BDBA | Experimental |
_MM_PERM_BDBB | Experimental |
_MM_PERM_BDBC | Experimental |
_MM_PERM_BDBD | Experimental |
_MM_PERM_BDCA | Experimental |
_MM_PERM_BDCB | Experimental |
_MM_PERM_BDCC | Experimental |
_MM_PERM_BDCD | Experimental |
_MM_PERM_BDDA | Experimental |
_MM_PERM_BDDB | Experimental |
_MM_PERM_BDDC | Experimental |
_MM_PERM_BDDD | Experimental |
_MM_PERM_CAAA | Experimental |
_MM_PERM_CAAB | Experimental |
_MM_PERM_CAAC | Experimental |
_MM_PERM_CAAD | Experimental |
_MM_PERM_CABA | Experimental |
_MM_PERM_CABB | Experimental |
_MM_PERM_CABC | Experimental |
_MM_PERM_CABD | Experimental |
_MM_PERM_CACA | Experimental |
_MM_PERM_CACB | Experimental |
_MM_PERM_CACC | Experimental |
_MM_PERM_CACD | Experimental |
_MM_PERM_CADA | Experimental |
_MM_PERM_CADB | Experimental |
_MM_PERM_CADC | Experimental |
_MM_PERM_CADD | Experimental |
_MM_PERM_CBAA | Experimental |
_MM_PERM_CBAB | Experimental |
_MM_PERM_CBAC | Experimental |
_MM_PERM_CBAD | Experimental |
_MM_PERM_CBBA | Experimental |
_MM_PERM_CBBB | Experimental |
_MM_PERM_CBBC | Experimental |
_MM_PERM_CBBD | Experimental |
_MM_PERM_CBCA | Experimental |
_MM_PERM_CBCB | Experimental |
_MM_PERM_CBCC | Experimental |
_MM_PERM_CBCD | Experimental |
_MM_PERM_CBDA | Experimental |
_MM_PERM_CBDB | Experimental |
_MM_PERM_CBDC | Experimental |
_MM_PERM_CBDD | Experimental |
_MM_PERM_CCAA | Experimental |
_MM_PERM_CCAB | Experimental |
_MM_PERM_CCAC | Experimental |
_MM_PERM_CCAD | Experimental |
_MM_PERM_CCBA | Experimental |
_MM_PERM_CCBB | Experimental |
_MM_PERM_CCBC | Experimental |
_MM_PERM_CCBD | Experimental |
_MM_PERM_CCCA | Experimental |
_MM_PERM_CCCB | Experimental |
_MM_PERM_CCCC | Experimental |
_MM_PERM_CCCD | Experimental |
_MM_PERM_CCDA | Experimental |
_MM_PERM_CCDB | Experimental |
_MM_PERM_CCDC | Experimental |
_MM_PERM_CCDD | Experimental |
_MM_PERM_CDAA | Experimental |
_MM_PERM_CDAB | Experimental |
_MM_PERM_CDAC | Experimental |
_MM_PERM_CDAD | Experimental |
_MM_PERM_CDBA | Experimental |
_MM_PERM_CDBB | Experimental |
_MM_PERM_CDBC | Experimental |
_MM_PERM_CDBD | Experimental |
_MM_PERM_CDCA | Experimental |
_MM_PERM_CDCB | Experimental |
_MM_PERM_CDCC | Experimental |
_MM_PERM_CDCD | Experimental |
_MM_PERM_CDDA | Experimental |
_MM_PERM_CDDB | Experimental |
_MM_PERM_CDDC | Experimental |
_MM_PERM_CDDD | Experimental |
_MM_PERM_DAAA | Experimental |
_MM_PERM_DAAB | Experimental |
_MM_PERM_DAAC | Experimental |
_MM_PERM_DAAD | Experimental |
_MM_PERM_DABA | Experimental |
_MM_PERM_DABB | Experimental |
_MM_PERM_DABC | Experimental |
_MM_PERM_DABD | Experimental |
_MM_PERM_DACA | Experimental |
_MM_PERM_DACB | Experimental |
_MM_PERM_DACC | Experimental |
_MM_PERM_DACD | Experimental |
_MM_PERM_DADA | Experimental |
_MM_PERM_DADB | Experimental |
_MM_PERM_DADC | Experimental |
_MM_PERM_DADD | Experimental |
_MM_PERM_DBAA | Experimental |
_MM_PERM_DBAB | Experimental |
_MM_PERM_DBAC | Experimental |
_MM_PERM_DBAD | Experimental |
_MM_PERM_DBBA | Experimental |
_MM_PERM_DBBB | Experimental |
_MM_PERM_DBBC | Experimental |
_MM_PERM_DBBD | Experimental |
_MM_PERM_DBCA | Experimental |
_MM_PERM_DBCB | Experimental |
_MM_PERM_DBCC | Experimental |
_MM_PERM_DBCD | Experimental |
_MM_PERM_DBDA | Experimental |
_MM_PERM_DBDB | Experimental |
_MM_PERM_DBDC | Experimental |
_MM_PERM_DBDD | Experimental |
_MM_PERM_DCAA | Experimental |
_MM_PERM_DCAB | Experimental |
_MM_PERM_DCAC | Experimental |
_MM_PERM_DCAD | Experimental |
_MM_PERM_DCBA | Experimental |
_MM_PERM_DCBB | Experimental |
_MM_PERM_DCBC | Experimental |
_MM_PERM_DCBD | Experimental |
_MM_PERM_DCCA | Experimental |
_MM_PERM_DCCB | Experimental |
_MM_PERM_DCCC | Experimental |
_MM_PERM_DCCD | Experimental |
_MM_PERM_DCDA | Experimental |
_MM_PERM_DCDB | Experimental |
_MM_PERM_DCDC | Experimental |
_MM_PERM_DCDD | Experimental |
_MM_PERM_DDAA | Experimental |
_MM_PERM_DDAB | Experimental |
_MM_PERM_DDAC | Experimental |
_MM_PERM_DDAD | Experimental |
_MM_PERM_DDBA | Experimental |
_MM_PERM_DDBB | Experimental |
_MM_PERM_DDBC | Experimental |
_MM_PERM_DDBD | Experimental |
_MM_PERM_DDCA | Experimental |
_MM_PERM_DDCB | Experimental |
_MM_PERM_DDCC | Experimental |
_MM_PERM_DDCD | Experimental |
_MM_PERM_DDDA | Experimental |
_MM_PERM_DDDB | Experimental |
_MM_PERM_DDDC | Experimental |
_MM_PERM_DDDD | Experimental |
_XABORT_CAPACITY | Experimental Transaction abort due to the transaction using too much memory. |
_XABORT_CONFLICT | Experimental Transaction abort due to a memory conflict with another thread. |
_XABORT_DEBUG | Experimental Transaction abort due to a debug trap. |
_XABORT_EXPLICIT | Experimental Transaction explicitly aborted with xabort. The parameter passed to xabort is available with
|
_XABORT_NESTED | Experimental Transaction abort in a inner nested transaction. |
_XABORT_RETRY | Experimental Transaction retry is possible. |
_XBEGIN_STARTED | Experimental Transaction successfully started. |
_CMP_EQ_OQ | Equal (ordered, non-signaling) |
_CMP_EQ_OS | Equal (ordered, signaling) |
_CMP_EQ_UQ | Equal (unordered, non-signaling) |
_CMP_EQ_US | Equal (unordered, signaling) |
_CMP_FALSE_OQ | False (ordered, non-signaling) |
_CMP_FALSE_OS | False (ordered, signaling) |
_CMP_GE_OQ | Greater-than-or-equal (ordered, non-signaling) |
_CMP_GE_OS | Greater-than-or-equal (ordered, signaling) |
_CMP_GT_OQ | Greater-than (ordered, non-signaling) |
_CMP_GT_OS | Greater-than (ordered, signaling) |
_CMP_LE_OQ | Less-than-or-equal (ordered, non-signaling) |
_CMP_LE_OS | Less-than-or-equal (ordered, signaling) |
_CMP_LT_OQ | Less-than (ordered, non-signaling) |
_CMP_LT_OS | Less-than (ordered, signaling) |
_CMP_NEQ_OQ | Not-equal (ordered, non-signaling) |
_CMP_NEQ_OS | Not-equal (ordered, signaling) |
_CMP_NEQ_UQ | Not-equal (unordered, non-signaling) |
_CMP_NEQ_US | Not-equal (unordered, signaling) |
_CMP_NGE_UQ | Not-greater-than-or-equal (unordered, non-signaling) |
_CMP_NGE_US | Not-greater-than-or-equal (unordered, signaling) |
_CMP_NGT_UQ | Not-greater-than (unordered, non-signaling) |
_CMP_NGT_US | Not-greater-than (unordered, signaling) |
_CMP_NLE_UQ | Not-less-than-or-equal (unordered, non-signaling) |
_CMP_NLE_US | Not-less-than-or-equal (unordered, signaling) |
_CMP_NLT_UQ | Not-less-than (unordered, non-signaling) |
_CMP_NLT_US | Not-less-than (unordered, signaling) |
_CMP_ORD_Q | Ordered (non-signaling) |
_CMP_ORD_S | Ordered (signaling) |
_CMP_TRUE_UQ | True (unordered, non-signaling) |
_CMP_TRUE_US | True (unordered, signaling) |
_CMP_UNORD_Q | Unordered (non-signaling) |
_CMP_UNORD_S | Unordered (signaling) |
_MM_EXCEPT_DENORM | See |
_MM_EXCEPT_DIV_ZERO | See |
_MM_EXCEPT_INEXACT | See |
_MM_EXCEPT_INVALID | See |
_MM_EXCEPT_MASK | |
_MM_EXCEPT_OVERFLOW | See |
_MM_EXCEPT_UNDERFLOW | See |
_MM_FLUSH_ZERO_MASK | |
_MM_FLUSH_ZERO_OFF | See |
_MM_FLUSH_ZERO_ON | See |
_MM_FROUND_CEIL | round up and do not suppress exceptions |
_MM_FROUND_CUR_DIRECTION | use MXCSR.RC; see |
_MM_FROUND_FLOOR | round down and do not suppress exceptions |
_MM_FROUND_NEARBYINT | use MXCSR.RC and suppress exceptions; see |
_MM_FROUND_NINT | round to nearest and do not suppress exceptions |
_MM_FROUND_NO_EXC | suppress exceptions |
_MM_FROUND_RAISE_EXC | do not suppress exceptions |
_MM_FROUND_RINT | use MXCSR.RC and do not suppress exceptions; see
|
_MM_FROUND_TO_NEAREST_INT | round to nearest |
_MM_FROUND_TO_NEG_INF | round down |
_MM_FROUND_TO_POS_INF | round up |
_MM_FROUND_TO_ZERO | truncate |
_MM_FROUND_TRUNC | truncate and do not suppress exceptions |
_MM_HINT_NTA | See |
_MM_HINT_T0 | See |
_MM_HINT_T1 | See |
_MM_HINT_T2 | See |
_MM_MASK_DENORM | See |
_MM_MASK_DIV_ZERO | See |
_MM_MASK_INEXACT | See |
_MM_MASK_INVALID | See |
_MM_MASK_MASK | |
_MM_MASK_OVERFLOW | See |
_MM_MASK_UNDERFLOW | See |
_MM_ROUND_DOWN | See |
_MM_ROUND_MASK | |
_MM_ROUND_NEAREST | See |
_MM_ROUND_TOWARD_ZERO | See |
_MM_ROUND_UP | See |
_SIDD_BIT_MASK | Mask only: return the bit mask |
_SIDD_CMP_EQUAL_ANY | For each character in |
_SIDD_CMP_EQUAL_EACH | The strings defined by |
_SIDD_CMP_EQUAL_ORDERED | Search for the defined substring in the target |
_SIDD_CMP_RANGES | For each character in |
_SIDD_LEAST_SIGNIFICANT | Index only: return the least significant bit (Default) |
_SIDD_MASKED_NEGATIVE_POLARITY | Negates results only before the end of the string |
_SIDD_MASKED_POSITIVE_POLARITY | Do not negate results before the end of the string |
_SIDD_MOST_SIGNIFICANT | Index only: return the most significant bit |
_SIDD_NEGATIVE_POLARITY | Negates results |
_SIDD_POSITIVE_POLARITY | Do not negate results (Default) |
_SIDD_SBYTE_OPS | String contains signed 8-bit characters |
_SIDD_SWORD_OPS | String contains unsigned 16-bit characters |
_SIDD_UBYTE_OPS | String contains unsigned 8-bit characters (Default) |
_SIDD_UNIT_MASK | Mask only: return the byte mask |
_SIDD_UWORD_OPS | String contains unsigned 16-bit characters |
_XCR_XFEATURE_ENABLED_MASK |
|
Functions
_MM_SHUFFLE | Experimental A utility function for creating masks to use with Intel shuffle and permute intrinsics. |
_bittest⚠ | Experimental Returns the bit in position |
_bittest64⚠ | Experimental Returns the bit in position |
_bittestandcomplement⚠ | Experimental Returns the bit in position |
_bittestandcomplement64⚠ | Experimental Returns the bit in position |
_bittestandreset⚠ | Experimental Returns the bit in position |
_bittestandreset64⚠ | Experimental Returns the bit in position |
_bittestandset⚠ | Experimental Returns the bit in position |
_bittestandset64⚠ | Experimental Returns the bit in position |
_kadd_mask32⚠ | Experimentalavx512bw Add 32-bit masks in a and b, and store the result in k. |
_kadd_mask64⚠ | Experimentalavx512bw Add 64-bit masks in a and b, and store the result in k. |
_kand_mask16⚠ | Experimentalavx512f Compute the bitwise AND of 16-bit masks a and b, and store the result in k. |
_kand_mask32⚠ | Experimentalavx512bw Compute the bitwise AND of 32-bit masks a and b, and store the result in k. |
_kand_mask64⚠ | Experimentalavx512bw Compute the bitwise AND of 64-bit masks a and b, and store the result in k. |
_kandn_mask16⚠ | Experimentalavx512f Compute the bitwise NOT of 16-bit masks a and then AND with b, and store the result in k. |
_kandn_mask32⚠ | Experimentalavx512bw Compute the bitwise NOT of 32-bit masks a and then AND with b, and store the result in k. |
_kandn_mask64⚠ | Experimentalavx512bw Compute the bitwise NOT of 64-bit masks a and then AND with b, and store the result in k. |
_knot_mask16⚠ | Experimentalavx512f Compute the bitwise NOT of 16-bit mask a, and store the result in k. |
_knot_mask32⚠ | Experimentalavx512bw Compute the bitwise NOT of 32-bit mask a, and store the result in k. |
_knot_mask64⚠ | Experimentalavx512bw Compute the bitwise NOT of 64-bit mask a, and store the result in k. |
_kor_mask16⚠ | Experimentalavx512f Compute the bitwise OR of 16-bit masks a and b, and store the result in k. |
_kor_mask32⚠ | Experimentalavx512bw Compute the bitwise OR of 32-bit masks a and b, and store the result in k. |
_kor_mask64⚠ | Experimentalavx512bw Compute the bitwise OR of 64-bit masks a and b, and store the result in k. |
_kxnor_mask16⚠ | Experimentalavx512f Compute the bitwise XNOR of 16-bit masks a and b, and store the result in k. |
_kxnor_mask32⚠ | Experimentalavx512bw Compute the bitwise XNOR of 32-bit masks a and b, and store the result in k. |
_kxnor_mask64⚠ | Experimentalavx512bw Compute the bitwise XNOR of 64-bit masks a and b, and store the result in k. |
_kxor_mask16⚠ | Experimentalavx512f Compute the bitwise XOR of 16-bit masks a and b, and store the result in k. |
_kxor_mask32⚠ | Experimentalavx512bw Compute the bitwise XOR of 32-bit masks a and b, and store the result in k. |
_kxor_mask64⚠ | Experimentalavx512bw Compute the bitwise XOR of 64-bit masks a and b, and store the result in k. |
_load_mask32⚠ | Experimentalavx512bw Load 32-bit mask from memory into k. |
_load_mask64⚠ | Experimentalavx512bw Load 64-bit mask from memory into k. |
_mm256_aesdec_epi128⚠ | Experimentalavx512vaes,avx512vl Performs one round of an AES decryption flow on each 128-bit word (state) in |
_mm256_aesdeclast_epi128⚠ | Experimentalavx512vaes,avx512vl Performs the last round of an AES decryption flow on each 128-bit word (state) in |
_mm256_aesenc_epi128⚠ | Experimentalavx512vaes,avx512vl Performs one round of an AES encryption flow on each 128-bit word (state) in |
_mm256_aesenclast_epi128⚠ | Experimentalavx512vaes,avx512vl Performs the last round of an AES encryption flow on each 128-bit word (state) in |
_mm256_bitshuffle_epi64_mask⚠ | Experimentalavx512bitalg,avx512vl Considers the input |
_mm256_broadcastmb_epi64⚠ | Experimentalavx512cd,avx512vl Broadcast the low 8-bits from input mask k to all 64-bit elements of dst. |
_mm256_broadcastmw_epi32⚠ | Experimentalavx512cd,avx512vl Broadcast the low 16-bits from input mask k to all 32-bit elements of dst. |
_mm256_clmulepi64_epi128⚠ | Experimentalavx512vpclmulqdq,avx512vl Performs a carry-less multiplication of two 64-bit polynomials over the finite field GF(2^k) - in each of the 2 128-bit lanes. |
_mm256_conflict_epi32⚠ | Experimentalavx512cd,avx512vl Test each 32-bit element of a for equality with all other elements in a closer to the least significant bit. Each element’s comparison forms a zero extended bit vector in dst. |
_mm256_conflict_epi64⚠ | Experimentalavx512cd,avx512vl Test each 64-bit element of a for equality with all other elements in a closer to the least significant bit. Each element’s comparison forms a zero extended bit vector in dst. |
_mm256_cvtph_ps⚠ | Experimentalf16c Converts the 8 x 16-bit half-precision float values in the 128-bit vector
|
_mm256_cvtps_ph⚠ | Experimentalf16c Converts the 8 x 32-bit float values in the 256-bit vector |
_mm256_gf2p8affine_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs an affine transformation on the packed bytes in x. That is computes a*x+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm256_gf2p8affineinv_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs an affine transformation on the inverted packed bytes in x. That is computes a*inv(x)+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. The inverse of a byte is defined with respect to the reduction polynomial x^8+x^4+x^3+x+1. The inverse of 0 is 0. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm256_gf2p8mul_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs a multiplication in GF(2^8) on the packed bytes. The field is in polynomial representation with the reduction polynomial x^8 + x^4 + x^3 + x + 1. |
_mm256_lzcnt_epi32⚠ | Experimentalavx512cd,avx512vl Counts the number of leading zero bits in each packed 32-bit integer in a, and store the results in dst. |
_mm256_lzcnt_epi64⚠ | Experimentalavx512cd,avx512vl Counts the number of leading zero bits in each packed 64-bit integer in a, and store the results in dst. |
_mm256_madd52hi_epu64⚠ | Experimentalavx512ifma,avx512vl Multiply packed unsigned 52-bit integers in each 64-bit element of
|
_mm256_madd52lo_epu64⚠ | Experimentalavx512ifma,avx512vl Multiply packed unsigned 52-bit integers in each 64-bit element of
|
_mm256_mask2_permutex2var_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_avg_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_bitshuffle_epi64_mask⚠ | Experimentalavx512bitalg,avx512vl Considers the input |
_mm256_mask_blend_epi8⚠ | Experimentalavx512bw,avx512vl Blend packed 8-bit integers from a and b using control mask k, and store the results in dst. |
_mm256_mask_blend_epi16⚠ | Experimentalavx512bw,avx512vl Blend packed 16-bit integers from a and b using control mask k, and store the results in dst. |
_mm256_mask_broadcastb_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_conflict_epi32⚠ | Experimentalavx512cd,avx512vl Test each 32-bit element of a for equality with all other elements in a closer to the least significant bit using writemask k (elements are copied from src when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm256_mask_conflict_epi64⚠ | Experimentalavx512cd,avx512vl Test each 64-bit element of a for equality with all other elements in a closer to the least significant bit using writemask k (elements are copied from src when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm256_mask_gf2p8affine_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs an affine transformation on the packed bytes in x. That is computes a*x+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm256_mask_gf2p8affineinv_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs an affine transformation on the inverted packed bytes in x. That is computes a*inv(x)+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. The inverse of a byte is defined with respect to the reduction polynomial x^8+x^4+x^3+x+1. The inverse of 0 is 0. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm256_mask_gf2p8mul_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs a multiplication in GF(2^8) on the packed bytes. The field is in polynomial representation with the reduction polynomial x^8 + x^4 + x^3 + x + 1. |
_mm256_mask_lzcnt_epi32⚠ | Experimentalavx512cd,avx512vl Counts the number of leading zero bits in each packed 32-bit integer 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_lzcnt_epi64⚠ | Experimentalavx512cd,avx512vl Counts the number of leading zero bits in each packed 64-bit integer 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_madd_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi32⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi32⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_popcnt_epi8⚠ | Experimentalavx512bitalg,avx512vl For each packed 8-bit integer maps the value to the number of logical 1 bits. |
_mm256_mask_popcnt_epi16⚠ | Experimentalavx512bitalg,avx512vl For each packed 16-bit integer maps the value to the number of logical 1 bits. |
_mm256_mask_popcnt_epi32⚠ | Experimentalavx512vpopcntdq,avx512vl For each packed 32-bit integer maps the value to the number of logical 1 bits. |
_mm256_mask_popcnt_epi64⚠ | Experimentalavx512vpopcntdq,avx512vl For each packed 64-bit integer maps the value to the number of logical 1 bits. |
_mm256_mask_set1_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_sll_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_sub_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_unpackhi_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_avg_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_conflict_epi32⚠ | Experimentalavx512cd,avx512vl Test each 32-bit element of a for equality with all other elements in a closer to the least significant bit using zeromask k (elements are zeroed out when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm256_maskz_conflict_epi64⚠ | Experimentalavx512cd,avx512vl Test each 64-bit element of a for equality with all other elements in a closer to the least significant bit using zeromask k (elements are zeroed out when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm256_maskz_gf2p8affine_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs an affine transformation on the packed bytes in x. That is computes a*x+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm256_maskz_gf2p8affineinv_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs an affine transformation on the inverted packed bytes in x. That is computes a*inv(x)+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. The inverse of a byte is defined with respect to the reduction polynomial x^8+x^4+x^3+x+1. The inverse of 0 is 0. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm256_maskz_gf2p8mul_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512vl Performs a multiplication in GF(2^8) on the packed bytes. The field is in polynomial representation with the reduction polynomial x^8 + x^4 + x^3 + x + 1. |
_mm256_maskz_lzcnt_epi32⚠ | Experimentalavx512cd,avx512vl Counts the number of leading zero bits in each packed 32-bit integer 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_lzcnt_epi64⚠ | Experimentalavx512cd,avx512vl Counts the number of leading zero bits in each packed 64-bit integer 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_madd_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi32⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi32⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_popcnt_epi8⚠ | Experimentalavx512bitalg,avx512vl For each packed 8-bit integer maps the value to the number of logical 1 bits. |
_mm256_maskz_popcnt_epi16⚠ | Experimentalavx512bitalg,avx512vl For each packed 16-bit integer maps the value to the number of logical 1 bits. |
_mm256_maskz_popcnt_epi32⚠ | Experimentalavx512vpopcntdq,avx512vl For each packed 32-bit integer maps the value to the number of logical 1 bits. |
_mm256_maskz_popcnt_epi64⚠ | Experimentalavx512vpopcntdq,avx512vl For each packed 64-bit integer maps the value to the number of logical 1 bits. |
_mm256_maskz_set1_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_sll_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epu8⚠ | Experimentalavx512bw,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_epu16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi8⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_permutex2var_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,avx512vl Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst. |
_mm256_popcnt_epi8⚠ | Experimentalavx512bitalg,avx512vl For each packed 8-bit integer maps the value to the number of logical 1 bits. |
_mm256_popcnt_epi16⚠ | Experimentalavx512bitalg,avx512vl For each packed 16-bit integer maps the value to the number of logical 1 bits. |
_mm256_popcnt_epi32⚠ | Experimentalavx512vpopcntdq,avx512vl For each packed 32-bit integer maps the value to the number of logical 1 bits. |
_mm256_popcnt_epi64⚠ | Experimentalavx512vpopcntdq,avx512vl For each packed 64-bit integer maps the value to the number of logical 1 bits. |
_mm256_sllv_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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_epi16⚠ | Experimentalavx512bw,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. |
_mm512_abs_epi8⚠ | Experimentalavx512bw Compute the absolute value of packed signed 8-bit integers in a, and store the unsigned results in dst. |
_mm512_abs_epi16⚠ | Experimentalavx512bw Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in dst. |
_mm512_abs_epi32⚠ | Experimentalavx512f Computes the absolute values of packed 32-bit integers in |
_mm512_abs_epi64⚠ | Experimentalavx512f Compute the absolute value of packed signed 64-bit integers in a, and store the unsigned results in dst. |
_mm512_abs_pd⚠ | Experimentalavx512f Finds the absolute value of each packed double-precision (64-bit) floating-point element in v2, storing the results in dst. |
_mm512_abs_ps⚠ | Experimentalavx512f Finds the absolute value of each packed single-precision (32-bit) floating-point element in v2, storing the results in dst. |
_mm512_add_epi8⚠ | Experimentalavx512bw Add packed 8-bit integers in a and b, and store the results in dst. |
_mm512_add_epi16⚠ | Experimentalavx512bw Add packed 16-bit integers in a and b, and store the results in dst. |
_mm512_add_epi32⚠ | Experimentalavx512f Add packed 32-bit integers in a and b, and store the results in dst. |
_mm512_add_epi64⚠ | Experimentalavx512f Add packed 64-bit integers in a and b, and store the results in dst. |
_mm512_add_pd⚠ | Experimentalavx512f Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_add_ps⚠ | Experimentalavx512f Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_add_round_pd⚠ | Experimentalavx512f Add packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_add_round_ps⚠ | Experimentalavx512f Add packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_adds_epi8⚠ | Experimentalavx512bw Add packed signed 8-bit integers in a and b using saturation, and store the results in dst. |
_mm512_adds_epi16⚠ | Experimentalavx512bw Add packed signed 16-bit integers in a and b using saturation, and store the results in dst. |
_mm512_adds_epu8⚠ | Experimentalavx512bw Add packed unsigned 8-bit integers in a and b using saturation, and store the results in dst. |
_mm512_adds_epu16⚠ | Experimentalavx512bw Add packed unsigned 16-bit integers in a and b using saturation, and store the results in dst. |
_mm512_aesdec_epi128⚠ | Experimentalavx512vaes,avx512f Performs one round of an AES decryption flow on each 128-bit word (state) in |
_mm512_aesdeclast_epi128⚠ | Experimentalavx512vaes,avx512f Performs the last round of an AES decryption flow on each 128-bit word (state) in |
_mm512_aesenc_epi128⚠ | Experimentalavx512vaes,avx512f Performs one round of an AES encryption flow on each 128-bit word (state) in |
_mm512_aesenclast_epi128⚠ | Experimentalavx512vaes,avx512f Performs the last round of an AES encryption flow on each 128-bit word (state) in |
_mm512_alignr_epi8⚠ | Experimentalavx512bw 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_alignr_epi32⚠ | Experimentalavx512f Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 64 bytes (16 elements) in dst. |
_mm512_alignr_epi64⚠ | Experimentalavx512f Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 64 bytes (8 elements) in dst. |
_mm512_and_epi32⚠ | Experimentalavx512f Compute the bitwise AND of packed 32-bit integers in a and b, and store the results in dst. |
_mm512_and_epi64⚠ | Experimentalavx512f Compute the bitwise AND of 512 bits (composed of packed 64-bit integers) in a and b, and store the results in dst. |
_mm512_and_si512⚠ | Experimentalavx512f Compute the bitwise AND of 512 bits (representing integer data) in a and b, and store the result in dst. |
_mm512_andnot_epi32⚠ | Experimentalavx512f Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst. |
_mm512_andnot_epi64⚠ | Experimentalavx512f Compute the bitwise NOT of 512 bits (composed of packed 64-bit integers) in a and then AND with b, and store the results in dst. |
_mm512_andnot_si512⚠ | Experimentalavx512f Compute the bitwise NOT of 512 bits (representing integer data) in a and then AND with b, and store the result in dst. |
_mm512_avg_epu8⚠ | Experimentalavx512bw Average packed unsigned 8-bit integers in a and b, and store the results in dst. |
_mm512_avg_epu16⚠ | Experimentalavx512bw Average packed unsigned 16-bit integers in a and b, and store the results in dst. |
_mm512_bitshuffle_epi64_mask⚠ | Experimentalavx512bitalg Considers the input |
_mm512_broadcast_f32x4⚠ | Experimentalavx512f Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst. |
_mm512_broadcast_f64x4⚠ | Experimentalavx512f Broadcast the 4 packed double-precision (64-bit) floating-point elements from a to all elements of dst. |
_mm512_broadcast_i32x4⚠ | Experimentalavx512f Broadcast the 4 packed 32-bit integers from a to all elements of dst. |
_mm512_broadcast_i64x4⚠ | Experimentalavx512f Broadcast the 4 packed 64-bit integers from a to all elements of dst. |
_mm512_broadcastb_epi8⚠ | Experimentalavx512bw Broadcast the low packed 8-bit integer from a to all elements of dst. |
_mm512_broadcastd_epi32⚠ | Experimentalavx512f Broadcast the low packed 32-bit integer from a to all elements of dst. |
_mm512_broadcastmb_epi64⚠ | Experimentalavx512cd Broadcast the low 8-bits from input mask k to all 64-bit elements of dst. |
_mm512_broadcastmw_epi32⚠ | Experimentalavx512cd Broadcast the low 16-bits from input mask k to all 32-bit elements of dst. |
_mm512_broadcastq_epi64⚠ | Experimentalavx512f Broadcast the low packed 64-bit integer from a to all elements of dst. |
_mm512_broadcastsd_pd⚠ | Experimentalavx512f Broadcast the low double-precision (64-bit) floating-point element from a to all elements of dst. |
_mm512_broadcastss_ps⚠ | Experimentalavx512f Broadcast the low single-precision (32-bit) floating-point element from a to all elements of dst. |
_mm512_broadcastw_epi16⚠ | Experimentalavx512bw Broadcast the low packed 16-bit integer from a to all elements of dst. |
_mm512_bslli_epi128⚠ | Experimentalavx512bw Shift 128-bit lanes in a left by imm8 bytes while shifting in zeros, and store the results in dst. |
_mm512_bsrli_epi128⚠ | Experimentalavx512bw Shift 128-bit lanes in a right by imm8 bytes while shifting in zeros, and store the results in dst. |
_mm512_castpd128_pd512⚠ | Experimentalavx512f Cast vector of type __m128d to type __m512d; the upper 384 bits of the result are undefined. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castpd256_pd512⚠ | Experimentalavx512f Cast vector of type __m256d to type __m512d; the upper 256 bits of the result are undefined. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castpd512_pd128⚠ | Experimentalavx512f Cast vector of type __m512d to type __m128d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castpd512_pd256⚠ | Experimentalavx512f Cast vector of type __m512d to type __m256d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castpd_ps⚠ | Experimentalavx512f Cast vector of type __m512d to type __m512. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castpd_si512⚠ | Experimentalavx512f Cast vector of type __m512d to type __m512i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castps128_ps512⚠ | Experimentalavx512f Cast vector of type __m128 to type __m512; the upper 384 bits of the result are undefined. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castps256_ps512⚠ | Experimentalavx512f Cast vector of type __m256 to type __m512; the upper 256 bits of the result are undefined. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castps512_ps128⚠ | Experimentalavx512f Cast vector of type __m512 to type __m128. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castps512_ps256⚠ | Experimentalavx512f Cast vector of type __m512 to type __m256. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castps_pd⚠ | Experimentalavx512f Cast vector of type __m512 to type __m512d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castps_si512⚠ | Experimentalavx512f Cast vector of type __m512 to type __m512i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castsi128_si512⚠ | Experimentalavx512f Cast vector of type __m128i to type __m512i; the upper 384 bits of the result are undefined. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castsi256_si512⚠ | Experimentalavx512f Cast vector of type __m256i to type __m512i; the upper 256 bits of the result are undefined. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castsi512_pd⚠ | Experimentalavx512f Cast vector of type __m512i to type __m512d. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castsi512_ps⚠ | Experimentalavx512f Cast vector of type __m512i to type __m512. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castsi512_si128⚠ | Experimentalavx512f Cast vector of type __m512i to type __m128i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_castsi512_si256⚠ | Experimentalavx512f Cast vector of type __m512i to type __m256i. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency. |
_mm512_clmulepi64_epi128⚠ | Experimentalavx512vpclmulqdq,avx512f Performs a carry-less multiplication of two 64-bit polynomials over the finite field GF(2^k) - in each of the 4 128-bit lanes. |
_mm512_cmp_epi8_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k. |
_mm512_cmp_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmp_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k. |
_mm512_cmp_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by imm8, and store the results in mask vector k. |
_mm512_cmp_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k. |
_mm512_cmp_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k. |
_mm512_cmp_round_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k. |
_mm512_cmp_round_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8, and store the results in mask vector k. |
_mm512_cmpeq_epi8_mask⚠ | Experimentalavx512bw Compare packed signed 8-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_epi16_mask⚠ | Experimentalavx512bw Compare packed signed 16-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_epi32_mask⚠ | Experimentalavx512f Compare packed 32-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_epi64_mask⚠ | Experimentalavx512f Compare packed 64-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_epu8_mask⚠ | Experimentalavx512bw Compare packed unsigned 8-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_epu16_mask⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for equality, and store the results in mask vector k. |
_mm512_cmpeq_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for equality, and store the results in mask vector k. |
_mm512_cmpge_epi8_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k. |
_mm512_cmpge_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k. |
_mm512_cmpge_epu8_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k. |
_mm512_cmpge_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k. |
_mm512_cmpge_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for greater-than-or-equal, and store the results in mask vector k. |
_mm512_cmpgt_epi8_mask⚠ | Experimentalavx512bw Compare packed signed 8-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmpgt_epi16_mask⚠ | Experimentalavx512bw Compare packed signed 16-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmpgt_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmpgt_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmpgt_epu8_mask⚠ | Experimentalavx512bw Compare packed unsigned 8-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmpgt_epu16_mask⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmpgt_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmpgt_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in mask vector k. |
_mm512_cmple_epi8_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k. |
_mm512_cmple_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k. |
_mm512_cmple_epu8_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b for less-than-or-equal, and store the results in mask vector k. |
_mm512_cmple_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for less-than-or-equal, and store the results in mask vector k. |
_mm512_cmple_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for less-than-or-equal, and store the results in mask vector k. |
_mm512_cmple_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for less-than-or-equal, and store the results in mask vector k. |
_mm512_cmple_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for less-than-or-equal, and store the results in mask vector k. |
_mm512_cmplt_epi8_mask⚠ | Experimentalavx512bw Compare packed signed 8-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_epi16_mask⚠ | Experimentalavx512bw Compare packed signed 16-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_epu8_mask⚠ | Experimentalavx512bw Compare packed unsigned 8-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_epu16_mask⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for less-than, and store the results in mask vector k. |
_mm512_cmplt_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for less-than, and store the results in mask vector k. |
_mm512_cmpneq_epi8_mask⚠ | Experimentalavx512bw Compare packed signed 8-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_epi16_mask⚠ | Experimentalavx512bw Compare packed signed 16-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_epi32_mask⚠ | Experimentalavx512f Compare packed 32-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_epu8_mask⚠ | Experimentalavx512bw Compare packed unsigned 8-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_epu16_mask⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpneq_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for not-equal, and store the results in mask vector k. |
_mm512_cmpnle_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for not-less-than-or-equal, and store the results in mask vector k. |
_mm512_cmpnle_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for not-less-than-or-equal, and store the results in mask vector k. |
_mm512_cmpnlt_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for not-less-than, and store the results in mask vector k. |
_mm512_cmpnlt_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for not-less-than, and store the results in mask vector k. |
_mm512_cmpord_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b to see if neither is NaN, and store the results in mask vector k. |
_mm512_cmpord_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b to see if neither is NaN, and store the results in mask vector k. |
_mm512_cmpunord_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b to see if either is NaN, and store the results in mask vector k. |
_mm512_cmpunord_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b to see if either is NaN, and store the results in mask vector k. |
_mm512_conflict_epi32⚠ | Experimentalavx512cd Test each 32-bit element of a for equality with all other elements in a closer to the least significant bit. Each element’s comparison forms a zero extended bit vector in dst. |
_mm512_conflict_epi64⚠ | Experimentalavx512cd Test each 64-bit element of a for equality with all other elements in a closer to the least significant bit. Each element’s comparison forms a zero extended bit vector in dst. |
_mm512_cvt_roundepi32_ps⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvt_roundepu32_ps⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvt_roundpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst. |
_mm512_cvt_roundpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst. |
_mm512_cvt_roundpd_ps⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvt_roundph_ps⚠ | Experimentalavx512f Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvt_roundps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst. |
_mm512_cvt_roundps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst. |
_mm512_cvt_roundps_pd⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst. |
_mm512_cvt_roundps_ph⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst. |
_mm512_cvtepi8_epi16⚠ | Experimentalavx512bw Sign extend packed 8-bit integers in a to packed 16-bit integers, and store the results in dst. |
_mm512_cvtepi8_epi32⚠ | Experimentalavx512f Sign extend packed 8-bit integers in a to packed 32-bit integers, and store the results in dst. |
_mm512_cvtepi8_epi64⚠ | Experimentalavx512f Sign extend packed 8-bit integers in the low 8 bytes of a to packed 64-bit integers, and store the results in dst. |
_mm512_cvtepi16_epi8⚠ | Experimentalavx512bw Convert packed 16-bit integers in a to packed 8-bit integers with truncation, and store the results in dst. |
_mm512_cvtepi16_epi32⚠ | Experimentalavx512f Sign extend packed 16-bit integers in a to packed 32-bit integers, and store the results in dst. |
_mm512_cvtepi16_epi64⚠ | Experimentalavx512f Sign extend packed 16-bit integers in a to packed 64-bit integers, and store the results in dst. |
_mm512_cvtepi32_epi8⚠ | Experimentalavx512f Convert packed 32-bit integers in a to packed 8-bit integers with truncation, and store the results in dst. |
_mm512_cvtepi32_epi16⚠ | Experimentalavx512f Convert packed 32-bit integers in a to packed 16-bit integers with truncation, and store the results in dst. |
_mm512_cvtepi32_epi64⚠ | Experimentalavx512f Sign extend packed 32-bit integers in a to packed 64-bit integers, and store the results in dst. |
_mm512_cvtepi32_pd⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst. |
_mm512_cvtepi32_ps⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvtepi32lo_pd⚠ | Experimentalavx512f Performs element-by-element conversion of the lower half of packed 32-bit integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst. |
_mm512_cvtepi64_epi8⚠ | Experimentalavx512f Convert packed 64-bit integers in a to packed 8-bit integers with truncation, and store the results in dst. |
_mm512_cvtepi64_epi16⚠ | Experimentalavx512f Convert packed 64-bit integers in a to packed 16-bit integers with truncation, and store the results in dst. |
_mm512_cvtepi64_epi32⚠ | Experimentalavx512f Convert packed 64-bit integers in a to packed 32-bit integers with truncation, and store the results in dst. |
_mm512_cvtepu8_epi16⚠ | Experimentalavx512bw Zero extend packed unsigned 8-bit integers in a to packed 16-bit integers, and store the results in dst. |
_mm512_cvtepu8_epi32⚠ | Experimentalavx512f Zero extend packed unsigned 8-bit integers in a to packed 32-bit integers, and store the results in dst. |
_mm512_cvtepu8_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 8-bit integers in the low 8 byte sof a to packed 64-bit integers, and store the results in dst. |
_mm512_cvtepu16_epi32⚠ | Experimentalavx512f Zero extend packed unsigned 16-bit integers in a to packed 32-bit integers, and store the results in dst. |
_mm512_cvtepu16_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 16-bit integers in a to packed 64-bit integers, and store the results in dst. |
_mm512_cvtepu32_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 32-bit integers in a to packed 64-bit integers, and store the results in dst. |
_mm512_cvtepu32_pd⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst. |
_mm512_cvtepu32_ps⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvtepu32lo_pd⚠ | Experimentalavx512f Performs element-by-element conversion of the lower half of packed 32-bit unsigned integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst. |
_mm512_cvtpd_ps⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvtpd_pslo⚠ | Experimentalavx512f Performs an element-by-element conversion of packed double-precision (64-bit) floating-point elements in v2 to single-precision (32-bit) floating-point elements and stores them in dst. The elements are stored in the lower half of the results vector, while the remaining upper half locations are set to 0. |
_mm512_cvtph_ps⚠ | Experimentalavx512f Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst. |
_mm512_cvtps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers, and store the results in dst. |
_mm512_cvtps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers, and store the results in dst. |
_mm512_cvtps_pd⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst. |
_mm512_cvtps_ph⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst. |
_mm512_cvtpslo_pd⚠ | Experimentalavx512f Performs element-by-element conversion of the lower half of packed single-precision (32-bit) floating-point elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst. |
_mm512_cvtsepi16_epi8⚠ | Experimentalavx512bw Convert packed signed 16-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst. |
_mm512_cvtsepi32_epi8⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst. |
_mm512_cvtsepi32_epi16⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst. |
_mm512_cvtsepi64_epi8⚠ | Experimentalavx512f Convert packed signed 64-bit integers in a to packed 8-bit integers with signed saturation, and store the results in dst. |
_mm512_cvtsepi64_epi16⚠ | Experimentalavx512f Convert packed signed 64-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst. |
_mm512_cvtsepi64_epi32⚠ | Experimentalavx512f Convert packed signed 64-bit integers in a to packed 32-bit integers with signed saturation, and store the results in dst. |
_mm512_cvtt_roundpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst. |
_mm512_cvtt_roundpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst. |
_mm512_cvtt_roundps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst. |
_mm512_cvtt_roundps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst. |
_mm512_cvttpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst. |
_mm512_cvttpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst. |
_mm512_cvttps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation, and store the results in dst. |
_mm512_cvttps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-bit integers with truncation, and store the results in dst. |
_mm512_cvtusepi16_epi8⚠ | Experimentalavx512bw Convert packed unsigned 16-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst. |
_mm512_cvtusepi32_epi8⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst. |
_mm512_cvtusepi32_epi16⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst. |
_mm512_cvtusepi64_epi8⚠ | Experimentalavx512f Convert packed unsigned 64-bit integers in a to packed unsigned 8-bit integers with unsigned saturation, and store the results in dst. |
_mm512_cvtusepi64_epi16⚠ | Experimentalavx512f Convert packed unsigned 64-bit integers in a to packed unsigned 16-bit integers with unsigned saturation, and store the results in dst. |
_mm512_cvtusepi64_epi32⚠ | Experimentalavx512f Convert packed unsigned 64-bit integers in a to packed unsigned 32-bit integers with unsigned saturation, and store the results in dst. |
_mm512_dbsad_epu8⚠ | Experimentalavx512bw 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_div_pd⚠ | Experimentalavx512f Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst. |
_mm512_div_ps⚠ | Experimentalavx512f Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst. |
_mm512_div_round_pd⚠ | Experimentalavx512f Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, =and store the results in dst. |
_mm512_div_round_ps⚠ | Experimentalavx512f Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst. |
_mm512_extractf32x4_ps⚠ | Experimentalavx512f Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the result in dst. |
_mm512_extractf64x4_pd⚠ | Experimentalavx512f Extract 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a, selected with imm8, and store the result in dst. |
_mm512_extracti32x4_epi32⚠ | Experimentalavx512f Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with imm8, and store the result in dst. |
_mm512_extracti64x4_epi64⚠ | Experimentalavx512f Extract 256 bits (composed of 4 packed 64-bit integers) from a, selected with imm8, and store the result in dst. |
_mm512_fixupimm_pd⚠ | Experimentalavx512f Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting. |
_mm512_fixupimm_ps⚠ | Experimentalavx512f Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting. |
_mm512_fixupimm_round_pd⚠ | Experimentalavx512f Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting. |
_mm512_fixupimm_round_ps⚠ | Experimentalavx512f Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst. imm8 is used to set the required flags reporting. |
_mm512_fmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst. |
_mm512_fmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst. |
_mm512_fmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst. |
_mm512_fmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst. |
_mm512_fmaddsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst. |
_mm512_fmaddsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst. |
_mm512_fmaddsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst. |
_mm512_fmaddsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst. |
_mm512_fmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst. |
_mm512_fmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst. |
_mm512_fmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst. |
_mm512_fmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst. |
_mm512_fmsubadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst. |
_mm512_fmsubadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst. |
_mm512_fmsubadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst. |
_mm512_fmsubadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst. |
_mm512_fnmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst. |
_mm512_fnmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst. |
_mm512_fnmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst. |
_mm512_fnmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst. |
_mm512_fnmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst. |
_mm512_fnmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst. |
_mm512_fnmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst. |
_mm512_fnmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst. |
_mm512_getexp_pd⚠ | Experimentalavx512f Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_getexp_ps⚠ | Experimentalavx512f Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_getexp_round_pd⚠ | Experimentalavx512f Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_getexp_round_ps⚠ | Experimentalavx512f Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst. This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_getmant_pd⚠ | Experimentalavx512f Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_getmant_ps⚠ | Experimentalavx512f Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. The mantissa is normalized to the interval specified by interv, which can take the following values: _MM_MANT_NORM_1_2 // interval [1, 2) _MM_MANT_NORM_p5_2 // interval [0.5, 2) _MM_MANT_NORM_p5_1 // interval [0.5, 1) _MM_MANT_NORM_p75_1p5 // interval [0.75, 1.5) The sign is determined by sc which can take the following values: _MM_MANT_SIGN_src // sign = sign(src) _MM_MANT_SIGN_zero // sign = 0 _MM_MANT_SIGN_nan // dst = NaN if sign(src) = 1 |
_mm512_getmant_round_pd⚠ | Experimentalavx512f Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_getmant_round_ps⚠ | Experimentalavx512f Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_gf2p8affine_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs an affine transformation on the packed bytes in x. That is computes a*x+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm512_gf2p8affineinv_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs an affine transformation on the inverted packed bytes in x. That is computes a*inv(x)+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. The inverse of a byte is defined with respect to the reduction polynomial x^8+x^4+x^3+x+1. The inverse of 0 is 0. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm512_gf2p8mul_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs a multiplication in GF(2^8) on the packed bytes. The field is in polynomial representation with the reduction polynomial x^8 + x^4 + x^3 + x + 1. |
_mm512_i32gather_epi32⚠ | Experimentalavx512f Gather 32-bit integers from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i32gather_epi64⚠ | Experimentalavx512f Gather 64-bit integers from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i32gather_pd⚠ | Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i32gather_ps⚠ | Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i32scatter_epi32⚠ | Experimentalavx512f Scatter 32-bit integers from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8. |
_mm512_i32scatter_epi64⚠ | Experimentalavx512f Scatter 64-bit integers from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8. |
_mm512_i32scatter_pd⚠ | Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8. |
_mm512_i32scatter_ps⚠ | Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8. |
_mm512_i64gather_epi32⚠ | Experimentalavx512f Gather 32-bit integers from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i64gather_epi64⚠ | Experimentalavx512f Gather 64-bit integers from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i64gather_pd⚠ | Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i64gather_ps⚠ | Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst. scale should be 1, 2, 4 or 8. |
_mm512_i64scatter_epi32⚠ | Experimentalavx512f Scatter 32-bit integers from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8. |
_mm512_i64scatter_epi64⚠ | Experimentalavx512f Scatter 64-bit integers from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8. |
_mm512_i64scatter_pd⚠ | Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). scale should be 1, 2, 4 or 8. |
_mm512_i64scatter_ps⚠ | Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_insertf32x4⚠ | Experimentalavx512f Copy a to dst, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into dst at the location specified by imm8. |
_mm512_insertf64x4⚠ | Experimentalavx512f Copy a to dst, then insert 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from b into dst at the location specified by imm8. |
_mm512_inserti32x4⚠ | Experimentalavx512f Copy a to dst, then insert 128 bits (composed of 4 packed 32-bit integers) from b into dst at the location specified by imm8. |
_mm512_inserti64x4⚠ | Experimentalavx512f Copy a to dst, then insert 256 bits (composed of 4 packed 64-bit integers) from b into dst at the location specified by imm8. |
_mm512_int2mask⚠ | Experimentalavx512f Converts integer mask into bitmask, storing the result in dst. |
_mm512_kand⚠ | Experimentalavx512f Compute the bitwise AND of 16-bit masks a and b, and store the result in k. |
_mm512_kandn⚠ | Experimentalavx512f Compute the bitwise NOT of 16-bit masks a and then AND with b, and store the result in k. |
_mm512_kmov⚠ | Experimentalavx512f Copy 16-bit mask a to k. |
_mm512_knot⚠ | Experimentalavx512f Compute the bitwise NOT of 16-bit mask a, and store the result in k. |
_mm512_kor⚠ | Experimentalavx512f Compute the bitwise OR of 16-bit masks a and b, and store the result in k. |
_mm512_kortestc⚠ | Experimentalavx512f Performs bitwise OR between k1 and k2, storing the result in dst. CF flag is set if dst consists of all 1’s. |
_mm512_kunpackb⚠ | Experimentalavx512f Unpack and interleave 8 bits from masks a and b, and store the 16-bit result in k. |
_mm512_kxnor⚠ | Experimentalavx512f Compute the bitwise XNOR of 16-bit masks a and b, and store the result in k. |
_mm512_kxor⚠ | Experimentalavx512f Compute the bitwise XOR of 16-bit masks a and b, and store the result in k. |
_mm512_load_epi32⚠ | Experimentalavx512f Load 512-bits (composed of 16 packed 32-bit integers) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated. |
_mm512_load_epi64⚠ | Experimentalavx512f Load 512-bits (composed of 8 packed 64-bit integers) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated. |
_mm512_load_pd⚠ | Experimentalavx512f Load 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated. |
_mm512_load_ps⚠ | Experimentalavx512f Load 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated. |
_mm512_load_si512⚠ | Experimentalavx512f Load 512-bits of integer data from memory into dst. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated. |
_mm512_loadu_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_loadu_epi32⚠ | Experimentalavx512f Load 512-bits (composed of 16 packed 32-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary. |
_mm512_loadu_epi64⚠ | Experimentalavx512f Load 512-bits (composed of 8 packed 64-bit integers) from memory into dst. mem_addr does not need to be aligned on any particular boundary. |
_mm512_loadu_pd⚠ | Experimentalavx512f Loads 512-bits (composed of 8 packed double-precision (64-bit)
floating-point elements) from memory into result.
|
_mm512_loadu_ps⚠ | Experimentalavx512f Loads 512-bits (composed of 16 packed single-precision (32-bit)
floating-point elements) from memory into result.
|
_mm512_loadu_si512⚠ | Experimentalavx512f Load 512-bits of integer data from memory into dst. mem_addr does not need to be aligned on any particular boundary. |
_mm512_lzcnt_epi32⚠ | Experimentalavx512cd Counts the number of leading zero bits in each packed 32-bit integer in a, and store the results in dst. |
_mm512_lzcnt_epi64⚠ | Experimentalavx512cd Counts the number of leading zero bits in each packed 64-bit integer in a, and store the results in dst. |
_mm512_madd52hi_epu64⚠ | Experimentalavx512ifma Multiply packed unsigned 52-bit integers in each 64-bit element of
|
_mm512_madd52lo_epu64⚠ | Experimentalavx512ifma Multiply packed unsigned 52-bit integers in each 64-bit element of
|
_mm512_madd_epi16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mask2_permutex2var_epi32⚠ | Experimentalavx512f Shuffle 32-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_mask2_permutex2var_epi64⚠ | Experimentalavx512f Shuffle 64-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_mask2_permutex2var_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements 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_mask2_permutex2var_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements 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_mask2int⚠ | Experimentalavx512f Converts bit mask k1 into an integer value, storing the results in dst. |
_mm512_mask3_fmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmaddsub_pd⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmaddsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmaddsub_round_pd⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmaddsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsubadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsubadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsubadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fmsubadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask3_fnmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from c when the corresponding mask bit is not set). |
_mm512_mask_abs_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_abs_epi32⚠ | Experimentalavx512f Computes the absolute value of packed 32-bit integers in |
_mm512_mask_abs_epi64⚠ | Experimentalavx512f Compute the absolute value of packed signed 64-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_pd⚠ | Experimentalavx512f Finds the absolute value of each packed double-precision (64-bit) floating-point element in v2, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_abs_ps⚠ | Experimentalavx512f Finds the absolute value of each packed single-precision (32-bit) floating-point element in v2, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_add_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_add_epi32⚠ | Experimentalavx512f Add packed 32-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_epi64⚠ | Experimentalavx512f Add packed 64-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_pd⚠ | Experimentalavx512f Add packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Add packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Add packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Add packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_epi8⚠ | Experimentalavx512bw 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_alignr_epi32⚠ | Experimentalavx512f Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 32-bit elements, and store the low 64 bytes (16 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_alignr_epi64⚠ | Experimentalavx512f Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 64-bit elements, and store the low 64 bytes (8 elements) in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_and_epi32⚠ | Experimentalavx512f Performs element-by-element bitwise AND between packed 32-bit integer elements of v2 and v3, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_and_epi64⚠ | Experimentalavx512f Compute the bitwise AND of packed 64-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_andnot_epi32⚠ | Experimentalavx512f Compute the bitwise NOT of packed 32-bit integers in a and then AND with 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_andnot_epi64⚠ | Experimentalavx512f Compute the bitwise NOT of packed 64-bit integers in a and then AND with 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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_bitshuffle_epi64_mask⚠ | Experimentalavx512bitalg Considers the input |
_mm512_mask_blend_epi8⚠ | Experimentalavx512bw Blend packed 8-bit integers from a and b using control mask k, and store the results in dst. |
_mm512_mask_blend_epi16⚠ | Experimentalavx512bw Blend packed 16-bit integers from a and b using control mask k, and store the results in dst. |
_mm512_mask_blend_epi32⚠ | Experimentalavx512f Blend packed 32-bit integers from a and b using control mask k, and store the results in dst. |
_mm512_mask_blend_epi64⚠ | Experimentalavx512f Blend packed 64-bit integers from a and b using control mask k, and store the results in dst. |
_mm512_mask_blend_pd⚠ | Experimentalavx512f Blend packed double-precision (64-bit) floating-point elements from a and b using control mask k, and store the results in dst. |
_mm512_mask_blend_ps⚠ | Experimentalavx512f Blend packed single-precision (32-bit) floating-point elements from a and b using control mask k, and store the results in dst. |
_mm512_mask_broadcast_f32x4⚠ | Experimentalavx512f Broadcast the 4 packed single-precision (32-bit) floating-point elements 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_broadcast_f64x4⚠ | Experimentalavx512f Broadcast the 4 packed double-precision (64-bit) floating-point elements 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_broadcast_i32x4⚠ | Experimentalavx512f Broadcast the 4 packed 32-bit integers 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_broadcast_i64x4⚠ | Experimentalavx512f Broadcast the 4 packed 64-bit integers 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_broadcastb_epi8⚠ | Experimentalavx512bw 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_broadcastd_epi32⚠ | Experimentalavx512f Broadcast the low packed 32-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_broadcastq_epi64⚠ | Experimentalavx512f Broadcast the low packed 64-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_broadcastsd_pd⚠ | Experimentalavx512f Broadcast the low double-precision (64-bit) floating-point element 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_broadcastss_ps⚠ | Experimentalavx512f Broadcast the low single-precision (32-bit) floating-point element 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_epi16⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-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_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmp_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_round_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_round_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed 32-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_epi64_mask⚠ | Experimentalavx512f Compare packed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmpeq_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-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_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmpge_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-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_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmpgt_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-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_cmple_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmple_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-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_cmple_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed signed 32-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_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmplt_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_epi32_mask⚠ | Experimentalavx512f Compare packed 32-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_epi64_mask⚠ | Experimentalavx512f Compare packed signed 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_cmpneq_epu32_mask⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64_mask⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_cmpnle_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for not-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_cmpnle_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for not-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_cmpnlt_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for not-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_cmpnlt_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for not-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_cmpord_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b to see if neither is NaN, 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_cmpord_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b to see if neither is NaN, 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_cmpunord_pd_mask⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b to see if either is NaN, 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_cmpunord_ps_mask⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b to see if either is NaN, 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_compress_epi32⚠ | Experimentalavx512f Contiguously store the active 32-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src. |
_mm512_mask_compress_epi64⚠ | Experimentalavx512f Contiguously store the active 64-bit integers in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src. |
_mm512_mask_compress_pd⚠ | Experimentalavx512f Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src. |
_mm512_mask_compress_ps⚠ | Experimentalavx512f Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in writemask k) to dst, and pass through the remaining elements from src. |
_mm512_mask_conflict_epi32⚠ | Experimentalavx512cd Test each 32-bit element of a for equality with all other elements in a closer to the least significant bit using writemask k (elements are copied from src when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm512_mask_conflict_epi64⚠ | Experimentalavx512cd Test each 64-bit element of a for equality with all other elements in a closer to the least significant bit using writemask k (elements are copied from src when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm512_mask_cvt_roundepi32_ps⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvt_roundepu32_ps⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvt_roundpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-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_cvt_roundpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-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_cvt_roundpd_ps⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvt_roundph_ps⚠ | Experimentalavx512f Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvt_roundps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvt_roundps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvt_roundps_pd⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvt_roundps_ph⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtepi8_epi16⚠ | Experimentalavx512bw 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_cvtepi8_epi32⚠ | Experimentalavx512f Sign extend packed 8-bit integers in a to packed 32-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_cvtepi8_epi64⚠ | Experimentalavx512f Sign extend packed 8-bit integers in the low 8 bytes of a to packed 64-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_epi8⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512f Sign extend packed 16-bit integers in a to packed 32-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_epi64⚠ | Experimentalavx512f Sign extend packed 16-bit integers in a to packed 64-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_cvtepi32_epi8⚠ | Experimentalavx512f Convert packed 32-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_cvtepi32_epi16⚠ | Experimentalavx512f Convert packed 32-bit integers in a to packed 16-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_cvtepi32_epi64⚠ | Experimentalavx512f Sign extend packed 32-bit integers in a to packed 64-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_cvtepi32_pd⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtepi32_ps⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtepi32lo_pd⚠ | Experimentalavx512f Performs element-by-element conversion of the lower half of packed 32-bit integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtepi64_epi8⚠ | Experimentalavx512f Convert packed 64-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_cvtepi64_epi16⚠ | Experimentalavx512f Convert packed 64-bit integers in a to packed 16-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_cvtepi64_epi32⚠ | Experimentalavx512f Convert packed 64-bit integers in a to packed 32-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_cvtepu8_epi16⚠ | Experimentalavx512bw 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_cvtepu8_epi32⚠ | Experimentalavx512f Zero extend packed unsigned 8-bit integers in a to packed 32-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_cvtepu8_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 8-bit integers in the low 8 bytes of a to packed 64-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_cvtepu16_epi32⚠ | Experimentalavx512f Zero extend packed unsigned 16-bit integers in a to packed 32-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_cvtepu16_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 16-bit integers in a to packed 64-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_cvtepu32_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 32-bit integers in a to packed 64-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_cvtepu32_pd⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtepu32_ps⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtepu32lo_pd⚠ | Experimentalavx512f Performs element-by-element conversion of the lower half of 32-bit unsigned integer elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtpd_ps⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtpd_pslo⚠ | Experimentalavx512f Performs an element-by-element conversion of packed double-precision (64-bit) floating-point elements in v2 to single-precision (32-bit) floating-point elements and stores them in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The elements are stored in the lower half of the results vector, while the remaining upper half locations are set to 0. |
_mm512_mask_cvtph_ps⚠ | Experimentalavx512f Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvtps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvtps_pd⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtps_ph⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtpslo_pd⚠ | Experimentalavx512f Performs element-by-element conversion of the lower half of packed single-precision (32-bit) floating-point elements in v2 to packed double-precision (64-bit) floating-point elements, storing the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_cvtsepi16_epi8⚠ | Experimentalavx512bw 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_cvtsepi32_epi8⚠ | Experimentalavx512f Convert packed signed 32-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_cvtsepi32_epi16⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed 16-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_cvtsepi64_epi8⚠ | Experimentalavx512f Convert packed signed 64-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_cvtsepi64_epi16⚠ | Experimentalavx512f Convert packed signed 64-bit integers in a to packed 16-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_cvtsepi64_epi32⚠ | Experimentalavx512f Convert packed signed 64-bit integers in a to packed 32-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_cvtt_roundpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-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_cvtt_roundpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-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_cvtt_roundps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvtt_roundps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvttpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-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_cvttpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-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_cvttps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvttps_epu32⚠ | Experimentalavx512f Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvtusepi16_epi8⚠ | Experimentalavx512bw 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_cvtusepi32_epi8⚠ | Experimentalavx512f Convert packed unsigned 32-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_cvtusepi32_epi16⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed unsigned 16-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_cvtusepi64_epi8⚠ | Experimentalavx512f Convert packed unsigned 64-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_cvtusepi64_epi16⚠ | Experimentalavx512f Convert packed unsigned 64-bit integers in a to packed unsigned 16-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_cvtusepi64_epi32⚠ | Experimentalavx512f Convert packed unsigned 64-bit integers in a to packed unsigned 32-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_dbsad_epu8⚠ | Experimentalavx512bw 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_div_pd⚠ | Experimentalavx512f Divide packed double-precision (64-bit) floating-point elements in a by packed elements in 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_div_ps⚠ | Experimentalavx512f Divide packed single-precision (32-bit) floating-point elements in a by packed elements in 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_div_round_pd⚠ | Experimentalavx512f Divide packed double-precision (64-bit) floating-point elements in a by packed elements in 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_div_round_ps⚠ | Experimentalavx512f Divide packed single-precision (32-bit) floating-point elements in a by packed elements in 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_expand_epi32⚠ | Experimentalavx512f Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_expand_epi64⚠ | Experimentalavx512f Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_expand_pd⚠ | Experimentalavx512f Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_expand_ps⚠ | Experimentalavx512f Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_extractf32x4_ps⚠ | Experimentalavx512f Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_extractf64x4_pd⚠ | Experimentalavx512f Extract 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a, selected with imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_extracti32x4_epi32⚠ | Experimentalavx512f Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_extracti64x4_epi64⚠ | Experimentalavx512f Extract 256 bits (composed of 4 packed 64-bit integers) from a, selected with imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_fixupimm_pd⚠ | Experimentalavx512f Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_mask_fixupimm_ps⚠ | Experimentalavx512f Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_mask_fixupimm_round_pd⚠ | Experimentalavx512f Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_mask_fixupimm_round_ps⚠ | Experimentalavx512f Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_mask_fmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmaddsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmaddsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmaddsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmaddsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsubadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsubadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsubadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fmsubadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_fnmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using writemask k (elements are copied from a when the corresponding mask bit is not set). |
_mm512_mask_getexp_pd⚠ | Experimentalavx512f Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_mask_getexp_ps⚠ | Experimentalavx512f Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_mask_getexp_round_pd⚠ | Experimentalavx512f Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_mask_getexp_round_ps⚠ | Experimentalavx512f Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_mask_getmant_pd⚠ | Experimentalavx512f Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_mask_getmant_ps⚠ | Experimentalavx512f Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_mask_getmant_round_pd⚠ | Experimentalavx512f Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_mask_getmant_round_ps⚠ | Experimentalavx512f Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_mask_gf2p8affine_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs an affine transformation on the packed bytes in x. That is computes a*x+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm512_mask_gf2p8affineinv_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs an affine transformation on the inverted packed bytes in x. That is computes a*inv(x)+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. The inverse of a byte is defined with respect to the reduction polynomial x^8+x^4+x^3+x+1. The inverse of 0 is 0. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm512_mask_gf2p8mul_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs a multiplication in GF(2^8) on the packed bytes. The field is in polynomial representation with the reduction polynomial x^8 + x^4 + x^3 + x + 1. |
_mm512_mask_i32gather_epi32⚠ | Experimentalavx512f Gather 32-bit integers from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i32gather_epi64⚠ | Experimentalavx512f Gather 64-bit integers from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i32gather_pd⚠ | Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 32-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i32gather_ps⚠ | Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 32-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i32scatter_epi32⚠ | Experimentalavx512f Scatter 32-bit integers from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i32scatter_epi64⚠ | Experimentalavx512f Scatter 64-bit integers from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i32scatter_pd⚠ | Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from a into memory using 32-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i32scatter_ps⚠ | Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from a into memory using 32-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 32-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64gather_epi32⚠ | Experimentalavx512f Gather 32-bit integers from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64gather_epi64⚠ | Experimentalavx512f Gather 64-bit integers from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64gather_pd⚠ | Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 64-bit indices. 64-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64gather_ps⚠ | Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 64-bit indices. 32-bit elements are loaded from addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale). Gathered elements are merged into dst using writemask k (elements are copied from src when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64scatter_epi32⚠ | Experimentalavx512f Scatter 32-bit integers from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64scatter_epi64⚠ | Experimentalavx512f Scatter 64-bit integers from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64scatter_pd⚠ | Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from a into memory using 64-bit indices. 64-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_i64scatter_ps⚠ | Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from a into memory using 64-bit indices. 32-bit elements are stored at addresses starting at base_addr and offset by each 64-bit element in vindex (each index is scaled by the factor in scale) subject to mask k (elements are not stored when the corresponding mask bit is not set). scale should be 1, 2, 4 or 8. |
_mm512_mask_insertf32x4⚠ | Experimentalavx512f Copy a to tmp, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_insertf64x4⚠ | Experimentalavx512f Copy a to tmp, then insert 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_inserti32x4⚠ | Experimentalavx512f Copy a to tmp, then insert 128 bits (composed of 4 packed 32-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_inserti64x4⚠ | Experimentalavx512f Copy a to tmp, then insert 256 bits (composed of 4 packed 64-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_lzcnt_epi32⚠ | Experimentalavx512cd Counts the number of leading zero bits in each packed 32-bit integer 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_lzcnt_epi64⚠ | Experimentalavx512cd Counts the number of leading zero bits in each packed 64-bit integer 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_madd_epi16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512f Compare packed signed 32-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_epi64⚠ | Experimentalavx512f Compare packed signed 64-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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_max_epu32⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512f Compare packed signed 32-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_epi64⚠ | Experimentalavx512f Compare packed signed 64-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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_min_epu32⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mov_epi32⚠ | Experimentalavx512f Move packed 32-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_mov_epi64⚠ | Experimentalavx512f Move packed 64-bit integers from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_mov_pd⚠ | Experimentalavx512f Move packed double-precision (64-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_mov_ps⚠ | Experimentalavx512f Move packed single-precision (32-bit) floating-point elements from a to dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_movedup_pd⚠ | Experimentalavx512f Duplicate even-indexed double-precision (64-bit) floating-point elements from 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_movehdup_ps⚠ | Experimentalavx512f Duplicate odd-indexed single-precision (32-bit) floating-point elements from 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_moveldup_ps⚠ | Experimentalavx512f Duplicate even-indexed single-precision (32-bit) floating-point elements from 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_mul_epi32⚠ | Experimentalavx512f Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_mul_epu32⚠ | Experimentalavx512f Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_mul_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements 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). RM. |
_mm512_mask_mul_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements 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). RM. |
_mm512_mask_mul_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements 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_mul_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements 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_mulhi_epi16⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mullo_epi32⚠ | Experimentalavx512f Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 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_mullox_epi64⚠ | Experimentalavx512f Multiplies elements in packed 64-bit integer vectors a and b together, storing the lower 64 bits of the result in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_or_epi32⚠ | Experimentalavx512f Compute the bitwise OR of packed 32-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_or_epi64⚠ | Experimentalavx512f Compute the bitwise OR of packed 64-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_packs_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512bw 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_permute_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_permute_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_permutevar_epi32⚠ | Experimentalavx512f Shuffle 32-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). Note that this intrinsic shuffles across 128-bit lanes, unlike past intrinsics that use the permutevar name. This intrinsic is identical to _mm512_mask_permutexvar_epi32, and it is recommended that you use that intrinsic name. |
_mm512_mask_permutevar_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in 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_permutevar_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in 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_permutex2var_epi16⚠ | Experimentalavx512bw 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_permutex2var_epi32⚠ | Experimentalavx512f Shuffle 32-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_permutex2var_epi64⚠ | Experimentalavx512f Shuffle 64-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_permutex2var_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements 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_permutex2var_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements 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_permutex_epi64⚠ | Experimentalavx512f Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_permutex_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_permutexvar_epi16⚠ | Experimentalavx512bw 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_permutexvar_epi32⚠ | Experimentalavx512f Shuffle 32-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_permutexvar_epi64⚠ | Experimentalavx512f Shuffle 64-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_permutexvar_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements 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_permutexvar_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements 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_popcnt_epi8⚠ | Experimentalavx512bitalg For each packed 8-bit integer maps the value to the number of logical 1 bits. |
_mm512_mask_popcnt_epi16⚠ | Experimentalavx512bitalg For each packed 16-bit integer maps the value to the number of logical 1 bits. |
_mm512_mask_popcnt_epi32⚠ | Experimentalavx512vpopcntdq For each packed 32-bit integer maps the value to the number of logical 1 bits. |
_mm512_mask_popcnt_epi64⚠ | Experimentalavx512vpopcntdq For each packed 64-bit integer maps the value to the number of logical 1 bits. |
_mm512_mask_rcp14_pd⚠ | Experimentalavx512f Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_mask_rcp14_ps⚠ | Experimentalavx512f Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_mask_reduce_add_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by addition using mask k. Returns the sum of all active elements in a. |
_mm512_mask_reduce_add_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by addition using mask k. Returns the sum of all active elements in a. |
_mm512_mask_reduce_add_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by addition using mask k. Returns the sum of all active elements in a. |
_mm512_mask_reduce_add_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by addition using mask k. Returns the sum of all active elements in a. |
_mm512_mask_reduce_and_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by bitwise AND using mask k. Returns the bitwise AND of all active elements in a. |
_mm512_mask_reduce_and_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by addition using mask k. Returns the sum of all active elements in a. |
_mm512_mask_reduce_max_epi32⚠ | Experimentalavx512f Reduce the packed signed 32-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a. |
_mm512_mask_reduce_max_epi64⚠ | Experimentalavx512f Reduce the packed signed 64-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a. |
_mm512_mask_reduce_max_epu32⚠ | Experimentalavx512f Reduce the packed unsigned 32-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a. |
_mm512_mask_reduce_max_epu64⚠ | Experimentalavx512f Reduce the packed unsigned 64-bit integers in a by maximum using mask k. Returns the maximum of all active elements in a. |
_mm512_mask_reduce_max_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by maximum using mask k. Returns the maximum of all active elements in a. |
_mm512_mask_reduce_max_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by maximum using mask k. Returns the maximum of all active elements in a. |
_mm512_mask_reduce_min_epi32⚠ | Experimentalavx512f Reduce the packed signed 32-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a. |
_mm512_mask_reduce_min_epi64⚠ | Experimentalavx512f Reduce the packed signed 64-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a. |
_mm512_mask_reduce_min_epu32⚠ | Experimentalavx512f Reduce the packed unsigned 32-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a. |
_mm512_mask_reduce_min_epu64⚠ | Experimentalavx512f Reduce the packed signed 64-bit integers in a by maximum using mask k. Returns the minimum of all active elements in a. |
_mm512_mask_reduce_min_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by maximum using mask k. Returns the minimum of all active elements in a. |
_mm512_mask_reduce_min_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by maximum using mask k. Returns the minimum of all active elements in a. |
_mm512_mask_reduce_mul_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by multiplication using mask k. Returns the product of all active elements in a. |
_mm512_mask_reduce_mul_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by multiplication using mask k. Returns the product of all active elements in a. |
_mm512_mask_reduce_mul_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by multiplication using mask k. Returns the product of all active elements in a. |
_mm512_mask_reduce_mul_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by multiplication using mask k. Returns the product of all active elements in a. |
_mm512_mask_reduce_or_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by bitwise OR using mask k. Returns the bitwise OR of all active elements in a. |
_mm512_mask_reduce_or_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by bitwise OR using mask k. Returns the bitwise OR of all active elements in a. |
_mm512_mask_rol_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_rol_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_rolv_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding 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_rolv_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding 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_ror_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_ror_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_rorv_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding 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_rorv_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding 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_roundscale_pd⚠ | Experimentalavx512f Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_roundscale_ps⚠ | Experimentalavx512f Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_roundscale_round_pd⚠ | Experimentalavx512f Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_roundscale_round_ps⚠ | Experimentalavx512f Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_rsqrt14_pd⚠ | Experimentalavx512f Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_mask_rsqrt14_ps⚠ | Experimentalavx512f Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_mask_scalef_pd⚠ | Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from 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_scalef_ps⚠ | Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from 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_scalef_round_pd⚠ | Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from 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_scalef_round_ps⚠ | Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from 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_set1_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_set1_epi32⚠ | Experimentalavx512f Broadcast 32-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_epi64⚠ | Experimentalavx512f Broadcast 64-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_epi8⚠ | Experimentalavx512bw 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_shuffle_epi32⚠ | Experimentalavx512f Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_shuffle_f32x4⚠ | Experimentalavx512f Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from 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_shuffle_f64x2⚠ | Experimentalavx512f Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from 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_shuffle_i32x4⚠ | Experimentalavx512f Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from 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_shuffle_i64x2⚠ | Experimentalavx512f Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from 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_shuffle_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_shuffle_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, 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_epi16⚠ | Experimentalavx512bw 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 from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_shufflelo_epi16⚠ | Experimentalavx512bw 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 from a to dst, using writemask k (elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_sll_epi16⚠ | Experimentalavx512bw 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_sll_epi32⚠ | Experimentalavx512f Shift packed 32-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_sll_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_slli_epi32⚠ | Experimentalavx512f Shift packed 32-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_slli_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_sllv_epi32⚠ | Experimentalavx512f Shift packed 32-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_sllv_epi64⚠ | Experimentalavx512f Shift packed 64-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_sqrt_pd⚠ | Experimentalavx512f Compute the square root of packed double-precision (64-bit) floating-point elements 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_sqrt_ps⚠ | Experimentalavx512f Compute the square root of packed single-precision (32-bit) floating-point elements 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_sqrt_round_pd⚠ | Experimentalavx512f Compute the square root of packed double-precision (64-bit) floating-point elements 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_sqrt_round_ps⚠ | Experimentalavx512f Compute the square root of packed single-precision (32-bit) floating-point elements 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_sra_epi16⚠ | Experimentalavx512bw 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_sra_epi32⚠ | Experimentalavx512f Shift packed 32-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_sra_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srai_epi32⚠ | Experimentalavx512f Shift packed 32-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_srai_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srav_epi32⚠ | Experimentalavx512f Shift packed 32-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_srav_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srl_epi32⚠ | Experimentalavx512f Shift packed 32-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_srl_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srli_epi32⚠ | Experimentalavx512f Shift packed 32-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_srli_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srlv_epi32⚠ | Experimentalavx512f Shift packed 32-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_srlv_epi64⚠ | Experimentalavx512f Shift packed 64-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_sub_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_sub_epi32⚠ | Experimentalavx512f Subtract packed 32-bit integers in b from packed 32-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_epi64⚠ | Experimentalavx512f Subtract packed 64-bit integers in b from packed 64-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_pd⚠ | Experimentalavx512f Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_ternarylogic_epi32⚠ | Experimentalavx512f Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 32-bit granularity (32-bit elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_ternarylogic_epi64⚠ | Experimentalavx512f Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from src, a, and b are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using writemask k at 64-bit granularity (64-bit elements are copied from src when the corresponding mask bit is not set). |
_mm512_mask_test_epi8_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_test_epi32_mask⚠ | Experimentalavx512f Compute the bitwise AND of packed 32-bit integers in a and b, producing intermediate 32-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_epi64_mask⚠ | Experimentalavx512f Compute the bitwise AND of packed 64-bit integers in a and b, producing intermediate 64-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_mask⚠ | Experimentalavx512bw 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_mask⚠ | Experimentalavx512bw 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_testn_epi32_mask⚠ | Experimentalavx512f Compute the bitwise NAND of packed 32-bit integers in a and b, producing intermediate 32-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero. |
_mm512_mask_testn_epi64_mask⚠ | Experimentalavx512f Compute the bitwise NAND of packed 64-bit integers in a and b, producing intermediate 64-bit values, and set the corresponding bit in result mask k (subject to writemask k) if the intermediate value is zero. |
_mm512_mask_unpackhi_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_unpackhi_epi32⚠ | Experimentalavx512f Unpack and interleave 32-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_epi64⚠ | Experimentalavx512f Unpack and interleave 64-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_pd⚠ | Experimentalavx512f Unpack and interleave double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Unpack and interleave single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mask_unpacklo_epi32⚠ | Experimentalavx512f Unpack and interleave 32-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_epi64⚠ | Experimentalavx512f Unpack and interleave 64-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_pd⚠ | Experimentalavx512f Unpack and interleave double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Unpack and interleave single-precision (32-bit) floating-point elements 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_xor_epi32⚠ | Experimentalavx512f Compute the bitwise XOR of packed 32-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_xor_epi64⚠ | Experimentalavx512f Compute the bitwise XOR of packed 64-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_maskz_abs_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_abs_epi32⚠ | Experimentalavx512f Computes the absolute value of packed 32-bit integers in |
_mm512_maskz_abs_epi64⚠ | Experimentalavx512f Compute the absolute value of packed signed 64-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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_add_epi32⚠ | Experimentalavx512f Add packed 32-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_epi64⚠ | Experimentalavx512f Add packed 64-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_pd⚠ | Experimentalavx512f Add packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Add packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Add packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Add packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_epi8⚠ | Experimentalavx512bw 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_alignr_epi32⚠ | Experimentalavx512f Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 32-bit elements, and stores the low 64 bytes (16 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_alignr_epi64⚠ | Experimentalavx512f Concatenate a and b into a 128-byte immediate result, shift the result right by imm8 64-bit elements, and stores the low 64 bytes (8 elements) in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_and_epi32⚠ | Experimentalavx512f Compute the bitwise AND of packed 32-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_and_epi64⚠ | Experimentalavx512f Compute the bitwise AND of packed 32-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_andnot_epi32⚠ | Experimentalavx512f Compute the bitwise NOT of packed 32-bit integers in a and then AND with b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_andnot_epi64⚠ | Experimentalavx512f Compute the bitwise NOT of packed 64-bit integers in a and then AND with 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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_broadcast_f32x4⚠ | Experimentalavx512f Broadcast the 4 packed single-precision (32-bit) floating-point elements from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_broadcast_f64x4⚠ | Experimentalavx512f Broadcast the 4 packed double-precision (64-bit) floating-point elements from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_broadcast_i32x4⚠ | Experimentalavx512f Broadcast the 4 packed 32-bit integers from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_broadcast_i64x4⚠ | Experimentalavx512f Broadcast the 4 packed 64-bit integers from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_broadcastb_epi8⚠ | Experimentalavx512bw 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_broadcastd_epi32⚠ | Experimentalavx512f Broadcast the low packed 32-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_broadcastq_epi64⚠ | Experimentalavx512f Broadcast the low packed 64-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_broadcastsd_pd⚠ | Experimentalavx512f Broadcast the low double-precision (64-bit) floating-point element from a to all elements of dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_broadcastss_ps⚠ | Experimentalavx512f Broadcast the low single-precision (32-bit) floating-point element 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_epi16⚠ | Experimentalavx512bw 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_compress_epi32⚠ | Experimentalavx512f Contiguously store the active 32-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero. |
_mm512_maskz_compress_epi64⚠ | Experimentalavx512f Contiguously store the active 64-bit integers in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero. |
_mm512_maskz_compress_pd⚠ | Experimentalavx512f Contiguously store the active double-precision (64-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero. |
_mm512_maskz_compress_ps⚠ | Experimentalavx512f Contiguously store the active single-precision (32-bit) floating-point elements in a (those with their respective bit set in zeromask k) to dst, and set the remaining elements to zero. |
_mm512_maskz_conflict_epi32⚠ | Experimentalavx512cd Test each 32-bit element of a for equality with all other elements in a closer to the least significant bit using zeromask k (elements are zeroed out when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm512_maskz_conflict_epi64⚠ | Experimentalavx512cd Test each 64-bit element of a for equality with all other elements in a closer to the least significant bit using zeromask k (elements are zeroed out when the corresponding mask bit is not set). Each element’s comparison forms a zero extended bit vector in dst. |
_mm512_maskz_cvt_roundepi32_ps⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvt_roundepu32_ps⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvt_roundpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-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_cvt_roundpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-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_cvt_roundpd_ps⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvt_roundph_ps⚠ | Experimentalavx512f Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvt_roundps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvt_roundps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvt_roundps_pd⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvt_roundps_ph⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtepi8_epi16⚠ | Experimentalavx512bw 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_cvtepi8_epi32⚠ | Experimentalavx512f Sign extend packed 8-bit integers in a to packed 32-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_cvtepi8_epi64⚠ | Experimentalavx512f Sign extend packed 8-bit integers in the low 8 bytes of a to packed 64-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_epi8⚠ | Experimentalavx512bw 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_cvtepi16_epi32⚠ | Experimentalavx512f Sign extend packed 16-bit integers in a to packed 32-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_epi64⚠ | Experimentalavx512f Sign extend packed 16-bit integers in a to packed 64-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_cvtepi32_epi8⚠ | Experimentalavx512f Convert packed 32-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_cvtepi32_epi16⚠ | Experimentalavx512f Convert packed 32-bit integers in a to packed 16-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_cvtepi32_epi64⚠ | Experimentalavx512f Sign extend packed 32-bit integers in a to packed 64-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_cvtepi32_pd⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtepi32_ps⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtepi64_epi8⚠ | Experimentalavx512f Convert packed 64-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_cvtepi64_epi16⚠ | Experimentalavx512f Convert packed 64-bit integers in a to packed 16-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_cvtepi64_epi32⚠ | Experimentalavx512f Convert packed 64-bit integers in a to packed 32-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_epi16⚠ | Experimentalavx512bw 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_cvtepu8_epi32⚠ | Experimentalavx512f Zero extend packed unsigned 8-bit integers in a to packed 32-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_cvtepu8_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 8-bit integers in the low 8 bytes of a to packed 64-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_cvtepu16_epi32⚠ | Experimentalavx512f Zero extend packed unsigned 16-bit integers in a to packed 32-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_cvtepu16_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 16-bit integers in a to packed 64-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_cvtepu32_epi64⚠ | Experimentalavx512f Zero extend packed unsigned 32-bit integers in a to packed 64-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_cvtepu32_pd⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtepu32_ps⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtpd_ps⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtph_ps⚠ | Experimentalavx512f Convert packed half-precision (16-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvtps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvtps_pd⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtps_ph⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed half-precision (16-bit) floating-point elements, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_cvtsepi16_epi8⚠ | Experimentalavx512bw 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_cvtsepi32_epi8⚠ | Experimentalavx512f Convert packed signed 32-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_cvtsepi32_epi16⚠ | Experimentalavx512f Convert packed signed 32-bit integers in a to packed 16-bit integers with signed saturation, and store the results in dst. |
_mm512_maskz_cvtsepi64_epi8⚠ | Experimentalavx512f Convert packed signed 64-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_cvtsepi64_epi16⚠ | Experimentalavx512f Convert packed signed 64-bit integers in a to packed 16-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_cvtsepi64_epi32⚠ | Experimentalavx512f Convert packed signed 64-bit integers in a to packed 32-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_cvtt_roundpd_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvtt_roundpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-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_cvtt_roundps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvtt_roundps_epu32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvttpd_epi32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed 32-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_cvttpd_epu32⚠ | Experimentalavx512f Convert packed double-precision (64-bit) floating-point elements in a to packed unsigned 32-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_cvttps_epi32⚠ | Experimentalavx512f Convert packed single-precision (32-bit) floating-point elements in a to packed 32-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_cvttps_epu32⚠ | Experimentalavx512f Convert packed double-precision (32-bit) floating-point elements in a to packed unsigned 32-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_cvtusepi16_epi8⚠ | Experimentalavx512bw 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_cvtusepi32_epi8⚠ | Experimentalavx512f Convert packed unsigned 32-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_cvtusepi32_epi16⚠ | Experimentalavx512f Convert packed unsigned 32-bit integers in a to packed unsigned 16-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_cvtusepi64_epi8⚠ | Experimentalavx512f Convert packed unsigned 64-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_cvtusepi64_epi16⚠ | Experimentalavx512f Convert packed unsigned 64-bit integers in a to packed unsigned 16-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_cvtusepi64_epi32⚠ | Experimentalavx512f Convert packed unsigned 64-bit integers in a to packed unsigned 32-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_epu8⚠ | Experimentalavx512bw 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_div_pd⚠ | Experimentalavx512f Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_div_ps⚠ | Experimentalavx512f Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_div_round_pd⚠ | Experimentalavx512f Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_div_round_ps⚠ | Experimentalavx512f Divide packed single-precision (32-bit) floating-point elements in a by packed elements in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_expand_epi32⚠ | Experimentalavx512f Load contiguous active 32-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_expand_epi64⚠ | Experimentalavx512f Load contiguous active 64-bit integers from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_expand_pd⚠ | Experimentalavx512f Load contiguous active double-precision (64-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_expand_ps⚠ | Experimentalavx512f Load contiguous active single-precision (32-bit) floating-point elements from a (those with their respective bit set in mask k), and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_extractf32x4_ps⚠ | Experimentalavx512f Extract 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_extractf64x4_pd⚠ | Experimentalavx512f Extract 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a, selected with imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_extracti32x4_epi32⚠ | Experimentalavx512f Extract 128 bits (composed of 4 packed 32-bit integers) from a, selected with imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_extracti64x4_epi64⚠ | Experimentalavx512f Extract 256 bits (composed of 4 packed 64-bit integers) from a, selected with imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fixupimm_pd⚠ | Experimentalavx512f Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_maskz_fixupimm_ps⚠ | Experimentalavx512f Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_maskz_fixupimm_round_pd⚠ | Experimentalavx512f Fix up packed double-precision (64-bit) floating-point elements in a and b using packed 64-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_maskz_fixupimm_round_ps⚠ | Experimentalavx512f Fix up packed single-precision (32-bit) floating-point elements in a and b using packed 32-bit integers in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). imm8 is used to set the required flags reporting. |
_mm512_maskz_fmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the intermediate result to packed elements in c, and store the results in a using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmaddsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmaddsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmaddsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmaddsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsubadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsubadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsubadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fmsubadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmadd_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmadd_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmadd_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmadd_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, add the negated intermediate result to packed elements in c, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmsub_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmsub_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmsub_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_fnmsub_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, subtract packed elements in c from the negated intermediate result, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_getexp_pd⚠ | Experimentalavx512f Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_maskz_getexp_ps⚠ | Experimentalavx512f Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_maskz_getexp_round_pd⚠ | Experimentalavx512f Convert the exponent of each packed double-precision (64-bit) floating-point element in a to a double-precision (64-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_maskz_getexp_round_ps⚠ | Experimentalavx512f Convert the exponent of each packed single-precision (32-bit) floating-point element in a to a single-precision (32-bit) floating-point number representing the integer exponent, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates floor(log2(x)) for each element. |
_mm512_maskz_getmant_pd⚠ | Experimentalavx512f Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_maskz_getmant_ps⚠ | Experimentalavx512f Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_maskz_getmant_round_pd⚠ | Experimentalavx512f Normalize the mantissas of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_maskz_getmant_round_ps⚠ | Experimentalavx512f Normalize the mantissas of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). This intrinsic essentially calculates ±(2^k)*|x.significand|, where k depends on the interval range defined by interv and the sign depends on sc and the source sign. |
_mm512_maskz_gf2p8affine_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs an affine transformation on the packed bytes in x. That is computes a*x+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm512_maskz_gf2p8affineinv_epi64_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs an affine transformation on the inverted packed bytes in x. That is computes a*inv(x)+b over the Galois Field 2^8 for each packed byte with a being a 8x8 bit matrix and b being a constant 8-bit immediate value. The inverse of a byte is defined with respect to the reduction polynomial x^8+x^4+x^3+x+1. The inverse of 0 is 0. Each pack of 8 bytes in x is paired with the 64-bit word at the same position in a. |
_mm512_maskz_gf2p8mul_epi8⚠ | Experimentalavx512gfni,avx512bw,avx512f Performs a multiplication in GF(2^8) on the packed bytes. The field is in polynomial representation with the reduction polynomial x^8 + x^4 + x^3 + x + 1. |
_mm512_maskz_insertf32x4⚠ | Experimentalavx512f Copy a to tmp, then insert 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_insertf64x4⚠ | Experimentalavx512f Copy a to tmp, then insert 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_inserti32x4⚠ | Experimentalavx512f Copy a to tmp, then insert 128 bits (composed of 4 packed 32-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_inserti64x4⚠ | Experimentalavx512f Copy a to tmp, then insert 256 bits (composed of 4 packed 64-bit integers) from b into tmp at the location specified by imm8. Store tmp to dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_lzcnt_epi32⚠ | Experimentalavx512cd Counts the number of leading zero bits in each packed 32-bit integer 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_lzcnt_epi64⚠ | Experimentalavx512cd Counts the number of leading zero bits in each packed 64-bit integer 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_madd_epi16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512f Compare packed signed 32-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_epi64⚠ | Experimentalavx512f Compare packed signed 64-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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_max_epu32⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512f Compare packed signed 32-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_epi64⚠ | Experimentalavx512f Compare packed signed 64-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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_min_epu32⚠ | Experimentalavx512f Compare packed unsigned 32-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_epu64⚠ | Experimentalavx512f Compare packed unsigned 64-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_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mov_epi32⚠ | Experimentalavx512f Move packed 32-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_mov_epi64⚠ | Experimentalavx512f Move packed 64-bit integers from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_mov_pd⚠ | Experimentalavx512f Move packed double-precision (64-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_mov_ps⚠ | Experimentalavx512f Move packed single-precision (32-bit) floating-point elements from a into dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_movedup_pd⚠ | Experimentalavx512f Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_movehdup_ps⚠ | Experimentalavx512f Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_moveldup_ps⚠ | Experimentalavx512f Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_mul_epi32⚠ | Experimentalavx512f Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_mul_epu32⚠ | Experimentalavx512f Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_mul_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements 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_mul_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements 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_mul_round_pd⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements 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_mul_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements 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_mulhi_epi16⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mullo_epi32⚠ | Experimentalavx512f Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_or_epi32⚠ | Experimentalavx512f Compute the bitwise OR of packed 32-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_or_epi64⚠ | Experimentalavx512f Compute the bitwise OR of packed 64-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_packs_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512bw 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_permute_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_permute_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_permutevar_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_permutevar_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_permutex2var_epi16⚠ | Experimentalavx512bw 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_permutex2var_epi32⚠ | Experimentalavx512f Shuffle 32-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_permutex2var_epi64⚠ | Experimentalavx512f Shuffle 64-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_permutex2var_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements 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_permutex2var_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements 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_permutex_epi64⚠ | Experimentalavx512f Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_permutex_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_permutexvar_epi16⚠ | Experimentalavx512bw 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_permutexvar_epi32⚠ | Experimentalavx512f Shuffle 32-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_permutexvar_epi64⚠ | Experimentalavx512f Shuffle 64-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_permutexvar_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements 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_permutexvar_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements 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_popcnt_epi8⚠ | Experimentalavx512bitalg For each packed 8-bit integer maps the value to the number of logical 1 bits. |
_mm512_maskz_popcnt_epi16⚠ | Experimentalavx512bitalg For each packed 16-bit integer maps the value to the number of logical 1 bits. |
_mm512_maskz_popcnt_epi32⚠ | Experimentalavx512vpopcntdq For each packed 32-bit integer maps the value to the number of logical 1 bits. |
_mm512_maskz_popcnt_epi64⚠ | Experimentalavx512vpopcntdq For each packed 64-bit integer maps the value to the number of logical 1 bits. |
_mm512_maskz_rcp14_pd⚠ | Experimentalavx512f Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_maskz_rcp14_ps⚠ | Experimentalavx512f Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_maskz_rol_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_rol_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_rolv_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding 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_rolv_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding 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_ror_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_ror_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_rorv_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding 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_rorv_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding 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_roundscale_pd⚠ | Experimentalavx512f Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_roundscale_ps⚠ | Experimentalavx512f Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_roundscale_round_pd⚠ | Experimentalavx512f Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_roundscale_round_ps⚠ | Experimentalavx512f Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_rsqrt14_pd⚠ | Experimentalavx512f Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_maskz_rsqrt14_ps⚠ | Experimentalavx512f Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). The maximum relative error for this approximation is less than 2^-14. |
_mm512_maskz_scalef_pd⚠ | Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_scalef_ps⚠ | Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_scalef_round_pd⚠ | Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_scalef_round_ps⚠ | Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_set1_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_set1_epi32⚠ | Experimentalavx512f Broadcast 32-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_epi64⚠ | Experimentalavx512f Broadcast 64-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_shuffle_epi8⚠ | Experimentalavx512bw 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_shuffle_epi32⚠ | Experimentalavx512f Shuffle 32-bit integers in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_shuffle_f32x4⚠ | Experimentalavx512f Shuffle 128-bits (composed of 4 single-precision (32-bit) floating-point elements) selected by imm8 from 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_shuffle_f64x2⚠ | Experimentalavx512f Shuffle 128-bits (composed of 2 double-precision (64-bit) floating-point elements) selected by imm8 from 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_shuffle_i32x4⚠ | Experimentalavx512f Shuffle 128-bits (composed of 4 32-bit integers) selected by imm8 from 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_shuffle_i64x2⚠ | Experimentalavx512f Shuffle 128-bits (composed of 2 64-bit integers) selected by imm8 from 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_shuffle_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_shuffle_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_shufflehi_epi16⚠ | Experimentalavx512bw 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 from a to dst, using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_shufflelo_epi16⚠ | Experimentalavx512bw 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 from a to dst, using zeromask k (elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_sll_epi16⚠ | Experimentalavx512bw 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_sll_epi32⚠ | Experimentalavx512f Shift packed 32-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_sll_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_slli_epi32⚠ | Experimentalavx512f Shift packed 32-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_slli_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_sllv_epi32⚠ | Experimentalavx512f Shift packed 32-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_sllv_epi64⚠ | Experimentalavx512f Shift packed 64-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_sqrt_pd⚠ | Experimentalavx512f Compute the square root of packed double-precision (64-bit) floating-point elements 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_sqrt_ps⚠ | Experimentalavx512f Compute the square root of packed single-precision (32-bit) floating-point elements 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_sqrt_round_pd⚠ | Experimentalavx512f Compute the square root of packed double-precision (64-bit) floating-point elements 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_sqrt_round_ps⚠ | Experimentalavx512f Compute the square root of packed single-precision (32-bit) floating-point elements 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_sra_epi16⚠ | Experimentalavx512bw 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_sra_epi32⚠ | Experimentalavx512f Shift packed 32-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_sra_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srai_epi32⚠ | Experimentalavx512f Shift packed 32-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_srai_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srav_epi32⚠ | Experimentalavx512f Shift packed 32-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_srav_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srl_epi32⚠ | Experimentalavx512f Shift packed 32-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_srl_epi64⚠ | Experimentalavx512f Shift packed 64-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_srli_epi16⚠ | Experimentalavx512bw 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_srli_epi32⚠ | Experimentalavx512f Shift packed 32-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_srli_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi16⚠ | Experimentalavx512bw 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_srlv_epi32⚠ | Experimentalavx512f Shift packed 32-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_srlv_epi64⚠ | Experimentalavx512f Shift packed 64-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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_sub_epi32⚠ | Experimentalavx512f Subtract packed 32-bit integers in b from packed 32-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_epi64⚠ | Experimentalavx512f Subtract packed 64-bit integers in b from packed 64-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_pd⚠ | Experimentalavx512f Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements 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_round_pd⚠ | Experimentalavx512f Subtract packed double-precision (64-bit) floating-point elements in b from packed double-precision (64-bit) floating-point elements 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_round_ps⚠ | Experimentalavx512f Subtract packed single-precision (32-bit) floating-point elements in b from packed single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epu8⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_ternarylogic_epi32⚠ | Experimentalavx512f Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 32-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 32-bit granularity (32-bit elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_ternarylogic_epi64⚠ | Experimentalavx512f Bitwise ternary logic that provides the capability to implement any three-operand binary function; the specific binary function is specified by value in imm8. For each bit in each packed 64-bit integer, the corresponding bit from a, b, and c are used to form a 3 bit index into imm8, and the value at that bit in imm8 is written to the corresponding bit in dst using zeromask k at 64-bit granularity (64-bit elements are zeroed out when the corresponding mask bit is not set). |
_mm512_maskz_unpackhi_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_unpackhi_epi32⚠ | Experimentalavx512f Unpack and interleave 32-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_epi64⚠ | Experimentalavx512f Unpack and interleave 64-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_pd⚠ | Experimentalavx512f Unpack and interleave double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Unpack and interleave single-precision (32-bit) floating-point elements 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_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_maskz_unpacklo_epi32⚠ | Experimentalavx512f Unpack and interleave 32-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_epi64⚠ | Experimentalavx512f Unpack and interleave 64-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_pd⚠ | Experimentalavx512f Unpack and interleave double-precision (64-bit) floating-point elements 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_ps⚠ | Experimentalavx512f Unpack and interleave single-precision (32-bit) floating-point elements 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_xor_epi32⚠ | Experimentalavx512f Compute the bitwise XOR of packed 32-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_xor_epi64⚠ | Experimentalavx512f Compute the bitwise XOR of packed 64-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_max_epi8⚠ | Experimentalavx512bw Compare packed signed 8-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_epi16⚠ | Experimentalavx512bw Compare packed signed 16-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_epi32⚠ | Experimentalavx512f Compare packed signed 32-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_epi64⚠ | Experimentalavx512f Compare packed signed 64-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_epu8⚠ | Experimentalavx512bw Compare packed unsigned 8-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_epu16⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_epu32⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_epu64⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b, and store packed maximum values in dst. |
_mm512_max_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst. |
_mm512_max_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst. |
_mm512_max_round_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed maximum values in dst. |
_mm512_max_round_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed maximum values in dst. |
_mm512_min_epi8⚠ | Experimentalavx512bw Compare packed signed 8-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_epi16⚠ | Experimentalavx512bw Compare packed signed 16-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_epi32⚠ | Experimentalavx512f Compare packed signed 32-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_epi64⚠ | Experimentalavx512f Compare packed signed 64-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_epu8⚠ | Experimentalavx512bw Compare packed unsigned 8-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_epu16⚠ | Experimentalavx512bw Compare packed unsigned 16-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_epu32⚠ | Experimentalavx512f Compare packed unsigned 32-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_epu64⚠ | Experimentalavx512f Compare packed unsigned 64-bit integers in a and b, and store packed minimum values in dst. |
_mm512_min_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst. |
_mm512_min_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst. |
_mm512_min_round_pd⚠ | Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b, and store packed minimum values in dst. |
_mm512_min_round_ps⚠ | Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b, and store packed minimum values in dst. |
_mm512_movedup_pd⚠ | Experimentalavx512f Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and store the results in dst. |
_mm512_movehdup_ps⚠ | Experimentalavx512f Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst. |
_mm512_moveldup_ps⚠ | Experimentalavx512f Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and store the results in dst. |
_mm512_movepi8_mask⚠ | Experimentalavx512bw Set each bit of mask register k based on the most significant bit of the corresponding packed 8-bit integer in a. |
_mm512_movepi16_mask⚠ | Experimentalavx512bw Set each bit of mask register k based on the most significant bit of the corresponding packed 16-bit integer in a. |
_mm512_movm_epi8⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mul_epi32⚠ | Experimentalavx512f Multiply the low signed 32-bit integers from each packed 64-bit element in a and b, and store the signed 64-bit results in dst. |
_mm512_mul_epu32⚠ | Experimentalavx512f Multiply the low unsigned 32-bit integers from each packed 64-bit element in a and b, and store the unsigned 64-bit results in dst. |
_mm512_mul_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_mul_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_mul_round_pd⚠ | Experimentalavx512f Multiply packed double-precision (64-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_mul_round_ps⚠ | Experimentalavx512f Multiply packed single-precision (32-bit) floating-point elements in a and b, and store the results in dst. |
_mm512_mulhi_epi16⚠ | Experimentalavx512bw 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_epu16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_mullo_epi32⚠ | Experimentalavx512f Multiply the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and store the low 32 bits of the intermediate integers in dst. |
_mm512_mullox_epi64⚠ | Experimentalavx512f Multiplies elements in packed 64-bit integer vectors a and b together, storing the lower 64 bits of the result in dst. |
_mm512_or_epi32⚠ | Experimentalavx512f Compute the bitwise OR of packed 32-bit integers in a and b, and store the results in dst. |
_mm512_or_epi64⚠ | Experimentalavx512f Compute the bitwise OR of packed 64-bit integers in a and b, and store the resut in dst. |
_mm512_or_si512⚠ | Experimentalavx512f Compute the bitwise OR of 512 bits (representing integer data) in a and b, and store the result in dst. |
_mm512_packs_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512bw 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_epi16⚠ | Experimentalavx512bw 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_epi32⚠ | Experimentalavx512bw 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_permute_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst. |
_mm512_permute_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8, and store the results in dst. |
_mm512_permutevar_epi32⚠ | Experimentalavx512f Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst. Note that this intrinsic shuffles across 128-bit lanes, unlike past intrinsics that use the permutevar name. This intrinsic is identical to _mm512_permutexvar_epi32, and it is recommended that you use that intrinsic name. |
_mm512_permutevar_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst. |
_mm512_permutevar_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b, and store the results in dst. |
_mm512_permutex2var_epi16⚠ | Experimentalavx512bw 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_permutex2var_epi32⚠ | Experimentalavx512f Shuffle 32-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst. |
_mm512_permutex2var_epi64⚠ | Experimentalavx512f Shuffle 64-bit integers in a and b across lanes using the corresponding selector and index in idx, and store the results in dst. |
_mm512_permutex2var_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst. |
_mm512_permutex2var_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a and b across lanes using the corresponding selector and index in idx, and store the results in dst. |
_mm512_permutex_epi64⚠ | Experimentalavx512f Shuffle 64-bit integers in a within 256-bit lanes using the control in imm8, and store the results in dst. |
_mm512_permutex_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in imm8, and store the results in dst. |
_mm512_permutexvar_epi16⚠ | Experimentalavx512bw Shuffle 16-bit integers in a across lanes using the corresponding index in idx, and store the results in dst. |
_mm512_permutexvar_epi32⚠ | Experimentalavx512f Shuffle 32-bit integers in a across lanes using the corresponding index in idx, and store the results in dst. |
_mm512_permutexvar_epi64⚠ | Experimentalavx512f Shuffle 64-bit integers in a across lanes using the corresponding index in idx, and store the results in dst. |
_mm512_permutexvar_pd⚠ | Experimentalavx512f Shuffle double-precision (64-bit) floating-point elements in a across lanes using the corresponding index in idx, and store the results in dst. |
_mm512_permutexvar_ps⚠ | Experimentalavx512f Shuffle single-precision (32-bit) floating-point elements in a across lanes using the corresponding index in idx. |
_mm512_popcnt_epi8⚠ | Experimentalavx512bitalg For each packed 8-bit integer maps the value to the number of logical 1 bits. |
_mm512_popcnt_epi16⚠ | Experimentalavx512bitalg For each packed 16-bit integer maps the value to the number of logical 1 bits. |
_mm512_popcnt_epi32⚠ | Experimentalavx512vpopcntdq For each packed 32-bit integer maps the value to the number of logical 1 bits. |
_mm512_popcnt_epi64⚠ | Experimentalavx512vpopcntdq For each packed 64-bit integer maps the value to the number of logical 1 bits. |
_mm512_rcp14_pd⚠ | Experimentalavx512f Compute the approximate reciprocal of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14. |
_mm512_rcp14_ps⚠ | Experimentalavx512f Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14. |
_mm512_reduce_add_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by addition. Returns the sum of all elements in a. |
_mm512_reduce_add_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by addition. Returns the sum of all elements in a. |
_mm512_reduce_add_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by addition. Returns the sum of all elements in a. |
_mm512_reduce_add_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by addition. Returns the sum of all elements in a. |
_mm512_reduce_and_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by bitwise AND. Returns the bitwise AND of all elements in a. |
_mm512_reduce_and_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by bitwise AND. Returns the bitwise AND of all elements in a. |
_mm512_reduce_max_epi32⚠ | Experimentalavx512f Reduce the packed signed 32-bit integers in a by maximum. Returns the maximum of all elements in a. |
_mm512_reduce_max_epi64⚠ | Experimentalavx512f Reduce the packed signed 64-bit integers in a by maximum. Returns the maximum of all elements in a. |
_mm512_reduce_max_epu32⚠ | Experimentalavx512f Reduce the packed unsigned 32-bit integers in a by maximum. Returns the maximum of all elements in a. |
_mm512_reduce_max_epu64⚠ | Experimentalavx512f Reduce the packed unsigned 64-bit integers in a by maximum. Returns the maximum of all elements in a. |
_mm512_reduce_max_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by maximum. Returns the maximum of all elements in a. |
_mm512_reduce_max_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by maximum. Returns the maximum of all elements in a. |
_mm512_reduce_min_epi32⚠ | Experimentalavx512f Reduce the packed signed 32-bit integers in a by minimum. Returns the minimum of all elements in a. |
_mm512_reduce_min_epi64⚠ | Experimentalavx512f Reduce the packed signed 64-bit integers in a by minimum. Returns the minimum of all elements in a. |
_mm512_reduce_min_epu32⚠ | Experimentalavx512f Reduce the packed unsigned 32-bit integers in a by minimum. Returns the minimum of all elements in a. |
_mm512_reduce_min_epu64⚠ | Experimentalavx512f Reduce the packed unsigned 64-bit integers in a by minimum. Returns the minimum of all elements in a. |
_mm512_reduce_min_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by minimum. Returns the minimum of all elements in a. |
_mm512_reduce_min_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by minimum. Returns the minimum of all elements in a. |
_mm512_reduce_mul_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by multiplication. Returns the product of all elements in a. |
_mm512_reduce_mul_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by multiplication. Returns the product of all elements in a. |
_mm512_reduce_mul_pd⚠ | Experimentalavx512f Reduce the packed double-precision (64-bit) floating-point elements in a by multiplication. Returns the product of all elements in a. |
_mm512_reduce_mul_ps⚠ | Experimentalavx512f Reduce the packed single-precision (32-bit) floating-point elements in a by multiplication. Returns the product of all elements in a. |
_mm512_reduce_or_epi32⚠ | Experimentalavx512f Reduce the packed 32-bit integers in a by bitwise OR. Returns the bitwise OR of all elements in a. |
_mm512_reduce_or_epi64⚠ | Experimentalavx512f Reduce the packed 64-bit integers in a by bitwise OR. Returns the bitwise OR of all elements in a. |
_mm512_rol_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst. |
_mm512_rol_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in imm8, and store the results in dst. |
_mm512_rolv_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst. |
_mm512_rolv_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the left by the number of bits specified in the corresponding element of b, and store the results in dst. |
_mm512_ror_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst. |
_mm512_ror_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in imm8, and store the results in dst. |
_mm512_rorv_epi32⚠ | Experimentalavx512f Rotate the bits in each packed 32-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst. |
_mm512_rorv_epi64⚠ | Experimentalavx512f Rotate the bits in each packed 64-bit integer in a to the right by the number of bits specified in the corresponding element of b, and store the results in dst. |
_mm512_roundscale_pd⚠ | Experimentalavx512f Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst. |
_mm512_roundscale_ps⚠ | Experimentalavx512f Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst. |
_mm512_roundscale_round_pd⚠ | Experimentalavx512f Round packed double-precision (64-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst. |
_mm512_roundscale_round_ps⚠ | Experimentalavx512f Round packed single-precision (32-bit) floating-point elements in a to the number of fraction bits specified by imm8, and store the results in dst. |
_mm512_rsqrt14_pd⚠ | Experimentalavx512f Compute the approximate reciprocal square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14. |
_mm512_rsqrt14_ps⚠ | Experimentalavx512f Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst. The maximum relative error for this approximation is less than 2^-14. |
_mm512_sad_epu8⚠ | Experimentalavx512bw 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_scalef_pd⚠ | Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst. |
_mm512_scalef_ps⚠ | Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst. |
_mm512_scalef_round_pd⚠ | Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, and store the results in dst. |
_mm512_scalef_round_ps⚠ | Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, and store the results in dst. |
_mm512_set1_epi8⚠ | Experimentalavx512f Broadcast 8-bit integer a to all elements of dst. |
_mm512_set1_epi16⚠ | Experimentalavx512f Broadcast the low packed 16-bit integer from a to all all elements of dst. |
_mm512_set1_epi32⚠ | Experimentalavx512f Broadcast 32-bit integer |
_mm512_set1_epi64⚠ | Experimentalavx512f Broadcast 64-bit integer |
_mm512_set1_pd⚠ | Experimentalavx512f Broadcast 64-bit float |
_mm512_set1_ps⚠ | Experimentalavx512f Broadcast 32-bit float |
_mm512_set4_epi32⚠ | Experimentalavx512f Set packed 32-bit integers in dst with the repeated 4 element sequence. |
_mm512_set4_epi64⚠ | Experimentalavx512f Set packed 64-bit integers in dst with the repeated 4 element sequence. |
_mm512_set4_pd⚠ | Experimentalavx512f Set packed double-precision (64-bit) floating-point elements in dst with the repeated 4 element sequence. |
_mm512_set4_ps⚠ | Experimentalavx512f Set packed single-precision (32-bit) floating-point elements in dst with the repeated 4 element sequence. |
_mm512_set_epi8⚠ | Experimentalavx512f Set packed 8-bit integers in dst with the supplied values. |
_mm512_set_epi16⚠ | Experimentalavx512f Set packed 16-bit integers in dst with the supplied values. |
_mm512_set_epi32⚠ | Experimentalavx512f Sets packed 32-bit integers in |
_mm512_set_epi64⚠ | Experimentalavx512f Set packed 64-bit integers in dst with the supplied values. |
_mm512_set_pd⚠ | Experimentalavx512f Set packed double-precision (64-bit) floating-point elements in dst with the supplied values. |
_mm512_set_ps⚠ | Experimentalavx512f Sets packed 32-bit integers in |
_mm512_setr4_epi32⚠ | Experimentalavx512f Set packed 32-bit integers in dst with the repeated 4 element sequence in reverse order. |
_mm512_setr4_epi64⚠ | Experimentalavx512f Set packed 64-bit integers in dst with the repeated 4 element sequence in reverse order. |
_mm512_setr4_pd⚠ | Experimentalavx512f Set packed double-precision (64-bit) floating-point elements in dst with the repeated 4 element sequence in reverse order. |
_mm512_setr4_ps⚠ | Experimentalavx512f Set packed single-precision (32-bit) floating-point elements in dst with the repeated 4 element sequence in reverse order. |
_mm512_setr_epi32⚠ | Experimentalavx512f Sets packed 32-bit integers in |
_mm512_setr_epi64⚠ | Experimentalavx512f Set packed 64-bit integers in dst with the supplied values in reverse order. |
_mm512_setr_pd⚠ | Experimentalavx512f Set packed double-precision (64-bit) floating-point elements in dst with the supplied values in reverse order. |
_mm512_setr_ps⚠ | Experimentalavx512f Sets packed 32-bit integers in |
_mm512_setzero⚠ | Experimentalavx512f Return vector of type __m512 with all elements set to zero. |