Module core::arch::x86_64

This is supported on x86-64 only.

Platform-specific intrinsics for the x86_64 platform.

See the module documentation for more details.

Structs

__m512	Experimental 512-bit wide set of sixteen f32 types, x86-specific
__m512d	Experimental 512-bit wide set of eight f64 types, x86-specific
__m512i	Experimental 512-bit wide integer vector type, x86-specific
CpuidResult	Result of the cpuid instruction.
__m128	128-bit wide set of four f32 types, x86-specific
__m128d	128-bit wide set of two f64 types, x86-specific
__m128i	128-bit wide integer vector type, x86-specific
__m256	256-bit wide set of eight f32 types, x86-specific
__m256d	256-bit wide set of four f64 types, x86-specific
__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_code(status).
_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_setcsr
_MM_EXCEPT_DIV_ZERO	See _mm_setcsr
_MM_EXCEPT_INEXACT	See _mm_setcsr
_MM_EXCEPT_INVALID	See _mm_setcsr
_MM_EXCEPT_MASK	See _MM_GET_EXCEPTION_STATE
_MM_EXCEPT_OVERFLOW	See _mm_setcsr
_MM_EXCEPT_UNDERFLOW	See _mm_setcsr
_MM_FLUSH_ZERO_MASK	See _MM_GET_FLUSH_ZERO_MODE
_MM_FLUSH_ZERO_OFF	See _mm_setcsr
_MM_FLUSH_ZERO_ON	See _mm_setcsr
_MM_FROUND_CEIL	round up and do not suppress exceptions
_MM_FROUND_CUR_DIRECTION	use MXCSR.RC; see vendor::_MM_SET_ROUNDING_MODE
_MM_FROUND_FLOOR	round down and do not suppress exceptions
_MM_FROUND_NEARBYINT	use MXCSR.RC and suppress exceptions; see vendor::_MM_SET_ROUNDING_MODE
_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 vendor::_MM_SET_ROUNDING_MODE
_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_prefetch.
_MM_HINT_T0	See _mm_prefetch.
_MM_HINT_T1	See _mm_prefetch.
_MM_HINT_T2	See _mm_prefetch.
_MM_MASK_DENORM	See _mm_setcsr
_MM_MASK_DIV_ZERO	See _mm_setcsr
_MM_MASK_INEXACT	See _mm_setcsr
_MM_MASK_INVALID	See _mm_setcsr
_MM_MASK_MASK	See _MM_GET_EXCEPTION_MASK
_MM_MASK_OVERFLOW	See _mm_setcsr
_MM_MASK_UNDERFLOW	See _mm_setcsr
_MM_ROUND_DOWN	See _mm_setcsr
_MM_ROUND_MASK	See _MM_GET_ROUNDING_MODE
_MM_ROUND_NEAREST	See _mm_setcsr
_MM_ROUND_TOWARD_ZERO	See _mm_setcsr
_MM_ROUND_UP	See _mm_setcsr
_SIDD_BIT_MASK	Mask only: return the bit mask
_SIDD_CMP_EQUAL_ANY	For each character in a, find if it is in b (Default)
_SIDD_CMP_EQUAL_EACH	The strings defined by a and b are equal
_SIDD_CMP_EQUAL_ORDERED	Search for the defined substring in the target
_SIDD_CMP_RANGES	For each character in a, determine if b[0] <= c <= b[1] or b[1] <= c <= b[2]...
_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	XFEATURE_ENABLED_MASK for XCR

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 b of the memory addressed by p.
_bittest64⚠	Experimental Returns the bit in position b of the memory addressed by p.
_bittestandcomplement⚠	Experimental Returns the bit in position b of the memory addressed by p, then inverts that bit.
_bittestandcomplement64⚠	Experimental Returns the bit in position b of the memory addressed by p, then inverts that bit.
_bittestandreset⚠	Experimental Returns the bit in position b of the memory addressed by p, then resets that bit to 0.
_bittestandreset64⚠	Experimental Returns the bit in position b of the memory addressed by p, then resets that bit to 0.
_bittestandset⚠	Experimental Returns the bit in position b of the memory addressed by p, then sets the bit to 1.
_bittestandset64⚠	Experimental Returns the bit in position b of the memory addressed by p, then sets the bit to 1.
_kand_mask16⚠	Experimentalavx512f Compute the bitwise AND of 16-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.
_knot_mask16⚠	Experimentalavx512f Compute the bitwise NOT of 16-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.
_kxnor_mask16⚠	Experimentalavx512f Compute the bitwise XNOR of 16-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.
_mm256_cvtph_ps⚠	Experimentalf16c Converts the 8 x 16-bit half-precision float values in the 128-bit vector a into 8 x 32-bit float values stored in a 256-bit wide vector.
_mm256_cvtps_ph⚠	Experimentalf16c Converts the 8 x 32-bit float values in the 256-bit vector a into 8 x 16-bit half-precision float values stored in a 128-bit wide vector.
_mm256_madd52hi_epu64⚠	Experimentalavx512ifma,avx512vl Multiply packed unsigned 52-bit integers in each 64-bit element of b and c to form a 104-bit intermediate result. Add the high 52-bit unsigned integer from the intermediate result with the corresponding unsigned 64-bit integer in a, and store the results in dst.
_mm256_madd52lo_epu64⚠	Experimentalavx512ifma,avx512vl Multiply packed unsigned 52-bit integers in each 64-bit element of b and c to form a 104-bit intermediate result. Add the low 52-bit unsigned integer from the intermediate result with the corresponding unsigned 64-bit integer in a, and store the results in dst.
_mm512_abs_epi32⚠	Experimentalavx512f Computes the absolute values of packed 32-bit integers in a.
_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_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_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_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_broadcastd_epi32⚠	Experimentalavx512f Broadcast the low packed 32-bit integer from a to all 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_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_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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_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_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_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_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_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_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_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_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_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. 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_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. 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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. mem_addr does not need to be aligned on any particular boundary.
_mm512_loadu_ps⚠	Experimentalavx512f Loads 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from memory into result. mem_addr does not need to be aligned on any particular boundary.
_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_madd52hi_epu64⚠	Experimentalavx512ifma Multiply packed unsigned 52-bit integers in each 64-bit element of b and c to form a 104-bit intermediate result. Add the high 52-bit unsigned integer from the intermediate result with the corresponding unsigned 64-bit integer in a, and store the results in dst.
_mm512_madd52lo_epu64⚠	Experimentalavx512ifma Multiply packed unsigned 52-bit integers in each 64-bit element of b and c to form a 104-bit intermediate result. Add the low 52-bit unsigned integer from the intermediate result with the corresponding unsigned 64-bit integer in a, and store the results in dst.
_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_epi32⚠	Experimentalavx512f Computes the absolute value of packed 32-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_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_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_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_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_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_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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_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_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_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_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_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_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_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_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_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. 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_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. 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_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. 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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_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_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_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_epi32⚠	Experimentalavx512f Computes the absolute value of packed 32-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_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_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_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_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_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_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. 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_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. 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_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. 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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_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_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_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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). Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_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_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_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_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_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_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_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. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_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_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 a to all elements of dst.
_mm512_set1_epi64⚠	Experimentalavx512f Broadcast 64-bit integer a to all elements of dst.
_mm512_set1_pd⚠	Experimentalavx512f Broadcast 64-bit float a to all elements of dst.
_mm512_set1_ps⚠	Experimentalavx512f Broadcast 32-bit float a to all elements of dst.
_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 dst with the supplied values.
_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 dst with the supplied values.
_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 dst with the supplied values in reverse order.
_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 dst with the supplied values in reverse order.
_mm512_setzero⚠	Experimentalavx512f Return vector of type __m512 with all elements set to zero.
_mm512_setzero_epi32⚠	Experimentalavx512f Return vector of type __m512i with all elements set to zero.
_mm512_setzero_pd⚠	Experimentalavx512f Returns vector of type __m512d with all elements set to zero.
_mm512_setzero_ps⚠	Experimentalavx512f Returns vector of type __m512d with all elements set to zero.
_mm512_setzero_si512⚠	Experimentalavx512f Returns vector of type __m512i with all elements set to zero.
_mm512_shuffle_epi32⚠	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_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_sll_epi32⚠	Experimentalavx512f Shift packed 32-bit integers in a left by count while shifting in zeros, and store the results in dst.
_mm512_sll_epi64⚠	Experimentalavx512f Shift packed 64-bit integers in a left by count while shifting in zeros, and store the results in dst.
_mm512_slli_epi32⚠	Experimentalavx512f Shift packed 32-bit integers in a left by imm8 while shifting in zeros, and store the results in dst.
_mm512_slli_epi64⚠	Experimentalavx512f Shift packed 64-bit integers in a left by imm8 while shifting in zeros, and store the results in dst.
_mm512_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.
_mm512_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.
_mm512_sqrt_pd⚠	Experimentalavx512f Compute the square root of packed double-precision (64-bit) floating-point elements in a, and store the results in dst.
_mm512_sqrt_ps⚠	Experimentalavx512f Compute the square root of packed single-precision (32-bit) floating-point elements in a, and store the results in dst.
_mm512_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.
_mm512_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.
_mm512_sra_epi32⚠	Experimentalavx512f Shift packed 32-bit integers in a right by count while shifting in sign bits, and store the results in dst.
_mm512_sra_epi64⚠	Experimentalavx512f Shift packed 64-bit integers in a right by count while shifting in sign bits, and store the results in dst.
_mm512_srai_epi32⚠	Experimentalavx512f Shift packed 32-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst.
_mm512_srai_epi64⚠	Experimentalavx512f Shift packed 64-bit integers in a right by imm8 while shifting in sign bits, and store the results in dst.
_mm512_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.
_mm512_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.
_mm512_srl_epi32⚠	Experimentalavx512f Shift packed 32-bit integers in a right by count while shifting in zeros, and store the results in dst.
_mm512_srl_epi64⚠	Experimentalavx512f Shift packed 64-bit integers in a right by count while shifting in zeros, and store the results in dst.
_mm512_srli_epi32⚠	Experimentalavx512f Shift packed 32-bit integers in a right by imm8 while shifting in zeros, and store the results in dst.
_mm512_srli_epi64⚠	Experimentalavx512f Shift packed 64-bit integers in a right by imm8 while shifting in zeros, and store the results in dst.
_mm512_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.
_mm512_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.
_mm512_store_epi32⚠	Experimentalavx512f Store 512-bits (composed of 16 packed 32-bit integers) from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_epi64⚠	Experimentalavx512f Store 512-bits (composed of 8 packed 64-bit integers) from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_pd⚠	Experimentalavx512f Store 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_ps⚠	Experimentalavx512f Store 512-bits of integer data from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_store_si512⚠	Experimentalavx512f Store 512-bits of integer data from a into memory. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_storeu_epi32⚠	Experimentalavx512f Store 512-bits (composed of 16 packed 32-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_storeu_epi64⚠	Experimentalavx512f Store 512-bits (composed of 8 packed 64-bit integers) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_storeu_pd⚠	Experimentalavx512f Stores 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_storeu_si512⚠	Experimentalavx512f Store 512-bits of integer data from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm512_stream_pd⚠	Experimentalavx512f Store 512-bits (composed of 8 packed double-precision (64-bit) floating-point elements) from a into memory using a non-temporal memory hint. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_stream_ps⚠	Experimentalavx512f Store 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from a into memory using a non-temporal memory hint. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_stream_si512⚠	Experimentalavx512f Store 512-bits of integer data from a into memory using a non-temporal memory hint. mem_addr must be aligned on a 64-byte boundary or a general-protection exception may be generated.
_mm512_sub_epi32⚠	Experimentalavx512f Subtract packed 32-bit integers in b from packed 32-bit integers in a, and store the results in dst.
_mm512_sub_epi64⚠	Experimentalavx512f Subtract packed 64-bit integers in b from packed 64-bit integers in a, and store the results in dst.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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 if the intermediate value is non-zero.
_mm512_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 if the intermediate value is non-zero.
_mm512_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 if the intermediate value is zero.
_mm512_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 if the intermediate value is zero.
_mm512_undefined⚠	Experimentalavx512f Return vector of type __m512 with undefined elements.
_mm512_undefined_epi32⚠	Experimentalavx512f Return vector of type __m512i with undefined elements.
_mm512_undefined_pd⚠	Experimentalavx512f Returns vector of type __m512d with undefined elements.
_mm512_undefined_ps⚠	Experimentalavx512f Returns vector of type __m512 with undefined elements.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_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.
_mm512_xor_epi32⚠	Experimentalavx512f Compute the bitwise XOR of packed 32-bit integers in a and b, and store the results in dst.
_mm512_xor_epi64⚠	Experimentalavx512f Compute the bitwise XOR of packed 64-bit integers in a and b, and store the results in dst.
_mm512_xor_si512⚠	Experimentalavx512f Compute the bitwise XOR of 512 bits (representing integer data) in a and b, and store the result in dst.
_mm512_zextpd128_pd512⚠	Experimentalavx512f Cast vector of type __m128d to type __m512d; the upper 384 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextpd256_pd512⚠	Experimentalavx512f Cast vector of type __m256d to type __m512d; the upper 256 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextps128_ps512⚠	Experimentalavx512f Cast vector of type __m128 to type __m512; the upper 384 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextps256_ps512⚠	Experimentalavx512f Cast vector of type __m256 to type __m512; the upper 256 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextsi128_si512⚠	Experimentalavx512f Cast vector of type __m128i to type __m512i; the upper 384 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm512_zextsi256_si512⚠	Experimentalavx512f Cast vector of type __m256i to type __m512i; the upper 256 bits of the result are zeroed. This intrinsic is only used for compilation and does not generate any instructions, thus it has zero latency.
_mm_add_round_sd⚠	Experimentalavx512f Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_add_round_ss⚠	Experimentalavx512f Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cmp_round_sd_mask⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cmp_round_ss_mask⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cmp_sd_mask⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k.
_mm_cmp_ss_mask⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k.
_mm_comi_round_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and return the boolean result (0 or 1). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_comi_round_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and return the boolean result (0 or 1). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvt_roundi32_ss⚠	Experimentalavx512f Convert the signed 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvt_roundsd_i32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvt_roundsd_si32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvt_roundsd_ss⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvt_roundsd_u32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
_mm_cvt_roundsi32_ss⚠	Experimentalavx512f Convert the signed 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvt_roundss_i32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvt_roundss_sd⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvt_roundss_si32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvt_roundss_u32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
_mm_cvt_roundu32_ss⚠	Experimentalavx512f Convert the unsigned 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvti32_sd⚠	Experimentalavx512f Convert the signed 32-bit integer b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_cvti32_ss⚠	Experimentalavx512f Convert the signed 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvtph_ps⚠	Experimentalf16c Converts the 4 x 16-bit half-precision float values in the lowest 64-bit of the 128-bit vector a into 4 x 32-bit float values stored in a 128-bit wide vector.
_mm_cvtps_ph⚠	Experimentalf16c Converts the 4 x 32-bit float values in the 128-bit vector a into 4 x 16-bit half-precision float values stored in the lowest 64-bit of a 128-bit vector.
_mm_cvtsd_i32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvtsd_u32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
_mm_cvtss_i32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer, and store the result in dst.
_mm_cvtss_u32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer, and store the result in dst.
_mm_cvtt_roundsd_i32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundsd_si32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundsd_u32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundss_i32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundss_si32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvtt_roundss_u32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_cvttsd_i32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
_mm_cvttsd_u32⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst.
_mm_cvttss_i32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to a 32-bit integer with truncation, and store the result in dst.
_mm_cvttss_u32⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in a to an unsigned 32-bit integer with truncation, and store the result in dst.
_mm_cvtu32_sd⚠	Experimentalavx512f Convert the unsigned 32-bit integer b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_cvtu32_ss⚠	Experimentalavx512f Convert the unsigned 32-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_cvtu64_sd⚠	Experimentalavx512f Convert the unsigned 64-bit integer b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_cvtu64_ss⚠	Experimentalavx512f Convert the unsigned 64-bit integer b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_div_round_sd⚠	Experimentalavx512f Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_div_round_ss⚠	Experimentalavx512f Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_fixupimm_round_sd⚠	Experimentalavx512f Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_fixupimm_round_ss⚠	Experimentalavx512f Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_fixupimm_sd⚠	Experimentalavx512f Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_fixupimm_ss⚠	Experimentalavx512f Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_fmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_fmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_fmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_fmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_fnmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_fnmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_fnmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_fnmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, subtract the lower element in c from the negated intermediate result, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_getexp_round_sd⚠	Experimentalavx512f Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getexp_round_ss⚠	Experimentalavx512f Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getexp_sd⚠	Experimentalavx512f Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_getexp_ss⚠	Experimentalavx512f Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_getmant_round_sd⚠	Experimentalavx512f Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getmant_round_ss⚠	Experimentalavx512f Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getmant_sd⚠	Experimentalavx512f Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_getmant_ss⚠	Experimentalavx512f Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_madd52hi_epu64⚠	Experimentalavx512ifma,avx512vl Multiply packed unsigned 52-bit integers in each 64-bit element of b and c to form a 104-bit intermediate result. Add the high 52-bit unsigned integer from the intermediate result with the corresponding unsigned 64-bit integer in a, and store the results in dst.
_mm_madd52lo_epu64⚠	Experimentalavx512ifma,avx512vl Multiply packed unsigned 52-bit integers in each 64-bit element of b and c to form a 104-bit intermediate result. Add the low 52-bit unsigned integer from the intermediate result with the corresponding unsigned 64-bit integer in a, and store the results in dst.
_mm_mask3_fmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fmadd_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fmadd_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fmsub_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fmsub_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fnmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fnmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fnmadd_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fnmadd_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fnmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fnmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask3_fnmsub_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from c to the upper element of dst.
_mm_mask3_fnmsub_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from c to the upper elements of dst.
_mm_mask_add_round_sd⚠	Experimentalavx512f Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_add_round_ss⚠	Experimentalavx512f Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_add_sd⚠	Experimentalavx512f Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_add_ss⚠	Experimentalavx512f Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_cmp_round_sd_mask⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not set). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_cmp_round_ss_mask⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not seti). Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_cmp_sd_mask⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not set).
_mm_mask_cmp_ss_mask⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, and store the result in mask vector k using zeromask k1 (the element is zeroed out when mask bit 0 is not set).
_mm_mask_cvt_roundsd_ss⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_cvt_roundss_sd⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_cvtsd_ss⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_cvtss_sd⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_div_round_sd⚠	Experimentalavx512f Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_div_round_ss⚠	Experimentalavx512f Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_div_sd⚠	Experimentalavx512f Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_div_ss⚠	Experimentalavx512f Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fixupimm_round_sd⚠	Experimentalavx512f Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_mask_fixupimm_round_ss⚠	Experimentalavx512f Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_mask_fixupimm_sd⚠	Experimentalavx512f Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_mask_fixupimm_ss⚠	Experimentalavx512f Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_mask_fmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fmadd_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fmadd_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fmsub_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fmsub_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fnmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fnmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fnmadd_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fnmadd_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using writemask k (the element is copied from a when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fnmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fnmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_fnmsub_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_fnmsub_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using writemask k (the element is copied from c when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_getexp_round_sd⚠	Experimentalavx512f Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getexp_round_ss⚠	Experimentalavx512f Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getexp_sd⚠	Experimentalavx512f Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_mask_getexp_ss⚠	Experimentalavx512f Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_mask_getmant_round_sd⚠	Experimentalavx512f Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getmant_round_ss⚠	Experimentalavx512f Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getmant_sd⚠	Experimentalavx512f Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_getmant_ss⚠	Experimentalavx512f Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_max_round_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_max_round_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_max_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_max_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_min_round_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_min_round_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mask_min_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_min_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_move_sd⚠	Experimentalavx512f Move the lower double-precision (64-bit) floating-point element from b to the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_move_ss⚠	Experimentalavx512f Move the lower single-precision (32-bit) floating-point element from b to the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_mul_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_mul_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_mul_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_mul_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_rcp14_sd⚠	Experimentalavx512f Compute the approximate reciprocal of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rcp14_ss⚠	Experimentalavx512f Compute the approximate reciprocal of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_roundscale_round_sd⚠	Experimentalavx512f Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_mask_roundscale_round_ss⚠	Experimentalavx512f Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_mask_roundscale_sd⚠	Experimentalavx512f Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_mask_roundscale_ss⚠	Experimentalavx512f Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_mask_rsqrt14_sd⚠	Experimentalavx512f Compute the approximate reciprocal square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_rsqrt14_ss⚠	Experimentalavx512f Compute the approximate reciprocal square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_mask_scalef_round_sd⚠	Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_scalef_round_ss⚠	Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_scalef_sd⚠	Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_scalef_ss⚠	Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_sqrt_round_sd⚠	Experimentalavx512f Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_sqrt_round_ss⚠	Experimentalavx512f Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_sqrt_sd⚠	Experimentalavx512f Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_sqrt_ss⚠	Experimentalavx512f Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_sub_round_sd⚠	Experimentalavx512f Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_sub_round_ss⚠	Experimentalavx512f Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_mask_sub_sd⚠	Experimentalavx512f Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_mask_sub_ss⚠	Experimentalavx512f Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using writemask k (the element is copied from src when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_add_round_sd⚠	Experimentalavx512f Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_add_round_ss⚠	Experimentalavx512f Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_add_sd⚠	Experimentalavx512f Add the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_add_ss⚠	Experimentalavx512f Add the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_cvt_roundsd_ss⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_cvt_roundss_sd⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_cvtsd_ss⚠	Experimentalavx512f Convert the lower double-precision (64-bit) floating-point element in b to a single-precision (32-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_cvtss_sd⚠	Experimentalavx512f Convert the lower single-precision (32-bit) floating-point element in b to a double-precision (64-bit) floating-point element, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_div_round_sd⚠	Experimentalavx512f Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_div_round_ss⚠	Experimentalavx512f Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_div_sd⚠	Experimentalavx512f Divide the lower double-precision (64-bit) floating-point element in a by the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_div_ss⚠	Experimentalavx512f Divide the lower single-precision (32-bit) floating-point element in a by the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fixupimm_round_sd⚠	Experimentalavx512f Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_maskz_fixupimm_round_ss⚠	Experimentalavx512f Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_maskz_fixupimm_sd⚠	Experimentalavx512f Fix up the lower double-precision (64-bit) floating-point elements in a and b using the lower 64-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. imm8 is used to set the required flags reporting.
_mm_maskz_fixupimm_ss⚠	Experimentalavx512f Fix up the lower single-precision (32-bit) floating-point elements in a and b using the lower 32-bit integer in c, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. imm8 is used to set the required flags reporting.
_mm_maskz_fmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fmadd_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fmadd_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fmsub_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fmsub_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fnmadd_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fnmadd_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fnmadd_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fnmadd_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to the lower element in c. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fnmsub_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fnmsub_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_fnmsub_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_fnmsub_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point elements in a and b, and subtract the lower element in c from the negated intermediate result. Store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_getexp_round_sd⚠	Experimentalavx512f Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getexp_round_ss⚠	Experimentalavx512f Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getexp_sd⚠	Experimentalavx512f Convert the exponent of the lower double-precision (64-bit) floating-point element in b to a double-precision (64-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_maskz_getexp_ss⚠	Experimentalavx512f Convert the exponent of the lower single-precision (32-bit) floating-point element in b to a single-precision (32-bit) floating-point number representing the integer exponent, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. This intrinsic essentially calculates floor(log2(x)) for the lower element.
_mm_maskz_getmant_round_sd⚠	Experimentalavx512f Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getmant_round_ss⚠	Experimentalavx512f Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getmant_sd⚠	Experimentalavx512f Normalize the mantissas of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_getmant_ss⚠	Experimentalavx512f Normalize the mantissas of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of 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 Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_max_round_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_max_round_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_max_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_max_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_min_round_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_min_round_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_maskz_min_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_min_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_move_sd⚠	Experimentalavx512f Move the lower double-precision (64-bit) floating-point element from b to the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_move_ss⚠	Experimentalavx512f Move the lower single-precision (32-bit) floating-point element from b to the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_mul_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_mul_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_mul_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_mul_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_rcp14_sd⚠	Experimentalavx512f Compute the approximate reciprocal of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rcp14_ss⚠	Experimentalavx512f Compute the approximate reciprocal of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_roundscale_round_sd⚠	Experimentalavx512f Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_maskz_roundscale_round_ss⚠	Experimentalavx512f Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_maskz_roundscale_sd⚠	Experimentalavx512f Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_maskz_roundscale_ss⚠	Experimentalavx512f Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_maskz_rsqrt14_sd⚠	Experimentalavx512f Compute the approximate reciprocal square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_rsqrt14_ss⚠	Experimentalavx512f Compute the approximate reciprocal square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_maskz_scalef_round_sd⚠	Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_scalef_round_ss⚠	Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_scalef_sd⚠	Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_scalef_ss⚠	Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_sqrt_round_sd⚠	Experimentalavx512f Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_sqrt_round_ss⚠	Experimentalavx512f Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_sqrt_sd⚠	Experimentalavx512f Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_sqrt_ss⚠	Experimentalavx512f Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_sub_round_sd⚠	Experimentalavx512f Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_sub_round_ss⚠	Experimentalavx512f Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_maskz_sub_sd⚠	Experimentalavx512f Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper element from a to the upper element of dst.
_mm_maskz_sub_ss⚠	Experimentalavx512f Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_max_round_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the maximum value in the lower element of dst, and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_max_round_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the maximum value in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_min_round_sd⚠	Experimentalavx512f Compare the lower double-precision (64-bit) floating-point elements in a and b, store the minimum value in the lower element of dst , and copy the upper element from a to the upper element of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_min_round_ss⚠	Experimentalavx512f Compare the lower single-precision (32-bit) floating-point elements in a and b, store the minimum value in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. Exceptions can be suppressed by passing _MM_FROUND_NO_EXC in the sae parameter.
_mm_mul_round_sd⚠	Experimentalavx512f Multiply the lower double-precision (64-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_mul_round_ss⚠	Experimentalavx512f Multiply the lower single-precision (32-bit) floating-point element in a and b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_rcp14_sd⚠	Experimentalavx512f Compute the approximate reciprocal of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rcp14_ss⚠	Experimentalavx512f Compute the approximate reciprocal of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_roundscale_round_sd⚠	Experimentalavx512f Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_roundscale_round_ss⚠	Experimentalavx512f Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_roundscale_sd⚠	Experimentalavx512f Round the lower double-precision (64-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_roundscale_ss⚠	Experimentalavx512f Round the lower single-precision (32-bit) floating-point element in b to the number of fraction bits specified by imm8, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. Rounding is done according to the imm8[2:0] parameter, which can be one of: _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_CUR_DIRECTION // use MXCSR.RC; see _MM_SET_ROUNDING_MODE
_mm_rsqrt14_sd⚠	Experimentalavx512f Compute the approximate reciprocal square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_rsqrt14_ss⚠	Experimentalavx512f Compute the approximate reciprocal square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst. The maximum relative error for this approximation is less than 2^-14.
_mm_scalef_round_sd⚠	Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_scalef_round_ss⚠	Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_scalef_sd⚠	Experimentalavx512f Scale the packed double-precision (64-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_scalef_ss⚠	Experimentalavx512f Scale the packed single-precision (32-bit) floating-point elements in a using values from b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_sqrt_round_sd⚠	Experimentalavx512f Compute the square root of the lower double-precision (64-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_sqrt_round_ss⚠	Experimentalavx512f Compute the square root of the lower single-precision (32-bit) floating-point element in b, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_mm_sub_round_sd⚠	Experimentalavx512f Subtract the lower double-precision (64-bit) floating-point element in b from the lower double-precision (64-bit) floating-point element in a, store the result in the lower element of dst, and copy the upper element from a to the upper element of dst.
_mm_sub_round_ss⚠	Experimentalavx512f Subtract the lower single-precision (32-bit) floating-point element in b from the lower single-precision (32-bit) floating-point element in a, store the result in the lower element of dst, and copy the upper 3 packed elements from a to the upper elements of dst.
_xabort⚠	Experimentalrtm Forces a restricted transactional memory (RTM) region to abort.
_xabort_code	Experimental Retrieves the parameter passed to _xabort when _xbegin's status has the _XABORT_EXPLICIT flag set.
_xbegin⚠	Experimentalrtm Specifies the start of a restricted transactional memory (RTM) code region and returns a value indicating status.
_xend⚠	Experimentalrtm Specifies the end of a restricted transactional memory (RTM) code region.
_xtest⚠	Experimentalrtm Queries whether the processor is executing in a transactional region identified by restricted transactional memory (RTM) or hardware lock elision (HLE).
cmpxchg16b⚠	Experimentalcmpxchg16b Compares and exchange 16 bytes (128 bits) of data atomically.
has_cpuid	Experimental Does the host support the cpuid instruction?
ud2⚠	Experimental Generates the trap instruction UD2
_MM_GET_EXCEPTION_MASK⚠	sse See _mm_setcsr
_MM_GET_EXCEPTION_STATE⚠	sse See _mm_setcsr
_MM_GET_FLUSH_ZERO_MODE⚠	sse See _mm_setcsr
_MM_GET_ROUNDING_MODE⚠	sse See _mm_setcsr
_MM_SET_EXCEPTION_MASK⚠	sse See _mm_setcsr
_MM_SET_EXCEPTION_STATE⚠	sse See _mm_setcsr
_MM_SET_FLUSH_ZERO_MODE⚠	sse See _mm_setcsr
_MM_SET_ROUNDING_MODE⚠	sse See _mm_setcsr
_MM_TRANSPOSE4_PS⚠	sse Transpose the 4x4 matrix formed by 4 rows of __m128 in place.
__cpuid⚠	See __cpuid_count.
__cpuid_count⚠	Returns the result of the cpuid instruction for a given leaf (EAX) and sub_leaf (ECX).
__get_cpuid_max⚠	Returns the highest-supported leaf (EAX) and sub-leaf (ECX) cpuid values.
__rdtscp⚠	Reads the current value of the processor’s time-stamp counter and the IA32_TSC_AUX MSR.
_addcarry_u32⚠	Adds unsigned 32-bit integers a and b with unsigned 8-bit carry-in c_in (carry flag), and store the unsigned 32-bit result in out, and the carry-out is returned (carry or overflow flag).
_addcarry_u64⚠	Adds unsigned 64-bit integers a and b with unsigned 8-bit carry-in c_in (carry flag), and store the unsigned 64-bit result in out, and the carry-out is returned (carry or overflow flag).
_addcarryx_u32⚠	adx Adds unsigned 32-bit integers a and b with unsigned 8-bit carry-in c_in (carry or overflow flag), and store the unsigned 32-bit result in out, and the carry-out is returned (carry or overflow flag).
_addcarryx_u64⚠	adx Adds unsigned 64-bit integers a and b with unsigned 8-bit carry-in c_in (carry or overflow flag), and store the unsigned 64-bit result in out, and the carry-out is returned (carry or overflow flag).
_andn_u32⚠	bmi1 Bitwise logical AND of inverted a with b.
_andn_u64⚠	bmi1 Bitwise logical AND of inverted a with b.
_bextr2_u32⚠	bmi1 Extracts bits of a specified by control into the least significant bits of the result.
_bextr2_u64⚠	bmi1 Extracts bits of a specified by control into the least significant bits of the result.
_bextr_u32⚠	bmi1 Extracts bits in range [start, start + length) from a into the least significant bits of the result.
_bextr_u64⚠	bmi1 Extracts bits in range [start, start + length) from a into the least significant bits of the result.
_blcfill_u32⚠	tbm Clears all bits below the least significant zero bit of x.
_blcfill_u64⚠	tbm Clears all bits below the least significant zero bit of x.
_blci_u32⚠	tbm Sets all bits of x to 1 except for the least significant zero bit.
_blci_u64⚠	tbm Sets all bits of x to 1 except for the least significant zero bit.
_blcic_u32⚠	tbm Sets the least significant zero bit of x and clears all other bits.
_blcic_u64⚠	tbm Sets the least significant zero bit of x and clears all other bits.
_blcmsk_u32⚠	tbm Sets the least significant zero bit of x and clears all bits above that bit.
_blcmsk_u64⚠	tbm Sets the least significant zero bit of x and clears all bits above that bit.
_blcs_u32⚠	tbm Sets the least significant zero bit of x.
_blcs_u64⚠	tbm Sets the least significant zero bit of x.
_blsfill_u32⚠	tbm Sets all bits of x below the least significant one.
_blsfill_u64⚠	tbm Sets all bits of x below the least significant one.
_blsi_u32⚠	bmi1 Extracts lowest set isolated bit.
_blsi_u64⚠	bmi1 Extracts lowest set isolated bit.
_blsic_u32⚠	tbm Clears least significant bit and sets all other bits.
_blsic_u64⚠	tbm Clears least significant bit and sets all other bits.
_blsmsk_u32⚠	bmi1 Gets mask up to lowest set bit.
_blsmsk_u64⚠	bmi1 Gets mask up to lowest set bit.
_blsr_u32⚠	bmi1 Resets the lowest set bit of x.
_blsr_u64⚠	bmi1 Resets the lowest set bit of x.
_bswap⚠	Returns an integer with the reversed byte order of x
_bswap64⚠	Returns an integer with the reversed byte order of x
_bzhi_u32⚠	bmi2 Zeroes higher bits of a >= index.
_bzhi_u64⚠	bmi2 Zeroes higher bits of a >= index.
_fxrstor⚠	fxsr Restores the XMM, MMX, MXCSR, and x87 FPU registers from the 512-byte-long 16-byte-aligned memory region mem_addr.
_fxrstor64⚠	fxsr Restores the XMM, MMX, MXCSR, and x87 FPU registers from the 512-byte-long 16-byte-aligned memory region mem_addr.
_fxsave⚠	fxsr Saves the x87 FPU, MMX technology, XMM, and MXCSR registers to the 512-byte-long 16-byte-aligned memory region mem_addr.
_fxsave64⚠	fxsr Saves the x87 FPU, MMX technology, XMM, and MXCSR registers to the 512-byte-long 16-byte-aligned memory region mem_addr.
_lzcnt_u32⚠	lzcnt Counts the leading most significant zero bits.
_lzcnt_u64⚠	lzcnt Counts the leading most significant zero bits.
_mm256_abs_epi8⚠	avx2 Computes the absolute values of packed 8-bit integers in a.
_mm256_abs_epi16⚠	avx2 Computes the absolute values of packed 16-bit integers in a.
_mm256_abs_epi32⚠	avx2 Computes the absolute values of packed 32-bit integers in a.
_mm256_add_epi8⚠	avx2 Adds packed 8-bit integers in a and b.
_mm256_add_epi16⚠	avx2 Adds packed 16-bit integers in a and b.
_mm256_add_epi32⚠	avx2 Adds packed 32-bit integers in a and b.
_mm256_add_epi64⚠	avx2 Adds packed 64-bit integers in a and b.
_mm256_add_pd⚠	avx Adds packed double-precision (64-bit) floating-point elements in a and b.
_mm256_add_ps⚠	avx Adds packed single-precision (32-bit) floating-point elements in a and b.
_mm256_adds_epi8⚠	avx2 Adds packed 8-bit integers in a and b using saturation.
_mm256_adds_epi16⚠	avx2 Adds packed 16-bit integers in a and b using saturation.
_mm256_adds_epu8⚠	avx2 Adds packed unsigned 8-bit integers in a and b using saturation.
_mm256_adds_epu16⚠	avx2 Adds packed unsigned 16-bit integers in a and b using saturation.
_mm256_addsub_pd⚠	avx Alternatively adds and subtracts packed double-precision (64-bit) floating-point elements in a to/from packed elements in b.
_mm256_addsub_ps⚠	avx Alternatively adds and subtracts packed single-precision (32-bit) floating-point elements in a to/from packed elements in b.
_mm256_alignr_epi8⚠	avx2 Concatenates pairs of 16-byte blocks in a and b into a 32-byte temporary result, shifts the result right by n bytes, and returns the low 16 bytes.
_mm256_and_pd⚠	avx Computes the bitwise AND of a packed double-precision (64-bit) floating-point elements in a and b.
_mm256_and_ps⚠	avx Computes the bitwise AND of packed single-precision (32-bit) floating-point elements in a and b.
_mm256_and_si256⚠	avx2 Computes the bitwise AND of 256 bits (representing integer data) in a and b.
_mm256_andnot_pd⚠	avx Computes the bitwise NOT of packed double-precision (64-bit) floating-point elements in a, and then AND with b.
_mm256_andnot_ps⚠	avx Computes the bitwise NOT of packed single-precision (32-bit) floating-point elements in a and then AND with b.
_mm256_andnot_si256⚠	avx2 Computes the bitwise NOT of 256 bits (representing integer data) in a and then AND with b.
_mm256_avg_epu8⚠	avx2 Averages packed unsigned 8-bit integers in a and b.
_mm256_avg_epu16⚠	avx2 Averages packed unsigned 16-bit integers in a and b.
_mm256_blend_epi16⚠	avx2 Blends packed 16-bit integers from a and b using control mask imm8.
_mm256_blend_epi32⚠	avx2 Blends packed 32-bit integers from a and b using control mask imm8.
_mm256_blend_pd⚠	avx Blends packed double-precision (64-bit) floating-point elements from a and b using control mask imm8.
_mm256_blend_ps⚠	avx Blends packed single-precision (32-bit) floating-point elements from a and b using control mask imm8.
_mm256_blendv_epi8⚠	avx2 Blends packed 8-bit integers from a and b using mask.
_mm256_blendv_pd⚠	avx Blends packed double-precision (64-bit) floating-point elements from a and b using c as a mask.
_mm256_blendv_ps⚠	avx Blends packed single-precision (32-bit) floating-point elements from a and b using c as a mask.
_mm256_broadcast_pd⚠	avx Broadcasts 128 bits from memory (composed of 2 packed double-precision (64-bit) floating-point elements) to all elements of the returned vector.
_mm256_broadcast_ps⚠	avx Broadcasts 128 bits from memory (composed of 4 packed single-precision (32-bit) floating-point elements) to all elements of the returned vector.
_mm256_broadcast_sd⚠	avx Broadcasts a double-precision (64-bit) floating-point element from memory to all elements of the returned vector.
_mm256_broadcast_ss⚠	avx Broadcasts a single-precision (32-bit) floating-point element from memory to all elements of the returned vector.
_mm256_broadcastb_epi8⚠	avx2 Broadcasts the low packed 8-bit integer from a to all elements of the 256-bit returned value.
_mm256_broadcastd_epi32⚠	avx2 Broadcasts the low packed 32-bit integer from a to all elements of the 256-bit returned value.
_mm256_broadcastq_epi64⚠	avx2 Broadcasts the low packed 64-bit integer from a to all elements of the 256-bit returned value.
_mm256_broadcastsd_pd⚠	avx2 Broadcasts the low double-precision (64-bit) floating-point element from a to all elements of the 256-bit returned value.
_mm256_broadcastsi128_si256⚠	avx2 Broadcasts 128 bits of integer data from a to all 128-bit lanes in the 256-bit returned value.
_mm256_broadcastss_ps⚠	avx2 Broadcasts the low single-precision (32-bit) floating-point element from a to all elements of the 256-bit returned value.
_mm256_broadcastw_epi16⚠	avx2 Broadcasts the low packed 16-bit integer from a to all elements of the 256-bit returned value
_mm256_bslli_epi128⚠	avx2 Shifts 128-bit lanes in a left by imm8 bytes while shifting in zeros.
_mm256_bsrli_epi128⚠	avx2 Shifts 128-bit lanes in a right by imm8 bytes while shifting in zeros.
_mm256_castpd128_pd256⚠	avx Casts vector of type __m128d to type __m256d; the upper 128 bits of the result are undefined.
_mm256_castpd256_pd128⚠	avx Casts vector of type __m256d to type __m128d.
_mm256_castpd_ps⚠	avx Cast vector of type __m256d to type __m256.
_mm256_castpd_si256⚠	avx Casts vector of type __m256d to type __m256i.
_mm256_castps128_ps256⚠	avx Casts vector of type __m128 to type __m256; the upper 128 bits of the result are undefined.
_mm256_castps256_ps128⚠