Module core::arch::x86

This is supported on x86 only.

Platform-specific intrinsics for the x86 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.
_bittestandcomplement⚠	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.
_bittestandset⚠	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_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 op.
_mm512_cmp_epi64_mask⚠	Experimentalavx512f Compare packed signed 64-bit integers in a and b based on the comparison operand specified by op.
_mm512_cmp_epu32_mask⚠	Experimentalavx512f Compare packed unsigned 32-bit integers in a and b based on the comparison operand specified by op.
_mm512_cmp_epu64_mask⚠	Experimentalavx512f Compare packed unsigned 64-bit integers in a and b based on the comparison operand specified by op.
_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 op.
_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 op.
_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 op.
_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 op.
_mm512_cmpeq_epi32_mask⚠	Experimentalavx512f Compare packed signed 32-bit integers in a and b for equality, and store the results in a mask vector.
_mm512_cmpeq_epi64_mask⚠	Experimentalavx512f Compare packed signed 64-bit integers in a and b for equality, and store the results in a mask vector.
_mm512_cmpeq_epu32_mask⚠	Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for equality, and store the results in a mask vector.
_mm512_cmpeq_epu64_mask⚠	Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for equality, and store the results in a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_mm512_cmpgt_epi32_mask⚠	Experimentalavx512f Compare packed signed 32-bit integers in a and b for greater-than, and store the results in a mask vector.
_mm512_cmpgt_epi64_mask⚠	Experimentalavx512f Compare packed signed 64-bit integers in a and b for greater-than, and store the results in a mask vector.
_mm512_cmpgt_epu32_mask⚠	Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for greater-than, and store the results in a mask vector.
_mm512_cmpgt_epu64_mask⚠	Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for greater-than, and store the results in a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_mm512_cmplt_epi32_mask⚠	Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in a mask vector.
_mm512_cmplt_epi64_mask⚠	Experimentalavx512f Compare packed signed 64-bit integers in a and b for less-than, and store the results in a mask vector.
_mm512_cmplt_epu32_mask⚠	Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in a mask vector.
_mm512_cmplt_epu64_mask⚠	Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for less-than, and store the results in a mask vector.
_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 a mask vector.
_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 a mask vector.
_mm512_cmpneq_epi32_mask⚠	Experimentalavx512f Compare packed signed 32-bit integers in a and b for inequality, and store the results in a mask vector.
_mm512_cmpneq_epi64_mask⚠	Experimentalavx512f Compare packed signed 64-bit integers in a and b for inequality, and store the results in a mask vector.
_mm512_cmpneq_epu32_mask⚠	Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for inequality, and store the results in a mask vector.
_mm512_cmpneq_epu64_mask⚠	Experimentalavx512f Compare packed unsigned 64-bit integers in a and b for inequality, and store the results in a mask vector.
_mm512_cmpneq_pd_mask⚠	Experimentalavx512f Compare packed double-precision (64-bit) floating-point elements in a and b for inequality, and store the results in a mask vector.
_mm512_cmpneq_ps_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for inequality, and store the results in a mask vector.
_mm512_cmpnle_pd_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for greater-than, and store the results in a mask vector.
_mm512_cmpnle_ps_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for greater-than, and store the results in a mask vector.
_mm512_cmpnlt_pd_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for greater-than, and store the results in a mask vector.
_mm512_cmpnlt_ps_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for greater-than, and store the results in a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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_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_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_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_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.
_mm512_i32gather_epi64⚠	Experimentalavx512f Gather 64-bit integers from memory using 32-bit indices.
_mm512_i32gather_pd⚠	Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 32-bit indices.
_mm512_i32gather_ps⚠	Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 32-bit indices.
_mm512_i32scatter_epi32⚠	Experimentalavx512f Scatter 32-bit integers from src into memory using 32-bit indices.
_mm512_i32scatter_epi64⚠	Experimentalavx512f Scatter 64-bit integers from src into memory using 32-bit indices.
_mm512_i32scatter_pd⚠	Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from memory using 32-bit indices.
_mm512_i32scatter_ps⚠	Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from memory using 32-bit indices.
_mm512_i64gather_epi32⚠	Experimentalavx512f Gather 32-bit integers from memory using 64-bit indices.
_mm512_i64gather_epi64⚠	Experimentalavx512f Gather 64-bit integers from memory using 64-bit indices.
_mm512_i64gather_pd⚠	Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 64-bit indices.
_mm512_i64gather_ps⚠	Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 64-bit indices.
_mm512_i64scatter_epi32⚠	Experimentalavx512f Scatter 32-bit integers from src into memory using 64-bit indices.
_mm512_i64scatter_epi64⚠	Experimentalavx512f Scatter 64-bit integers from src into memory using 64-bit indices.
_mm512_i64scatter_pd⚠	Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from src into memory using 64-bit indices.
_mm512_i64scatter_ps⚠	Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from src into memory using 64-bit indices.
_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_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_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_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_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_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_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 op, using zeromask m (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 op, using zeromask m (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 op, using zeromask m (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 op, using zeromask m (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 op, using zeromask m (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 op, using zeromask m (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 op, using zeromask m (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmp_round_ps_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by op, using zeromask m (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpeq_epi32_mask⚠	Experimentalavx512f Compare packed signed 32-bit integers in a and b for equality, and store the results in a mask vector k using zeromask m (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpeq_epi64_mask⚠	Experimentalavx512f Compare packed signed 64-bit integers in a and b for equality, and store the results in a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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-or-equal, and store the results in a mask vector k using zeromask m (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 a mask vector k using zeromask m (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-or-equal, and store the results in a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmplt_epi32_mask⚠	Experimentalavx512f Compare packed unsigned 32-bit integers in a and b for less-than, and store the results in a mask vector k using zeromask m (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 a mask vector k using zeromask m (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, and store the results in a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (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 a mask vector k using zeromask m (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpneq_epi32_mask⚠	Experimentalavx512f Compare packed signed 32-bit integers in a and b for inequality, and store the results in a mask vector k using zeromask m (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 inequality, and store the results in a mask vector k using zeromask m (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 inequality, and store the results in a mask vector k using zeromask m (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 inequality, and store the results in a mask vector k using zeromask m (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 inequality, and store the results in a mask vector k using zeromask m (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 inequality, and store the results in a mask vector k using zeromask m (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpnle_pd_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for greater-than, and store the results in a mask vector k using zeromask m (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 greater-than, and store the results in a mask vector k using zeromask m (elements are zeroed out when the corresponding mask bit is not set).
_mm512_mask_cmpnlt_pd_mask⚠	Experimentalavx512f Compare packed single-precision (32-bit) floating-point elements in a and b for greater-than, and store the results in a mask vector k using zeromask m (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 greater-than, and store the results in a mask vector k using zeromask m (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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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 a mask vector.
_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_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_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_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_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.
_mm512_mask_i32gather_epi64⚠	Experimentalavx512f Gather 64-bit integers from memory using 32-bit indices.
_mm512_mask_i32gather_pd⚠	Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 32-bit indices.
_mm512_mask_i32gather_ps⚠	Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 32-bit indices.
_mm512_mask_i32scatter_epi32⚠	Experimentalavx512f Scatter 32-bit integers from src into memory using 32-bit indices.
_mm512_mask_i32scatter_epi64⚠	Experimentalavx512f Scatter 64-bit integers from src into memory using 32-bit indices.
_mm512_mask_i32scatter_pd⚠	Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from src into memory using 32-bit indices.
_mm512_mask_i32scatter_ps⚠	Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from src into memory using 32-bit indices.
_mm512_mask_i64gather_epi32⚠	Experimentalavx512f Gather 32-bit integers from memory using 64-bit indices.
_mm512_mask_i64gather_epi64⚠	Experimentalavx512f Gather 64-bit integers from memory using 64-bit indices.
_mm512_mask_i64gather_pd⚠	Experimentalavx512f Gather double-precision (64-bit) floating-point elements from memory using 64-bit indices.
_mm512_mask_i64gather_ps⚠	Experimentalavx512f Gather single-precision (32-bit) floating-point elements from memory using 64-bit indices.
_mm512_mask_i64scatter_epi32⚠	Experimentalavx512f Scatter 32-bit integers from src into memory using 64-bit indices.
_mm512_mask_i64scatter_epi64⚠	Experimentalavx512f Scatter 64-bit integers from src into memory using 64-bit indices.
_mm512_mask_i64scatter_pd⚠	Experimentalavx512f Scatter double-precision (64-bit) floating-point elements from src into memory using 64-bit indices.
_mm512_mask_i64scatter_ps⚠	Experimentalavx512f Scatter single-precision (32-bit) floating-point elements from src into memory using 64-bit indices.
_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_set_epi32⚠	Experimentalavx512f Sets packed 32-bit integers in dst with the supplied values.
_mm512_set_pd⚠	Experimentalavx512f Sets packed 64-bit integers in dst with the supplied values.
_mm512_set_ps⚠	Experimentalavx512f Sets packed 32-bit integers in dst with the supplied values.
_mm512_setr_epi32⚠	Experimentalavx512f Sets packed 32-bit integers in dst with the supplied values in reverse order.
_mm512_setr_pd⚠	Experimentalavx512f Sets packed 64-bit integers 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_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_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_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_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.
_mm_cmp_round_sd_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 a mask vector.
_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 a mask vector.
_mm_cmp_sd_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 a mask vector.
_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 a mask vector.
_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_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_mask_cmp_round_sd_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 a mask vector using zeromask m (the element is zeroed out when mask bit 0 is not set).
_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 a mask vector using zeromask m (the element is zeroed out when mask bit 0 is not set).
_mm_mask_cmp_sd_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 a mask vector using zeromask m (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 a mask vector using zeromask m (the element is zeroed out when mask bit 0 is not set).
_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).
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).
_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).
_andn_u32⚠	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.
_bextr_u32⚠	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.
_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.
_blsr_u32⚠	bmi1 Resets the lowest set bit of x.
_bswap⚠	Returns an integer with the reversed byte order of x
_bzhi_u32⚠	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.
_fxsave⚠	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.
_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⚠	avx Casts vector of type __m256 to type __m128.
_mm256_castps_pd⚠	avx Cast vector of type __m256 to type __m256d.
_mm256_castps_si256⚠	avx Casts vector of type __m256 to type __m256i.
_mm256_castsi128_si256⚠	avx Casts vector of type __m128i to type __m256i; the upper 128 bits of the result are undefined.
_mm256_castsi256_pd⚠	avx Casts vector of type __m256i to type __m256d.
_mm256_castsi256_ps⚠	avx Casts vector of type __m256i to type __m256.
_mm256_castsi256_si128⚠	avx Casts vector of type __m256i to type __m128i.
_mm256_ceil_pd⚠	avx Rounds packed double-precision (64-bit) floating point elements in a toward positive infinity.
_mm256_ceil_ps⚠	avx Rounds packed single-precision (32-bit) floating point elements in a toward positive infinity.
_mm256_cmp_pd⚠	avx Compares packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8.
_mm256_cmp_ps⚠	avx Compares packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8.
_mm256_cmpeq_epi8⚠	avx2 Compares packed 8-bit integers in a and b for equality.
_mm256_cmpeq_epi16⚠	avx2 Compares packed 16-bit integers in a and b for equality.
_mm256_cmpeq_epi32⚠	avx2 Compares packed 32-bit integers in a and b for equality.
_mm256_cmpeq_epi64⚠	avx2 Compares packed 64-bit integers in a and b for equality.
_mm256_cmpgt_epi8⚠	avx2 Compares packed 8-bit integers in a and b for greater-than.
_mm256_cmpgt_epi16⚠	avx2 Compares packed 16-bit integers in a and b for greater-than.
_mm256_cmpgt_epi32⚠	avx2 Compares packed 32-bit integers in a and b for greater-than.
_mm256_cmpgt_epi64⚠	avx2 Compares packed 64-bit integers in a and b for greater-than.
_mm256_cvtepi8_epi16⚠	avx2 Sign-extend 8-bit integers to 16-bit integers.
_mm256_cvtepi8_epi32⚠	avx2 Sign-extend 8-bit integers to 32-bit integers.
_mm256_cvtepi8_epi64⚠	avx2 Sign-extend 8-bit integers to 64-bit integers.
_mm256_cvtepi16_epi32⚠	avx2 Sign-extend 16-bit integers to 32-bit integers.
_mm256_cvtepi16_epi64⚠	avx2 Sign-extend 16-bit integers to 64-bit integers.
_mm256_cvtepi32_epi64⚠	avx2 Sign-extend 32-bit integers to 64-bit integers.
_mm256_cvtepi32_pd⚠	avx Converts packed 32-bit integers in a to packed double-precision (64-bit) floating-point elements.
_mm256_cvtepi32_ps⚠	avx Converts packed 32-bit integers in a to packed single-precision (32-bit) floating-point elements.
_mm256_cvtepu8_epi16⚠	avx2 Zero-extend unsigned 8-bit integers in a to 16-bit integers.
_mm256_cvtepu8_epi32⚠	avx2 Zero-extend the lower eight unsigned 8-bit integers in a to 32-bit integers. The upper eight elements of a are unused.
_mm256_cvtepu8_epi64⚠	avx2 Zero-extend the lower four unsigned 8-bit integers in a to 64-bit integers. The upper twelve elements of a are unused.
_mm256_cvtepu16_epi32⚠	avx2 Zeroes extend packed unsigned 16-bit integers in a to packed 32-bit integers, and stores the results in dst.
_mm256_cvtepu16_epi64⚠	avx2 Zero-extend the lower four unsigned 16-bit integers in a to 64-bit integers. The upper four elements of a are unused.
_mm256_cvtepu32_epi64⚠	avx2 Zero-extend unsigned 32-bit integers in a to 64-bit integers.
_mm256_cvtpd_epi32⚠	avx Converts packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers.
_mm256_cvtpd_ps⚠	avx Converts packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements.
_mm256_cvtps_epi32⚠	avx Converts packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers.
_mm256_cvtps_pd⚠	avx Converts packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements.
_mm256_cvtsd_f64⚠	avx2 Returns the first element of the input vector of [4 x double].
_mm256_cvtsi256_si32⚠	avx2 Returns the first element of the input vector of [8 x i32].
_mm256_cvtss_f32⚠	avx Returns the first element of the input vector of [8 x float].
_mm256_cvttpd_epi32⚠	avx Converts packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation.
_mm256_cvttps_epi32⚠	avx Converts packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation.
_mm256_div_pd⚠	avx Computes the division of each of the 4 packed 64-bit floating-point elements in a by the corresponding packed elements in b.
_mm256_div_ps⚠	avx Computes the division of each of the 8 packed 32-bit floating-point elements in a by the corresponding packed elements in b.
_mm256_dp_ps⚠	avx Conditionally multiplies the packed single-precision (32-bit) floating-point elements in a and b using the high 4 bits in imm8, sum the four products, and conditionally return the sum using the low 4 bits of imm8.
_mm256_extract_epi8⚠	avx2 Extracts an 8-bit integer from a, selected with imm8. Returns a 32-bit integer containing the zero-extended integer data.
_mm256_extract_epi16⚠	avx2 Extracts a 16-bit integer from a, selected with imm8. Returns a 32-bit integer containing the zero-extended integer data.
_mm256_extract_epi32⚠	avx2 Extracts a 32-bit integer from a, selected with imm8.
_mm256_extractf128_pd⚠	avx Extracts 128 bits (composed of 2 packed double-precision (64-bit) floating-point elements) from a, selected with imm8.
_mm256_extractf128_ps⚠	avx Extracts 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from a, selected with imm8.
_mm256_extractf128_si256⚠	avx Extracts 128 bits (composed of integer data) from a, selected with imm8.
_mm256_extracti128_si256⚠	avx2 Extracts 128 bits (of integer data) from a selected with imm8.
_mm256_floor_pd⚠	avx Rounds packed double-precision (64-bit) floating point elements in a toward negative infinity.
_mm256_floor_ps⚠	avx Rounds packed single-precision (32-bit) floating point elements in a toward negative infinity.
_mm256_fmadd_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to packed elements in c.
_mm256_fmadd_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to packed elements in c.
_mm256_fmaddsub_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and alternatively add and subtract packed elements in c to/from the intermediate result.
_mm256_fmaddsub_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and alternatively add and subtract packed elements in c to/from the intermediate result.
_mm256_fmsub_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and subtract packed elements in c from the intermediate result.
_mm256_fmsub_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and subtract packed elements in c from the intermediate result.
_mm256_fmsubadd_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and alternatively subtract and add packed elements in c from/to the intermediate result.
_mm256_fmsubadd_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and alternatively subtract and add packed elements in c from/to the intermediate result.
_mm256_fnmadd_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to packed elements in c.
_mm256_fnmadd_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to packed elements in c.
_mm256_fnmsub_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and subtract packed elements in c from the negated intermediate result.
_mm256_fnmsub_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and subtract packed elements in c from the negated intermediate result.
_mm256_hadd_epi16⚠	avx2 Horizontally adds adjacent pairs of 16-bit integers in a and b.
_mm256_hadd_epi32⚠	avx2 Horizontally adds adjacent pairs of 32-bit integers in a and b.
_mm256_hadd_pd⚠	avx Horizontal addition of adjacent pairs in the two packed vectors of 4 64-bit floating points a and b. In the result, sums of elements from a are returned in even locations, while sums of elements from b are returned in odd locations.
_mm256_hadd_ps⚠	avx Horizontal addition of adjacent pairs in the two packed vectors of 8 32-bit floating points a and b. In the result, sums of elements from a are returned in locations of indices 0, 1, 4, 5; while sums of elements from b are locations 2, 3, 6, 7.
_mm256_hadds_epi16⚠	avx2 Horizontally adds adjacent pairs of 16-bit integers in a and b using saturation.
_mm256_hsub_epi16⚠	avx2 Horizontally subtract adjacent pairs of 16-bit integers in a and b.
_mm256_hsub_epi32⚠	avx2 Horizontally subtract adjacent pairs of 32-bit integers in a and b.
_mm256_hsub_pd⚠	avx Horizontal subtraction of adjacent pairs in the two packed vectors of 4 64-bit floating points a and b. In the result, sums of elements from a are returned in even locations, while sums of elements from b are returned in odd locations.
_mm256_hsub_ps⚠	avx Horizontal subtraction of adjacent pairs in the two packed vectors of 8 32-bit floating points a and b. In the result, sums of elements from a are returned in locations of indices 0, 1, 4, 5; while sums of elements from b are locations 2, 3, 6, 7.
_mm256_hsubs_epi16⚠	avx2 Horizontally subtract adjacent pairs of 16-bit integers in a and b using saturation.
_mm256_i32gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_i32gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_i32gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_i32gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_i64gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_i64gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_i64gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_i64gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm256_insert_epi8⚠	avx Copies a to result, and inserts the 8-bit integer i into result at the location specified by index.
_mm256_insert_epi16⚠	avx Copies a to result, and inserts the 16-bit integer i into result at the location specified by index.
_mm256_insert_epi32⚠	avx Copies a to result, and inserts the 32-bit integer i into result at the location specified by index.
_mm256_insertf128_pd⚠	avx Copies a to result, then inserts 128 bits (composed of 2 packed double-precision (64-bit) floating-point elements) from b into result at the location specified by imm8.
_mm256_insertf128_ps⚠	avx Copies a to result, then inserts 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into result at the location specified by imm8.
_mm256_insertf128_si256⚠	avx Copies a to result, then inserts 128 bits from b into result at the location specified by imm8.
_mm256_inserti128_si256⚠	avx2 Copies a to dst, then insert 128 bits (of integer data) from b at the location specified by imm8.
_mm256_lddqu_si256⚠	avx Loads 256-bits of integer data from unaligned memory into result. This intrinsic may perform better than _mm256_loadu_si256 when the data crosses a cache line boundary.
_mm256_load_pd⚠	avx Loads 256-bits (composed of 4 packed double-precision (64-bit) floating-point elements) from memory into result. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_load_ps⚠	avx Loads 256-bits (composed of 8 packed single-precision (32-bit) floating-point elements) from memory into result. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_load_si256⚠	avx Loads 256-bits of integer data from memory into result. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_loadu2_m128⚠	avx,sse Loads two 128-bit values (composed of 4 packed single-precision (32-bit) floating-point elements) from memory, and combine them into a 256-bit value. hiaddr and loaddr do not need to be aligned on any particular boundary.
_mm256_loadu2_m128d⚠	avx,sse2 Loads two 128-bit values (composed of 2 packed double-precision (64-bit) floating-point elements) from memory, and combine them into a 256-bit value. hiaddr and loaddr do not need to be aligned on any particular boundary.
_mm256_loadu2_m128i⚠	avx,sse2 Loads two 128-bit values (composed of integer data) from memory, and combine them into a 256-bit value. hiaddr and loaddr do not need to be aligned on any particular boundary.
_mm256_loadu_pd⚠	avx Loads 256-bits (composed of 4 packed double-precision (64-bit) floating-point elements) from memory into result. mem_addr does not need to be aligned on any particular boundary.
_mm256_loadu_ps⚠	avx Loads 256-bits (composed of 8 packed single-precision (32-bit) floating-point elements) from memory into result. mem_addr does not need to be aligned on any particular boundary.
_mm256_loadu_si256⚠	avx Loads 256-bits of integer data from memory into result. mem_addr does not need to be aligned on any particular boundary.
_mm256_madd_epi16⚠	avx2 Multiplies packed signed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Horizontally add adjacent pairs of intermediate 32-bit integers.
_mm256_maddubs_epi16⚠	avx2 Vertically multiplies each unsigned 8-bit integer from a with the corresponding signed 8-bit integer from b, producing intermediate signed 16-bit integers. Horizontally add adjacent pairs of intermediate signed 16-bit integers
_mm256_mask_i32gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_mask_i32gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_mask_i32gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_mask_i32gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_mask_i64gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_mask_i64gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_mask_i64gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_mask_i64gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm256_maskload_epi32⚠	avx2 Loads packed 32-bit integers from memory pointed by mem_addr using mask (elements are zeroed out when the highest bit is not set in the corresponding element).
_mm256_maskload_epi64⚠	avx2 Loads packed 64-bit integers from memory pointed by mem_addr using mask (elements are zeroed out when the highest bit is not set in the corresponding element).
_mm256_maskload_pd⚠	avx Loads packed double-precision (64-bit) floating-point elements from memory into result using mask (elements are zeroed out when the high bit of the corresponding element is not set).
_mm256_maskload_ps⚠	avx Loads packed single-precision (32-bit) floating-point elements from memory into result using mask (elements are zeroed out when the high bit of the corresponding element is not set).
_mm256_maskstore_epi32⚠	avx2 Stores packed 32-bit integers from a into memory pointed by mem_addr using mask (elements are not stored when the highest bit is not set in the corresponding element).
_mm256_maskstore_epi64⚠	avx2 Stores packed 64-bit integers from a into memory pointed by mem_addr using mask (elements are not stored when the highest bit is not set in the corresponding element).
_mm256_maskstore_pd⚠	avx Stores packed double-precision (64-bit) floating-point elements from a into memory using mask.
_mm256_maskstore_ps⚠	avx Stores packed single-precision (32-bit) floating-point elements from a into memory using mask.
_mm256_max_epi8⚠	avx2 Compares packed 8-bit integers in a and b, and returns the packed maximum values.
_mm256_max_epi16⚠	avx2 Compares packed 16-bit integers in a and b, and returns the packed maximum values.
_mm256_max_epi32⚠	avx2 Compares packed 32-bit integers in a and b, and returns the packed maximum values.
_mm256_max_epu8⚠	avx2 Compares packed unsigned 8-bit integers in a and b, and returns the packed maximum values.
_mm256_max_epu16⚠	avx2 Compares packed unsigned 16-bit integers in a and b, and returns the packed maximum values.
_mm256_max_epu32⚠	avx2 Compares packed unsigned 32-bit integers in a and b, and returns the packed maximum values.
_mm256_max_pd⚠	avx Compares packed double-precision (64-bit) floating-point elements in a and b, and returns packed maximum values
_mm256_max_ps⚠	avx Compares packed single-precision (32-bit) floating-point elements in a and b, and returns packed maximum values
_mm256_min_epi8⚠	avx2 Compares packed 8-bit integers in a and b, and returns the packed minimum values.
_mm256_min_epi16⚠	avx2 Compares packed 16-bit integers in a and b, and returns the packed minimum values.
_mm256_min_epi32⚠	avx2 Compares packed 32-bit integers in a and b, and returns the packed minimum values.
_mm256_min_epu8⚠	avx2 Compares packed unsigned 8-bit integers in a and b, and returns the packed minimum values.
_mm256_min_epu16⚠	avx2 Compares packed unsigned 16-bit integers in a and b, and returns the packed minimum values.
_mm256_min_epu32⚠	avx2 Compares packed unsigned 32-bit integers in a and b, and returns the packed minimum values.
_mm256_min_pd⚠	avx Compares packed double-precision (64-bit) floating-point elements in a and b, and returns packed minimum values
_mm256_min_ps⚠	avx Compares packed single-precision (32-bit) floating-point elements in a and b, and returns packed minimum values
_mm256_movedup_pd⚠	avx Duplicate even-indexed double-precision (64-bit) floating-point elements from a, and returns the results.
_mm256_movehdup_ps⚠	avx Duplicate odd-indexed single-precision (32-bit) floating-point elements from a, and returns the results.
_mm256_moveldup_ps⚠	avx Duplicate even-indexed single-precision (32-bit) floating-point elements from a, and returns the results.
_mm256_movemask_epi8⚠	avx2 Creates mask from the most significant bit of each 8-bit element in a, return the result.
_mm256_movemask_pd⚠	avx Sets each bit of the returned mask based on the most significant bit of the corresponding packed double-precision (64-bit) floating-point element in a.
_mm256_movemask_ps⚠	avx Sets each bit of the returned mask based on the most significant bit of the corresponding packed single-precision (32-bit) floating-point element in a.
_mm256_mpsadbw_epu8⚠	avx2 Computes the sum of absolute differences (SADs) of quadruplets of unsigned 8-bit integers in a compared to those in b, and stores the 16-bit results in dst. Eight SADs are performed for each 128-bit lane using one quadruplet from b and eight quadruplets from a. One quadruplet is selected from b starting at on the offset specified in imm8. Eight quadruplets are formed from sequential 8-bit integers selected from a starting at the offset specified in imm8.
_mm256_mul_epi32⚠	avx2 Multiplies the low 32-bit integers from each packed 64-bit element in a and b
_mm256_mul_epu32⚠	avx2 Multiplies the low unsigned 32-bit integers from each packed 64-bit element in a and b
_mm256_mul_pd⚠	avx Multiplies packed double-precision (64-bit) floating-point elements in a and b.
_mm256_mul_ps⚠	avx Multiplies packed single-precision (32-bit) floating-point elements in a and b.
_mm256_mulhi_epi16⚠	avx2 Multiplies the packed 16-bit integers in a and b, producing intermediate 32-bit integers and returning the high 16 bits of the intermediate integers.
_mm256_mulhi_epu16⚠	avx2 Multiplies the packed unsigned 16-bit integers in a and b, producing intermediate 32-bit integers and returning the high 16 bits of the intermediate integers.
_mm256_mulhrs_epi16⚠	avx2 Multiplies packed 16-bit integers in a and b, producing intermediate signed 32-bit integers. Truncate each intermediate integer to the 18 most significant bits, round by adding 1, and return bits [16:1].
_mm256_mullo_epi16⚠	avx2 Multiplies the packed 16-bit integers in a and b, producing intermediate 32-bit integers, and returns the low 16 bits of the intermediate integers
_mm256_mullo_epi32⚠	avx2 Multiplies the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and returns the low 32 bits of the intermediate integers
_mm256_or_pd⚠	avx Computes the bitwise OR packed double-precision (64-bit) floating-point elements in a and b.
_mm256_or_ps⚠	avx Computes the bitwise OR packed single-precision (32-bit) floating-point elements in a and b.
_mm256_or_si256⚠	avx2 Computes the bitwise OR of 256 bits (representing integer data) in a and b
_mm256_packs_epi16⚠	avx2 Converts packed 16-bit integers from a and b to packed 8-bit integers using signed saturation
_mm256_packs_epi32⚠	avx2 Converts packed 32-bit integers from a and b to packed 16-bit integers using signed saturation
_mm256_packus_epi16⚠	avx2 Converts packed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation
_mm256_packus_epi32⚠	avx2 Converts packed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation
_mm256_permute2f128_pd⚠	avx Shuffles 256 bits (composed of 4 packed double-precision (64-bit) floating-point elements) selected by imm8 from a and b.
_mm256_permute2f128_ps⚠	avx Shuffles 256 bits (composed of 8 packed single-precision (32-bit) floating-point elements) selected by imm8 from a and b.
_mm256_permute2f128_si256⚠	avx Shuffles 128-bits (composed of integer data) selected by imm8 from a and b.
_mm256_permute2x128_si256⚠	avx2 Shuffles 128-bits of integer data selected by imm8 from a and b.
_mm256_permute4x64_epi64⚠	avx2 Permutes 64-bit integers from a using control mask imm8.
_mm256_permute4x64_pd⚠	avx2 Shuffles 64-bit floating-point elements in a across lanes using the control in imm8.
_mm256_permute_pd⚠	avx Shuffles double-precision (64-bit) floating-point elements in a within 128-bit lanes using the control in imm8.
_mm256_permute_ps⚠	avx Shuffles single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8.
_mm256_permutevar8x32_epi32⚠	avx2 Permutes packed 32-bit integers from a according to the content of b.
_mm256_permutevar8x32_ps⚠	avx2 Shuffles eight 32-bit foating-point elements in a across lanes using the corresponding 32-bit integer index in idx.
_mm256_permutevar_pd⚠	avx Shuffles double-precision (64-bit) floating-point elements in a within 256-bit lanes using the control in b.
_mm256_permutevar_ps⚠	avx Shuffles single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in b.
_mm256_rcp_ps⚠	avx Computes the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a, and returns the results. The maximum relative error for this approximation is less than 1.5*2^-12.
_mm256_round_pd⚠	avx Rounds packed double-precision (64-bit) floating point elements in a according to the flag b. The value of b may be as follows:
_mm256_round_ps⚠	avx Rounds packed single-precision (32-bit) floating point elements in a according to the flag b. The value of b may be as follows:
_mm256_rsqrt_ps⚠	avx Computes the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and returns the results. The maximum relative error for this approximation is less than 1.5*2^-12.
_mm256_sad_epu8⚠	avx2 Computes the absolute differences of packed unsigned 8-bit integers in a and b, then horizontally sum each consecutive 8 differences to produce four unsigned 16-bit integers, and pack these unsigned 16-bit integers in the low 16 bits of the 64-bit return value
_mm256_set1_epi8⚠	avx Broadcasts 8-bit integer a to all elements of returned vector. This intrinsic may generate the vpbroadcastb.
_mm256_set1_epi16⚠	avx Broadcasts 16-bit integer a to all all elements of returned vector. This intrinsic may generate the vpbroadcastw.
_mm256_set1_epi32⚠	avx Broadcasts 32-bit integer a to all elements of returned vector. This intrinsic may generate the vpbroadcastd.
_mm256_set1_epi64x⚠	avx Broadcasts 64-bit integer a to all elements of returned vector. This intrinsic may generate the vpbroadcastq.
_mm256_set1_pd⚠	avx Broadcasts double-precision (64-bit) floating-point value a to all elements of returned vector.
_mm256_set1_ps⚠	avx Broadcasts single-precision (32-bit) floating-point value a to all elements of returned vector.
_mm256_set_epi8⚠	avx Sets packed 8-bit integers in returned vector with the supplied values in reverse order.
_mm256_set_epi16⚠	avx Sets packed 16-bit integers in returned vector with the supplied values.
_mm256_set_epi32⚠	avx Sets packed 32-bit integers in returned vector with the supplied values.
_mm256_set_epi64x⚠	avx Sets packed 64-bit integers in returned vector with the supplied values.
_mm256_set_m128⚠	avx Sets packed __m256 returned vector with the supplied values.
_mm256_set_m128d⚠	avx Sets packed __m256d returned vector with the supplied values.
_mm256_set_m128i⚠	avx Sets packed __m256i returned vector with the supplied values.
_mm256_set_pd⚠	avx Sets packed double-precision (64-bit) floating-point elements in returned vector with the supplied values.
_mm256_set_ps⚠	avx Sets packed single-precision (32-bit) floating-point elements in returned vector with the supplied values.
_mm256_setr_epi8⚠	avx Sets packed 8-bit integers in returned vector with the supplied values in reverse order.
_mm256_setr_epi16⚠	avx Sets packed 16-bit integers in returned vector with the supplied values in reverse order.
_mm256_setr_epi32⚠	avx Sets packed 32-bit integers in returned vector with the supplied values in reverse order.
_mm256_setr_epi64x⚠	avx Sets packed 64-bit integers in returned vector with the supplied values in reverse order.
_mm256_setr_m128⚠	avx Sets packed __m256 returned vector with the supplied values.
_mm256_setr_m128d⚠	avx Sets packed __m256d returned vector with the supplied values.
_mm256_setr_m128i⚠	avx Sets packed __m256i returned vector with the supplied values.
_mm256_setr_pd⚠	avx Sets packed double-precision (64-bit) floating-point elements in returned vector with the supplied values in reverse order.
_mm256_setr_ps⚠	avx Sets packed single-precision (32-bit) floating-point elements in returned vector with the supplied values in reverse order.
_mm256_setzero_pd⚠	avx Returns vector of type __m256d with all elements set to zero.
_mm256_setzero_ps⚠	avx Returns vector of type __m256 with all elements set to zero.
_mm256_setzero_si256⚠	avx Returns vector of type __m256i with all elements set to zero.
_mm256_shuffle_epi8⚠	avx2 Shuffles bytes from a according to the content of b.
_mm256_shuffle_epi32⚠	avx2 Shuffles 32-bit integers in 128-bit lanes of a using the control in imm8.
_mm256_shuffle_pd⚠	avx Shuffles double-precision (64-bit) floating-point elements within 128-bit lanes using the control in imm8.
_mm256_shuffle_ps⚠	avx Shuffles single-precision (32-bit) floating-point elements in a within 128-bit lanes using the control in imm8.
_mm256_shufflehi_epi16⚠	avx2 Shuffles 16-bit integers in the high 64 bits of 128-bit lanes of a using the control in imm8. The low 64 bits of 128-bit lanes of a are copied to the output.
_mm256_shufflelo_epi16⚠	avx2 Shuffles 16-bit integers in the low 64 bits of 128-bit lanes of a using the control in imm8. The high 64 bits of 128-bit lanes of a are copied to the output.
_mm256_sign_epi8⚠	avx2 Negates packed 8-bit integers in a when the corresponding signed 8-bit integer in b is negative, and returns the results. Results are zeroed out when the corresponding element in b is zero.
_mm256_sign_epi16⚠	avx2 Negates packed 16-bit integers in a when the corresponding signed 16-bit integer in b is negative, and returns the results. Results are zeroed out when the corresponding element in b is zero.
_mm256_sign_epi32⚠	avx2 Negates packed 32-bit integers in a when the corresponding signed 32-bit integer in b is negative, and returns the results. Results are zeroed out when the corresponding element in b is zero.
_mm256_sll_epi16⚠	avx2 Shifts packed 16-bit integers in a left by count while shifting in zeros, and returns the result
_mm256_sll_epi32⚠	avx2 Shifts packed 32-bit integers in a left by count while shifting in zeros, and returns the result
_mm256_sll_epi64⚠	avx2 Shifts packed 64-bit integers in a left by count while shifting in zeros, and returns the result
_mm256_slli_epi16⚠	avx2 Shifts packed 16-bit integers in a left by imm8 while shifting in zeros, return the results;
_mm256_slli_epi32⚠	avx2 Shifts packed 32-bit integers in a left by imm8 while shifting in zeros, return the results;
_mm256_slli_epi64⚠	avx2 Shifts packed 64-bit integers in a left by imm8 while shifting in zeros, return the results;
_mm256_slli_si256⚠	avx2 Shifts 128-bit lanes in a left by imm8 bytes while shifting in zeros.
_mm256_sllv_epi32⚠	avx2 Shifts packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and returns the result.
_mm256_sllv_epi64⚠	avx2 Shifts packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and returns the result.
_mm256_sqrt_pd⚠	avx Returns the square root of packed double-precision (64-bit) floating point elements in a.
_mm256_sqrt_ps⚠	avx Returns the square root of packed single-precision (32-bit) floating point elements in a.
_mm256_sra_epi16⚠	avx2 Shifts packed 16-bit integers in a right by count while shifting in sign bits.
_mm256_sra_epi32⚠	avx2 Shifts packed 32-bit integers in a right by count while shifting in sign bits.
_mm256_srai_epi16⚠	avx2 Shifts packed 16-bit integers in a right by imm8 while shifting in sign bits.
_mm256_srai_epi32⚠	avx2 Shifts packed 32-bit integers in a right by imm8 while shifting in sign bits.
_mm256_srav_epi32⚠	avx2 Shifts packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits.
_mm256_srl_epi16⚠	avx2 Shifts packed 16-bit integers in a right by count while shifting in zeros.
_mm256_srl_epi32⚠	avx2 Shifts packed 32-bit integers in a right by count while shifting in zeros.
_mm256_srl_epi64⚠	avx2 Shifts packed 64-bit integers in a right by count while shifting in zeros.
_mm256_srli_epi16⚠	avx2 Shifts packed 16-bit integers in a right by imm8 while shifting in zeros
_mm256_srli_epi32⚠	avx2 Shifts packed 32-bit integers in a right by imm8 while shifting in zeros
_mm256_srli_epi64⚠	avx2 Shifts packed 64-bit integers in a right by imm8 while shifting in zeros
_mm256_srli_si256⚠	avx2 Shifts 128-bit lanes in a right by imm8 bytes while shifting in zeros.
_mm256_srlv_epi32⚠	avx2 Shifts packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros,
_mm256_srlv_epi64⚠	avx2 Shifts packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros,
_mm256_store_pd⚠	avx Stores 256-bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_store_ps⚠	avx Stores 256-bits (composed of 8 packed single-precision (32-bit) floating-point elements) from a into memory. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_store_si256⚠	avx Stores 256-bits of integer data from a into memory. mem_addr must be aligned on a 32-byte boundary or a general-protection exception may be generated.
_mm256_storeu2_m128⚠	avx,sse Stores the high and low 128-bit halves (each composed of 4 packed single-precision (32-bit) floating-point elements) from a into memory two different 128-bit locations. hiaddr and loaddr do not need to be aligned on any particular boundary.
_mm256_storeu2_m128d⚠	avx,sse2 Stores the high and low 128-bit halves (each composed of 2 packed double-precision (64-bit) floating-point elements) from a into memory two different 128-bit locations. hiaddr and loaddr do not need to be aligned on any particular boundary.
_mm256_storeu2_m128i⚠	avx,sse2 Stores the high and low 128-bit halves (each composed of integer data) from a into memory two different 128-bit locations. hiaddr and loaddr do not need to be aligned on any particular boundary.
_mm256_storeu_pd⚠	avx Stores 256-bits (composed of 4 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm256_storeu_ps⚠	avx Stores 256-bits (composed of 8 packed single-precision (32-bit) floating-point elements) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm256_storeu_si256⚠	avx Stores 256-bits of integer data from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm256_stream_pd⚠	avx Moves double-precision values from a 256-bit vector of [4 x double] to a 32-byte aligned memory location. To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon).
_mm256_stream_ps⚠	avx Moves single-precision floating point values from a 256-bit vector of [8 x float] to a 32-byte aligned memory location. To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon).
_mm256_stream_si256⚠	avx Moves integer data from a 256-bit integer vector to a 32-byte aligned memory location. To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon)
_mm256_sub_epi8⚠	avx2 Subtract packed 8-bit integers in b from packed 8-bit integers in a
_mm256_sub_epi16⚠	avx2 Subtract packed 16-bit integers in b from packed 16-bit integers in a
_mm256_sub_epi32⚠	avx2 Subtract packed 32-bit integers in b from packed 32-bit integers in a
_mm256_sub_epi64⚠	avx2 Subtract packed 64-bit integers in b from packed 64-bit integers in a
_mm256_sub_pd⚠	avx Subtracts packed double-precision (64-bit) floating-point elements in b from packed elements in a.
_mm256_sub_ps⚠	avx Subtracts packed single-precision (32-bit) floating-point elements in b from packed elements in a.
_mm256_subs_epi8⚠	avx2 Subtract packed 8-bit integers in b from packed 8-bit integers in a using saturation.
_mm256_subs_epi16⚠	avx2 Subtract packed 16-bit integers in b from packed 16-bit integers in a using saturation.
_mm256_subs_epu8⚠	avx2 Subtract packed unsigned 8-bit integers in b from packed 8-bit integers in a using saturation.
_mm256_subs_epu16⚠	avx2 Subtract packed unsigned 16-bit integers in b from packed 16-bit integers in a using saturation.
_mm256_testc_pd⚠	avx Computes the bitwise AND of 256 bits (representing double-precision (64-bit) floating-point elements) in a and b, producing an intermediate 256-bit value, and set ZF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set CF to 0. Return the CF value.
_mm256_testc_ps⚠	avx Computes the bitwise AND of 256 bits (representing single-precision (32-bit) floating-point elements) in a and b, producing an intermediate 256-bit value, and set ZF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set CF to 0. Return the CF value.
_mm256_testc_si256⚠	avx Computes the bitwise AND of 256 bits (representing integer data) in a and b, and set ZF to 1 if the result is zero, otherwise set ZF to 0. Computes the bitwise NOT of a and then AND with b, and set CF to 1 if the result is zero, otherwise set CF to 0. Return the CF value.
_mm256_testnzc_pd⚠	avx Computes the bitwise AND of 256 bits (representing double-precision (64-bit) floating-point elements) in a and b, producing an intermediate 256-bit value, and set ZF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set CF to 0. Return 1 if both the ZF and CF values are zero, otherwise return 0.
_mm256_testnzc_ps⚠	avx Computes the bitwise AND of 256 bits (representing single-precision (32-bit) floating-point elements) in a and b, producing an intermediate 256-bit value, and set ZF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set CF to 0. Return 1 if both the ZF and CF values are zero, otherwise return 0.
_mm256_testnzc_si256⚠	avx Computes the bitwise AND of 256 bits (representing integer data) in a and b, and set ZF to 1 if the result is zero, otherwise set ZF to 0. Computes the bitwise NOT of a and then AND with b, and set CF to 1 if the result is zero, otherwise set CF to 0. Return 1 if both the ZF and CF values are zero, otherwise return 0.
_mm256_testz_pd⚠	avx Computes the bitwise AND of 256 bits (representing double-precision (64-bit) floating-point elements) in a and b, producing an intermediate 256-bit value, and set ZF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set CF to 0. Return the ZF value.
_mm256_testz_ps⚠	avx Computes the bitwise AND of 256 bits (representing single-precision (32-bit) floating-point elements) in a and b, producing an intermediate 256-bit value, and set ZF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set CF to 0. Return the ZF value.
_mm256_testz_si256⚠	avx Computes the bitwise AND of 256 bits (representing integer data) in a and b, and set ZF to 1 if the result is zero, otherwise set ZF to 0. Computes the bitwise NOT of a and then AND with b, and set CF to 1 if the result is zero, otherwise set CF to 0. Return the ZF value.
_mm256_undefined_pd⚠	avx Returns vector of type __m256d with undefined elements.
_mm256_undefined_ps⚠	avx Returns vector of type __m256 with undefined elements.
_mm256_undefined_si256⚠	avx Returns vector of type __m256i with undefined elements.
_mm256_unpackhi_epi8⚠	avx2 Unpacks and interleave 8-bit integers from the high half of each 128-bit lane in a and b.
_mm256_unpackhi_epi16⚠	avx2 Unpacks and interleave 16-bit integers from the high half of each 128-bit lane of a and b.
_mm256_unpackhi_epi32⚠	avx2 Unpacks and interleave 32-bit integers from the high half of each 128-bit lane of a and b.
_mm256_unpackhi_epi64⚠	avx2 Unpacks and interleave 64-bit integers from the high half of each 128-bit lane of a and b.
_mm256_unpackhi_pd⚠	avx Unpacks and interleave double-precision (64-bit) floating-point elements from the high half of each 128-bit lane in a and b.
_mm256_unpackhi_ps⚠	avx Unpacks and interleave single-precision (32-bit) floating-point elements from the high half of each 128-bit lane in a and b.
_mm256_unpacklo_epi8⚠	avx2 Unpacks and interleave 8-bit integers from the low half of each 128-bit lane of a and b.
_mm256_unpacklo_epi16⚠	avx2 Unpacks and interleave 16-bit integers from the low half of each 128-bit lane of a and b.
_mm256_unpacklo_epi32⚠	avx2 Unpacks and interleave 32-bit integers from the low half of each 128-bit lane of a and b.
_mm256_unpacklo_epi64⚠	avx2 Unpacks and interleave 64-bit integers from the low half of each 128-bit lane of a and b.
_mm256_unpacklo_pd⚠	avx Unpacks and interleave double-precision (64-bit) floating-point elements from the low half of each 128-bit lane in a and b.
_mm256_unpacklo_ps⚠	avx Unpacks and interleave single-precision (32-bit) floating-point elements from the low half of each 128-bit lane in a and b.
_mm256_xor_pd⚠	avx Computes the bitwise XOR of packed double-precision (64-bit) floating-point elements in a and b.
_mm256_xor_ps⚠	avx Computes the bitwise XOR of packed single-precision (32-bit) floating-point elements in a and b.
_mm256_xor_si256⚠	avx2 Computes the bitwise XOR of 256 bits (representing integer data) in a and b
_mm256_zeroall⚠	avx Zeroes the contents of all XMM or YMM registers.
_mm256_zeroupper⚠	avx Zeroes the upper 128 bits of all YMM registers; the lower 128-bits of the registers are unmodified.
_mm256_zextpd128_pd256⚠	avx,sse2 Constructs a 256-bit floating-point vector of [4 x double] from a 128-bit floating-point vector of [2 x double]. The lower 128 bits contain the value of the source vector. The upper 128 bits are set to zero.
_mm256_zextps128_ps256⚠	avx,sse Constructs a 256-bit floating-point vector of [8 x float] from a 128-bit floating-point vector of [4 x float]. The lower 128 bits contain the value of the source vector. The upper 128 bits are set to zero.
_mm256_zextsi128_si256⚠	avx,sse2 Constructs a 256-bit integer vector from a 128-bit integer vector. The lower 128 bits contain the value of the source vector. The upper 128 bits are set to zero.
_mm512_storeu_ps⚠	avx512f Stores 512-bits (composed of 16 packed single-precision (32-bit) floating-point elements) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm_abs_epi8⚠	ssse3 Computes the absolute value of packed 8-bit signed integers in a and return the unsigned results.
_mm_abs_epi16⚠	ssse3 Computes the absolute value of each of the packed 16-bit signed integers in a and return the 16-bit unsigned integer
_mm_abs_epi32⚠	ssse3 Computes the absolute value of each of the packed 32-bit signed integers in a and return the 32-bit unsigned integer
_mm_add_epi8⚠	sse2 Adds packed 8-bit integers in a and b.
_mm_add_epi16⚠	sse2 Adds packed 16-bit integers in a and b.
_mm_add_epi32⚠	sse2 Adds packed 32-bit integers in a and b.
_mm_add_epi64⚠	sse2 Adds packed 64-bit integers in a and b.
_mm_add_pd⚠	sse2 Adds packed double-precision (64-bit) floating-point elements in a and b.
_mm_add_ps⚠	sse Adds __m128 vectors.
_mm_add_sd⚠	sse2 Returns a new vector with the low element of a replaced by the sum of the low elements of a and b.
_mm_add_ss⚠	sse Adds the first component of a and b, the other components are copied from a.
_mm_adds_epi8⚠	sse2 Adds packed 8-bit integers in a and b using saturation.
_mm_adds_epi16⚠	sse2 Adds packed 16-bit integers in a and b using saturation.
_mm_adds_epu8⚠	sse2 Adds packed unsigned 8-bit integers in a and b using saturation.
_mm_adds_epu16⚠	sse2 Adds packed unsigned 16-bit integers in a and b using saturation.
_mm_addsub_pd⚠	sse3 Alternatively add and subtract packed double-precision (64-bit) floating-point elements in a to/from packed elements in b.
_mm_addsub_ps⚠	sse3 Alternatively add and subtract packed single-precision (32-bit) floating-point elements in a to/from packed elements in b.
_mm_aesdec_si128⚠	aes Performs one round of an AES decryption flow on data (state) in a.
_mm_aesdeclast_si128⚠	aes Performs the last round of an AES decryption flow on data (state) in a.
_mm_aesenc_si128⚠	aes Performs one round of an AES encryption flow on data (state) in a.
_mm_aesenclast_si128⚠	aes Performs the last round of an AES encryption flow on data (state) in a.
_mm_aesimc_si128⚠	aes Performs the InvMixColumns transformation on a.
_mm_aeskeygenassist_si128⚠	aes Assist in expanding the AES cipher key.
_mm_alignr_epi8⚠	ssse3 Concatenate 16-byte blocks in a and b into a 32-byte temporary result, shift the result right by n bytes, and returns the low 16 bytes.
_mm_and_pd⚠	sse2 Computes the bitwise AND of packed double-precision (64-bit) floating-point elements in a and b.
_mm_and_ps⚠	sse Bitwise AND of packed single-precision (32-bit) floating-point elements.
_mm_and_si128⚠	sse2 Computes the bitwise AND of 128 bits (representing integer data) in a and b.
_mm_andnot_pd⚠	sse2 Computes the bitwise NOT of a and then AND with b.
_mm_andnot_ps⚠	sse Bitwise AND-NOT of packed single-precision (32-bit) floating-point elements.
_mm_andnot_si128⚠	sse2 Computes the bitwise NOT of 128 bits (representing integer data) in a and then AND with b.
_mm_avg_epu8⚠	sse2 Averages packed unsigned 8-bit integers in a and b.
_mm_avg_epu16⚠	sse2 Averages packed unsigned 16-bit integers in a and b.
_mm_blend_epi16⚠	sse4.1 Blend packed 16-bit integers from a and b using the mask imm8.
_mm_blend_epi32⚠	avx2 Blends packed 32-bit integers from a and b using control mask imm8.
_mm_blend_pd⚠	sse4.1 Blend packed double-precision (64-bit) floating-point elements from a and b using control mask imm2
_mm_blend_ps⚠	sse4.1 Blend packed single-precision (32-bit) floating-point elements from a and b using mask imm4
_mm_blendv_epi8⚠	sse4.1 Blend packed 8-bit integers from a and b using mask
_mm_blendv_pd⚠	sse4.1 Blend packed double-precision (64-bit) floating-point elements from a and b using mask
_mm_blendv_ps⚠	sse4.1 Blend packed single-precision (32-bit) floating-point elements from a and b using mask
_mm_broadcast_ss⚠	avx Broadcasts a single-precision (32-bit) floating-point element from memory to all elements of the returned vector.
_mm_broadcastb_epi8⚠	avx2 Broadcasts the low packed 8-bit integer from a to all elements of the 128-bit returned value.
_mm_broadcastd_epi32⚠	avx2 Broadcasts the low packed 32-bit integer from a to all elements of the 128-bit returned value.
_mm_broadcastq_epi64⚠	avx2 Broadcasts the low packed 64-bit integer from a to all elements of the 128-bit returned value.
_mm_broadcastsd_pd⚠	avx2 Broadcasts the low double-precision (64-bit) floating-point element from a to all elements of the 128-bit returned value.
_mm_broadcastss_ps⚠	avx2 Broadcasts the low single-precision (32-bit) floating-point element from a to all elements of the 128-bit returned value.
_mm_broadcastw_epi16⚠	avx2 Broadcasts the low packed 16-bit integer from a to all elements of the 128-bit returned value
_mm_bslli_si128⚠	sse2 Shifts a left by imm8 bytes while shifting in zeros.
_mm_bsrli_si128⚠	sse2 Shifts a right by imm8 bytes while shifting in zeros.
_mm_castpd_ps⚠	sse2 Casts a 128-bit floating-point vector of [2 x double] into a 128-bit floating-point vector of [4 x float].
_mm_castpd_si128⚠	sse2 Casts a 128-bit floating-point vector of [2 x double] into a 128-bit integer vector.
_mm_castps_pd⚠	sse2 Casts a 128-bit floating-point vector of [4 x float] into a 128-bit floating-point vector of [2 x double].
_mm_castps_si128⚠	sse2 Casts a 128-bit floating-point vector of [4 x float] into a 128-bit integer vector.
_mm_castsi128_pd⚠	sse2 Casts a 128-bit integer vector into a 128-bit floating-point vector of [2 x double].
_mm_castsi128_ps⚠	sse2 Casts a 128-bit integer vector into a 128-bit floating-point vector of [4 x float].
_mm_ceil_pd⚠	sse4.1 Round the packed double-precision (64-bit) floating-point elements in a up to an integer value, and stores the results as packed double-precision floating-point elements.
_mm_ceil_ps⚠	sse4.1 Round the packed single-precision (32-bit) floating-point elements in a up to an integer value, and stores the results as packed single-precision floating-point elements.
_mm_ceil_sd⚠	sse4.1 Round the lower double-precision (64-bit) floating-point element in b up to an integer value, store the result as a double-precision floating-point element in the lower element of the intrisic result, and copies the upper element from a to the upper element of the intrinsic result.
_mm_ceil_ss⚠	sse4.1 Round the lower single-precision (32-bit) floating-point element in b up to an integer value, store the result as a single-precision floating-point element in the lower element of the intrinsic result, and copies the upper 3 packed elements from a to the upper elements of the intrinsic result.
_mm_clflush⚠	sse2 Invalidates and flushes the cache line that contains p from all levels of the cache hierarchy.
_mm_clmulepi64_si128⚠	pclmulqdq Performs a carry-less multiplication of two 64-bit polynomials over the finite field GF(2^k).
_mm_cmp_pd⚠	avx,sse2 Compares packed double-precision (64-bit) floating-point elements in a and b based on the comparison operand specified by imm8.
_mm_cmp_ps⚠	avx,sse Compares packed single-precision (32-bit) floating-point elements in a and b based on the comparison operand specified by imm8.
_mm_cmp_sd⚠	avx,sse2 Compares the lower double-precision (64-bit) floating-point element in a and b based on the comparison operand specified by imm8, store the result in the lower element of returned vector, and copies the upper element from a to the upper element of returned vector.
_mm_cmp_ss⚠	avx,sse Compares the lower single-precision (32-bit) floating-point element in a and b based on the comparison operand specified by imm8, store the result in the lower element of returned vector, and copies the upper 3 packed elements from a to the upper elements of returned vector.
_mm_cmpeq_epi8⚠	sse2 Compares packed 8-bit integers in a and b for equality.
_mm_cmpeq_epi16⚠	sse2 Compares packed 16-bit integers in a and b for equality.
_mm_cmpeq_epi32⚠	sse2 Compares packed 32-bit integers in a and b for equality.
_mm_cmpeq_epi64⚠	sse4.1 Compares packed 64-bit integers in a and b for equality
_mm_cmpeq_pd⚠	sse2 Compares corresponding elements in a and b for equality.
_mm_cmpeq_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input elements were equal, or 0 otherwise.
_mm_cmpeq_sd⚠	sse2 Returns a new vector with the low element of a replaced by the equality comparison of the lower elements of a and b.
_mm_cmpeq_ss⚠	sse Compares the lowest f32 of both inputs for equality. The lowest 32 bits of the result will be 0xffffffff if the two inputs are equal, or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpestra⚠	sse4.2 Compares packed strings in a and b with lengths la and lb using the control in imm8, and return 1 if b did not contain a null character and the resulting mask was zero, and 0 otherwise.
_mm_cmpestrc⚠	sse4.2 Compares packed strings in a and b with lengths la and lb using the control in imm8, and return 1 if the resulting mask was non-zero, and 0 otherwise.
_mm_cmpestri⚠	sse4.2 Compares packed strings a and b with lengths la and lb using the control in imm8 and return the generated index. Similar to _mm_cmpistri with the exception that _mm_cmpistri implicitly determines the length of a and b.
_mm_cmpestrm⚠	sse4.2 Compares packed strings in a and b with lengths la and lb using the control in imm8, and return the generated mask.
_mm_cmpestro⚠	sse4.2 Compares packed strings in a and b with lengths la and lb using the control in imm8, and return bit 0 of the resulting bit mask.
_mm_cmpestrs⚠	sse4.2 Compares packed strings in a and b with lengths la and lb using the control in imm8, and return 1 if any character in a was null, and 0 otherwise.
_mm_cmpestrz⚠	sse4.2 Compares packed strings in a and b with lengths la and lb using the control in imm8, and return 1 if any character in b was null, and 0 otherwise.
_mm_cmpge_pd⚠	sse2 Compares corresponding elements in a and b for greater-than-or-equal.
_mm_cmpge_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is greater than or equal to the corresponding element in b, or 0 otherwise.
_mm_cmpge_sd⚠	sse2 Returns a new vector with the low element of a replaced by the greater-than-or-equal comparison of the lower elements of a and b.
_mm_cmpge_ss⚠	sse Compares the lowest f32 of both inputs for greater than or equal. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is greater than or equal b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpgt_epi8⚠	sse2 Compares packed 8-bit integers in a and b for greater-than.
_mm_cmpgt_epi16⚠	sse2 Compares packed 16-bit integers in a and b for greater-than.
_mm_cmpgt_epi32⚠	sse2 Compares packed 32-bit integers in a and b for greater-than.
_mm_cmpgt_epi64⚠	sse4.2 Compares packed 64-bit integers in a and b for greater-than, return the results.
_mm_cmpgt_pd⚠	sse2 Compares corresponding elements in a and b for greater-than.
_mm_cmpgt_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is greater than the corresponding element in b, or 0 otherwise.
_mm_cmpgt_sd⚠	sse2 Returns a new vector with the low element of a replaced by the greater-than comparison of the lower elements of a and b.
_mm_cmpgt_ss⚠	sse Compares the lowest f32 of both inputs for greater than. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is greater than b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpistra⚠	sse4.2 Compares packed strings with implicit lengths in a and b using the control in imm8, and return 1 if b did not contain a null character and the resulting mask was zero, and 0 otherwise.
_mm_cmpistrc⚠	sse4.2 Compares packed strings with implicit lengths in a and b using the control in imm8, and return 1 if the resulting mask was non-zero, and 0 otherwise.
_mm_cmpistri⚠	sse4.2 Compares packed strings with implicit lengths in a and b using the control in imm8 and return the generated index. Similar to _mm_cmpestri with the exception that _mm_cmpestri requires the lengths of a and b to be explicitly specified.
_mm_cmpistrm⚠	sse4.2 Compares packed strings with implicit lengths in a and b using the control in imm8, and return the generated mask.
_mm_cmpistro⚠	sse4.2 Compares packed strings with implicit lengths in a and b using the control in imm8, and return bit 0 of the resulting bit mask.
_mm_cmpistrs⚠	sse4.2 Compares packed strings with implicit lengths in a and b using the control in imm8, and returns 1 if any character in a was null, and 0 otherwise.
_mm_cmpistrz⚠	sse4.2 Compares packed strings with implicit lengths in a and b using the control in imm8, and return 1 if any character in b was null. and 0 otherwise.
_mm_cmple_pd⚠	sse2 Compares corresponding elements in a and b for less-than-or-equal
_mm_cmple_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is less than or equal to the corresponding element in b, or 0 otherwise.
_mm_cmple_sd⚠	sse2 Returns a new vector with the low element of a replaced by the less-than-or-equal comparison of the lower elements of a and b.
_mm_cmple_ss⚠	sse Compares the lowest f32 of both inputs for less than or equal. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is less than or equal b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmplt_epi8⚠	sse2 Compares packed 8-bit integers in a and b for less-than.
_mm_cmplt_epi16⚠	sse2 Compares packed 16-bit integers in a and b for less-than.
_mm_cmplt_epi32⚠	sse2 Compares packed 32-bit integers in a and b for less-than.
_mm_cmplt_pd⚠	sse2 Compares corresponding elements in a and b for less-than.
_mm_cmplt_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is less than the corresponding element in b, or 0 otherwise.
_mm_cmplt_sd⚠	sse2 Returns a new vector with the low element of a replaced by the less-than comparison of the lower elements of a and b.
_mm_cmplt_ss⚠	sse Compares the lowest f32 of both inputs for less than. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is less than b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpneq_pd⚠	sse2 Compares corresponding elements in a and b for not-equal.
_mm_cmpneq_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input elements are not equal, or 0 otherwise.
_mm_cmpneq_sd⚠	sse2 Returns a new vector with the low element of a replaced by the not-equal comparison of the lower elements of a and b.
_mm_cmpneq_ss⚠	sse Compares the lowest f32 of both inputs for inequality. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is not equal to b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpnge_pd⚠	sse2 Compares corresponding elements in a and b for not-greater-than-or-equal.
_mm_cmpnge_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is not greater than or equal to the corresponding element in b, or 0 otherwise.
_mm_cmpnge_sd⚠	sse2 Returns a new vector with the low element of a replaced by the not-greater-than-or-equal comparison of the lower elements of a and b.
_mm_cmpnge_ss⚠	sse Compares the lowest f32 of both inputs for not-greater-than-or-equal. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is not greater than or equal to b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpngt_pd⚠	sse2 Compares corresponding elements in a and b for not-greater-than.
_mm_cmpngt_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is not greater than the corresponding element in b, or 0 otherwise.
_mm_cmpngt_sd⚠	sse2 Returns a new vector with the low element of a replaced by the not-greater-than comparison of the lower elements of a and b.
_mm_cmpngt_ss⚠	sse Compares the lowest f32 of both inputs for not-greater-than. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is not greater than b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpnle_pd⚠	sse2 Compares corresponding elements in a and b for not-less-than-or-equal.
_mm_cmpnle_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is not less than or equal to the corresponding element in b, or 0 otherwise.
_mm_cmpnle_sd⚠	sse2 Returns a new vector with the low element of a replaced by the not-less-than-or-equal comparison of the lower elements of a and b.
_mm_cmpnle_ss⚠	sse Compares the lowest f32 of both inputs for not-less-than-or-equal. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is not less than or equal to b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpnlt_pd⚠	sse2 Compares corresponding elements in a and b for not-less-than.
_mm_cmpnlt_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. The result in the output vector will be 0xffffffff if the input element in a is not less than the corresponding element in b, or 0 otherwise.
_mm_cmpnlt_sd⚠	sse2 Returns a new vector with the low element of a replaced by the not-less-than comparison of the lower elements of a and b.
_mm_cmpnlt_ss⚠	sse Compares the lowest f32 of both inputs for not-less-than. The lowest 32 bits of the result will be 0xffffffff if a.extract(0) is not less than b.extract(0), or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpord_pd⚠	sse2 Compares corresponding elements in a and b to see if neither is NaN.
_mm_cmpord_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. Returns four floats that have one of two possible bit patterns. The element in the output vector will be 0xffffffff if the input elements in a and b are ordered (i.e., neither of them is a NaN), or 0 otherwise.
_mm_cmpord_sd⚠	sse2 Returns a new vector with the low element of a replaced by the result of comparing both of the lower elements of a and b to NaN. If neither are equal to NaN then 0xFFFFFFFFFFFFFFFF is used and 0 otherwise.
_mm_cmpord_ss⚠	sse Checks if the lowest f32 of both inputs are ordered. The lowest 32 bits of the result will be 0xffffffff if neither of a.extract(0) or b.extract(0) is a NaN, or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_cmpunord_pd⚠	sse2 Compares corresponding elements in a and b to see if either is NaN.
_mm_cmpunord_ps⚠	sse Compares each of the four floats in a to the corresponding element in b. Returns four floats that have one of two possible bit patterns. The element in the output vector will be 0xffffffff if the input elements in a and b are unordered (i.e., at least on of them is a NaN), or 0 otherwise.
_mm_cmpunord_sd⚠	sse2 Returns a new vector with the low element of a replaced by the result of comparing both of the lower elements of a and b to NaN. If either is equal to NaN then 0xFFFFFFFFFFFFFFFF is used and 0 otherwise.
_mm_cmpunord_ss⚠	sse Checks if the lowest f32 of both inputs are unordered. The lowest 32 bits of the result will be 0xffffffff if any of a.extract(0) or b.extract(0) is a NaN, or 0 otherwise. The upper 96 bits of the result are the upper 96 bits of a.
_mm_comieq_sd⚠	sse2 Compares the lower element of a and b for equality.
_mm_comieq_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if they are equal, or 0 otherwise.
_mm_comige_sd⚠	sse2 Compares the lower element of a and b for greater-than-or-equal.
_mm_comige_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is greater than or equal to the one from b, or 0 otherwise.
_mm_comigt_sd⚠	sse2 Compares the lower element of a and b for greater-than.
_mm_comigt_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is greater than the one from b, or 0 otherwise.
_mm_comile_sd⚠	sse2 Compares the lower element of a and b for less-than-or-equal.
_mm_comile_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is less than or equal to the one from b, or 0 otherwise.
_mm_comilt_sd⚠	sse2 Compares the lower element of a and b for less-than.
_mm_comilt_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is less than the one from b, or 0 otherwise.
_mm_comineq_sd⚠	sse2 Compares the lower element of a and b for not-equal.
_mm_comineq_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if they are not equal, or 0 otherwise.
_mm_crc32_u8⚠	sse4.2 Starting with the initial value in crc, return the accumulated CRC32 value for unsigned 8-bit integer v.
_mm_crc32_u16⚠	sse4.2 Starting with the initial value in crc, return the accumulated CRC32 value for unsigned 16-bit integer v.
_mm_crc32_u32⚠	sse4.2 Starting with the initial value in crc, return the accumulated CRC32 value for unsigned 32-bit integer v.
_mm_cvt_si2ss⚠	sse Alias for _mm_cvtsi32_ss.
_mm_cvt_ss2si⚠	sse Alias for _mm_cvtss_si32.
_mm_cvtepi8_epi16⚠	sse4.1 Sign extend packed 8-bit integers in a to packed 16-bit integers
_mm_cvtepi8_epi32⚠	sse4.1 Sign extend packed 8-bit integers in a to packed 32-bit integers
_mm_cvtepi8_epi64⚠	sse4.1 Sign extend packed 8-bit integers in the low 8 bytes of a to packed 64-bit integers
_mm_cvtepi16_epi32⚠	sse4.1 Sign extend packed 16-bit integers in a to packed 32-bit integers
_mm_cvtepi16_epi64⚠	sse4.1 Sign extend packed 16-bit integers in a to packed 64-bit integers
_mm_cvtepi32_epi64⚠	sse4.1 Sign extend packed 32-bit integers in a to packed 64-bit integers
_mm_cvtepi32_pd⚠	sse2 Converts the lower two packed 32-bit integers in a to packed double-precision (64-bit) floating-point elements.
_mm_cvtepi32_ps⚠	sse2 Converts packed 32-bit integers in a to packed single-precision (32-bit) floating-point elements.
_mm_cvtepu8_epi16⚠	sse4.1 Zeroes extend packed unsigned 8-bit integers in a to packed 16-bit integers
_mm_cvtepu8_epi32⚠	sse4.1 Zeroes extend packed unsigned 8-bit integers in a to packed 32-bit integers
_mm_cvtepu8_epi64⚠	sse4.1 Zeroes extend packed unsigned 8-bit integers in a to packed 64-bit integers
_mm_cvtepu16_epi32⚠	sse4.1 Zeroes extend packed unsigned 16-bit integers in a to packed 32-bit integers
_mm_cvtepu16_epi64⚠	sse4.1 Zeroes extend packed unsigned 16-bit integers in a to packed 64-bit integers
_mm_cvtepu32_epi64⚠	sse4.1 Zeroes extend packed unsigned 32-bit integers in a to packed 64-bit integers
_mm_cvtpd_epi32⚠	sse2 Converts packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers.
_mm_cvtpd_ps⚠	sse2 Converts packed double-precision (64-bit) floating-point elements in a to packed single-precision (32-bit) floating-point elements
_mm_cvtps_epi32⚠	sse2 Converts packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers.
_mm_cvtps_pd⚠	sse2 Converts packed single-precision (32-bit) floating-point elements in a to packed double-precision (64-bit) floating-point elements.
_mm_cvtsd_f64⚠	sse2 Returns the lower double-precision (64-bit) floating-point element of a.
_mm_cvtsd_si32⚠	sse2 Converts the lower double-precision (64-bit) floating-point element in a to a 32-bit integer.
_mm_cvtsd_ss⚠	sse2 Converts 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 the return value, and copies the upper element from a to the upper element the return value.
_mm_cvtsi32_sd⚠	sse2 Returns a with its lower element replaced by b after converting it to an f64.
_mm_cvtsi32_si128⚠	sse2 Returns a vector whose lowest element is a and all higher elements are 0.
_mm_cvtsi32_ss⚠	sse Converts a 32 bit integer to a 32 bit float. The result vector is the input vector a with the lowest 32 bit float replaced by the converted integer.
_mm_cvtsi128_si32⚠	sse2 Returns the lowest element of a.
_mm_cvtss_f32⚠	sse Extracts the lowest 32 bit float from the input vector.
_mm_cvtss_sd⚠	sse2 Converts 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 the return value, and copies the upper element from a to the upper element the return value.
_mm_cvtss_si32⚠	sse Converts the lowest 32 bit float in the input vector to a 32 bit integer.
_mm_cvtt_ss2si⚠	sse Alias for _mm_cvttss_si32.
_mm_cvttpd_epi32⚠	sse2 Converts packed double-precision (64-bit) floating-point elements in a to packed 32-bit integers with truncation.
_mm_cvttps_epi32⚠	sse2 Converts packed single-precision (32-bit) floating-point elements in a to packed 32-bit integers with truncation.
_mm_cvttsd_si32⚠	sse2 Converts the lower double-precision (64-bit) floating-point element in a to a 32-bit integer with truncation.
_mm_cvttss_si32⚠	sse Converts the lowest 32 bit float in the input vector to a 32 bit integer with truncation.
_mm_div_pd⚠	sse2 Divide packed double-precision (64-bit) floating-point elements in a by packed elements in b.
_mm_div_ps⚠	sse Divides __m128 vectors.
_mm_div_sd⚠	sse2 Returns a new vector with the low element of a replaced by the result of diving the lower element of a by the lower element of b.
_mm_div_ss⚠	sse Divides the first component of b by a, the other components are copied from a.
_mm_dp_pd⚠	sse4.1 Returns the dot product of two __m128d vectors.
_mm_dp_ps⚠	sse4.1 Returns the dot product of two __m128 vectors.
_mm_extract_epi8⚠	sse4.1 Extracts an 8-bit integer from a, selected with imm8. Returns a 32-bit integer containing the zero-extended integer data.
_mm_extract_epi16⚠	sse2 Returns the imm8 element of a.
_mm_extract_epi32⚠	sse4.1 Extracts an 32-bit integer from a selected with imm8
_mm_extract_ps⚠	sse4.1 Extracts a single-precision (32-bit) floating-point element from a, selected with imm8
_mm_extract_si64⚠	sse4a Extracts the bit range specified by y from the lower 64 bits of x.
_mm_floor_pd⚠	sse4.1 Round the packed double-precision (64-bit) floating-point elements in a down to an integer value, and stores the results as packed double-precision floating-point elements.
_mm_floor_ps⚠	sse4.1 Round the packed single-precision (32-bit) floating-point elements in a down to an integer value, and stores the results as packed single-precision floating-point elements.
_mm_floor_sd⚠	sse4.1 Round the lower double-precision (64-bit) floating-point element in b down to an integer value, store the result as a double-precision floating-point element in the lower element of the intrinsic result, and copies the upper element from a to the upper element of the intrinsic result.
_mm_floor_ss⚠	sse4.1 Round the lower single-precision (32-bit) floating-point element in b down to an integer value, store the result as a single-precision floating-point element in the lower element of the intrinsic result, and copies the upper 3 packed elements from a to the upper elements of the intrinsic result.
_mm_fmadd_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to packed elements in c.
_mm_fmadd_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to packed elements in c.
_mm_fmadd_sd⚠	fma Multiplies the lower double-precision (64-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Stores the result in the lower element of the returned value, and copy the upper element from a to the upper elements of the result.
_mm_fmadd_ss⚠	fma Multiplies the lower single-precision (32-bit) floating-point elements in a and b, and add the intermediate result to the lower element in c. Stores the result in the lower element of the returned value, and copy the 3 upper elements from a to the upper elements of the result.
_mm_fmaddsub_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and alternatively add and subtract packed elements in c to/from the intermediate result.
_mm_fmaddsub_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and alternatively add and subtract packed elements in c to/from the intermediate result.
_mm_fmsub_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and subtract packed elements in c from the intermediate result.
_mm_fmsub_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and subtract packed elements in c from the intermediate result.
_mm_fmsub_sd⚠	fma Multiplies 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 the returned value, and copy the upper element from a to the upper elements of the result.
_mm_fmsub_ss⚠	fma Multiplies 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 the returned value, and copy the 3 upper elements from a to the upper elements of the result.
_mm_fmsubadd_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and alternatively subtract and add packed elements in c from/to the intermediate result.
_mm_fmsubadd_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and alternatively subtract and add packed elements in c from/to the intermediate result.
_mm_fnmadd_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and add the negated intermediate result to packed elements in c.
_mm_fnmadd_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and add the negated intermediate result to packed elements in c.
_mm_fnmadd_sd⚠	fma Multiplies 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 the returned value, and copy the upper element from a to the upper elements of the result.
_mm_fnmadd_ss⚠	fma Multiplies 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 the returned value, and copy the 3 upper elements from a to the upper elements of the result.
_mm_fnmsub_pd⚠	fma Multiplies packed double-precision (64-bit) floating-point elements in a and b, and subtract packed elements in c from the negated intermediate result.
_mm_fnmsub_ps⚠	fma Multiplies packed single-precision (32-bit) floating-point elements in a and b, and subtract packed elements in c from the negated intermediate result.
_mm_fnmsub_sd⚠	fma Multiplies the lower double-precision (64-bit) floating-point elements in a and b, and subtract packed elements in c from the negated intermediate result. Store the result in the lower element of the returned value, and copy the upper element from a to the upper elements of the result.
_mm_fnmsub_ss⚠	fma Multiplies the lower single-precision (32-bit) floating-point elements in a and b, and subtract packed elements in c from the negated intermediate result. Store the result in the lower element of the returned value, and copy the 3 upper elements from a to the upper elements of the result.
_mm_getcsr⚠	sse Gets the unsigned 32-bit value of the MXCSR control and status register.
_mm_hadd_epi16⚠	ssse3 Horizontally adds the adjacent pairs of values contained in 2 packed 128-bit vectors of [8 x i16].
_mm_hadd_epi32⚠	ssse3 Horizontally adds the adjacent pairs of values contained in 2 packed 128-bit vectors of [4 x i32].
_mm_hadd_pd⚠	sse3 Horizontally adds adjacent pairs of double-precision (64-bit) floating-point elements in a and b, and pack the results.
_mm_hadd_ps⚠	sse3 Horizontally adds adjacent pairs of single-precision (32-bit) floating-point elements in a and b, and pack the results.
_mm_hadds_epi16⚠	ssse3 Horizontally adds the adjacent pairs of values contained in 2 packed 128-bit vectors of [8 x i16]. Positive sums greater than 7FFFh are saturated to 7FFFh. Negative sums less than 8000h are saturated to 8000h.
_mm_hsub_epi16⚠	ssse3 Horizontally subtract the adjacent pairs of values contained in 2 packed 128-bit vectors of [8 x i16].
_mm_hsub_epi32⚠	ssse3 Horizontally subtract the adjacent pairs of values contained in 2 packed 128-bit vectors of [4 x i32].
_mm_hsub_pd⚠	sse3 Horizontally subtract adjacent pairs of double-precision (64-bit) floating-point elements in a and b, and pack the results.
_mm_hsub_ps⚠	sse3 Horizontally adds adjacent pairs of single-precision (32-bit) floating-point elements in a and b, and pack the results.
_mm_hsubs_epi16⚠	ssse3 Horizontally subtract the adjacent pairs of values contained in 2 packed 128-bit vectors of [8 x i16]. Positive differences greater than 7FFFh are saturated to 7FFFh. Negative differences less than 8000h are saturated to 8000h.
_mm_i32gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_i32gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_i32gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_i32gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_i64gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_i64gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_i64gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_i64gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8.
_mm_insert_epi8⚠	sse4.1 Returns a copy of a with the 8-bit integer from i inserted at a location specified by imm8.
_mm_insert_epi16⚠	sse2 Returns a new vector where the imm8 element of a is replaced with i.
_mm_insert_epi32⚠	sse4.1 Returns a copy of a with the 32-bit integer from i inserted at a location specified by imm8.
_mm_insert_ps⚠	sse4.1 Select a single value in a to store at some position in b, Then zero elements according to imm8.
_mm_insert_si64⚠	sse4a Inserts the [length:0] bits of y into x at index.
_mm_lddqu_si128⚠	sse3 Loads 128-bits of integer data from unaligned memory. This intrinsic may perform better than _mm_loadu_si128 when the data crosses a cache line boundary.
_mm_lfence⚠	sse2 Performs a serializing operation on all load-from-memory instructions that were issued prior to this instruction.
_mm_load1_pd⚠	sse2 Loads a double-precision (64-bit) floating-point element from memory into both elements of returned vector.
_mm_load1_ps⚠	sse Construct a __m128 by duplicating the value read from p into all elements.
_mm_load_pd⚠	sse2 Loads 128-bits (composed of 2 packed double-precision (64-bit) floating-point elements) from memory into the returned vector. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_load_pd1⚠	sse2 Loads a double-precision (64-bit) floating-point element from memory into both elements of returned vector.
_mm_load_ps⚠	sse Loads four f32 values from aligned memory into a __m128. If the pointer is not aligned to a 128-bit boundary (16 bytes) a general protection fault will be triggered (fatal program crash).
_mm_load_ps1⚠	sse Alias for _mm_load1_ps
_mm_load_sd⚠	sse2 Loads a 64-bit double-precision value to the low element of a 128-bit integer vector and clears the upper element.
_mm_load_si128⚠	sse2 Loads 128-bits of integer data from memory into a new vector.
_mm_load_ss⚠	sse Construct a __m128 with the lowest element read from p and the other elements set to zero.
_mm_loaddup_pd⚠	sse3 Loads a double-precision (64-bit) floating-point element from memory into both elements of return vector.
_mm_loadh_pd⚠	sse2 Loads a double-precision value into the high-order bits of a 128-bit vector of [2 x double]. The low-order bits are copied from the low-order bits of the first operand.
_mm_loadl_epi64⚠	sse2 Loads 64-bit integer from memory into first element of returned vector.
_mm_loadl_pd⚠	sse2 Loads a double-precision value into the low-order bits of a 128-bit vector of [2 x double]. The high-order bits are copied from the high-order bits of the first operand.
_mm_loadr_pd⚠	sse2 Loads 2 double-precision (64-bit) floating-point elements from memory into the returned vector in reverse order. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_loadr_ps⚠	sse Loads four f32 values from aligned memory into a __m128 in reverse order.
_mm_loadu_pd⚠	sse2 Loads 128-bits (composed of 2 packed double-precision (64-bit) floating-point elements) from memory into the returned vector. mem_addr does not need to be aligned on any particular boundary.
_mm_loadu_ps⚠	sse Loads four f32 values from memory into a __m128. There are no restrictions on memory alignment. For aligned memory _mm_load_ps may be faster.
_mm_loadu_si64⚠	sse Loads unaligned 64-bits of integer data from memory into new vector.
_mm_loadu_si128⚠	sse2 Loads 128-bits of integer data from memory into a new vector.
_mm_madd_epi16⚠	sse2 Multiplies and then horizontally add signed 16 bit integers in a and b.
_mm_maddubs_epi16⚠	ssse3 Multiplies corresponding pairs of packed 8-bit unsigned integer values contained in the first source operand and packed 8-bit signed integer values contained in the second source operand, add pairs of contiguous products with signed saturation, and writes the 16-bit sums to the corresponding bits in the destination.
_mm_mask_i32gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_mask_i32gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_mask_i32gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_mask_i32gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_mask_i64gather_epi32⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_mask_i64gather_epi64⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_mask_i64gather_pd⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_mask_i64gather_ps⚠	avx2 Returns values from slice at offsets determined by offsets * scale, where scale is between 1 and 8. If mask is set, load the value from src in that position instead.
_mm_maskload_epi32⚠	avx2 Loads packed 32-bit integers from memory pointed by mem_addr using mask (elements are zeroed out when the highest bit is not set in the corresponding element).
_mm_maskload_epi64⚠	avx2 Loads packed 64-bit integers from memory pointed by mem_addr using mask (elements are zeroed out when the highest bit is not set in the corresponding element).
_mm_maskload_pd⚠	avx Loads packed double-precision (64-bit) floating-point elements from memory into result using mask (elements are zeroed out when the high bit of the corresponding element is not set).
_mm_maskload_ps⚠	avx Loads packed single-precision (32-bit) floating-point elements from memory into result using mask (elements are zeroed out when the high bit of the corresponding element is not set).
_mm_maskmoveu_si128⚠	sse2 Conditionally store 8-bit integer elements from a into memory using mask.
_mm_maskstore_epi32⚠	avx2 Stores packed 32-bit integers from a into memory pointed by mem_addr using mask (elements are not stored when the highest bit is not set in the corresponding element).
_mm_maskstore_epi64⚠	avx2 Stores packed 64-bit integers from a into memory pointed by mem_addr using mask (elements are not stored when the highest bit is not set in the corresponding element).
_mm_maskstore_pd⚠	avx Stores packed double-precision (64-bit) floating-point elements from a into memory using mask.
_mm_maskstore_ps⚠	avx Stores packed single-precision (32-bit) floating-point elements from a into memory using mask.
_mm_max_epi8⚠	sse4.1 Compares packed 8-bit integers in a and b and returns packed maximum values in dst.
_mm_max_epi16⚠	sse2 Compares packed 16-bit integers in a and b, and returns the packed maximum values.
_mm_max_epi32⚠	sse4.1 Compares packed 32-bit integers in a and b, and returns packed maximum values.
_mm_max_epu8⚠	sse2 Compares packed unsigned 8-bit integers in a and b, and returns the packed maximum values.
_mm_max_epu16⚠	sse4.1 Compares packed unsigned 16-bit integers in a and b, and returns packed maximum.
_mm_max_epu32⚠	sse4.1 Compares packed unsigned 32-bit integers in a and b, and returns packed maximum values.
_mm_max_pd⚠	sse2 Returns a new vector with the maximum values from corresponding elements in a and b.
_mm_max_ps⚠	sse Compares packed single-precision (32-bit) floating-point elements in a and b, and return the corresponding maximum values.
_mm_max_sd⚠	sse2 Returns a new vector with the low element of a replaced by the maximum of the lower elements of a and b.
_mm_max_ss⚠	sse Compares the first single-precision (32-bit) floating-point element of a and b, and return the maximum value in the first element of the return value, the other elements are copied from a.
_mm_mfence⚠	sse2 Performs a serializing operation on all load-from-memory and store-to-memory instructions that were issued prior to this instruction.
_mm_min_epi8⚠	sse4.1 Compares packed 8-bit integers in a and b and returns packed minimum values in dst.
_mm_min_epi16⚠	sse2 Compares packed 16-bit integers in a and b, and returns the packed minimum values.
_mm_min_epi32⚠	sse4.1 Compares packed 32-bit integers in a and b, and returns packed minimum values.
_mm_min_epu8⚠	sse2 Compares packed unsigned 8-bit integers in a and b, and returns the packed minimum values.
_mm_min_epu16⚠	sse4.1 Compares packed unsigned 16-bit integers in a and b, and returns packed minimum.
_mm_min_epu32⚠	sse4.1 Compares packed unsigned 32-bit integers in a and b, and returns packed minimum values.
_mm_min_pd⚠	sse2 Returns a new vector with the minimum values from corresponding elements in a and b.
_mm_min_ps⚠	sse Compares packed single-precision (32-bit) floating-point elements in a and b, and return the corresponding minimum values.
_mm_min_sd⚠	sse2 Returns a new vector with the low element of a replaced by the minimum of the lower elements of a and b.
_mm_min_ss⚠	sse Compares the first single-precision (32-bit) floating-point element of a and b, and return the minimum value in the first element of the return value, the other elements are copied from a.
_mm_minpos_epu16⚠	sse4.1 Finds the minimum unsigned 16-bit element in the 128-bit __m128i vector, returning a vector containing its value in its first position, and its index in its second position; all other elements are set to zero.
_mm_move_epi64⚠	sse2 Returns a vector where the low element is extracted from a and its upper element is zero.
_mm_move_sd⚠	sse2 Constructs a 128-bit floating-point vector of [2 x double]. The lower 64 bits are set to the lower 64 bits of the second parameter. The upper 64 bits are set to the upper 64 bits of the first parameter.
_mm_move_ss⚠	sse Returns a __m128 with the first component from b and the remaining components from a.
_mm_movedup_pd⚠	sse3 Duplicate the low double-precision (64-bit) floating-point element from a.
_mm_movehdup_ps⚠	sse3 Duplicate odd-indexed single-precision (32-bit) floating-point elements from a.
_mm_movehl_ps⚠	sse Combine higher half of a and b. The highwe half of b occupies the lower half of result.
_mm_moveldup_ps⚠	sse3 Duplicate even-indexed single-precision (32-bit) floating-point elements from a.
_mm_movelh_ps⚠	sse Combine lower half of a and b. The lower half of b occupies the higher half of result.
_mm_movemask_epi8⚠	sse2 Returns a mask of the most significant bit of each element in a.
_mm_movemask_pd⚠	sse2 Returns a mask of the most significant bit of each element in a.
_mm_movemask_ps⚠	sse Returns a mask of the most significant bit of each element in a.
_mm_mpsadbw_epu8⚠	sse4.1 Subtracts 8-bit unsigned integer values and computes the absolute values of the differences to the corresponding bits in the destination. Then sums of the absolute differences are returned according to the bit fields in the immediate operand.
_mm_mul_epi32⚠	sse4.1 Multiplies the low 32-bit integers from each packed 64-bit element in a and b, and returns the signed 64-bit result.
_mm_mul_epu32⚠	sse2 Multiplies the low unsigned 32-bit integers from each packed 64-bit element in a and b.
_mm_mul_pd⚠	sse2 Multiplies packed double-precision (64-bit) floating-point elements in a and b.
_mm_mul_ps⚠	sse Multiplies __m128 vectors.
_mm_mul_sd⚠	sse2 Returns a new vector with the low element of a replaced by multiplying the low elements of a and b.
_mm_mul_ss⚠	sse Multiplies the first component of a and b, the other components are copied from a.
_mm_mulhi_epi16⚠	sse2 Multiplies the packed 16-bit integers in a and b.
_mm_mulhi_epu16⚠	sse2 Multiplies the packed unsigned 16-bit integers in a and b.
_mm_mulhrs_epi16⚠	ssse3 Multiplies packed 16-bit signed integer values, truncate the 32-bit product to the 18 most significant bits by right-shifting, round the truncated value by adding 1, and write bits [16:1] to the destination.
_mm_mullo_epi16⚠	sse2 Multiplies the packed 16-bit integers in a and b.
_mm_mullo_epi32⚠	sse4.1 Multiplies the packed 32-bit integers in a and b, producing intermediate 64-bit integers, and returns the lowest 32-bit, whatever they might be, reinterpreted as a signed integer. While pmulld __m128i::splat(2), __m128i::splat(2) returns the obvious __m128i::splat(4), due to wrapping arithmetic pmulld __m128i::splat(i32::MAX), __m128i::splat(2) would return a negative number.
_mm_or_pd⚠	sse2 Computes the bitwise OR of a and b.
_mm_or_ps⚠	sse Bitwise OR of packed single-precision (32-bit) floating-point elements.
_mm_or_si128⚠	sse2 Computes the bitwise OR of 128 bits (representing integer data) in a and b.
_mm_packs_epi16⚠	sse2 Converts packed 16-bit integers from a and b to packed 8-bit integers using signed saturation.
_mm_packs_epi32⚠	sse2 Converts packed 32-bit integers from a and b to packed 16-bit integers using signed saturation.
_mm_packus_epi16⚠	sse2 Converts packed 16-bit integers from a and b to packed 8-bit integers using unsigned saturation.
_mm_packus_epi32⚠	sse4.1 Converts packed 32-bit integers from a and b to packed 16-bit integers using unsigned saturation
_mm_pause⚠	Provides a hint to the processor that the code sequence is a spin-wait loop.
_mm_permute_pd⚠	avx,sse2 Shuffles double-precision (64-bit) floating-point elements in a using the control in imm8.
_mm_permute_ps⚠	avx,sse Shuffles single-precision (32-bit) floating-point elements in a using the control in imm8.
_mm_permutevar_pd⚠	avx Shuffles double-precision (64-bit) floating-point elements in a using the control in b.
_mm_permutevar_ps⚠	avx Shuffles single-precision (32-bit) floating-point elements in a using the control in b.
_mm_prefetch⚠	sse Fetch the cache line that contains address p using the given strategy.
_mm_rcp_ps⚠	sse Returns the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a.
_mm_rcp_ss⚠	sse Returns the approximate reciprocal of the first single-precision (32-bit) floating-point element in a, the other elements are unchanged.
_mm_round_pd⚠	sse4.1 Round the packed double-precision (64-bit) floating-point elements in a using the rounding parameter, and stores the results as packed double-precision floating-point elements. Rounding is done according to the rounding parameter, which can be one of:
_mm_round_ps⚠	sse4.1 Round the packed single-precision (32-bit) floating-point elements in a using the rounding parameter, and stores the results as packed single-precision floating-point elements. Rounding is done according to the rounding parameter, which can be one of:
_mm_round_sd⚠	sse4.1 Round the lower double-precision (64-bit) floating-point element in b using the rounding parameter, store the result as a double-precision floating-point element in the lower element of the intrinsic result, and copies the upper element from a to the upper element of the intrinsic result. Rounding is done according to the rounding parameter, which can be one of:
_mm_round_ss⚠	sse4.1 Round the lower single-precision (32-bit) floating-point element in b using the rounding parameter, store the result as a single-precision floating-point element in the lower element of the intrinsic result, and copies the upper 3 packed elements from a to the upper elements of the instrinsic result. Rounding is done according to the rounding parameter, which can be one of:
_mm_rsqrt_ps⚠	sse Returns the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a.
_mm_rsqrt_ss⚠	sse Returns the approximate reciprocal square root of the fist single-precision (32-bit) floating-point elements in a, the other elements are unchanged.
_mm_sad_epu8⚠	sse2 Sum the absolute differences of packed unsigned 8-bit integers.
_mm_set1_epi8⚠	sse2 Broadcasts 8-bit integer a to all elements.
_mm_set1_epi16⚠	sse2 Broadcasts 16-bit integer a to all elements.
_mm_set1_epi32⚠	sse2 Broadcasts 32-bit integer a to all elements.
_mm_set1_epi64x⚠	sse2 Broadcasts 64-bit integer a to all elements.
_mm_set1_pd⚠	sse2 Broadcasts double-precision (64-bit) floating-point value a to all elements of the return value.
_mm_set1_ps⚠	sse Construct a __m128 with all element set to a.
_mm_set_epi8⚠	sse2 Sets packed 8-bit integers with the supplied values.
_mm_set_epi16⚠	sse2 Sets packed 16-bit integers with the supplied values.
_mm_set_epi32⚠	sse2 Sets packed 32-bit integers with the supplied values.
_mm_set_epi64x⚠	sse2 Sets packed 64-bit integers with the supplied values, from highest to lowest.
_mm_set_pd⚠	sse2 Sets packed double-precision (64-bit) floating-point elements in the return value with the supplied values.
_mm_set_pd1⚠	sse2 Broadcasts double-precision (64-bit) floating-point value a to all elements of the return value.
_mm_set_ps⚠	sse Construct a __m128 from four floating point values highest to lowest.
_mm_set_ps1⚠	sse Alias for _mm_set1_ps
_mm_set_sd⚠	sse2 Copies double-precision (64-bit) floating-point element a to the lower element of the packed 64-bit return value.
_mm_set_ss⚠	sse Construct a __m128 with the lowest element set to a and the rest set to zero.
_mm_setcsr⚠	sse Sets the MXCSR register with the 32-bit unsigned integer value.
_mm_setr_epi8⚠	sse2 Sets packed 8-bit integers with the supplied values in reverse order.
_mm_setr_epi16⚠	sse2 Sets packed 16-bit integers with the supplied values in reverse order.
_mm_setr_epi32⚠	sse2 Sets packed 32-bit integers with the supplied values in reverse order.
_mm_setr_pd⚠	sse2 Sets packed double-precision (64-bit) floating-point elements in the return value with the supplied values in reverse order.
_mm_setr_ps⚠	sse Construct a __m128 from four floating point values lowest to highest.
_mm_setzero_pd⚠	sse2 Returns packed double-precision (64-bit) floating-point elements with all zeros.
_mm_setzero_ps⚠	sse Construct a __m128 with all elements initialized to zero.
_mm_setzero_si128⚠	sse2 Returns a vector with all elements set to zero.
_mm_sfence⚠	sse Performs a serializing operation on all store-to-memory instructions that were issued prior to this instruction.
_mm_sha1msg1_epu32⚠	sha Performs an intermediate calculation for the next four SHA1 message values (unsigned 32-bit integers) using previous message values from a and b, and returning the result.
_mm_sha1msg2_epu32⚠	sha Performs the final calculation for the next four SHA1 message values (unsigned 32-bit integers) using the intermediate result in a and the previous message values in b, and returns the result.
_mm_sha1nexte_epu32⚠	sha Calculate SHA1 state variable E after four rounds of operation from the current SHA1 state variable a, add that value to the scheduled values (unsigned 32-bit integers) in b, and returns the result.
_mm_sha1rnds4_epu32⚠	sha Performs four rounds of SHA1 operation using an initial SHA1 state (A,B,C,D) from a and some pre-computed sum of the next 4 round message values (unsigned 32-bit integers), and state variable E from b, and return the updated SHA1 state (A,B,C,D). func contains the logic functions and round constants.
_mm_sha256msg1_epu32⚠	sha Performs an intermediate calculation for the next four SHA256 message values (unsigned 32-bit integers) using previous message values from a and b, and return the result.
_mm_sha256msg2_epu32⚠	sha Performs the final calculation for the next four SHA256 message values (unsigned 32-bit integers) using previous message values from a and b, and return the result.
_mm_sha256rnds2_epu32⚠	sha Performs 2 rounds of SHA256 operation using an initial SHA256 state (C,D,G,H) from a, an initial SHA256 state (A,B,E,F) from b, and a pre-computed sum of the next 2 round message values (unsigned 32-bit integers) and the corresponding round constants from k, and store the updated SHA256 state (A,B,E,F) in dst.
_mm_shuffle_epi8⚠	ssse3 Shuffles bytes from a according to the content of b.
_mm_shuffle_epi32⚠	sse2 Shuffles 32-bit integers in a using the control in imm8.
_mm_shuffle_pd⚠	sse2 Constructs a 128-bit floating-point vector of [2 x double] from two 128-bit vector parameters of [2 x double], using the immediate-value parameter as a specifier.
_mm_shuffle_ps⚠	sse Shuffles packed single-precision (32-bit) floating-point elements in a and b using mask.
_mm_shufflehi_epi16⚠	sse2 Shuffles 16-bit integers in the high 64 bits of a using the control in imm8.
_mm_shufflelo_epi16⚠	sse2 Shuffles 16-bit integers in the low 64 bits of a using the control in imm8.
_mm_sign_epi8⚠	ssse3 Negates packed 8-bit integers in a when the corresponding signed 8-bit integer in b is negative, and returns the result. Elements in result are zeroed out when the corresponding element in b is zero.
_mm_sign_epi16⚠	ssse3 Negates packed 16-bit integers in a when the corresponding signed 16-bit integer in b is negative, and returns the results. Elements in result are zeroed out when the corresponding element in b is zero.
_mm_sign_epi32⚠	ssse3 Negates packed 32-bit integers in a when the corresponding signed 32-bit integer in b is negative, and returns the results. Element in result are zeroed out when the corresponding element in b is zero.
_mm_sll_epi16⚠	sse2 Shifts packed 16-bit integers in a left by count while shifting in zeros.
_mm_sll_epi32⚠	sse2 Shifts packed 32-bit integers in a left by count while shifting in zeros.
_mm_sll_epi64⚠	sse2 Shifts packed 64-bit integers in a left by count while shifting in zeros.
_mm_slli_epi16⚠	sse2 Shifts packed 16-bit integers in a left by imm8 while shifting in zeros.
_mm_slli_epi32⚠	sse2 Shifts packed 32-bit integers in a left by imm8 while shifting in zeros.
_mm_slli_epi64⚠	sse2 Shifts packed 64-bit integers in a left by imm8 while shifting in zeros.
_mm_slli_si128⚠	sse2 Shifts a left by imm8 bytes while shifting in zeros.
_mm_sllv_epi32⚠	avx2 Shifts packed 32-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and returns the result.
_mm_sllv_epi64⚠	avx2 Shifts packed 64-bit integers in a left by the amount specified by the corresponding element in count while shifting in zeros, and returns the result.
_mm_sqrt_pd⚠	sse2 Returns a new vector with the square root of each of the values in a.
_mm_sqrt_ps⚠	sse Returns the square root of packed single-precision (32-bit) floating-point elements in a.
_mm_sqrt_sd⚠	sse2 Returns a new vector with the low element of a replaced by the square root of the lower element b.
_mm_sqrt_ss⚠	sse Returns the square root of the first single-precision (32-bit) floating-point element in a, the other elements are unchanged.
_mm_sra_epi16⚠	sse2 Shifts packed 16-bit integers in a right by count while shifting in sign bits.
_mm_sra_epi32⚠	sse2 Shifts packed 32-bit integers in a right by count while shifting in sign bits.
_mm_srai_epi16⚠	sse2 Shifts packed 16-bit integers in a right by imm8 while shifting in sign bits.
_mm_srai_epi32⚠	sse2 Shifts packed 32-bit integers in a right by imm8 while shifting in sign bits.
_mm_srav_epi32⚠	avx2 Shifts packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in sign bits.
_mm_srl_epi16⚠	sse2 Shifts packed 16-bit integers in a right by count while shifting in zeros.
_mm_srl_epi32⚠	sse2 Shifts packed 32-bit integers in a right by count while shifting in zeros.
_mm_srl_epi64⚠	sse2 Shifts packed 64-bit integers in a right by count while shifting in zeros.
_mm_srli_epi16⚠	sse2 Shifts packed 16-bit integers in a right by imm8 while shifting in zeros.
_mm_srli_epi32⚠	sse2 Shifts packed 32-bit integers in a right by imm8 while shifting in zeros.
_mm_srli_epi64⚠	sse2 Shifts packed 64-bit integers in a right by imm8 while shifting in zeros.
_mm_srli_si128⚠	sse2 Shifts a right by imm8 bytes while shifting in zeros.
_mm_srlv_epi32⚠	avx2 Shifts packed 32-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros,
_mm_srlv_epi64⚠	avx2 Shifts packed 64-bit integers in a right by the amount specified by the corresponding element in count while shifting in zeros,
_mm_store1_pd⚠	sse2 Stores the lower double-precision (64-bit) floating-point element from a into 2 contiguous elements in memory. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_store1_ps⚠	sse Stores the lowest 32 bit float of a repeated four times into aligned memory.
_mm_store_pd⚠	sse2 Stores 128-bits (composed of 2 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_store_pd1⚠	sse2 Stores the lower double-precision (64-bit) floating-point element from a into 2 contiguous elements in memory. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_store_ps⚠	sse Stores four 32-bit floats into aligned memory.
_mm_store_ps1⚠	sse Alias for _mm_store1_ps
_mm_store_sd⚠	sse2 Stores the lower 64 bits of a 128-bit vector of [2 x double] to a memory location.
_mm_store_si128⚠	sse2 Stores 128-bits of integer data from a into memory.
_mm_store_ss⚠	sse Stores the lowest 32 bit float of a into memory.
_mm_storeh_pd⚠	sse2 Stores the upper 64 bits of a 128-bit vector of [2 x double] to a memory location.
_mm_storel_epi64⚠	sse2 Stores the lower 64-bit integer a to a memory location.
_mm_storel_pd⚠	sse2 Stores the lower 64 bits of a 128-bit vector of [2 x double] to a memory location.
_mm_storer_pd⚠	sse2 Stores 2 double-precision (64-bit) floating-point elements from a into memory in reverse order. mem_addr must be aligned on a 16-byte boundary or a general-protection exception may be generated.
_mm_storer_ps⚠	sse Stores four 32-bit floats into aligned memory in reverse order.
_mm_storeu_pd⚠	sse2 Stores 128-bits (composed of 2 packed double-precision (64-bit) floating-point elements) from a into memory. mem_addr does not need to be aligned on any particular boundary.
_mm_storeu_ps⚠	sse Stores four 32-bit floats into memory. There are no restrictions on memory alignment. For aligned memory _mm_store_ps may be faster.
_mm_storeu_si128⚠	sse2 Stores 128-bits of integer data from a into memory.
_mm_stream_pd⚠	sse2 Stores a 128-bit floating point vector of [2 x double] to a 128-bit aligned memory location. To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon).
_mm_stream_ps⚠	sse Stores a into the memory at mem_addr using a non-temporal memory hint.
_mm_stream_sd⚠	sse4a Non-temporal store of a.0 into p.
_mm_stream_si32⚠	sse2 Stores a 32-bit integer value in the specified memory location. To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon).
_mm_stream_si128⚠	sse2 Stores a 128-bit integer vector to a 128-bit aligned memory location. To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon).
_mm_stream_ss⚠	sse4a Non-temporal store of a.0 into p.
_mm_sub_epi8⚠	sse2 Subtracts packed 8-bit integers in b from packed 8-bit integers in a.
_mm_sub_epi16⚠	sse2 Subtracts packed 16-bit integers in b from packed 16-bit integers in a.
_mm_sub_epi32⚠	sse2 Subtract packed 32-bit integers in b from packed 32-bit integers in a.
_mm_sub_epi64⚠	sse2 Subtract packed 64-bit integers in b from packed 64-bit integers in a.
_mm_sub_pd⚠	sse2 Subtract packed double-precision (64-bit) floating-point elements in b from a.
_mm_sub_ps⚠	sse Subtracts __m128 vectors.
_mm_sub_sd⚠	sse2 Returns a new vector with the low element of a replaced by subtracting the low element by b from the low element of a.
_mm_sub_ss⚠	sse Subtracts the first component of b from a, the other components are copied from a.
_mm_subs_epi8⚠	sse2 Subtract packed 8-bit integers in b from packed 8-bit integers in a using saturation.
_mm_subs_epi16⚠	sse2 Subtract packed 16-bit integers in b from packed 16-bit integers in a using saturation.
_mm_subs_epu8⚠	sse2 Subtract packed unsigned 8-bit integers in b from packed unsigned 8-bit integers in a using saturation.
_mm_subs_epu16⚠	sse2 Subtract packed unsigned 16-bit integers in b from packed unsigned 16-bit integers in a using saturation.
_mm_test_all_ones⚠	sse4.1 Tests whether the specified bits in a 128-bit integer vector are all ones.
_mm_test_all_zeros⚠	sse4.1 Tests whether the specified bits in a 128-bit integer vector are all zeros.
_mm_test_mix_ones_zeros⚠	sse4.1 Tests whether the specified bits in a 128-bit integer vector are neither all zeros nor all ones.
_mm_testc_pd⚠	avx Computes the bitwise AND of 128 bits (representing double-precision (64-bit) floating-point elements) in a and b, producing an intermediate 128-bit value, and set ZF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set CF to 0. Return the CF value.
_mm_testc_ps⚠	avx Computes the bitwise AND of 128 bits (representing single-precision (32-bit) floating-point elements) in a and b, producing an intermediate 128-bit value, and set ZF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set CF to 0. Return the CF value.
_mm_testc_si128⚠	sse4.1 Tests whether the specified bits in a 128-bit integer vector are all ones.
_mm_testnzc_pd⚠	avx Computes the bitwise AND of 128 bits (representing double-precision (64-bit) floating-point elements) in a and b, producing an intermediate 128-bit value, and set ZF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set CF to 0. Return 1 if both the ZF and CF values are zero, otherwise return 0.
_mm_testnzc_ps⚠	avx Computes the bitwise AND of 128 bits (representing single-precision (32-bit) floating-point elements) in a and b, producing an intermediate 128-bit value, and set ZF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set CF to 0. Return 1 if both the ZF and CF values are zero, otherwise return 0.
_mm_testnzc_si128⚠	sse4.1 Tests whether the specified bits in a 128-bit integer vector are neither all zeros nor all ones.
_mm_testz_pd⚠	avx Computes the bitwise AND of 128 bits (representing double-precision (64-bit) floating-point elements) in a and b, producing an intermediate 128-bit value, and set ZF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 64-bit element in the intermediate value is zero, otherwise set CF to 0. Return the ZF value.
_mm_testz_ps⚠	avx Computes the bitwise AND of 128 bits (representing single-precision (32-bit) floating-point elements) in a and b, producing an intermediate 128-bit value, and set ZF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set ZF to 0. Compute the bitwise NOT of a and then AND with b, producing an intermediate value, and set CF to 1 if the sign bit of each 32-bit element in the intermediate value is zero, otherwise set CF to 0. Return the ZF value.
_mm_testz_si128⚠	sse4.1 Tests whether the specified bits in a 128-bit integer vector are all zeros.
_mm_tzcnt_32⚠	bmi1 Counts the number of trailing least significant zero bits.
_mm_ucomieq_sd⚠	sse2 Compares the lower element of a and b for equality.
_mm_ucomieq_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if they are equal, or 0 otherwise. This instruction will not signal an exception if either argument is a quiet NaN.
_mm_ucomige_sd⚠	sse2 Compares the lower element of a and b for greater-than-or-equal.
_mm_ucomige_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is greater than or equal to the one from b, or 0 otherwise. This instruction will not signal an exception if either argument is a quiet NaN.
_mm_ucomigt_sd⚠	sse2 Compares the lower element of a and b for greater-than.
_mm_ucomigt_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is greater than the one from b, or 0 otherwise. This instruction will not signal an exception if either argument is a quiet NaN.
_mm_ucomile_sd⚠	sse2 Compares the lower element of a and b for less-than-or-equal.
_mm_ucomile_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is less than or equal to the one from b, or 0 otherwise. This instruction will not signal an exception if either argument is a quiet NaN.
_mm_ucomilt_sd⚠	sse2 Compares the lower element of a and b for less-than.
_mm_ucomilt_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if the value from a is less than the one from b, or 0 otherwise. This instruction will not signal an exception if either argument is a quiet NaN.
_mm_ucomineq_sd⚠	sse2 Compares the lower element of a and b for not-equal.
_mm_ucomineq_ss⚠	sse Compares two 32-bit floats from the low-order bits of a and b. Returns 1 if they are not equal, or 0 otherwise. This instruction will not signal an exception if either argument is a quiet NaN.
_mm_undefined_pd⚠	sse2 Returns vector of type __m128d with undefined elements.
_mm_undefined_ps⚠	sse Returns vector of type __m128 with undefined elements.
_mm_undefined_si128⚠	sse2 Returns vector of type __m128i with undefined elements.
_mm_unpackhi_epi8⚠	sse2 Unpacks and interleave 8-bit integers from the high half of a and b.
_mm_unpackhi_epi16⚠	sse2 Unpacks and interleave 16-bit integers from the high half of a and b.
_mm_unpackhi_epi32⚠	sse2 Unpacks and interleave 32-bit integers from the high half of a and b.
_mm_unpackhi_epi64⚠	sse2 Unpacks and interleave 64-bit integers from the high half of a and b.
_mm_unpackhi_pd⚠	sse2 The resulting __m128d element is composed by the low-order values of the two __m128d interleaved input elements, i.e.:
_mm_unpackhi_ps⚠	sse Unpacks and interleave single-precision (32-bit) floating-point elements from the higher half of a and b.
_mm_unpacklo_epi8⚠	sse2 Unpacks and interleave 8-bit integers from the low half of a and b.
_mm_unpacklo_epi16⚠	sse2 Unpacks and interleave 16-bit integers from the low half of a and b.
_mm_unpacklo_epi32⚠	sse2 Unpacks and interleave 32-bit integers from the low half of a and b.
_mm_unpacklo_epi64⚠	sse2 Unpacks and interleave 64-bit integers from the low half of a and b.
_mm_unpacklo_pd⚠	sse2 The resulting __m128d element is composed by the high-order values of the two __m128d interleaved input elements, i.e.:
_mm_unpacklo_ps⚠	sse Unpacks and interleave single-precision (32-bit) floating-point elements from the lower half of a and b.
_mm_xor_pd⚠	sse2 Computes the bitwise OR of a and b.
_mm_xor_ps⚠	sse Bitwise exclusive OR of packed single-precision (32-bit) floating-point elements.
_mm_xor_si128⚠	sse2 Computes the bitwise XOR of 128 bits (representing integer data) in a and b.
_mulx_u32⚠	bmi2 Unsigned multiply without affecting flags.
_pdep_u32⚠	bmi2 Scatter contiguous low order bits of a to the result at the positions specified by the mask.
_pext_u32⚠	bmi2 Gathers the bits of x specified by the mask into the contiguous low order bit positions of the result.
_popcnt32⚠	popcnt Counts the bits that are set.
_rdrand16_step⚠	rdrand Read a hardware generated 16-bit random value and store the result in val. Returns 1 if a random value was generated, and 0 otherwise.
_rdrand32_step⚠	rdrand Read a hardware generated 32-bit random value and store the result in val. Returns 1 if a random value was generated, and 0 otherwise.
_rdseed16_step⚠	rdseed Read a 16-bit NIST SP800-90B and SP800-90C compliant random value and store in val. Return 1 if a random value was generated, and 0 otherwise.
_rdseed32_step⚠	rdseed Read a 32-bit NIST SP800-90B and SP800-90C compliant random value and store in val. Return 1 if a random value was generated, and 0 otherwise.
_rdtsc⚠	Reads the current value of the processor’s time-stamp counter.
_subborrow_u32⚠	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).
_t1mskc_u32⚠	tbm Clears all bits below the least significant zero of x and sets all other bits.
_t1mskc_u64⚠	tbm Clears all bits below the least significant zero of x and sets all other bits.
_tzcnt_u32⚠	bmi1 Counts the number of trailing least significant zero bits.
_tzmsk_u32⚠	tbm Sets all bits below the least significant one of x and clears all other bits.
_tzmsk_u64⚠	tbm Sets all bits below the least significant one of x and clears all other bits.
_xgetbv⚠	xsave Reads the contents of the extended control register XCR specified in xcr_no.
_xrstor⚠	xsave Performs a full or partial restore of the enabled processor states using the state information stored in memory at mem_addr.
_xrstors⚠	xsave,xsaves Performs a full or partial restore of the enabled processor states using the state information stored in memory at mem_addr.
_xsave⚠	xsave Performs a full or partial save of the enabled processor states to memory at mem_addr.
_xsavec⚠	xsave,xsavec Performs a full or partial save of the enabled processor states to memory at mem_addr.
_xsaveopt⚠	xsave,xsaveopt Performs a full or partial save of the enabled processor states to memory at mem_addr.
_xsaves⚠	xsave,xsaves Performs a full or partial save of the enabled processor states to memory at mem_addr
_xsetbv⚠	xsave Copies 64-bits from val to the extended control register (XCR) specified by a.

Type Definitions

_MM_CMPINT_ENUM	Experimental The _MM_CMPINT_ENUM type used to specify comparison operations in AVX-512 intrinsics.
_MM_MANTISSA_NORM_ENUM	Experimental The MM_MANTISSA_NORM_ENUM type used to specify mantissa normalized operations in AVX-512 intrinsics.
_MM_MANTISSA_SIGN_ENUM	Experimental The MM_MANTISSA_SIGN_ENUM type used to specify mantissa signed operations in AVX-512 intrinsics.
_MM_PERM_ENUM	Experimental The MM_PERM_ENUM type used to specify shuffle operations in AVX-512 intrinsics.
__mmask8	Experimental The __mmask8 type used in AVX-512 intrinsics, a 8-bit integer
__mmask16	Experimental The __mmask16 type used in AVX-512 intrinsics, a 16-bit integer