#include <xmmintrin.h>

Macros
#define	__DEFAULT_FN_ATTRS

#define	__DEFAULT_FN_ATTRS_MMX

#define	_mm_load_pd1(dp) _mm_load1_pd(dp)

#define	_mm_slli_si128(a, imm)
	Left-shifts the 128-bit integer vector operand by the specified number of bytes.

#define	_mm_bslli_si128(a, imm)

#define	_mm_srli_si128(a, imm)
	Right-shifts the 128-bit integer vector operand by the specified number of bytes.

#define	_mm_bsrli_si128(a, imm)

#define	_mm_extract_epi16(a, imm)
	Extracts 16 bits from a 128-bit integer vector of [8 x i16], using the immediate-value parameter as a selector.

#define	_mm_insert_epi16(a, b, imm)
	Constructs a 128-bit integer vector by first making a copy of the 128-bit integer vector parameter, and then inserting the lower 16 bits of an integer parameter into an offset specified by the immediate-value parameter.

#define	_mm_shuffle_epi32(a, imm) ((__m128i)__builtin_ia32_pshufd((__v4si)(__m128i)(a), (int)(imm)))
	Constructs a 128-bit integer vector by shuffling four 32-bit elements of a 128-bit integer vector parameter, using the immediate-value parameter as a specifier.

#define	_mm_shufflelo_epi16(a, imm) ((__m128i)__builtin_ia32_pshuflw((__v8hi)(__m128i)(a), (int)(imm)))
	Constructs a 128-bit integer vector by shuffling four lower 16-bit elements of a 128-bit integer vector of [8 x i16], using the immediate value parameter as a specifier.

#define	_mm_shufflehi_epi16(a, imm) ((__m128i)__builtin_ia32_pshufhw((__v8hi)(__m128i)(a), (int)(imm)))
	Constructs a 128-bit integer vector by shuffling four upper 16-bit elements of a 128-bit integer vector of [8 x i16], using the immediate value parameter as a specifier.

#define	_mm_shuffle_pd(a, b, i)
	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.

#define	_mm_cmp_pd(a, b, c)
	Compares each of the corresponding double-precision values of two 128-bit vectors of [2 x double], using the operation specified by the immediate integer operand.

#define	_mm_cmp_sd(a, b, c)
	Compares each of the corresponding scalar double-precision values of two 128-bit vectors of [2 x double], using the operation specified by the immediate integer operand.

#define	_MM_SHUFFLE2(x, y) (((x) << 1) \| (y))

#define	_MM_DENORMALS_ZERO_ON (0x0040U)

#define	_MM_DENORMALS_ZERO_OFF (0x0000U)

#define	_MM_DENORMALS_ZERO_MASK (0x0040U)

#define	_MM_GET_DENORMALS_ZERO_MODE() (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK)

#define	_MM_SET_DENORMALS_ZERO_MODE(x) (_mm_setcsr((_mm_getcsr() & ~_MM_DENORMALS_ZERO_MASK) \| (x)))

Typedefs
typedef double __m128d	__attribute__((__vector_size__(16), __aligned__(16)))

Functions
static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_add_sd (__m128d __a, __m128d __b)
	Adds lower double-precision values in both operands and returns the sum in the lower 64 bits of the result.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_add_pd (__m128d __a, __m128d __b)
	Adds two 128-bit vectors of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_sub_sd (__m128d __a, __m128d __b)
	Subtracts the lower double-precision value of the second operand from the lower double-precision value of the first operand and returns the difference in the lower 64 bits of the result.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_sub_pd (__m128d __a, __m128d __b)
	Subtracts two 128-bit vectors of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_mul_sd (__m128d __a, __m128d __b)
	Multiplies lower double-precision values in both operands and returns the product in the lower 64 bits of the result.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_mul_pd (__m128d __a, __m128d __b)
	Multiplies two 128-bit vectors of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_div_sd (__m128d __a, __m128d __b)
	Divides the lower double-precision value of the first operand by the lower double-precision value of the second operand and returns the quotient in the lower 64 bits of the result.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_div_pd (__m128d __a, __m128d __b)
	Performs an element-by-element division of two 128-bit vectors of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_sqrt_sd (__m128d __a, __m128d __b)
	Calculates the square root of the lower double-precision value of the second operand and returns it in the lower 64 bits of the result.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_sqrt_pd (__m128d __a)
	Calculates the square root of the each of two values stored in a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_min_sd (__m128d __a, __m128d __b)
	Compares lower 64-bit double-precision values of both operands, and returns the lesser of the pair of values in the lower 64-bits of the result.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_min_pd (__m128d __a, __m128d __b)
	Performs element-by-element comparison of the two 128-bit vectors of [2 x double] and returns a vector containing the lesser of each pair of values.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_max_sd (__m128d __a, __m128d __b)
	Compares lower 64-bit double-precision values of both operands, and returns the greater of the pair of values in the lower 64-bits of the result.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_max_pd (__m128d __a, __m128d __b)
	Performs element-by-element comparison of the two 128-bit vectors of [2 x double] and returns a vector containing the greater of each pair of values.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_and_pd (__m128d __a, __m128d __b)
	Performs a bitwise AND of two 128-bit vectors of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_andnot_pd (__m128d __a, __m128d __b)
	Performs a bitwise AND of two 128-bit vectors of [2 x double], using the one's complement of the values contained in the first source operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_or_pd (__m128d __a, __m128d __b)
	Performs a bitwise OR of two 128-bit vectors of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_xor_pd (__m128d __a, __m128d __b)
	Performs a bitwise XOR of two 128-bit vectors of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpeq_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] for equality.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmplt_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are less than those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmple_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are less than or equal to those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpgt_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are greater than those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpge_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are greater than or equal to those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpord_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are ordered with respect to those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpunord_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are unordered with respect to those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpneq_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are unequal to those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpnlt_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not less than those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpnle_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not less than or equal to those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpngt_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not greater than those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpnge_pd (__m128d __a, __m128d __b)
	Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not greater than or equal to those in the second operand.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpeq_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] for equality.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmplt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmple_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than or equal to the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpgt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpge_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than or equal to the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpord_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is ordered with respect to the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpunord_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unordered with respect to the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpneq_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unequal to the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpnlt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not less than the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpnle_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not less than or equal to the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpngt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not greater than the corresponding value in the second parameter.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cmpnge_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not greater than or equal to the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_comieq_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] for equality.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_comilt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_comile_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than or equal to the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_comigt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_comige_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than or equal to the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_comineq_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unequal to the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_ucomieq_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] for equality.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_ucomilt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_ucomile_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than or equal to the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_ucomigt_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_ucomige_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than or equal to the corresponding value in the second parameter.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_ucomineq_sd (__m128d __a, __m128d __b)
	Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unequal to the corresponding value in the second parameter.

static __inline__ __m128 __DEFAULT_FN_ATTRS	_mm_cvtpd_ps (__m128d __a)
	Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two single-precision floating-point values, returned in the lower 64 bits of a 128-bit vector of [4 x float].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cvtps_pd (__m128 __a)
	Converts the lower two single-precision floating-point elements of a 128-bit vector of [4 x float] into two double-precision floating-point values, returned in a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cvtepi32_pd (__m128i __a)
	Converts the lower two integer elements of a 128-bit vector of [4 x i32] into two double-precision floating-point values, returned in a 128-bit vector of [2 x double].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cvtpd_epi32 (__m128d __a)
	Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed 32-bit integer values, returned in the lower 64 bits of a 128-bit vector of [4 x i32].

static __inline__ int __DEFAULT_FN_ATTRS	_mm_cvtsd_si32 (__m128d __a)
	Converts the low-order element of a 128-bit vector of [2 x double] into a 32-bit signed integer value.

static __inline__ __m128 __DEFAULT_FN_ATTRS	_mm_cvtsd_ss (__m128 __a, __m128d __b)
	Converts the lower double-precision floating-point element of a 128-bit vector of [2 x double], in the second parameter, into a single-precision floating-point value, returned in the lower 32 bits of a 128-bit vector of [4 x float].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cvtsi32_sd (__m128d __a, int __b)
	Converts a 32-bit signed integer value, in the second parameter, into a double-precision floating-point value, returned in the lower 64 bits of a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_cvtss_sd (__m128d __a, __m128 __b)
	Converts the lower single-precision floating-point element of a 128-bit vector of [4 x float], in the second parameter, into a double-precision floating-point value, returned in the lower 64 bits of a 128-bit vector of [2 x double].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cvttpd_epi32 (__m128d __a)
	Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed truncated (rounded toward zero) 32-bit integer values, returned in the lower 64 bits of a 128-bit vector of [4 x i32].

static __inline__ int __DEFAULT_FN_ATTRS	_mm_cvttsd_si32 (__m128d __a)
	Converts the low-order element of a [2 x double] vector into a 32-bit signed truncated (rounded toward zero) integer value.

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX	_mm_cvtpd_pi32 (__m128d __a)
	Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed 32-bit integer values, returned in a 64-bit vector of [2 x i32].

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX	_mm_cvttpd_pi32 (__m128d __a)
	Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed truncated (rounded toward zero) 32-bit integer values, returned in a 64-bit vector of [2 x i32].

static __inline__ __m128d __DEFAULT_FN_ATTRS_MMX	_mm_cvtpi32_pd (__m64 __a)
	Converts the two signed 32-bit integer elements of a 64-bit vector of [2 x i32] into two double-precision floating-point values, returned in a 128-bit vector of [2 x double].

static __inline__ double __DEFAULT_FN_ATTRS	_mm_cvtsd_f64 (__m128d __a)
	Returns the low-order element of a 128-bit vector of [2 x double] as a double-precision floating-point value.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_load_pd (double const *__dp)
	Loads a 128-bit floating-point vector of [2 x double] from an aligned memory location.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_load1_pd (double const *__dp)
	Loads a double-precision floating-point value from a specified memory location and duplicates it to both vector elements of a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_loadr_pd (double const *__dp)
	Loads two double-precision values, in reverse order, from an aligned memory location into a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_loadu_pd (double const *__dp)
	Loads a 128-bit floating-point vector of [2 x double] from an unaligned memory location.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_loadu_si64 (void const *__a)
	Loads a 64-bit integer value to the low element of a 128-bit integer vector and clears the upper element.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_loadu_si32 (void const *__a)
	Loads a 32-bit integer value to the low element of a 128-bit integer vector and clears the upper element.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_loadu_si16 (void const *__a)
	Loads a 16-bit integer value to the low element of a 128-bit integer vector and clears the upper element.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_load_sd (double const *__dp)
	Loads a 64-bit double-precision value to the low element of a 128-bit integer vector and clears the upper element.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_loadh_pd (__m128d __a, double const *__dp)
	Loads a double-precision value into the high-order bits of a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_loadl_pd (__m128d __a, double const *__dp)
	Loads a double-precision value into the low-order bits of a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_undefined_pd (void)
	Constructs a 128-bit floating-point vector of [2 x double] with unspecified content.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_set_sd (double __w)
	Constructs a 128-bit floating-point vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_set1_pd (double __w)
	Constructs a 128-bit floating-point vector of [2 x double], with each of the two double-precision floating-point vector elements set to the specified double-precision floating-point value.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_set_pd1 (double __w)
	Constructs a 128-bit floating-point vector of [2 x double], with each of the two double-precision floating-point vector elements set to the specified double-precision floating-point value.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_set_pd (double __w, double __x)
	Constructs a 128-bit floating-point vector of [2 x double] initialized with the specified double-precision floating-point values.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_setr_pd (double __w, double __x)
	Constructs a 128-bit floating-point vector of [2 x double], initialized in reverse order with the specified double-precision floating-point values.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_setzero_pd (void)
	Constructs a 128-bit floating-point vector of [2 x double] initialized to zero.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_move_sd (__m128d __a, __m128d __b)
	Constructs a 128-bit floating-point vector of [2 x double].

static __inline__ void __DEFAULT_FN_ATTRS	_mm_store_sd (double *__dp, __m128d __a)
	Stores the lower 64 bits of a 128-bit vector of [2 x double] to a memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_store_pd (double *__dp, __m128d __a)
	Moves packed double-precision values from a 128-bit vector of [2 x double] to a memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_store1_pd (double *__dp, __m128d __a)
	Moves the lower 64 bits of a 128-bit vector of [2 x double] twice to the upper and lower 64 bits of a memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_store_pd1 (double *__dp, __m128d __a)
	Moves the lower 64 bits of a 128-bit vector of [2 x double] twice to the upper and lower 64 bits of a memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storeu_pd (double *__dp, __m128d __a)
	Stores a 128-bit vector of [2 x double] into an unaligned memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storer_pd (double *__dp, __m128d __a)
	Stores two double-precision values, in reverse order, from a 128-bit vector of [2 x double] to a 16-byte aligned memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storeh_pd (double *__dp, __m128d __a)
	Stores the upper 64 bits of a 128-bit vector of [2 x double] to a memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storel_pd (double *__dp, __m128d __a)
	Stores the lower 64 bits of a 128-bit vector of [2 x double] to a memory location.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_add_epi8 (__m128i __a, __m128i __b)
	Adds the corresponding elements of two 128-bit vectors of [16 x i8], saving the lower 8 bits of each sum in the corresponding element of a 128-bit result vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_add_epi16 (__m128i __a, __m128i __b)
	Adds the corresponding elements of two 128-bit vectors of [8 x i16], saving the lower 16 bits of each sum in the corresponding element of a 128-bit result vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_add_epi32 (__m128i __a, __m128i __b)
	Adds the corresponding elements of two 128-bit vectors of [4 x i32], saving the lower 32 bits of each sum in the corresponding element of a 128-bit result vector of [4 x i32].

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX	_mm_add_si64 (__m64 __a, __m64 __b)
	Adds two signed or unsigned 64-bit integer values, returning the lower 64 bits of the sum.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_add_epi64 (__m128i __a, __m128i __b)
	Adds the corresponding elements of two 128-bit vectors of [2 x i64], saving the lower 64 bits of each sum in the corresponding element of a 128-bit result vector of [2 x i64].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_adds_epi8 (__m128i __a, __m128i __b)
	Adds, with saturation, the corresponding elements of two 128-bit signed [16 x i8] vectors, saving each sum in the corresponding element of a 128-bit result vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_adds_epi16 (__m128i __a, __m128i __b)
	Adds, with saturation, the corresponding elements of two 128-bit signed [8 x i16] vectors, saving each sum in the corresponding element of a 128-bit result vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_adds_epu8 (__m128i __a, __m128i __b)
	Adds, with saturation, the corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving each sum in the corresponding element of a 128-bit result vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_adds_epu16 (__m128i __a, __m128i __b)
	Adds, with saturation, the corresponding elements of two 128-bit unsigned [8 x i16] vectors, saving each sum in the corresponding element of a 128-bit result vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_avg_epu8 (__m128i __a, __m128i __b)
	Computes the rounded averages of corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving each result in the corresponding element of a 128-bit result vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_avg_epu16 (__m128i __a, __m128i __b)
	Computes the rounded averages of corresponding elements of two 128-bit unsigned [8 x i16] vectors, saving each result in the corresponding element of a 128-bit result vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_madd_epi16 (__m128i __a, __m128i __b)
	Multiplies the corresponding elements of two 128-bit signed [8 x i16] vectors, producing eight intermediate 32-bit signed integer products, and adds the consecutive pairs of 32-bit products to form a 128-bit signed [4 x i32] vector.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_max_epi16 (__m128i __a, __m128i __b)
	Compares corresponding elements of two 128-bit signed [8 x i16] vectors, saving the greater value from each comparison in the corresponding element of a 128-bit result vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_max_epu8 (__m128i __a, __m128i __b)
	Compares corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving the greater value from each comparison in the corresponding element of a 128-bit result vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_min_epi16 (__m128i __a, __m128i __b)
	Compares corresponding elements of two 128-bit signed [8 x i16] vectors, saving the smaller value from each comparison in the corresponding element of a 128-bit result vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_min_epu8 (__m128i __a, __m128i __b)
	Compares corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving the smaller value from each comparison in the corresponding element of a 128-bit result vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_mulhi_epi16 (__m128i __a, __m128i __b)
	Multiplies the corresponding elements of two signed [8 x i16] vectors, saving the upper 16 bits of each 32-bit product in the corresponding element of a 128-bit signed [8 x i16] result vector.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_mulhi_epu16 (__m128i __a, __m128i __b)
	Multiplies the corresponding elements of two unsigned [8 x i16] vectors, saving the upper 16 bits of each 32-bit product in the corresponding element of a 128-bit unsigned [8 x i16] result vector.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_mullo_epi16 (__m128i __a, __m128i __b)
	Multiplies the corresponding elements of two signed [8 x i16] vectors, saving the lower 16 bits of each 32-bit product in the corresponding element of a 128-bit signed [8 x i16] result vector.

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX	_mm_mul_su32 (__m64 __a, __m64 __b)
	Multiplies 32-bit unsigned integer values contained in the lower bits of the two 64-bit integer vectors and returns the 64-bit unsigned product.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_mul_epu32 (__m128i __a, __m128i __b)
	Multiplies 32-bit unsigned integer values contained in the lower bits of the corresponding elements of two [2 x i64] vectors, and returns the 64-bit products in the corresponding elements of a [2 x i64] vector.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sad_epu8 (__m128i __a, __m128i __b)
	Computes the absolute differences of corresponding 8-bit integer values in two 128-bit vectors.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sub_epi8 (__m128i __a, __m128i __b)
	Subtracts the corresponding 8-bit integer values in the operands.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sub_epi16 (__m128i __a, __m128i __b)
	Subtracts the corresponding 16-bit integer values in the operands.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sub_epi32 (__m128i __a, __m128i __b)
	Subtracts the corresponding 32-bit integer values in the operands.

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX	_mm_sub_si64 (__m64 __a, __m64 __b)
	Subtracts signed or unsigned 64-bit integer values and writes the difference to the corresponding bits in the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sub_epi64 (__m128i __a, __m128i __b)
	Subtracts the corresponding elements of two [2 x i64] vectors.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_subs_epi8 (__m128i __a, __m128i __b)
	Subtracts, with saturation, corresponding 8-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_subs_epi16 (__m128i __a, __m128i __b)
	Subtracts, with saturation, corresponding 16-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_subs_epu8 (__m128i __a, __m128i __b)
	Subtracts, with saturation, corresponding 8-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_subs_epu16 (__m128i __a, __m128i __b)
	Subtracts, with saturation, corresponding 16-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_and_si128 (__m128i __a, __m128i __b)
	Performs a bitwise AND of two 128-bit integer vectors.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_andnot_si128 (__m128i __a, __m128i __b)
	Performs a bitwise AND of two 128-bit integer vectors, using the one's complement of the values contained in the first source operand.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_or_si128 (__m128i __a, __m128i __b)
	Performs a bitwise OR of two 128-bit integer vectors.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_xor_si128 (__m128i __a, __m128i __b)
	Performs a bitwise exclusive OR of two 128-bit integer vectors.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_slli_epi16 (__m128i __a, int __count)
	Left-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sll_epi16 (__m128i __a, __m128i __count)
	Left-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_slli_epi32 (__m128i __a, int __count)
	Left-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sll_epi32 (__m128i __a, __m128i __count)
	Left-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_slli_epi64 (__m128i __a, int __count)
	Left-shifts each 64-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sll_epi64 (__m128i __a, __m128i __count)
	Left-shifts each 64-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srai_epi16 (__m128i __a, int __count)
	Right-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sra_epi16 (__m128i __a, __m128i __count)
	Right-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srai_epi32 (__m128i __a, int __count)
	Right-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_sra_epi32 (__m128i __a, __m128i __count)
	Right-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srli_epi16 (__m128i __a, int __count)
	Right-shifts each of 16-bit values in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srl_epi16 (__m128i __a, __m128i __count)
	Right-shifts each of 16-bit values in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srli_epi32 (__m128i __a, int __count)
	Right-shifts each of 32-bit values in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srl_epi32 (__m128i __a, __m128i __count)
	Right-shifts each of 32-bit values in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srli_epi64 (__m128i __a, int __count)
	Right-shifts each of 64-bit values in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_srl_epi64 (__m128i __a, __m128i __count)
	Right-shifts each of 64-bit values in the 128-bit integer vector operand by the specified number of bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmpeq_epi8 (__m128i __a, __m128i __b)
	Compares each of the corresponding 8-bit values of the 128-bit integer vectors for equality.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmpeq_epi16 (__m128i __a, __m128i __b)
	Compares each of the corresponding 16-bit values of the 128-bit integer vectors for equality.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmpeq_epi32 (__m128i __a, __m128i __b)
	Compares each of the corresponding 32-bit values of the 128-bit integer vectors for equality.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmpgt_epi8 (__m128i __a, __m128i __b)
	Compares each of the corresponding signed 8-bit values of the 128-bit integer vectors to determine if the values in the first operand are greater than those in the second operand.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmpgt_epi16 (__m128i __a, __m128i __b)
	Compares each of the corresponding signed 16-bit values of the 128-bit integer vectors to determine if the values in the first operand are greater than those in the second operand.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmpgt_epi32 (__m128i __a, __m128i __b)
	Compares each of the corresponding signed 32-bit values of the 128-bit integer vectors to determine if the values in the first operand are greater than those in the second operand.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmplt_epi8 (__m128i __a, __m128i __b)
	Compares each of the corresponding signed 8-bit values of the 128-bit integer vectors to determine if the values in the first operand are less than those in the second operand.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmplt_epi16 (__m128i __a, __m128i __b)
	Compares each of the corresponding signed 16-bit values of the 128-bit integer vectors to determine if the values in the first operand are less than those in the second operand.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cmplt_epi32 (__m128i __a, __m128i __b)
	Compares each of the corresponding signed 32-bit values of the 128-bit integer vectors to determine if the values in the first operand are less than those in the second operand.

static __inline__ __m128 __DEFAULT_FN_ATTRS	_mm_cvtepi32_ps (__m128i __a)
	Converts a vector of [4 x i32] into a vector of [4 x float].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cvtps_epi32 (__m128 __a)
	Converts a vector of [4 x float] into a vector of [4 x i32].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cvttps_epi32 (__m128 __a)
	Converts a vector of [4 x float] into four signed truncated (rounded toward zero) 32-bit integers, returned in a vector of [4 x i32].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cvtsi32_si128 (int __a)
	Returns a vector of [4 x i32] where the lowest element is the input operand and the remaining elements are zero.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_cvtsi64_si128 (long long __a)
	Returns a vector of [2 x i64] where the lower element is the input operand and the upper element is zero.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_cvtsi128_si32 (__m128i __a)
	Moves the least significant 32 bits of a vector of [4 x i32] to a 32-bit signed integer value.

static __inline__ long long __DEFAULT_FN_ATTRS	_mm_cvtsi128_si64 (__m128i __a)
	Moves the least significant 64 bits of a vector of [2 x i64] to a 64-bit signed integer value.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_load_si128 (__m128i const *__p)
	Moves packed integer values from an aligned 128-bit memory location to elements in a 128-bit integer vector.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_loadu_si128 (__m128i_u const *__p)
	Moves packed integer values from an unaligned 128-bit memory location to elements in a 128-bit integer vector.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_loadl_epi64 (__m128i_u const *__p)
	Returns a vector of [2 x i64] where the lower element is taken from the lower element of the operand, and the upper element is zero.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_undefined_si128 (void)
	Generates a 128-bit vector of [4 x i32] with unspecified content.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set_epi64x (long long __q1, long long __q0)
	Initializes both 64-bit values in a 128-bit vector of [2 x i64] with the specified 64-bit integer values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set_epi64 (__m64 __q1, __m64 __q0)
	Initializes both 64-bit values in a 128-bit vector of [2 x i64] with the specified 64-bit integer values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set_epi32 (int __i3, int __i2, int __i1, int __i0)
	Initializes the 32-bit values in a 128-bit vector of [4 x i32] with the specified 32-bit integer values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set_epi16 (short __w7, short __w6, short __w5, short __w4, short __w3, short __w2, short __w1, short __w0)
	Initializes the 16-bit values in a 128-bit vector of [8 x i16] with the specified 16-bit integer values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set_epi8 (char __b15, char __b14, char __b13, char __b12, char __b11, char __b10, char __b9, char __b8, char __b7, char __b6, char __b5, char __b4, char __b3, char __b2, char __b1, char __b0)
	Initializes the 8-bit values in a 128-bit vector of [16 x i8] with the specified 8-bit integer values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set1_epi64x (long long __q)
	Initializes both values in a 128-bit integer vector with the specified 64-bit integer value.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set1_epi64 (__m64 __q)
	Initializes both values in a 128-bit vector of [2 x i64] with the specified 64-bit value.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set1_epi32 (int __i)
	Initializes all values in a 128-bit vector of [4 x i32] with the specified 32-bit value.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set1_epi16 (short __w)
	Initializes all values in a 128-bit vector of [8 x i16] with the specified 16-bit value.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_set1_epi8 (char __b)
	Initializes all values in a 128-bit vector of [16 x i8] with the specified 8-bit value.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_setr_epi64 (__m64 __q0, __m64 __q1)
	Constructs a 128-bit integer vector, initialized in reverse order with the specified 64-bit integral values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_setr_epi32 (int __i0, int __i1, int __i2, int __i3)
	Constructs a 128-bit integer vector, initialized in reverse order with the specified 32-bit integral values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_setr_epi16 (short __w0, short __w1, short __w2, short __w3, short __w4, short __w5, short __w6, short __w7)
	Constructs a 128-bit integer vector, initialized in reverse order with the specified 16-bit integral values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_setr_epi8 (char __b0, char __b1, char __b2, char __b3, char __b4, char __b5, char __b6, char __b7, char __b8, char __b9, char __b10, char __b11, char __b12, char __b13, char __b14, char __b15)
	Constructs a 128-bit integer vector, initialized in reverse order with the specified 8-bit integral values.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_setzero_si128 (void)
	Creates a 128-bit integer vector initialized to zero.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_store_si128 (__m128i *__p, __m128i __b)
	Stores a 128-bit integer vector to a memory location aligned on a 128-bit boundary.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storeu_si128 (__m128i_u *__p, __m128i __b)
	Stores a 128-bit integer vector to an unaligned memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storeu_si64 (void *__p, __m128i __b)
	Stores a 64-bit integer value from the low element of a 128-bit integer vector.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storeu_si32 (void *__p, __m128i __b)
	Stores a 32-bit integer value from the low element of a 128-bit integer vector.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storeu_si16 (void *__p, __m128i __b)
	Stores a 16-bit integer value from the low element of a 128-bit integer vector.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_maskmoveu_si128 (__m128i __d, __m128i __n, char *__p)
	Moves bytes selected by the mask from the first operand to the specified unaligned memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_storel_epi64 (__m128i_u *__p, __m128i __a)
	Stores the lower 64 bits of a 128-bit integer vector of [2 x i64] to a memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_stream_pd (void *__p, __m128d __a)
	Stores a 128-bit floating point vector of [2 x double] to a 128-bit aligned memory location.

static __inline__ void __DEFAULT_FN_ATTRS	_mm_stream_si128 (void *__p, __m128i __a)
	Stores a 128-bit integer vector to a 128-bit aligned memory location.

static __inline__ void	__attribute__ ((__always_inline__, __nodebug__, __target__("sse2"))) _mm_stream_si32(void *__p
	Stores a 32-bit integer value in the specified memory location.

void	_mm_clflush (void const *__p)
	The cache line containing __p is flushed and invalidated from all caches in the coherency domain.

void	_mm_lfence (void)
	Forces strong memory ordering (serialization) between load instructions preceding this instruction and load instructions following this instruction, ensuring the system completes all previous loads before executing subsequent loads.

void	_mm_mfence (void)
	Forces strong memory ordering (serialization) between load and store instructions preceding this instruction and load and store instructions following this instruction, ensuring that the system completes all previous memory accesses before executing subsequent memory accesses.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_packs_epi16 (__m128i __a, __m128i __b)
	Converts, with saturation, 16-bit signed integers from both 128-bit integer vector operands into 8-bit signed integers, and packs the results into the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_packs_epi32 (__m128i __a, __m128i __b)
	Converts, with saturation, 32-bit signed integers from both 128-bit integer vector operands into 16-bit signed integers, and packs the results into the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_packus_epi16 (__m128i __a, __m128i __b)
	Converts, with saturation, 16-bit signed integers from both 128-bit integer vector operands into 8-bit unsigned integers, and packs the results into the destination.

static __inline__ int __DEFAULT_FN_ATTRS	_mm_movemask_epi8 (__m128i __a)
	Copies the values of the most significant bits from each 8-bit element in a 128-bit integer vector of [16 x i8] to create a 16-bit mask value, zero-extends the value, and writes it to the destination.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpackhi_epi8 (__m128i __a, __m128i __b)
	Unpacks the high-order (index 8-15) values from two 128-bit vectors of [16 x i8] and interleaves them into a 128-bit vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpackhi_epi16 (__m128i __a, __m128i __b)
	Unpacks the high-order (index 4-7) values from two 128-bit vectors of [8 x i16] and interleaves them into a 128-bit vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpackhi_epi32 (__m128i __a, __m128i __b)
	Unpacks the high-order (index 2,3) values from two 128-bit vectors of [4 x i32] and interleaves them into a 128-bit vector of [4 x i32].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpackhi_epi64 (__m128i __a, __m128i __b)
	Unpacks the high-order 64-bit elements from two 128-bit vectors of [2 x i64] and interleaves them into a 128-bit vector of [2 x i64].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpacklo_epi8 (__m128i __a, __m128i __b)
	Unpacks the low-order (index 0-7) values from two 128-bit vectors of [16 x i8] and interleaves them into a 128-bit vector of [16 x i8].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpacklo_epi16 (__m128i __a, __m128i __b)
	Unpacks the low-order (index 0-3) values from each of the two 128-bit vectors of [8 x i16] and interleaves them into a 128-bit vector of [8 x i16].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpacklo_epi32 (__m128i __a, __m128i __b)
	Unpacks the low-order (index 0,1) values from two 128-bit vectors of [4 x i32] and interleaves them into a 128-bit vector of [4 x i32].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_unpacklo_epi64 (__m128i __a, __m128i __b)
	Unpacks the low-order 64-bit elements from two 128-bit vectors of [2 x i64] and interleaves them into a 128-bit vector of [2 x i64].

static __inline__ __m64 __DEFAULT_FN_ATTRS	_mm_movepi64_pi64 (__m128i __a)
	Returns the lower 64 bits of a 128-bit integer vector as a 64-bit integer.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_movpi64_epi64 (__m64 __a)
	Moves the 64-bit operand to a 128-bit integer vector, zeroing the upper bits.

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_move_epi64 (__m128i __a)
	Moves the lower 64 bits of a 128-bit integer vector to a 128-bit integer vector, zeroing the upper bits.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_unpackhi_pd (__m128d __a, __m128d __b)
	Unpacks the high-order 64-bit elements from two 128-bit vectors of [2 x double] and interleaves them into a 128-bit vector of [2 x double].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_unpacklo_pd (__m128d __a, __m128d __b)
	Unpacks the low-order 64-bit elements from two 128-bit vectors of [2 x double] and interleaves them into a 128-bit vector of [2 x double].

static __inline__ int __DEFAULT_FN_ATTRS	_mm_movemask_pd (__m128d __a)
	Extracts the sign bits of the double-precision values in the 128-bit vector of [2 x double], zero-extends the value, and writes it to the low-order bits of the destination.

static __inline__ __m128 __DEFAULT_FN_ATTRS	_mm_castpd_ps (__m128d __a)
	Casts a 128-bit floating-point vector of [2 x double] into a 128-bit floating-point vector of [4 x float].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_castpd_si128 (__m128d __a)
	Casts a 128-bit floating-point vector of [2 x double] into a 128-bit integer vector.

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_castps_pd (__m128 __a)
	Casts a 128-bit floating-point vector of [4 x float] into a 128-bit floating-point vector of [2 x double].

static __inline__ __m128i __DEFAULT_FN_ATTRS	_mm_castps_si128 (__m128 __a)
	Casts a 128-bit floating-point vector of [4 x float] into a 128-bit integer vector.

static __inline__ __m128 __DEFAULT_FN_ATTRS	_mm_castsi128_ps (__m128i __a)
	Casts a 128-bit integer vector into a 128-bit floating-point vector of [4 x float].

static __inline__ __m128d __DEFAULT_FN_ATTRS	_mm_castsi128_pd (__m128i __a)
	Casts a 128-bit integer vector into a 128-bit floating-point vector of [2 x double].

void	_mm_pause (void)
	Indicates that a spin loop is being executed for the purposes of optimizing power consumption during the loop.

Variables
static __inline__ void int	__a

Macro Definition Documentation

◆ __DEFAULT_FN_ATTRS

#define __DEFAULT_FN_ATTRS

Value:

__attribute__((__always_inline__, __nodebug__, \

__target__("sse2,no-evex512"), __min_vector_width__(128)))

__attribute__

double __m128d __attribute__((__vector_size__(16), __aligned__(16)))

Definition: emmintrin.h:19

Definition at line 52 of file emmintrin.h.

◆ __DEFAULT_FN_ATTRS_MMX

#define __DEFAULT_FN_ATTRS_MMX

Value:

__attribute__((__always_inline__, __nodebug__, \

__target__("mmx,sse2,no-evex512"), __min_vector_width__(64)))

Definition at line 55 of file emmintrin.h.

◆ _mm_bslli_si128

#define _mm_bslli_si128	(	a,
		imm
	)

Value:

((__m128i)__builtin_ia32_pslldqi128_byteshift((__v2di)(__m128i)(a), \

(int)(imm)))

int

__device__ int

Definition: __clang_hip_libdevice_declares.h:67

Definition at line 2740 of file emmintrin.h.

◆ _mm_bsrli_si128

#define _mm_bsrli_si128	(	a,
		imm
	)

Value:

((__m128i)__builtin_ia32_psrldqi128_byteshift((__v2di)(__m128i)(a), \

(int)(imm)))

Definition at line 2949 of file emmintrin.h.

◆ _mm_cmp_pd

#define _mm_cmp_pd	(	a,
		b,
		c
	)

Value:

((__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), (__v2df)(__m128d)(b), \

(c)))

b

__device__ __2f16 b

Definition: __clang_hip_libdevice_declares.h:303

c

__device__ __2f16 float c

Definition: __clang_hip_libdevice_declares.h:304

Compares each of the corresponding double-precision values of two 128-bit vectors of [2 x double], using the operation specified by the immediate integer operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, comparisons that are ordered return false, and comparisons that are unordered return true.

__m128d _mm_cmp_pd(__m128d a, __m128d b, const int c);

_mm_cmp_pd

#define _mm_cmp_pd(a, b, c)

Compares each of the corresponding double-precision values of two 128-bit vectors of [2 x double],...

Definition: emmintrin.h:4836

This intrinsic corresponds to the (V)CMPPD instruction.

Parameters

a	A 128-bit vector of [2 x double].
b	A 128-bit vector of [2 x double].
c	An immediate integer operand, with bits [4:0] specifying which comparison operation to use: 0x00: Equal (ordered, non-signaling) 0x01: Less-than (ordered, signaling) 0x02: Less-than-or-equal (ordered, signaling) 0x03: Unordered (non-signaling) 0x04: Not-equal (unordered, non-signaling) 0x05: Not-less-than (unordered, signaling) 0x06: Not-less-than-or-equal (unordered, signaling) 0x07: Ordered (non-signaling)

Returns: A 128-bit vector of [2 x double] containing the comparison results.

Definition at line 4836 of file emmintrin.h.

◆ _mm_cmp_sd

#define _mm_cmp_sd	(	a,
		b,
		c
	)

Value:

((__m128d)__builtin_ia32_cmpsd((__v2df)(__m128d)(a), (__v2df)(__m128d)(b), \

(c)))

Compares each of the corresponding scalar double-precision values of two 128-bit vectors of [2 x double], using the operation specified by the immediate integer operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, comparisons that are ordered return false, and comparisons that are unordered return true.

__m128d _mm_cmp_sd(__m128d a, __m128d b, const int c);

_mm_cmp_sd

#define _mm_cmp_sd(a, b, c)

Compares each of the corresponding scalar double-precision values of two 128-bit vectors of [2 x doub...

Definition: emmintrin.h:4872

This intrinsic corresponds to the (V)CMPSD instruction.

Parameters

a	A 128-bit vector of [2 x double].
b	A 128-bit vector of [2 x double].
c	An immediate integer operand, with bits [4:0] specifying which comparison operation to use: 0x00: Equal (ordered, non-signaling) 0x01: Less-than (ordered, signaling) 0x02: Less-than-or-equal (ordered, signaling) 0x03: Unordered (non-signaling) 0x04: Not-equal (unordered, non-signaling) 0x05: Not-less-than (unordered, signaling) 0x06: Not-less-than-or-equal (unordered, signaling) 0x07: Ordered (non-signaling)

Returns: A 128-bit vector of [2 x double] containing the comparison results.

Definition at line 4872 of file emmintrin.h.

◆ _MM_DENORMALS_ZERO_MASK

#define _MM_DENORMALS_ZERO_MASK (0x0040U)

Definition at line 4900 of file emmintrin.h.

◆ _MM_DENORMALS_ZERO_OFF

#define _MM_DENORMALS_ZERO_OFF (0x0000U)

Definition at line 4898 of file emmintrin.h.

◆ _MM_DENORMALS_ZERO_ON

#define _MM_DENORMALS_ZERO_ON (0x0040U)

Definition at line 4897 of file emmintrin.h.

◆ _mm_extract_epi16

#define _mm_extract_epi16	(	a,
		imm
	)

Value:

((int)(unsigned short)__builtin_ia32_vec_ext_v8hi((__v8hi)(__m128i)(a), \

(int)(imm)))

Extracts 16 bits from a 128-bit integer vector of [8 x i16], using the immediate-value parameter as a selector.

__m128i _mm_extract_epi16(__m128i a, const int imm);

_mm_extract_epi16

#define _mm_extract_epi16(a, imm)

Extracts 16 bits from a 128-bit integer vector of [8 x i16], using the immediate-value parameter as a...

Definition: emmintrin.h:4219

This intrinsic corresponds to the VPEXTRW / PEXTRW instruction.

Parameters

a A 128-bit integer vector.

imm An immediate value. Bits [2:0] selects values from a to be assigned to bits[15:0] of the result.
000: assign values from bits [15:0] of a.
001: assign values from bits [31:16] of a.
010: assign values from bits [47:32] of a.
011: assign values from bits [63:48] of a.
100: assign values from bits [79:64] of a.
101: assign values from bits [95:80] of a.
110: assign values from bits [111:96] of a.
111: assign values from bits [127:112] of a.

Returns: An integer, whose lower 16 bits are selected from the 128-bit integer vector parameter and the remaining bits are assigned zeros.

Definition at line 4219 of file emmintrin.h.

◆ _MM_GET_DENORMALS_ZERO_MODE

#define _MM_GET_DENORMALS_ZERO_MODE ( ) (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK)

Definition at line 4902 of file emmintrin.h.

◆ _mm_insert_epi16

#define _mm_insert_epi16	(	a,
		b,
		imm
	)

Value:

((__m128i)__builtin_ia32_vec_set_v8hi((__v8hi)(__m128i)(a), (int)(b), \

(int)(imm)))

Constructs a 128-bit integer vector by first making a copy of the 128-bit integer vector parameter, and then inserting the lower 16 bits of an integer parameter into an offset specified by the immediate-value parameter.

__m128i _mm_insert_epi16(__m128i a, int b, const int imm);

_mm_insert_epi16

#define _mm_insert_epi16(a, b, imm)

Constructs a 128-bit integer vector by first making a copy of the 128-bit integer vector parameter,...

Definition: emmintrin.h:4247

This intrinsic corresponds to the VPINSRW / PINSRW instruction.

Parameters

a	A 128-bit integer vector of [8 x i16]. This vector is copied to the result and then one of the eight elements in the result is replaced by the lower 16 bits of b.
b	An integer. The lower 16 bits of this parameter are written to the result beginning at an offset specified by imm.
imm	An immediate value specifying the bit offset in the result at which the lower 16 bits of b are written.

Returns: A 128-bit integer vector containing the constructed values.

Definition at line 4247 of file emmintrin.h.

◆ _mm_load_pd1

#define _mm_load_pd1 ( dp ) _mm_load1_pd(dp)

Definition at line 1577 of file emmintrin.h.

◆ _MM_SET_DENORMALS_ZERO_MODE

#define _MM_SET_DENORMALS_ZERO_MODE ( x ) (_mm_setcsr((_mm_getcsr() & ~_MM_DENORMALS_ZERO_MASK) | (x)))

Definition at line 4903 of file emmintrin.h.

◆ _MM_SHUFFLE2

#define _MM_SHUFFLE2	(	x,
		y
	)	(((x) << 1) \| (y))

Definition at line 4895 of file emmintrin.h.

◆ _mm_shuffle_epi32

#define _mm_shuffle_epi32	(	a,
		imm
	)	((__m128i)__builtin_ia32_pshufd((__v4si)(__m128i)(a), (int)(imm)))

Constructs a 128-bit integer vector by shuffling four 32-bit elements of a 128-bit integer vector parameter, using the immediate-value parameter as a specifier.

__m128i _mm_shuffle_epi32(__m128i a, const int imm);

_mm_shuffle_epi32

#define _mm_shuffle_epi32(a, imm)

Constructs a 128-bit integer vector by shuffling four 32-bit elements of a 128-bit integer vector par...

Definition: emmintrin.h:4298

This intrinsic corresponds to the VPSHUFD / PSHUFD instruction.

Parameters

a A 128-bit integer vector containing the values to be copied.

imm An immediate value containing an 8-bit value specifying which elements to copy from a. The destinations within the 128-bit destination are assigned values as follows:
Bits [1:0] are used to assign values to bits [31:0] of the result.
Bits [3:2] are used to assign values to bits [63:32] of the result.
Bits [5:4] are used to assign values to bits [95:64] of the result.
Bits [7:6] are used to assign values to bits [127:96] of the result.
Bit value assignments:
00: assign values from bits [31:0] of a.
01: assign values from bits [63:32] of a.
10: assign values from bits [95:64] of a.
11: assign values from bits [127:96] of a.
Note: To generate a mask, you can use the _MM_SHUFFLE macro. _MM_SHUFFLE(b6, b4, b2, b0) can create an 8-bit mask of the form [b6, b4, b2, b0].

Returns: A 128-bit integer vector containing the shuffled values.

Definition at line 4298 of file emmintrin.h.

◆ _mm_shuffle_pd

#define _mm_shuffle_pd	(	a,
		b,
		i
	)

Value:

((__m128d)__builtin_ia32_shufpd((__v2df)(__m128d)(a), (__v2df)(__m128d)(b), \

(int)(i)))

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.

__m128d _mm_shuffle_pd(__m128d a, __m128d b, const int i);

_mm_shuffle_pd

#define _mm_shuffle_pd(a, b, i)

Constructs a 128-bit floating-point vector of [2 x double] from two 128-bit vector parameters of [2 x...

Definition: emmintrin.h:4710

This intrinsic corresponds to the VSHUFPD / SHUFPD instruction.

Parameters

a	A 128-bit vector of [2 x double].
b	A 128-bit vector of [2 x double].
i	An 8-bit immediate value. The least significant two bits specify which elements to copy from a and b: Bit[0] = 0: lower element of a copied to lower element of result. Bit[0] = 1: upper element of a copied to lower element of result. Bit[1] = 0: lower element of b copied to upper element of result. Bit[1] = 1: upper element of b copied to upper element of result. Note: To generate a mask, you can use the `_MM_SHUFFLE2` macro. `_MM_SHUFFLE2(b1, b0)` can create a 2-bit mask of the form `[b1, b0]`.

Returns: A 128-bit vector of [2 x double] containing the shuffled values.

Definition at line 4710 of file emmintrin.h.

◆ _mm_shufflehi_epi16

#define _mm_shufflehi_epi16	(	a,
		imm
	)	((__m128i)__builtin_ia32_pshufhw((__v8hi)(__m128i)(a), (int)(imm)))

Constructs a 128-bit integer vector by shuffling four upper 16-bit elements of a 128-bit integer vector of [8 x i16], using the immediate value parameter as a specifier.

__m128i _mm_shufflehi_epi16(__m128i a, const int imm);

_mm_shufflehi_epi16

#define _mm_shufflehi_epi16(a, imm)

Constructs a 128-bit integer vector by shuffling four upper 16-bit elements of a 128-bit integer vect...

Definition: emmintrin.h:4364

This intrinsic corresponds to the VPSHUFHW / PSHUFHW instruction.

Parameters

a A 128-bit integer vector of [8 x i16]. Bits [63:0] are copied to bits [63:0] of the result.

imm An 8-bit immediate value specifying which elements to copy from a.
Bits[1:0] are used to assign values to bits [79:64] of the result.
Bits[3:2] are used to assign values to bits [95:80] of the result.
Bits[5:4] are used to assign values to bits [111:96] of the result.
Bits[7:6] are used to assign values to bits [127:112] of the result.
Bit value assignments:
00: assign values from bits [79:64] of a.
01: assign values from bits [95:80] of a.
10: assign values from bits [111:96] of a.
11: assign values from bits [127:112] of a.
Note: To generate a mask, you can use the _MM_SHUFFLE macro. _MM_SHUFFLE(b6, b4, b2, b0) can create an 8-bit mask of the form [b6, b4, b2, b0].

Returns: A 128-bit integer vector containing the shuffled values.

Definition at line 4364 of file emmintrin.h.

◆ _mm_shufflelo_epi16

#define _mm_shufflelo_epi16	(	a,
		imm
	)	((__m128i)__builtin_ia32_pshuflw((__v8hi)(__m128i)(a), (int)(imm)))

Constructs a 128-bit integer vector by shuffling four lower 16-bit elements of a 128-bit integer vector of [8 x i16], using the immediate value parameter as a specifier.

__m128i _mm_shufflelo_epi16(__m128i a, const int imm);

_mm_shufflelo_epi16

#define _mm_shufflelo_epi16(a, imm)

Constructs a 128-bit integer vector by shuffling four lower 16-bit elements of a 128-bit integer vect...

Definition: emmintrin.h:4331

This intrinsic corresponds to the VPSHUFLW / PSHUFLW instruction.

Parameters

a A 128-bit integer vector of [8 x i16]. Bits [127:64] are copied to bits [127:64] of the result.

imm An 8-bit immediate value specifying which elements to copy from a.
Bits[1:0] are used to assign values to bits [15:0] of the result.
Bits[3:2] are used to assign values to bits [31:16] of the result.
Bits[5:4] are used to assign values to bits [47:32] of the result.
Bits[7:6] are used to assign values to bits [63:48] of the result.
Bit value assignments:
00: assign values from bits [15:0] of a.
01: assign values from bits [31:16] of a.
10: assign values from bits [47:32] of a.
11: assign values from bits [63:48] of a.
Note: To generate a mask, you can use the _MM_SHUFFLE macro. _MM_SHUFFLE(b6, b4, b2, b0) can create an 8-bit mask of the form [b6, b4, b2, b0].

Returns: A 128-bit integer vector containing the shuffled values.

Definition at line 4331 of file emmintrin.h.

◆ _mm_slli_si128

#define _mm_slli_si128	(	a,
		imm
	)

Value:

((__m128i)__builtin_ia32_pslldqi128_byteshift((__v2di)(__m128i)(a), \

(int)(imm)))

Left-shifts the 128-bit integer vector operand by the specified number of bytes.

Low-order bits are cleared.

__m128i _mm_slli_si128(__m128i a, const int imm);

_mm_slli_si128

#define _mm_slli_si128(a, imm)

Left-shifts the 128-bit integer vector operand by the specified number of bytes.

Definition: emmintrin.h:2736

This intrinsic corresponds to the VPSLLDQ / PSLLDQ instruction.

Parameters

a	A 128-bit integer vector containing the source operand.
imm	An immediate value specifying the number of bytes to left-shift operand a.

Returns: A 128-bit integer vector containing the left-shifted value.

Definition at line 2736 of file emmintrin.h.

◆ _mm_srli_si128

#define _mm_srli_si128	(	a,
		imm
	)

Value:

((__m128i)__builtin_ia32_psrldqi128_byteshift((__v2di)(__m128i)(a), \

(int)(imm)))

Right-shifts the 128-bit integer vector operand by the specified number of bytes.

High-order bits are cleared.

__m128i _mm_srli_si128(__m128i a, const int imm);

_mm_srli_si128

#define _mm_srli_si128(a, imm)

Right-shifts the 128-bit integer vector operand by the specified number of bytes.

Definition: emmintrin.h:2945

This intrinsic corresponds to the VPSRLDQ / PSRLDQ instruction.

Parameters

a	A 128-bit integer vector containing the source operand.
imm	An immediate value specifying the number of bytes to right-shift operand a.

Returns: A 128-bit integer vector containing the right-shifted value.

Definition at line 2945 of file emmintrin.h.

Typedef Documentation

◆ attribute

typedef signed char __v16qs __attribute__((__vector_size__(16)))

Definition at line 19 of file emmintrin.h.

Function Documentation

◆ attribute()

static __inline__ void __attribute__ ( (__always_inline__, __nodebug__, __target__("sse2")) )

static

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).

This intrinsic corresponds to the MOVNTI instruction.

Parameters

__p	A pointer to the 32-bit memory location used to store the value.
__a	A 32-bit integer containing the value to be stored.

◆ _mm_add_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_add_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Adds the corresponding elements of two 128-bit vectors of [8 x i16], saving the lower 16 bits of each sum in the corresponding element of a 128-bit result vector of [8 x i16].

The integer elements of both parameters can be either signed or unsigned.

This intrinsic corresponds to the VPADDW / PADDW instruction.

Parameters

__a	A 128-bit vector of [8 x i16].
__b	A 128-bit vector of [8 x i16].

Returns: A 128-bit vector of [8 x i16] containing the sums of both parameters.

Definition at line 2073 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_add_epi16(), and _mm_maskz_add_epi16().

◆ _mm_add_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_add_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Adds the corresponding elements of two 128-bit vectors of [4 x i32], saving the lower 32 bits of each sum in the corresponding element of a 128-bit result vector of [4 x i32].

The integer elements of both parameters can be either signed or unsigned.

This intrinsic corresponds to the VPADDD / PADDD instruction.

Parameters

__a	A 128-bit vector of [4 x i32].
__b	A 128-bit vector of [4 x i32].

Returns: A 128-bit vector of [4 x i32] containing the sums of both parameters.

Definition at line 2094 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_add_epi32(), and _mm_maskz_add_epi32().

◆ _mm_add_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_add_epi64	(	__m128i	__a,
		__m128i	__b
	)

static

Adds the corresponding elements of two 128-bit vectors of [2 x i64], saving the lower 64 bits of each sum in the corresponding element of a 128-bit result vector of [2 x i64].

The integer elements of both parameters can be either signed or unsigned.

This intrinsic corresponds to the VPADDQ / PADDQ instruction.

Parameters

__a	A 128-bit vector of [2 x i64].
__b	A 128-bit vector of [2 x i64].

Returns: A 128-bit vector of [2 x i64] containing the sums of both parameters.

Definition at line 2132 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_add_epi64(), and _mm_maskz_add_epi64().

◆ _mm_add_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_add_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Adds the corresponding elements of two 128-bit vectors of [16 x i8], saving the lower 8 bits of each sum in the corresponding element of a 128-bit result vector of [16 x i8].

The integer elements of both parameters can be either signed or unsigned.

This intrinsic corresponds to the VPADDB / PADDB instruction.

Parameters

__a	A 128-bit vector of [16 x i8].
__b	A 128-bit vector of [16 x i8].

Returns: A 128-bit vector of [16 x i8] containing the sums of both parameters.

Definition at line 2052 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_add_epi8(), and _mm_maskz_add_epi8().

◆ _mm_add_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_add_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Adds two 128-bit vectors of [2 x double].

This intrinsic corresponds to the VADDPD / ADDPD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the source operands.
__b	A 128-bit vector of [2 x double] containing one of the source operands.

Returns: A 128-bit vector of [2 x double] containing the sums of both operands.

Definition at line 92 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_add_pd(), and _mm_maskz_add_pd().

◆ _mm_add_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_add_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Adds lower double-precision values in both operands and returns the sum in the lower 64 bits of the result.

The upper 64 bits of the result are copied from the upper double-precision value of the first operand.

This intrinsic corresponds to the VADDSD / ADDSD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the source operands.
__b	A 128-bit vector of [2 x double] containing one of the source operands.

Returns: A 128-bit vector of [2 x double] whose lower 64 bits contain the sum of the lower 64 bits of both operands. The upper 64 bits are copied from the upper 64 bits of the first source operand.

Definition at line 74 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_add_sd(), and _mm_maskz_add_sd().

◆ _mm_add_si64()

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX _mm_add_si64	(	__m64	__a,
		__m64	__b
	)

static

Adds two signed or unsigned 64-bit integer values, returning the lower 64 bits of the sum.

This intrinsic corresponds to the PADDQ instruction.

Parameters

__a	A 64-bit integer.
__b	A 64-bit integer.

Returns: A 64-bit integer containing the sum of both parameters.

Definition at line 2111 of file emmintrin.h.

References __a, and __b.

◆ _mm_adds_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_adds_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Adds, with saturation, the corresponding elements of two 128-bit signed [8 x i16] vectors, saving each sum in the corresponding element of a 128-bit result vector of [8 x i16].

Positive sums greater than 0x7FFF are saturated to 0x7FFF. Negative sums less than 0x8000 are saturated to 0x8000.

This intrinsic corresponds to the VPADDSW / PADDSW instruction.

Parameters

__a	A 128-bit signed [8 x i16] vector.
__b	A 128-bit signed [8 x i16] vector.

Returns: A 128-bit signed [8 x i16] vector containing the saturated sums of both parameters.

Definition at line 2176 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_adds_epi16(), and _mm_maskz_adds_epi16().

◆ _mm_adds_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_adds_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Adds, with saturation, the corresponding elements of two 128-bit signed [16 x i8] vectors, saving each sum in the corresponding element of a 128-bit result vector of [16 x i8].

Positive sums greater than 0x7F are saturated to 0x7F. Negative sums less than 0x80 are saturated to 0x80.

This intrinsic corresponds to the VPADDSB / PADDSB instruction.

Parameters

__a	A 128-bit signed [16 x i8] vector.
__b	A 128-bit signed [16 x i8] vector.

Returns: A 128-bit signed [16 x i8] vector containing the saturated sums of both parameters.

Definition at line 2154 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_adds_epi8(), and _mm_maskz_adds_epi8().

◆ _mm_adds_epu16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_adds_epu16	(	__m128i	__a,
		__m128i	__b
	)

static

Adds, with saturation, the corresponding elements of two 128-bit unsigned [8 x i16] vectors, saving each sum in the corresponding element of a 128-bit result vector of [8 x i16].

Positive sums greater than 0xFFFF are saturated to 0xFFFF. Negative sums are saturated to 0x0000.

This intrinsic corresponds to the VPADDUSB / PADDUSB instruction.

Parameters

__a	A 128-bit unsigned [8 x i16] vector.
__b	A 128-bit unsigned [8 x i16] vector.

Returns: A 128-bit unsigned [8 x i16] vector containing the saturated sums of both parameters.

Definition at line 2220 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_adds_epu16(), and _mm_maskz_adds_epu16().

◆ _mm_adds_epu8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_adds_epu8	(	__m128i	__a,
		__m128i	__b
	)

static

Adds, with saturation, the corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving each sum in the corresponding element of a 128-bit result vector of [16 x i8].

Positive sums greater than 0xFF are saturated to 0xFF. Negative sums are saturated to 0x00.

This intrinsic corresponds to the VPADDUSB / PADDUSB instruction.

Parameters

__a	A 128-bit unsigned [16 x i8] vector.
__b	A 128-bit unsigned [16 x i8] vector.

Returns: A 128-bit unsigned [16 x i8] vector containing the saturated sums of both parameters.

Definition at line 2198 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_adds_epu8(), and _mm_maskz_adds_epu8().

◆ _mm_and_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_and_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Performs a bitwise AND of two 128-bit vectors of [2 x double].

This intrinsic corresponds to the VPAND / PAND instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the source operands.
__b	A 128-bit vector of [2 x double] containing one of the source operands.

Returns: A 128-bit vector of [2 x double] containing the bitwise AND of the values between both operands.

Definition at line 361 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_and_pd(), and _mm_maskz_and_pd().

◆ _mm_and_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_and_si128	(	__m128i	__a,
		__m128i	__b
	)

static

Performs a bitwise AND of two 128-bit integer vectors.

This intrinsic corresponds to the VPAND / PAND instruction.

Parameters

__a	A 128-bit integer vector containing one of the source operands.
__b	A 128-bit integer vector containing one of the source operands.

Returns: A 128-bit integer vector containing the bitwise AND of the values in both operands.

Definition at line 2662 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_test_epi16_mask(), _mm_mask_test_epi32_mask(), _mm_mask_test_epi64_mask(), _mm_mask_test_epi8_mask(), _mm_mask_testn_epi16_mask(), _mm_mask_testn_epi32_mask(), _mm_mask_testn_epi64_mask(), _mm_mask_testn_epi8_mask(), _mm_test_epi16_mask(), _mm_test_epi32_mask(), _mm_test_epi64_mask(), _mm_test_epi8_mask(), _mm_testn_epi16_mask(), _mm_testn_epi32_mask(), _mm_testn_epi64_mask(), and _mm_testn_epi8_mask().

◆ _mm_andnot_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_andnot_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Performs a bitwise AND of two 128-bit vectors of [2 x double], using the one's complement of the values contained in the first source operand.

This intrinsic corresponds to the VPANDN / PANDN instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing the left source operand. The one's complement of this value is used in the bitwise AND.
__b	A 128-bit vector of [2 x double] containing the right source operand.

Returns: A 128-bit vector of [2 x double] containing the bitwise AND of the values in the second operand and the one's complement of the first operand.

Definition at line 381 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_andnot_pd(), and _mm_maskz_andnot_pd().

◆ _mm_andnot_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_andnot_si128	(	__m128i	__a,
		__m128i	__b
	)

static

Performs a bitwise AND of two 128-bit integer vectors, using the one's complement of the values contained in the first source operand.

This intrinsic corresponds to the VPANDN / PANDN instruction.

Parameters

__a	A 128-bit vector containing the left source operand. The one's complement of this value is used in the bitwise AND.
__b	A 128-bit vector containing the right source operand.

Returns: A 128-bit integer vector containing the bitwise AND of the one's complement of the first operand and the values in the second operand.

Definition at line 2681 of file emmintrin.h.

References __a, and __b.

◆ _mm_avg_epu16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_avg_epu16	(	__m128i	__a,
		__m128i	__b
	)

static

Computes the rounded averages of corresponding elements of two 128-bit unsigned [8 x i16] vectors, saving each result in the corresponding element of a 128-bit result vector of [8 x i16].

This intrinsic corresponds to the VPAVGW / PAVGW instruction.

Parameters

__a	A 128-bit unsigned [8 x i16] vector.
__b	A 128-bit unsigned [8 x i16] vector.

Returns: A 128-bit unsigned [8 x i16] vector containing the rounded averages of both parameters.

Definition at line 2258 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_avg_epu16(), and _mm_maskz_avg_epu16().

◆ _mm_avg_epu8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_avg_epu8	(	__m128i	__a,
		__m128i	__b
	)

static

Computes the rounded averages of corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving each result in the corresponding element of a 128-bit result vector of [16 x i8].

This intrinsic corresponds to the VPAVGB / PAVGB instruction.

Parameters

__a	A 128-bit unsigned [16 x i8] vector.
__b	A 128-bit unsigned [16 x i8] vector.

Returns: A 128-bit unsigned [16 x i8] vector containing the rounded averages of both parameters.

Definition at line 2239 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_avg_epu8(), and _mm_maskz_avg_epu8().

◆ _mm_castpd_ps()

static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_castpd_ps ( __m128d __a )

static

Casts a 128-bit floating-point vector of [2 x double] into a 128-bit floating-point vector of [4 x float].

This intrinsic has no corresponding instruction.

Parameters

__a	A 128-bit floating-point vector of [2 x double].

Returns: A 128-bit floating-point vector of [4 x float] containing the same bitwise pattern as the parameter.

Definition at line 4725 of file emmintrin.h.

References __a.

◆ _mm_castpd_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_castpd_si128 ( __m128d __a )

static

Casts a 128-bit floating-point vector of [2 x double] into a 128-bit integer vector.

This intrinsic has no corresponding instruction.

Parameters

__a	A 128-bit floating-point vector of [2 x double].

Returns: A 128-bit integer vector containing the same bitwise pattern as the parameter.

Definition at line 4740 of file emmintrin.h.

References __a.

◆ _mm_castps_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castps_pd ( __m128 __a )

static

Casts a 128-bit floating-point vector of [4 x float] into a 128-bit floating-point vector of [2 x double].

This intrinsic has no corresponding instruction.

Parameters

__a	A 128-bit floating-point vector of [4 x float].

Returns: A 128-bit floating-point vector of [2 x double] containing the same bitwise pattern as the parameter.

Definition at line 4755 of file emmintrin.h.

References __a.

◆ _mm_castps_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_castps_si128 ( __m128 __a )

static

Casts a 128-bit floating-point vector of [4 x float] into a 128-bit integer vector.

This intrinsic has no corresponding instruction.

Parameters

__a	A 128-bit floating-point vector of [4 x float].

Returns: A 128-bit integer vector containing the same bitwise pattern as the parameter.

Definition at line 4770 of file emmintrin.h.

References __a.

◆ _mm_castsi128_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd ( __m128i __a )

static

Casts a 128-bit integer vector into a 128-bit floating-point vector of [2 x double].

This intrinsic has no corresponding instruction.

Parameters

__a	A 128-bit integer vector.

Returns: A 128-bit floating-point vector of [2 x double] containing the same bitwise pattern as the parameter.

Definition at line 4800 of file emmintrin.h.

References __a.

◆ _mm_castsi128_ps()

static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_castsi128_ps ( __m128i __a )

static

Casts a 128-bit integer vector into a 128-bit floating-point vector of [4 x float].

This intrinsic has no corresponding instruction.

Parameters

__a	A 128-bit integer vector.

Returns: A 128-bit floating-point vector of [4 x float] containing the same bitwise pattern as the parameter.

Definition at line 4785 of file emmintrin.h.

References __a.

◆ _mm_clflush()

void _mm_clflush ( void const * __p )

The cache line containing __p is flushed and invalidated from all caches in the coherency domain.

This intrinsic corresponds to the CLFLUSH instruction.

Parameters

__p	A pointer to the memory location used to identify the cache line to be flushed.

◆ _mm_cmpeq_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmpeq_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding 16-bit values of the 128-bit integer vectors for equality.

Each comparison returns 0x0 for false, 0xFFFF for true.

This intrinsic corresponds to the VPCMPEQW / PCMPEQW instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3094 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpeq_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmpeq_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding 32-bit values of the 128-bit integer vectors for equality.

Each comparison returns 0x0 for false, 0xFFFFFFFF for true.

This intrinsic corresponds to the VPCMPEQD / PCMPEQD instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3113 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpeq_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmpeq_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding 8-bit values of the 128-bit integer vectors for equality.

Each comparison returns 0x0 for false, 0xFF for true.

This intrinsic corresponds to the VPCMPEQB / PCMPEQB instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3075 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpeq_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpeq_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] for equality.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPEQPD / CMPEQPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 435 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpeq_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpeq_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] for equality.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPEQSD / CMPEQSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 692 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpge_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpge_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are greater than or equal to those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLEPD / CMPLEPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 519 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpge_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpge_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than or equal to the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLESD / CMPLESD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 793 of file emmintrin.h.

References __a, __b, and __c.

◆ _mm_cmpgt_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmpgt_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding signed 16-bit values of the 128-bit integer vectors to determine if the values in the first operand are greater than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFF for true.

This intrinsic corresponds to the VPCMPGTW / PCMPGTW instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3155 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_cmplt_epi16().

◆ _mm_cmpgt_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmpgt_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding signed 32-bit values of the 128-bit integer vectors to determine if the values in the first operand are greater than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFF for true.

This intrinsic corresponds to the VPCMPGTD / PCMPGTD instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3175 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_cmplt_epi32().

◆ _mm_cmpgt_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmpgt_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding signed 8-bit values of the 128-bit integer vectors to determine if the values in the first operand are greater than those in the second operand.

Each comparison returns 0x0 for false, 0xFF for true.

This intrinsic corresponds to the VPCMPGTB / PCMPGTB instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3133 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_cmplt_epi8().

◆ _mm_cmpgt_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpgt_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are greater than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLTPD / CMPLTPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 498 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpgt_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpgt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLTSD / CMPLTSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 767 of file emmintrin.h.

References __a, __b, and __c.

◆ _mm_cmple_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmple_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are less than or equal to those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLEPD / CMPLEPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 477 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmple_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmple_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than or equal to the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLESD / CMPLESD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 742 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmplt_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmplt_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding signed 16-bit values of the 128-bit integer vectors to determine if the values in the first operand are less than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFF for true.

This intrinsic corresponds to the VPCMPGTW / PCMPGTW instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3215 of file emmintrin.h.

References __a, __b, and _mm_cmpgt_epi16().

◆ _mm_cmplt_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmplt_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding signed 32-bit values of the 128-bit integer vectors to determine if the values in the first operand are less than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFF for true.

This intrinsic corresponds to the VPCMPGTD / PCMPGTD instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3235 of file emmintrin.h.

References __a, __b, and _mm_cmpgt_epi32().

◆ _mm_cmplt_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cmplt_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Compares each of the corresponding signed 8-bit values of the 128-bit integer vectors to determine if the values in the first operand are less than those in the second operand.

Each comparison returns 0x0 for false, 0xFF for true.

This intrinsic corresponds to the VPCMPGTB / PCMPGTB instruction.

Parameters

__a	A 128-bit integer vector.
__b	A 128-bit integer vector.

Returns: A 128-bit integer vector containing the comparison results.

Definition at line 3195 of file emmintrin.h.

References __a, __b, and _mm_cmpgt_epi8().

◆ _mm_cmplt_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmplt_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are less than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLTPD / CMPLTPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 456 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmplt_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmplt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns false.

This intrinsic corresponds to the VCMPLTSD / CMPLTSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 717 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpneq_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpneq_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are unequal to those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNEQPD / CMPNEQPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 585 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpneq_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpneq_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unequal to the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNEQSD / CMPNEQSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 872 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpnge_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpnge_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not greater than or equal to those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLEPD / CMPNLEPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 669 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpnge_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpnge_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not greater than or equal to the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLESD / CMPNLESD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 973 of file emmintrin.h.

References __a, __b, and __c.

◆ _mm_cmpngt_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpngt_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not greater than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLTPD / CMPNLTPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 648 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpngt_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpngt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not greater than the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLTSD / CMPNLTSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 947 of file emmintrin.h.

References __a, __b, and __c.

◆ _mm_cmpnle_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpnle_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not less than or equal to those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLEPD / CMPNLEPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 627 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpnle_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpnle_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not less than or equal to the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLESD / CMPNLESD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 922 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpnlt_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpnlt_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are not less than those in the second operand.

Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLTPD / CMPNLTPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 606 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpnlt_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpnlt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is not less than the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. If either value in a comparison is NaN, returns true.

This intrinsic corresponds to the VCMPNLTSD / CMPNLTSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 897 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpord_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpord_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are ordered with respect to those in the second operand.

A pair of double-precision values are ordered with respect to each other if neither value is a NaN. Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true.

This intrinsic corresponds to the VCMPORDPD / CMPORDPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 541 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpord_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpord_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is ordered with respect to the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. A pair of double-precision values are ordered with respect to each other if neither value is a NaN.

This intrinsic corresponds to the VCMPORDSD / CMPORDSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 820 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpunord_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpunord_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] to determine if the values in the first operand are unordered with respect to those in the second operand.

A pair of double-precision values are unordered with respect to each other if one or both values are NaN. Each comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true.

This intrinsic corresponds to the VCMPUNORDPD / CMPUNORDPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].
__b	A 128-bit vector of [2 x double].

Returns: A 128-bit vector containing the comparison results.

Definition at line 564 of file emmintrin.h.

References __a, and __b.

◆ _mm_cmpunord_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cmpunord_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unordered with respect to the corresponding value in the second parameter.

The comparison returns 0x0 for false, 0xFFFFFFFFFFFFFFFF for true. A pair of double-precision values are unordered with respect to each other if one or both values are NaN.

This intrinsic corresponds to the VCMPUNORDSD / CMPUNORDSD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: A 128-bit vector. The lower 64 bits contains the comparison results. The upper 64 bits are copied from the upper 64 bits of __a.

Definition at line 847 of file emmintrin.h.

References __a, and __b.

◆ _mm_comieq_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_comieq_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] for equality.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VCOMISD / COMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 996 of file emmintrin.h.

References __a, and __b.

◆ _mm_comige_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_comige_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than or equal to the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VCOMISD / COMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1092 of file emmintrin.h.

References __a, and __b.

◆ _mm_comigt_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_comigt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VCOMISD / COMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1068 of file emmintrin.h.

References __a, and __b.

◆ _mm_comile_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_comile_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than or equal to the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VCOMISD / COMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1044 of file emmintrin.h.

References __a, and __b.

◆ _mm_comilt_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_comilt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VCOMISD / COMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1020 of file emmintrin.h.

References __a, and __b.

◆ _mm_comineq_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_comineq_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unequal to the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 1.

This intrinsic corresponds to the VCOMISD / COMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1116 of file emmintrin.h.

References __a, and __b.

◆ _mm_cvtepi32_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cvtepi32_pd ( __m128i __a )

static

Converts the lower two integer elements of a 128-bit vector of [4 x i32] into two double-precision floating-point values, returned in a 128-bit vector of [2 x double].

The upper two elements of the input vector are unused.

This intrinsic corresponds to the VCVTDQ2PD / CVTDQ2PD instruction.

Parameters

__a	A 128-bit integer vector of [4 x i32]. The lower two integer elements are converted to double-precision values.

The upper two elements are unused.

Returns: A 128-bit vector of [2 x double] containing the converted values.

Definition at line 1315 of file emmintrin.h.

References __a.

Referenced by _mm_mask_cvtepi32_pd(), and _mm_maskz_cvtepi32_pd().

◆ _mm_cvtepi32_ps()

static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_cvtepi32_ps ( __m128i __a )

static

Converts a vector of [4 x i32] into a vector of [4 x float].

This intrinsic corresponds to the VCVTDQ2PS / CVTDQ2PS instruction.

Parameters

__a	A 128-bit integer vector.

Returns: A 128-bit vector of [4 x float] containing the converted values.

Definition at line 3313 of file emmintrin.h.

References __a.

Referenced by _mm_mask_cvtepi32_ps(), and _mm_maskz_cvtepi32_ps().

◆ _mm_cvtpd_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cvtpd_epi32 ( __m128d __a )

static

Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed 32-bit integer values, returned in the lower 64 bits of a 128-bit vector of [4 x i32].

The upper 64 bits of the result vector are set to zero.

If a converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the VCVTPD2DQ / CVTPD2DQ instruction.

Parameters

__a	A 128-bit vector of [2 x double].

Returns: A 128-bit vector of [4 x i32] whose lower 64 bits contain the converted values. The upper 64 bits are set to zero.

Definition at line 1337 of file emmintrin.h.

References __a.

◆ _mm_cvtpd_pi32()

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX _mm_cvtpd_pi32 ( __m128d __a )

static

Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed 32-bit integer values, returned in a 64-bit vector of [2 x i32].

If a converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the CVTPD2PI instruction.

Parameters

__a	A 128-bit vector of [2 x double].

Returns: A 64-bit vector of [2 x i32] containing the converted values.

Definition at line 1489 of file emmintrin.h.

References __a.

◆ _mm_cvtpd_ps()

static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_cvtpd_ps ( __m128d __a )

static

Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two single-precision floating-point values, returned in the lower 64 bits of a 128-bit vector of [4 x float].

The upper 64 bits of the result vector are set to zero.

This intrinsic corresponds to the VCVTPD2PS / CVTPD2PS instruction.

Parameters

__a	A 128-bit vector of [2 x double].

Returns: A 128-bit vector of [4 x float] whose lower 64 bits contain the converted values. The upper 64 bits are set to zero.

Definition at line 1276 of file emmintrin.h.

References __a.

◆ _mm_cvtpi32_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS_MMX _mm_cvtpi32_pd ( __m64 __a )

static

Converts the two signed 32-bit integer elements of a 64-bit vector of [2 x i32] into two double-precision floating-point values, returned in a 128-bit vector of [2 x double].

This intrinsic corresponds to the CVTPI2PD instruction.

Parameters

__a	A 64-bit vector of [2 x i32].

Returns: A 128-bit vector of [2 x double] containing the converted values.

Definition at line 1523 of file emmintrin.h.

References __a.

◆ _mm_cvtps_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cvtps_epi32 ( __m128 __a )

static

Converts a vector of [4 x float] into a vector of [4 x i32].

If a converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the VCVTPS2DQ / CVTPS2DQ instruction.

Parameters

__a	A 128-bit vector of [4 x float].

Returns: A 128-bit integer vector of [4 x i32] containing the converted values.

Definition at line 3331 of file emmintrin.h.

References __a.

Referenced by _mm_mask_cvtps_epi32(), and _mm_maskz_cvtps_epi32().

◆ _mm_cvtps_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cvtps_pd ( __m128 __a )

static

Converts the lower two single-precision floating-point elements of a 128-bit vector of [4 x float] into two double-precision floating-point values, returned in a 128-bit vector of [2 x double].

The upper two elements of the input vector are unused.

This intrinsic corresponds to the VCVTPS2PD / CVTPS2PD instruction.

Parameters

__a	A 128-bit vector of [4 x float]. The lower two single-precision floating-point elements are converted to double-precision values. The upper two elements are unused.

Returns: A 128-bit vector of [2 x double] containing the converted values.

Definition at line 1294 of file emmintrin.h.

References __a.

Referenced by _mm_mask_cvtps_pd(), and _mm_maskz_cvtps_pd().

◆ _mm_cvtsd_f64()

static __inline__ double __DEFAULT_FN_ATTRS _mm_cvtsd_f64 ( __m128d __a )

static

Returns the low-order element of a 128-bit vector of [2 x double] as a double-precision floating-point value.

This intrinsic has no corresponding instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower 64 bits are returned.

Returns: A double-precision floating-point value copied from the lower 64 bits of __a.

Definition at line 1538 of file emmintrin.h.

References __a.

◆ _mm_cvtsd_si32()

static __inline__ int __DEFAULT_FN_ATTRS _mm_cvtsd_si32 ( __m128d __a )

static

Converts the low-order element of a 128-bit vector of [2 x double] into a 32-bit signed integer value.

If the converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the VCVTSD2SI / CVTSD2SI instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower 64 bits are used in the conversion.

Returns: A 32-bit signed integer containing the converted value.

Definition at line 1356 of file emmintrin.h.

References __a.

◆ _mm_cvtsd_ss()

static __inline__ __m128 __DEFAULT_FN_ATTRS _mm_cvtsd_ss	(	__m128	__a,
		__m128d	__b
	)

static

Converts the lower double-precision floating-point element of a 128-bit vector of [2 x double], in the second parameter, into a single-precision floating-point value, returned in the lower 32 bits of a 128-bit vector of [4 x float].

The upper 96 bits of the result vector are copied from the upper 96 bits of the first parameter.

This intrinsic corresponds to the VCVTSD2SS / CVTSD2SS instruction.

Parameters

__a	A 128-bit vector of [4 x float]. The upper 96 bits of this parameter are copied to the upper 96 bits of the result.
__b	A 128-bit vector of [2 x double]. The lower double-precision floating-point element is used in the conversion.

Returns: A 128-bit vector of [4 x float]. The lower 32 bits contain the converted value from the second parameter. The upper 96 bits are copied from the upper 96 bits of the first parameter.

Definition at line 1379 of file emmintrin.h.

References __a, and __b.

◆ _mm_cvtsi128_si32()

static __inline__ int __DEFAULT_FN_ATTRS _mm_cvtsi128_si32 ( __m128i __a )

static

Moves the least significant 32 bits of a vector of [4 x i32] to a 32-bit signed integer value.

This intrinsic corresponds to the VMOVD / MOVD instruction.

Parameters

__a	A vector of [4 x i32]. The least significant 32 bits are moved to the destination.

Returns: A 32-bit signed integer containing the moved value.

Definition at line 3394 of file emmintrin.h.

References __a, and __b.

◆ _mm_cvtsi128_si64()

static __inline__ long long __DEFAULT_FN_ATTRS _mm_cvtsi128_si64 ( __m128i __a )

static

Moves the least significant 64 bits of a vector of [2 x i64] to a 64-bit signed integer value.

This intrinsic corresponds to the VMOVQ / MOVQ instruction.

Parameters

__a	A vector of [2 x i64]. The least significant 64 bits are moved to the destination.

Returns: A 64-bit signed integer containing the moved value.

Definition at line 3410 of file emmintrin.h.

References __a.

◆ _mm_cvtsi32_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cvtsi32_sd	(	__m128d	__a,
		int	__b
	)

static

Converts a 32-bit signed integer value, in the second parameter, into a double-precision floating-point value, returned in the lower 64 bits of a 128-bit vector of [2 x double].

The upper 64 bits of the result vector are copied from the upper 64 bits of the first parameter.

This intrinsic corresponds to the VCVTSI2SD / CVTSI2SD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The upper 64 bits of this parameter are copied to the upper 64 bits of the result.
__b	A 32-bit signed integer containing the value to be converted.

Returns: A 128-bit vector of [2 x double]. The lower 64 bits contain the converted value from the second parameter. The upper 64 bits are copied from the upper 64 bits of the first parameter.

Definition at line 1401 of file emmintrin.h.

References __a, and __b.

◆ _mm_cvtsi32_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cvtsi32_si128 ( int __a )

static

Returns a vector of [4 x i32] where the lowest element is the input operand and the remaining elements are zero.

This intrinsic corresponds to the VMOVD / MOVD instruction.

Parameters

__a	A 32-bit signed integer operand.

Returns: A 128-bit vector of [4 x i32].

Definition at line 3364 of file emmintrin.h.

References __a.

◆ _mm_cvtsi64_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cvtsi64_si128 ( long long __a )

static

Returns a vector of [2 x i64] where the lower element is the input operand and the upper element is zero.

This intrinsic corresponds to the VMOVQ / MOVQ instruction in 64-bit mode.

Parameters

__a	A 64-bit signed integer operand containing the value to be converted.

Returns: A 128-bit vector of [2 x i64] containing the converted value.

Definition at line 3379 of file emmintrin.h.

References __a.

◆ _mm_cvtss_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_cvtss_sd	(	__m128d	__a,
		__m128	__b
	)

static

Converts the lower single-precision floating-point element of a 128-bit vector of [4 x float], in the second parameter, into a double-precision floating-point value, returned in the lower 64 bits of a 128-bit vector of [2 x double].

The upper 64 bits of the result vector are copied from the upper 64 bits of the first parameter.

This intrinsic corresponds to the VCVTSS2SD / CVTSS2SD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The upper 64 bits of this parameter are copied to the upper 64 bits of the result.
__b	A 128-bit vector of [4 x float]. The lower single-precision floating-point element is used in the conversion.

Returns: A 128-bit vector of [2 x double]. The lower 64 bits contain the converted value from the second parameter. The upper 64 bits are copied from the upper 64 bits of the first parameter.

Definition at line 1426 of file emmintrin.h.

References __a, and __b.

◆ _mm_cvttpd_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cvttpd_epi32 ( __m128d __a )

static

Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed truncated (rounded toward zero) 32-bit integer values, returned in the lower 64 bits of a 128-bit vector of [4 x i32].

If a converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the VCVTTPD2DQ / CVTTPD2DQ instruction.

Parameters

__a	A 128-bit vector of [2 x double].

Returns: A 128-bit vector of [4 x i32] whose lower 64 bits contain the converted values. The upper 64 bits are set to zero.

Definition at line 1450 of file emmintrin.h.

References __a.

◆ _mm_cvttpd_pi32()

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX _mm_cvttpd_pi32 ( __m128d __a )

static

Converts the two double-precision floating-point elements of a 128-bit vector of [2 x double] into two signed truncated (rounded toward zero) 32-bit integer values, returned in a 64-bit vector of [2 x i32].

If a converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the CVTTPD2PI instruction.

Parameters

__a	A 128-bit vector of [2 x double].

Returns: A 64-bit vector of [2 x i32] containing the converted values.

Definition at line 1508 of file emmintrin.h.

References __a.

◆ _mm_cvttps_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_cvttps_epi32 ( __m128 __a )

static

Converts a vector of [4 x float] into four signed truncated (rounded toward zero) 32-bit integers, returned in a vector of [4 x i32].

If a converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the VCVTTPS2DQ / CVTTPS2DQ instruction.

Parameters

__a	A 128-bit vector of [4 x float].

Returns: A 128-bit vector of [4 x i32] containing the converted values.

Definition at line 3350 of file emmintrin.h.

References __a.

Referenced by _mm_mask_cvttps_epi32(), and _mm_maskz_cvttps_epi32().

◆ _mm_cvttsd_si32()

static __inline__ int __DEFAULT_FN_ATTRS _mm_cvttsd_si32 ( __m128d __a )

static

Converts the low-order element of a [2 x double] vector into a 32-bit signed truncated (rounded toward zero) integer value.

If the converted value does not fit in a 32-bit integer, raises a floating-point invalid exception. If the exception is masked, returns the most negative integer.

This intrinsic corresponds to the VCVTTSD2SI / CVTTSD2SI instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower 64 bits are used in the conversion.

Returns: A 32-bit signed integer containing the converted value.

Definition at line 1470 of file emmintrin.h.

References __a.

◆ _mm_div_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_div_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Performs an element-by-element division of two 128-bit vectors of [2 x double].

This intrinsic corresponds to the VDIVPD / DIVPD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing the dividend.
__b	A 128-bit vector of [2 x double] containing the divisor.

Returns: A 128-bit vector of [2 x double] containing the quotients of both operands.

Definition at line 212 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_div_pd(), and _mm_maskz_div_pd().

◆ _mm_div_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_div_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Divides the lower double-precision value of the first operand by the lower double-precision value of the second operand and returns the quotient in the lower 64 bits of the result.

The upper 64 bits of the result are copied from the upper double-precision value of the first operand.

This intrinsic corresponds to the VDIVSD / DIVSD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing the dividend.
__b	A 128-bit vector of [2 x double] containing divisor.

Returns: A 128-bit vector of [2 x double] whose lower 64 bits contain the quotient of the lower 64 bits of both operands. The upper 64 bits are copied from the upper 64 bits of the first source operand.

Definition at line 193 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_div_sd(), and _mm_maskz_div_sd().

◆ _mm_lfence()

void _mm_lfence ( void )

Forces strong memory ordering (serialization) between load instructions preceding this instruction and load instructions following this instruction, ensuring the system completes all previous loads before executing subsequent loads.

This intrinsic corresponds to the LFENCE instruction.

◆ _mm_load1_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_load1_pd ( double const * __dp )

static

Loads a double-precision floating-point value from a specified memory location and duplicates it to both vector elements of a 128-bit vector of [2 x double].

This intrinsic corresponds to the VMOVDDUP / MOVDDUP instruction.

Parameters

__dp	A pointer to a memory location containing a double-precision value.

Returns: A 128-bit vector of [2 x double] containing the loaded and duplicated values.

Definition at line 1569 of file emmintrin.h.

◆ _mm_load_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_load_pd ( double const * __dp )

static

Loads a 128-bit floating-point vector of [2 x double] from an aligned memory location.

This intrinsic corresponds to the VMOVAPD / MOVAPD instruction.

Parameters

__dp	A pointer to a 128-bit memory location. The address of the memory location has to be 16-byte aligned.

Returns: A 128-bit vector of [2 x double] containing the loaded values.

Definition at line 1553 of file emmintrin.h.

◆ _mm_load_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_load_sd ( double const * __dp )

static

Loads a 64-bit double-precision value to the low element of a 128-bit integer vector and clears the upper element.

This intrinsic corresponds to the VMOVSD / MOVSD instruction.

Parameters

__dp	A pointer to a memory location containing a double-precision value. The address of the memory location does not have to be aligned.

Returns: A 128-bit vector of [2 x double] containing the loaded value.

Definition at line 1684 of file emmintrin.h.

◆ _mm_load_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_load_si128 ( __m128i const * __p )

static

Moves packed integer values from an aligned 128-bit memory location to elements in a 128-bit integer vector.

This intrinsic corresponds to the VMOVDQA / MOVDQA instruction.

Parameters

__p	An aligned pointer to a memory location containing integer values.

Returns: A 128-bit integer vector containing the moved values.

Definition at line 3425 of file emmintrin.h.

References __p.

Referenced by fastParseASCIIIdentifier().

◆ _mm_loadh_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_loadh_pd	(	__m128d	__a,
		double const *	__dp
	)

static

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.

This intrinsic corresponds to the VMOVHPD / MOVHPD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. Bits [63:0] are written to bits [63:0] of the result.
__dp	A pointer to a 64-bit memory location containing a double-precision floating-point value that is loaded. The loaded value is written to bits [127:64] of the result. The address of the memory location does not have to be aligned.

Returns: A 128-bit vector of [2 x double] containing the moved values.

Definition at line 1709 of file emmintrin.h.

References __a.

◆ _mm_loadl_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_loadl_epi64 ( __m128i_u const * __p )

static

Returns a vector of [2 x i64] where the lower element is taken from the lower element of the operand, and the upper element is zero.

This intrinsic corresponds to the VMOVQ / MOVQ instruction.

Parameters

__p	A 128-bit vector of [2 x i64]. Bits [63:0] are written to bits [63:0] of the destination.

Returns: A 128-bit vector of [2 x i64]. The lower order bits contain the moved value. The higher order bits are cleared.

Definition at line 3460 of file emmintrin.h.

References __p.

◆ _mm_loadl_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_loadl_pd	(	__m128d	__a,
		double const *	__dp
	)

static

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.

This intrinsic corresponds to the VMOVLPD / MOVLPD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. Bits [127:64] are written to bits [127:64] of the result.
__dp	A pointer to a 64-bit memory location containing a double-precision floating-point value that is loaded. The loaded value is written to bits [63:0] of the result. The address of the memory location does not have to be aligned.

Returns: A 128-bit vector of [2 x double] containing the moved values.

Definition at line 1735 of file emmintrin.h.

References __a.

◆ _mm_loadr_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_loadr_pd ( double const * __dp )

static

Loads two double-precision values, in reverse order, from an aligned memory location into a 128-bit vector of [2 x double].

This intrinsic corresponds to the VMOVAPD / MOVAPD instruction + needed shuffling instructions. In AVX mode, the shuffling may be combined with the VMOVAPD, resulting in only a VPERMILPD instruction.

Parameters

__dp	A 16-byte aligned pointer to an array of double-precision values to be loaded in reverse order.

Returns: A 128-bit vector of [2 x double] containing the reversed loaded values.

Definition at line 1593 of file emmintrin.h.

◆ _mm_loadu_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_loadu_pd ( double const * __dp )

static

Loads a 128-bit floating-point vector of [2 x double] from an unaligned memory location.

This intrinsic corresponds to the VMOVUPD / MOVUPD instruction.

Parameters

__dp	A pointer to a 128-bit memory location. The address of the memory location does not have to be aligned.

Returns: A 128-bit vector of [2 x double] containing the loaded values.

Definition at line 1609 of file emmintrin.h.

References __v.

Referenced by _mm256_broadcast_pd(), and _mm256_loadu2_m128d().

◆ _mm_loadu_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_loadu_si128 ( __m128i_u const * __p )

static

Moves packed integer values from an unaligned 128-bit memory location to elements in a 128-bit integer vector.

This intrinsic corresponds to the VMOVDQU / MOVDQU instruction.

Parameters

__p	A pointer to a memory location containing integer values.

Returns: A 128-bit integer vector containing the moved values.

Definition at line 3440 of file emmintrin.h.

References __p, and __v.

Referenced by _mm256_loadu2_m128i(), and fastParseASCIIIdentifier().

◆ _mm_loadu_si16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_loadu_si16 ( void const * __a )

static

Loads a 16-bit integer value to the low element of a 128-bit integer vector and clears the upper element.

This intrinsic does not correspond to a specific instruction.

Parameters

__a	A pointer to a 16-bit memory location. The address of the memory location does not have to be aligned.

Returns: A 128-bit vector of [8 x i16] containing the loaded value.

Definition at line 1665 of file emmintrin.h.

References __a, and __v.

◆ _mm_loadu_si32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_loadu_si32 ( void const * __a )

static

Loads a 32-bit integer value to the low element of a 128-bit integer vector and clears the upper element.

This intrinsic corresponds to the VMOVD / MOVD instruction.

Parameters

__a	A pointer to a 32-bit memory location. The address of the memory location does not have to be aligned.

Returns: A 128-bit vector of [4 x i32] containing the loaded value.

Definition at line 1646 of file emmintrin.h.

References __a, and __v.

◆ _mm_loadu_si64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_loadu_si64 ( void const * __a )

static

Loads a 64-bit integer value to the low element of a 128-bit integer vector and clears the upper element.

This intrinsic corresponds to the VMOVQ / MOVQ instruction.

Parameters

__a	A pointer to a 64-bit memory location. The address of the memory location does not have to be aligned.

Returns: A 128-bit vector of [2 x i64] containing the loaded value.

Definition at line 1627 of file emmintrin.h.

References __a, and __v.

◆ _mm_madd_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_madd_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Multiplies the corresponding elements of two 128-bit signed [8 x i16] vectors, producing eight intermediate 32-bit signed integer products, and adds the consecutive pairs of 32-bit products to form a 128-bit signed [4 x i32] vector.

For example, bits [15:0] of both parameters are multiplied producing a 32-bit product, bits [31:16] of both parameters are multiplied producing a 32-bit product, and the sum of those two products becomes bits [31:0] of the result.

This intrinsic corresponds to the VPMADDWD / PMADDWD instruction.

Parameters

__a	A 128-bit signed [8 x i16] vector.
__b	A 128-bit signed [8 x i16] vector.

Returns: A 128-bit signed [4 x i32] vector containing the sums of products of both parameters.

Definition at line 2283 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_madd_epi16(), and _mm_maskz_madd_epi16().

◆ _mm_maskmoveu_si128()

static __inline__ void __DEFAULT_FN_ATTRS _mm_maskmoveu_si128	(	__m128i	__d,
		__m128i	__n,
		char *	__p
	)

static

Moves bytes selected by the mask from the first operand to the specified unaligned memory location.

When a mask bit is 1, the corresponding byte is written, otherwise it is not written.

To minimize caching, the data is flagged as non-temporal (unlikely to be used again soon). Exception and trap behavior for elements not selected for storage to memory are implementation dependent.

This intrinsic corresponds to the VMASKMOVDQU / MASKMOVDQU instruction.

Parameters

__d	A 128-bit integer vector containing the values to be moved.
__n	A 128-bit integer vector containing the mask. The most significant bit of each byte represents the mask bits.
__p	A pointer to an unaligned 128-bit memory location where the specified values are moved.

Definition at line 3978 of file emmintrin.h.

References __p.

◆ _mm_max_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_max_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Compares corresponding elements of two 128-bit signed [8 x i16] vectors, saving the greater value from each comparison in the corresponding element of a 128-bit result vector of [8 x i16].

This intrinsic corresponds to the VPMAXSW / PMAXSW instruction.

Parameters

__a	A 128-bit signed [8 x i16] vector.
__b	A 128-bit signed [8 x i16] vector.

Returns: A 128-bit signed [8 x i16] vector containing the greater value of each comparison.

Definition at line 2302 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_max_epi16(), and _mm_maskz_max_epi16().

◆ _mm_max_epu8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_max_epu8	(	__m128i	__a,
		__m128i	__b
	)

static

Compares corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving the greater value from each comparison in the corresponding element of a 128-bit result vector of [16 x i8].

This intrinsic corresponds to the VPMAXUB / PMAXUB instruction.

Parameters

__a	A 128-bit unsigned [16 x i8] vector.
__b	A 128-bit unsigned [16 x i8] vector.

Returns: A 128-bit unsigned [16 x i8] vector containing the greater value of each comparison.

Definition at line 2321 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_max_epu8(), and _mm_maskz_max_epu8().

◆ _mm_max_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_max_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Performs element-by-element comparison of the two 128-bit vectors of [2 x double] and returns a vector containing the greater of each pair of values.

If either value in a comparison is NaN, returns the value from __b.

This intrinsic corresponds to the VMAXPD / MAXPD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the operands.
__b	A 128-bit vector of [2 x double] containing one of the operands.

Returns: A 128-bit vector of [2 x double] containing the maximum values between both operands.

Definition at line 344 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_max_pd(), and _mm_maskz_max_pd().

◆ _mm_max_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_max_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares lower 64-bit double-precision values of both operands, and returns the greater of the pair of values in the lower 64-bits of the result.

The upper 64 bits of the result are copied from the upper double-precision value of the first operand.

If either value in a comparison is NaN, returns the value from __b.

This intrinsic corresponds to the VMAXSD / MAXSD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the operands. The lower 64 bits of this operand are used in the comparison.
__b	A 128-bit vector of [2 x double] containing one of the operands. The lower 64 bits of this operand are used in the comparison.

Returns: A 128-bit vector of [2 x double] whose lower 64 bits contain the maximum value between both operands. The upper 64 bits are copied from the upper 64 bits of the first source operand.

Definition at line 323 of file emmintrin.h.

References __a, and __b.

◆ _mm_mfence()

void _mm_mfence ( void )

Forces strong memory ordering (serialization) between load and store instructions preceding this instruction and load and store instructions following this instruction, ensuring that the system completes all previous memory accesses before executing subsequent memory accesses.

This intrinsic corresponds to the MFENCE instruction.

◆ _mm_min_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_min_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Compares corresponding elements of two 128-bit signed [8 x i16] vectors, saving the smaller value from each comparison in the corresponding element of a 128-bit result vector of [8 x i16].

This intrinsic corresponds to the VPMINSW / PMINSW instruction.

Parameters

__a	A 128-bit signed [8 x i16] vector.
__b	A 128-bit signed [8 x i16] vector.

Returns: A 128-bit signed [8 x i16] vector containing the smaller value of each comparison.

Definition at line 2340 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_min_epi16(), and _mm_maskz_min_epi16().

◆ _mm_min_epu8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_min_epu8	(	__m128i	__a,
		__m128i	__b
	)

static

Compares corresponding elements of two 128-bit unsigned [16 x i8] vectors, saving the smaller value from each comparison in the corresponding element of a 128-bit result vector of [16 x i8].

This intrinsic corresponds to the VPMINUB / PMINUB instruction.

Parameters

__a	A 128-bit unsigned [16 x i8] vector.
__b	A 128-bit unsigned [16 x i8] vector.

Returns: A 128-bit unsigned [16 x i8] vector containing the smaller value of each comparison.

Definition at line 2359 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_min_epu8(), and _mm_maskz_min_epu8().

◆ _mm_min_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_min_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Performs element-by-element comparison of the two 128-bit vectors of [2 x double] and returns a vector containing the lesser of each pair of values.

If either value in a comparison is NaN, returns the value from __b.

This intrinsic corresponds to the VMINPD / MINPD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the operands.
__b	A 128-bit vector of [2 x double] containing one of the operands.

Returns: A 128-bit vector of [2 x double] containing the minimum values between both operands.

Definition at line 298 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_min_pd(), and _mm_maskz_min_pd().

◆ _mm_min_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_min_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares lower 64-bit double-precision values of both operands, and returns the lesser of the pair of values in the lower 64-bits of the result.

The upper 64 bits of the result are copied from the upper double-precision value of the first operand.

If either value in a comparison is NaN, returns the value from __b.

This intrinsic corresponds to the VMINSD / MINSD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the operands. The lower 64 bits of this operand are used in the comparison.
__b	A 128-bit vector of [2 x double] containing one of the operands. The lower 64 bits of this operand are used in the comparison.

Returns: A 128-bit vector of [2 x double] whose lower 64 bits contain the minimum value between both operands. The upper 64 bits are copied from the upper 64 bits of the first source operand.

Definition at line 277 of file emmintrin.h.

References __a, and __b.

◆ _mm_move_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_move_epi64 ( __m128i __a )

static

Moves the lower 64 bits of a 128-bit integer vector to a 128-bit integer vector, zeroing the upper bits.

This intrinsic corresponds to the VMOVQ / MOVQ instruction.

Parameters

__a	A 128-bit integer vector operand. The lower 64 bits are moved to the destination.

Returns: A 128-bit integer vector. The lower 64 bits contain the value from the operand. The upper 64 bits are assigned zeros.

Definition at line 4622 of file emmintrin.h.

References __a, and _mm_setzero_si128().

◆ _mm_move_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_move_sd	(	__m128d	__a,
		__m128d	__b
	)

static

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.

This intrinsic corresponds to the VBLENDPD / BLENDPD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The upper 64 bits are written to the upper 64 bits of the result.
__b	A 128-bit vector of [2 x double]. The lower 64 bits are written to the lower 64 bits of the result.

Returns: A 128-bit vector of [2 x double] containing the moved values.

Definition at line 1876 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_move_sd(), and _mm_maskz_move_sd().

◆ _mm_movemask_epi8()

static __inline__ int __DEFAULT_FN_ATTRS _mm_movemask_epi8 ( __m128i __a )

static

Copies the values of the most significant bits from each 8-bit element in a 128-bit integer vector of [16 x i8] to create a 16-bit mask value, zero-extends the value, and writes it to the destination.

This intrinsic corresponds to the VPMOVMSKB / PMOVMSKB instruction.

Parameters

__a	A 128-bit integer vector containing the values with bits to be extracted.

Returns: The most significant bits from each 8-bit element in __a, written to bits [15:0]. The other bits are assigned zeros.

Definition at line 4263 of file emmintrin.h.

References __a.

◆ _mm_movemask_pd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_movemask_pd ( __m128d __a )

static

Extracts the sign bits of the double-precision values in the 128-bit vector of [2 x double], zero-extends the value, and writes it to the low-order bits of the destination.

This intrinsic corresponds to the VMOVMSKPD / MOVMSKPD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing the values with sign bits to be extracted.

Returns: The sign bits from each of the double-precision elements in __a, written to bits [1:0]. The remaining bits are assigned values of zero.

Definition at line 4679 of file emmintrin.h.

References __a.

◆ _mm_movepi64_pi64()

static __inline__ __m64 __DEFAULT_FN_ATTRS _mm_movepi64_pi64 ( __m128i __a )

static

Returns the lower 64 bits of a 128-bit integer vector as a 64-bit integer.

This intrinsic corresponds to the MOVDQ2Q instruction.

Parameters

__a	A 128-bit integer vector operand. The lower 64 bits are moved to the destination.

Returns: A 64-bit integer containing the lower 64 bits of the parameter.

Definition at line 4591 of file emmintrin.h.

References __a.

◆ _mm_movpi64_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_movpi64_epi64 ( __m64 __a )

static

Moves the 64-bit operand to a 128-bit integer vector, zeroing the upper bits.

This intrinsic corresponds to the MOVD+VMOVQ instruction.

Parameters

__a	A 64-bit value.

Returns: A 128-bit integer vector. The lower 64 bits contain the value from the operand. The upper 64 bits are assigned zeros.

Definition at line 4606 of file emmintrin.h.

References __a.

◆ _mm_mul_epu32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_mul_epu32	(	__m128i	__a,
		__m128i	__b
	)

static

Multiplies 32-bit unsigned integer values contained in the lower bits of the corresponding elements of two [2 x i64] vectors, and returns the 64-bit products in the corresponding elements of a [2 x i64] vector.

This intrinsic corresponds to the VPMULUDQ / PMULUDQ instruction.

Parameters

__a	A [2 x i64] vector containing one of the source operands.
__b	A [2 x i64] vector containing one of the source operands.

Returns: A [2 x i64] vector containing the product of both operands.

Definition at line 2452 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_mul_epu32(), and _mm_maskz_mul_epu32().

◆ _mm_mul_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_mul_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Multiplies two 128-bit vectors of [2 x double].

This intrinsic corresponds to the VMULPD / MULPD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the operands.
__b	A 128-bit vector of [2 x double] containing one of the operands.

Returns: A 128-bit vector of [2 x double] containing the products of both operands.

Definition at line 171 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_mul_pd(), and _mm_maskz_mul_pd().

◆ _mm_mul_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_mul_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Multiplies lower double-precision values in both operands and returns the product in the lower 64 bits of the result.

The upper 64 bits of the result are copied from the upper double-precision value of the first operand.

This intrinsic corresponds to the VMULSD / MULSD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the source operands.
__b	A 128-bit vector of [2 x double] containing one of the source operands.

Returns: A 128-bit vector of [2 x double] whose lower 64 bits contain the product of the lower 64 bits of both operands. The upper 64 bits are copied from the upper 64 bits of the first source operand.

Definition at line 153 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_mul_sd(), and _mm_maskz_mul_sd().

◆ _mm_mul_su32()

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX _mm_mul_su32	(	__m64	__a,
		__m64	__b
	)

static

Multiplies 32-bit unsigned integer values contained in the lower bits of the two 64-bit integer vectors and returns the 64-bit unsigned product.

This intrinsic corresponds to the PMULUDQ instruction.

Parameters

__a	A 64-bit integer containing one of the source operands.
__b	A 64-bit integer containing one of the source operands.

Returns: A 64-bit integer vector containing the product of both operands.

Definition at line 2434 of file emmintrin.h.

References __a, and __b.

◆ _mm_mulhi_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_mulhi_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Multiplies the corresponding elements of two signed [8 x i16] vectors, saving the upper 16 bits of each 32-bit product in the corresponding element of a 128-bit signed [8 x i16] result vector.

This intrinsic corresponds to the VPMULHW / PMULHW instruction.

Parameters

__a	A 128-bit signed [8 x i16] vector.
__b	A 128-bit signed [8 x i16] vector.

Returns: A 128-bit signed [8 x i16] vector containing the upper 16 bits of each of the eight 32-bit products.

Definition at line 2378 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_mulhi_epi16(), and _mm_maskz_mulhi_epi16().

◆ _mm_mulhi_epu16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_mulhi_epu16	(	__m128i	__a,
		__m128i	__b
	)

static

Multiplies the corresponding elements of two unsigned [8 x i16] vectors, saving the upper 16 bits of each 32-bit product in the corresponding element of a 128-bit unsigned [8 x i16] result vector.

This intrinsic corresponds to the VPMULHUW / PMULHUW instruction.

Parameters

__a	A 128-bit unsigned [8 x i16] vector.
__b	A 128-bit unsigned [8 x i16] vector.

Returns: A 128-bit unsigned [8 x i16] vector containing the upper 16 bits of each of the eight 32-bit products.

Definition at line 2397 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_mulhi_epu16(), and _mm_maskz_mulhi_epu16().

◆ _mm_mullo_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_mullo_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Multiplies the corresponding elements of two signed [8 x i16] vectors, saving the lower 16 bits of each 32-bit product in the corresponding element of a 128-bit signed [8 x i16] result vector.

This intrinsic corresponds to the VPMULLW / PMULLW instruction.

Parameters

__a	A 128-bit signed [8 x i16] vector.
__b	A 128-bit signed [8 x i16] vector.

Returns: A 128-bit signed [8 x i16] vector containing the lower 16 bits of each of the eight 32-bit products.

Definition at line 2416 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_mullo_epi16(), and _mm_maskz_mullo_epi16().

◆ _mm_or_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_or_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Performs a bitwise OR of two 128-bit vectors of [2 x double].

This intrinsic corresponds to the VPOR / POR instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the source operands.
__b	A 128-bit vector of [2 x double] containing one of the source operands.

Returns: A 128-bit vector of [2 x double] containing the bitwise OR of the values between both operands.

Definition at line 398 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_or_pd(), and _mm_maskz_or_pd().

◆ _mm_or_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_or_si128	(	__m128i	__a,
		__m128i	__b
	)

static

Performs a bitwise OR of two 128-bit integer vectors.

This intrinsic corresponds to the VPOR / POR instruction.

Parameters

__a	A 128-bit integer vector containing one of the source operands.
__b	A 128-bit integer vector containing one of the source operands.

Returns: A 128-bit integer vector containing the bitwise OR of the values in both operands.

Definition at line 2697 of file emmintrin.h.

References __a, and __b.

◆ _mm_packs_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_packs_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Converts, with saturation, 16-bit signed integers from both 128-bit integer vector operands into 8-bit signed integers, and packs the results into the destination.

Positive values greater than 0x7F are saturated to 0x7F. Negative values less than 0x80 are saturated to 0x80.

This intrinsic corresponds to the VPACKSSWB / PACKSSWB instruction.

Parameters

__a	A 128-bit integer vector of [8 x i16]. The converted [8 x i8] values are written to the lower 64 bits of the result.
__b	A 128-bit integer vector of [8 x i16]. The converted [8 x i8] values are written to the higher 64 bits of the result.

Returns: A 128-bit vector of [16 x i8] containing the converted values.

Definition at line 4142 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_packs_epi16(), and _mm_maskz_packs_epi16().

◆ _mm_packs_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_packs_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Converts, with saturation, 32-bit signed integers from both 128-bit integer vector operands into 16-bit signed integers, and packs the results into the destination.

Positive values greater than 0x7FFF are saturated to 0x7FFF. Negative values less than 0x8000 are saturated to 0x8000.

This intrinsic corresponds to the VPACKSSDW / PACKSSDW instruction.

Parameters

__a	A 128-bit integer vector of [4 x i32]. The converted [4 x i16] values are written to the lower 64 bits of the result.
__b	A 128-bit integer vector of [4 x i32]. The converted [4 x i16] values are written to the higher 64 bits of the result.

Returns: A 128-bit vector of [8 x i16] containing the converted values.

Definition at line 4165 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_packs_epi32(), and _mm_maskz_packs_epi32().

◆ _mm_packus_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_packus_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Converts, with saturation, 16-bit signed integers from both 128-bit integer vector operands into 8-bit unsigned integers, and packs the results into the destination.

Values greater than 0xFF are saturated to 0xFF. Values less than 0x00 are saturated to 0x00.

This intrinsic corresponds to the VPACKUSWB / PACKUSWB instruction.

Parameters

__a	A 128-bit integer vector of [8 x i16]. The converted [8 x i8] values are written to the lower 64 bits of the result.
__b	A 128-bit integer vector of [8 x i16]. The converted [8 x i8] values are written to the higher 64 bits of the result.

Returns: A 128-bit vector of [16 x i8] containing the converted values.

Definition at line 4188 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_packus_epi16(), and _mm_maskz_packus_epi16().

◆ _mm_pause()

void _mm_pause ( void )

Indicates that a spin loop is being executed for the purposes of optimizing power consumption during the loop.

This intrinsic corresponds to the PAUSE instruction.

◆ _mm_sad_epu8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sad_epu8	(	__m128i	__a,
		__m128i	__b
	)

static

Computes the absolute differences of corresponding 8-bit integer values in two 128-bit vectors.

Sums the first 8 absolute differences, and separately sums the second 8 absolute differences. Packs these two unsigned 16-bit integer sums into the upper and lower elements of a [2 x i64] vector.

This intrinsic corresponds to the VPSADBW / PSADBW instruction.

Parameters

__a	A 128-bit integer vector containing one of the source operands.
__b	A 128-bit integer vector containing one of the source operands.

Returns: A [2 x i64] vector containing the sums of the sets of absolute differences between both operands.

Definition at line 2473 of file emmintrin.h.

References __a, and __b.

◆ _mm_set1_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set1_epi16 ( short __w )

static

Initializes all values in a 128-bit vector of [8 x i16] with the specified 16-bit value.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__w	A 16-bit value used to initialize the elements of the destination integer vector.

Returns: An initialized 128-bit vector of [8 x i16] with all elements containing the value provided in the operand.

Definition at line 3706 of file emmintrin.h.

References _mm_set_epi16().

Referenced by _mm_mask_reduce_and_epi16(), _mm_mask_reduce_max_epi16(), _mm_mask_reduce_min_epi16(), _mm_mask_reduce_min_epu16(), _mm_mask_reduce_mul_epi16(), _mm_mask_set1_epi16(), and _mm_maskz_set1_epi16().

◆ _mm_set1_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set1_epi32 ( int __i )

static

Initializes all values in a 128-bit vector of [4 x i32] with the specified 32-bit value.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__i	A 32-bit value used to initialize the elements of the destination integer vector.

Returns: An initialized 128-bit vector of [4 x i32] with all elements containing the value provided in the operand.

Definition at line 3689 of file emmintrin.h.

References _mm_set_epi32().

Referenced by _mm_broadcastmw_epi32(), _mm_mask_set1_epi32(), and _mm_maskz_set1_epi32().

◆ _mm_set1_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set1_epi64 ( __m64 __q )

static

Initializes both values in a 128-bit vector of [2 x i64] with the specified 64-bit value.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__q	A 64-bit value used to initialize the elements of the destination integer vector.

Returns: An initialized 128-bit vector of [2 x i64] with all elements containing the value provided in the operand.

Definition at line 3672 of file emmintrin.h.

References _mm_set_epi64().

◆ _mm_set1_epi64x()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set1_epi64x ( long long __q )

static

Initializes both values in a 128-bit integer vector with the specified 64-bit integer value.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__q	Integer value used to initialize the elements of the destination integer vector.

Returns: An initialized 128-bit integer vector of [2 x i64] with both elements containing the value provided in the operand.

Definition at line 3655 of file emmintrin.h.

References _mm_set_epi64x().

Referenced by _mm_broadcastmb_epi64(), _mm_mask_set1_epi64(), and _mm_maskz_set1_epi64().

◆ _mm_set1_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set1_epi8 ( char __b )

static

Initializes all values in a 128-bit vector of [16 x i8] with the specified 8-bit value.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__b	An 8-bit value used to initialize the elements of the destination integer vector.

Returns: An initialized 128-bit vector of [16 x i8] with all elements containing the value provided in the operand.

Definition at line 3723 of file emmintrin.h.

References __b, and _mm_set_epi8().

Referenced by _mm_mask_reduce_and_epi8(), _mm_mask_reduce_max_epi8(), _mm_mask_reduce_min_epi8(), _mm_mask_reduce_min_epu8(), _mm_mask_reduce_mul_epi8(), _mm_mask_set1_epi8(), and _mm_maskz_set1_epi8().

◆ _mm_set1_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_set1_pd ( double __w )

static

Constructs a 128-bit floating-point vector of [2 x double], with each of the two double-precision floating-point vector elements set to the specified double-precision floating-point value.

This intrinsic corresponds to the VMOVDDUP / MOVLHPS instruction.

Parameters

__w	A double-precision floating-point value used to initialize each vector element of the result.

Returns: An initialized 128-bit floating-point vector of [2 x double].

Definition at line 1789 of file emmintrin.h.

Referenced by _mm_set_pd1().

◆ _mm_set_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set_epi16	(	short	__w7,
		short	__w6,
		short	__w5,
		short	__w4,
		short	__w3,
		short	__w2,
		short	__w1,
		short	__w0
	)

static

Initializes the 16-bit values in a 128-bit vector of [8 x i16] with the specified 16-bit integer values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__w7	A 16-bit integer value used to initialize bits [127:112] of the destination vector.
__w6	A 16-bit integer value used to initialize bits [111:96] of the destination vector.
__w5	A 16-bit integer value used to initialize bits [95:80] of the destination vector.
__w4	A 16-bit integer value used to initialize bits [79:64] of the destination vector.
__w3	A 16-bit integer value used to initialize bits [63:48] of the destination vector.
__w2	A 16-bit integer value used to initialize bits [47:32] of the destination vector.
__w1	A 16-bit integer value used to initialize bits [31:16] of the destination vector.
__w0	A 16-bit integer value used to initialize bits [15:0] of the destination vector.

Returns: An initialized 128-bit vector of [8 x i16] containing the values provided in the operands.

Definition at line 3585 of file emmintrin.h.

Referenced by _mm_set1_epi16(), and _mm_setr_epi16().

◆ _mm_set_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set_epi32	(	int	__i3,
		int	__i2,
		int	__i1,
		int	__i0
	)

static

Initializes the 32-bit values in a 128-bit vector of [4 x i32] with the specified 32-bit integer values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__i3	A 32-bit integer value used to initialize bits [127:96] of the destination vector.
__i2	A 32-bit integer value used to initialize bits [95:64] of the destination vector.
__i1	A 32-bit integer value used to initialize bits [63:32] of the destination vector.
__i0	A 32-bit integer value used to initialize bits [31:0] of the destination vector.

Returns: An initialized 128-bit vector of [4 x i32] containing the values provided in the operands.

Definition at line 3545 of file emmintrin.h.

Referenced by _mm_set1_epi32(), and _mm_setr_epi32().

◆ _mm_set_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set_epi64	(	__m64	__q1,
		__m64	__q0
	)

static

Initializes both 64-bit values in a 128-bit vector of [2 x i64] with the specified 64-bit integer values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__q1	A 64-bit integer value used to initialize the upper 64 bits of the destination vector of [2 x i64].
__q0	A 64-bit integer value used to initialize the lower 64 bits of the destination vector of [2 x i64].

Returns: An initialized 128-bit vector of [2 x i64] containing the values provided in the operands.

Definition at line 3518 of file emmintrin.h.

References _mm_set_epi64x().

Referenced by _mm_set1_epi64(), and _mm_setr_epi64().

◆ _mm_set_epi64x()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set_epi64x	(	long long	__q1,
		long long	__q0
	)

static

Initializes both 64-bit values in a 128-bit vector of [2 x i64] with the specified 64-bit integer values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__q1	A 64-bit integer value used to initialize the upper 64 bits of the destination vector of [2 x i64].
__q0	A 64-bit integer value used to initialize the lower 64 bits of the destination vector of [2 x i64].

Returns: An initialized 128-bit vector of [2 x i64] containing the values provided in the operands.

Definition at line 3497 of file emmintrin.h.

Referenced by _mm_set1_epi64x(), and _mm_set_epi64().

◆ _mm_set_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_set_epi8	(	char	__b15,
		char	__b14,
		char	__b13,
		char	__b12,
		char	__b11,
		char	__b10,
		char	__b9,
		char	__b8,
		char	__b7,
		char	__b6,
		char	__b5,
		char	__b4,
		char	__b3,
		char	__b2,
		char	__b1,
		char	__b0
	)

static

Initializes the 8-bit values in a 128-bit vector of [16 x i8] with the specified 8-bit integer values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__b15	Initializes bits [127:120] of the destination vector.
__b14	Initializes bits [119:112] of the destination vector.
__b13	Initializes bits [111:104] of the destination vector.
__b12	Initializes bits [103:96] of the destination vector.
__b11	Initializes bits [95:88] of the destination vector.
__b10	Initializes bits [87:80] of the destination vector.
__b9	Initializes bits [79:72] of the destination vector.
__b8	Initializes bits [71:64] of the destination vector.
__b7	Initializes bits [63:56] of the destination vector.
__b6	Initializes bits [55:48] of the destination vector.
__b5	Initializes bits [47:40] of the destination vector.
__b4	Initializes bits [39:32] of the destination vector.
__b3	Initializes bits [31:24] of the destination vector.
__b2	Initializes bits [23:16] of the destination vector.
__b1	Initializes bits [15:8] of the destination vector.
__b0	Initializes bits [7:0] of the destination vector.

Returns: An initialized 128-bit vector of [16 x i8] containing the values provided in the operands.

Definition at line 3634 of file emmintrin.h.

Referenced by _mm_set1_epi8(), and _mm_setr_epi8().

◆ _mm_set_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_set_pd	(	double	__w,
		double	__x
	)

static

Constructs a 128-bit floating-point vector of [2 x double] initialized with the specified double-precision floating-point values.

This intrinsic corresponds to the VUNPCKLPD / UNPCKLPD instruction.

Parameters

__w	A double-precision floating-point value used to initialize the upper 64 bits of the result.
__x	A double-precision floating-point value used to initialize the lower 64 bits of the result.

Returns: An initialized 128-bit floating-point vector of [2 x double].

Definition at line 1823 of file emmintrin.h.

◆ _mm_set_pd1()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_set_pd1 ( double __w )

static

Constructs a 128-bit floating-point vector of [2 x double], with each of the two double-precision floating-point vector elements set to the specified double-precision floating-point value.

This intrinsic corresponds to the VMOVDDUP / MOVLHPS instruction.

Parameters

__w	A double-precision floating-point value used to initialize each vector element of the result.

Returns: An initialized 128-bit floating-point vector of [2 x double].

Definition at line 1805 of file emmintrin.h.

References _mm_set1_pd().

◆ _mm_set_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_set_sd ( double __w )

static

Constructs a 128-bit floating-point vector of [2 x double].

The lower 64 bits of the vector are initialized with the specified double-precision floating-point value. The upper 64 bits are set to zero.

This intrinsic corresponds to the VMOVQ / MOVQ instruction.

Parameters

__w	A double-precision floating-point value used to initialize the lower 64 bits of the result.

Returns: An initialized 128-bit floating-point vector of [2 x double]. The lower 64 bits contain the value of the parameter. The upper 64 bits are set to zero.

Definition at line 1773 of file emmintrin.h.

◆ _mm_setr_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_setr_epi16	(	short	__w0,
		short	__w1,
		short	__w2,
		short	__w3,
		short	__w4,
		short	__w5,
		short	__w6,
		short	__w7
	)

static

Constructs a 128-bit integer vector, initialized in reverse order with the specified 16-bit integral values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__w0	A 16-bit integral value used to initialize bits [15:0] of the result.
__w1	A 16-bit integral value used to initialize bits [31:16] of the result.
__w2	A 16-bit integral value used to initialize bits [47:32] of the result.
__w3	A 16-bit integral value used to initialize bits [63:48] of the result.
__w4	A 16-bit integral value used to initialize bits [79:64] of the result.
__w5	A 16-bit integral value used to initialize bits [95:80] of the result.
__w6	A 16-bit integral value used to initialize bits [111:96] of the result.
__w7	A 16-bit integral value used to initialize bits [127:112] of the result.

Returns: An initialized 128-bit integer vector.

Definition at line 3796 of file emmintrin.h.

References _mm_set_epi16().

◆ _mm_setr_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_setr_epi32	(	int	__i0,
		int	__i1,
		int	__i2,
		int	__i3
	)

static

Constructs a 128-bit integer vector, initialized in reverse order with the specified 32-bit integral values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__i0	A 32-bit integral value used to initialize bits [31:0] of the result.
__i1	A 32-bit integral value used to initialize bits [63:32] of the result.
__i2	A 32-bit integral value used to initialize bits [95:64] of the result.
__i3	A 32-bit integral value used to initialize bits [127:96] of the result.

Returns: An initialized 128-bit integer vector.

Definition at line 3764 of file emmintrin.h.

References _mm_set_epi32().

◆ _mm_setr_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_setr_epi64	(	__m64	__q0,
		__m64	__q1
	)

static

Constructs a 128-bit integer vector, initialized in reverse order with the specified 64-bit integral values.

This intrinsic does not correspond to a specific instruction.

Parameters

__q0	A 64-bit integral value used to initialize the lower 64 bits of the result.
__q1	A 64-bit integral value used to initialize the upper 64 bits of the result.

Returns: An initialized 128-bit integer vector.

Definition at line 3742 of file emmintrin.h.

References _mm_set_epi64().

◆ _mm_setr_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_setr_epi8	(	char	__b0,
		char	__b1,
		char	__b2,
		char	__b3,
		char	__b4,
		char	__b5,
		char	__b6,
		char	__b7,
		char	__b8,
		char	__b9,
		char	__b10,
		char	__b11,
		char	__b12,
		char	__b13,
		char	__b14,
		char	__b15
	)

static

Constructs a 128-bit integer vector, initialized in reverse order with the specified 8-bit integral values.

This intrinsic is a utility function and does not correspond to a specific instruction.

Parameters

__b0	An 8-bit integral value used to initialize bits [7:0] of the result.
__b1	An 8-bit integral value used to initialize bits [15:8] of the result.
__b2	An 8-bit integral value used to initialize bits [23:16] of the result.
__b3	An 8-bit integral value used to initialize bits [31:24] of the result.
__b4	An 8-bit integral value used to initialize bits [39:32] of the result.
__b5	An 8-bit integral value used to initialize bits [47:40] of the result.
__b6	An 8-bit integral value used to initialize bits [55:48] of the result.
__b7	An 8-bit integral value used to initialize bits [63:56] of the result.
__b8	An 8-bit integral value used to initialize bits [71:64] of the result.
__b9	An 8-bit integral value used to initialize bits [79:72] of the result.
__b10	An 8-bit integral value used to initialize bits [87:80] of the result.
__b11	An 8-bit integral value used to initialize bits [95:88] of the result.
__b12	An 8-bit integral value used to initialize bits [103:96] of the result.
__b13	An 8-bit integral value used to initialize bits [111:104] of the result.
__b14	An 8-bit integral value used to initialize bits [119:112] of the result.
__b15	An 8-bit integral value used to initialize bits [127:120] of the result.

Returns: An initialized 128-bit integer vector.

Definition at line 3843 of file emmintrin.h.

References _mm_set_epi8().

◆ _mm_setr_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_setr_pd	(	double	__w,
		double	__x
	)

static

Constructs a 128-bit floating-point vector of [2 x double], initialized in reverse order with the specified double-precision floating-point values.

This intrinsic corresponds to the VUNPCKLPD / UNPCKLPD instruction.

Parameters

__w	A double-precision floating-point value used to initialize the lower 64 bits of the result.
__x	A double-precision floating-point value used to initialize the upper 64 bits of the result.

Returns: An initialized 128-bit floating-point vector of [2 x double].

Definition at line 1843 of file emmintrin.h.

◆ _mm_setzero_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_setzero_pd ( void )

static

Constructs a 128-bit floating-point vector of [2 x double] initialized to zero.

This intrinsic corresponds to the VXORPS / XORPS instruction.

Returns: An initialized 128-bit floating-point vector of [2 x double] with all elements set to zero.

Definition at line 1857 of file emmintrin.h.

Referenced by _mm256_zextpd128_pd256(), _mm512_zextpd128_pd512(), _mm_getexp_pd(), _mm_getexp_sd(), _mm_mask_load_sd(), _mm_maskz_add_pd(), _mm_maskz_add_sd(), _mm_maskz_and_pd(), _mm_maskz_andnot_pd(), _mm_maskz_compress_pd(), _mm_maskz_cvtepi32_pd(), _mm_maskz_cvtepi64_pd(), _mm_maskz_cvtepu32_pd(), _mm_maskz_cvtepu64_pd(), _mm_maskz_cvtps_pd(), _mm_maskz_cvtss_sd(), _mm_maskz_div_pd(), _mm_maskz_div_sd(), _mm_maskz_expand_pd(), _mm_maskz_expandloadu_pd(), _mm_maskz_fmadd_pd(), _mm_maskz_fmaddsub_pd(), _mm_maskz_fmsub_pd(), _mm_maskz_fmsubadd_pd(), _mm_maskz_fnmadd_pd(), _mm_maskz_fnmsub_pd(), _mm_maskz_getexp_pd(), _mm_maskz_getexp_sd(), _mm_maskz_load_pd(), _mm_maskz_load_sd(), _mm_maskz_loadu_pd(), _mm_maskz_max_pd(), _mm_maskz_max_sd(), _mm_maskz_min_pd(), _mm_maskz_min_sd(), _mm_maskz_mov_pd(), _mm_maskz_move_sd(), _mm_maskz_movedup_pd(), _mm_maskz_mul_pd(), _mm_maskz_mul_sd(), _mm_maskz_or_pd(), _mm_maskz_permutevar_pd(), _mm_maskz_permutex2var_pd(), _mm_maskz_rcp14_pd(), _mm_maskz_rcp14_sd(), _mm_maskz_rsqrt14_pd(), _mm_maskz_rsqrt14_sd(), _mm_maskz_scalef_pd(), _mm_maskz_scalef_sd(), _mm_maskz_sqrt_pd(), _mm_maskz_sqrt_sd(), _mm_maskz_sub_pd(), _mm_maskz_sub_sd(), _mm_maskz_unpackhi_pd(), _mm_maskz_unpacklo_pd(), _mm_maskz_xor_pd(), _mm_rcp14_pd(), _mm_rcp14_sd(), _mm_rsqrt14_pd(), _mm_rsqrt14_sd(), _mm_scalef_pd(), and _mm_scalef_sd().

◆ _mm_setzero_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_setzero_si128 ( void )

static

Creates a 128-bit integer vector initialized to zero.

This intrinsic corresponds to the VXORPS / XORPS instruction.

Returns: An initialized 128-bit integer vector with all elements set to zero.

Definition at line 3858 of file emmintrin.h.

◆ _mm_sll_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sll_epi16	(	__m128i	__a,
		__m128i	__count
	)

static

Left-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

Low-order bits are cleared.

This intrinsic corresponds to the VPSLLW / PSLLW instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to left-shift each value in operand __a.

Returns: A 128-bit integer vector containing the left-shifted values.

Definition at line 2775 of file emmintrin.h.

References __a.

Referenced by _mm_mask_sll_epi16(), and _mm_maskz_sll_epi16().

◆ _mm_sll_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sll_epi32	(	__m128i	__a,
		__m128i	__count
	)

static

Left-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

Low-order bits are cleared.

This intrinsic corresponds to the VPSLLD / PSLLD instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to left-shift each value in operand __a.

Returns: A 128-bit integer vector containing the left-shifted values.

Definition at line 2811 of file emmintrin.h.

References __a.

Referenced by _mm_mask_sll_epi32(), and _mm_maskz_sll_epi32().

◆ _mm_sll_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sll_epi64	(	__m128i	__a,
		__m128i	__count
	)

static

Left-shifts each 64-bit value in the 128-bit integer vector operand by the specified number of bits.

Low-order bits are cleared.

This intrinsic corresponds to the VPSLLQ / PSLLQ instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to left-shift each value in operand __a.

Returns: A 128-bit integer vector containing the left-shifted values.

Definition at line 2847 of file emmintrin.h.

References __a.

Referenced by _mm_mask_sll_epi64(), and _mm_maskz_sll_epi64().

◆ _mm_slli_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_slli_epi16	(	__m128i	__a,
		int	__count
	)

static

Left-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

Low-order bits are cleared.

This intrinsic corresponds to the VPSLLW / PSLLW instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to left-shift each value in operand __a.

Returns: A 128-bit integer vector containing the left-shifted values.

Definition at line 2757 of file emmintrin.h.

References __a.

Referenced by _mm_mask_slli_epi16(), and _mm_maskz_slli_epi16().

◆ _mm_slli_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_slli_epi32	(	__m128i	__a,
		int	__count
	)

static

Left-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

Low-order bits are cleared.

This intrinsic corresponds to the VPSLLD / PSLLD instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to left-shift each value in operand __a.

Returns: A 128-bit integer vector containing the left-shifted values.

Definition at line 2793 of file emmintrin.h.

References __a.

Referenced by _mm_mask_slli_epi32(), and _mm_maskz_slli_epi32().

◆ _mm_slli_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_slli_epi64	(	__m128i	__a,
		int	__count
	)

static

Left-shifts each 64-bit value in the 128-bit integer vector operand by the specified number of bits.

Low-order bits are cleared.

This intrinsic corresponds to the VPSLLQ / PSLLQ instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to left-shift each value in operand __a.

Returns: A 128-bit integer vector containing the left-shifted values.

Definition at line 2829 of file emmintrin.h.

References __a.

Referenced by _mm_mask_slli_epi64(), and _mm_maskz_slli_epi64().

◆ _mm_sqrt_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_sqrt_pd ( __m128d __a )

static

Calculates the square root of the each of two values stored in a 128-bit vector of [2 x double].

This intrinsic corresponds to the VSQRTPD / SQRTPD instruction.

Parameters

__a	A 128-bit vector of [2 x double].

Returns: A 128-bit vector of [2 x double] containing the square roots of the values in the operand.

Definition at line 253 of file emmintrin.h.

References __a.

Referenced by _mm_mask_sqrt_pd(), and _mm_maskz_sqrt_pd().

◆ _mm_sqrt_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_sqrt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Calculates the square root of the lower double-precision value of the second operand and returns it in the lower 64 bits of the result.

The upper 64 bits of the result are copied from the upper double-precision value of the first operand.

This intrinsic corresponds to the VSQRTSD / SQRTSD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the operands. The upper 64 bits of this operand are copied to the upper 64 bits of the result.
__b	A 128-bit vector of [2 x double] containing one of the operands. The square root is calculated using the lower 64 bits of this operand.

Returns: A 128-bit vector of [2 x double] whose lower 64 bits contain the square root of the lower 64 bits of operand __b, and whose upper 64 bits are copied from the upper 64 bits of operand __a.

Definition at line 236 of file emmintrin.h.

References __a, __b, and __c.

◆ _mm_sra_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sra_epi16	(	__m128i	__a,
		__m128i	__count
	)

static

Right-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

High-order bits are filled with the sign bit of the initial value.

This intrinsic corresponds to the VPSRAW / PSRAW instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 2885 of file emmintrin.h.

References __a.

Referenced by _mm_mask_sra_epi16(), and _mm_maskz_sra_epi16().

◆ _mm_sra_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sra_epi32	(	__m128i	__a,
		__m128i	__count
	)

static

Right-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

High-order bits are filled with the sign bit of the initial value.

This intrinsic corresponds to the VPSRAD / PSRAD instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 2923 of file emmintrin.h.

References __a.

Referenced by _mm_mask_sra_epi32(), and _mm_maskz_sra_epi32().

◆ _mm_srai_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srai_epi16	(	__m128i	__a,
		int	__count
	)

static

Right-shifts each 16-bit value in the 128-bit integer vector operand by the specified number of bits.

High-order bits are filled with the sign bit of the initial value.

This intrinsic corresponds to the VPSRAW / PSRAW instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 2866 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srai_epi16(), and _mm_maskz_srai_epi16().

◆ _mm_srai_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srai_epi32	(	__m128i	__a,
		int	__count
	)

static

Right-shifts each 32-bit value in the 128-bit integer vector operand by the specified number of bits.

High-order bits are filled with the sign bit of the initial value.

This intrinsic corresponds to the VPSRAD / PSRAD instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 2904 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srai_epi32(), and _mm_maskz_srai_epi32().

◆ _mm_srl_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srl_epi16	(	__m128i	__a,
		__m128i	__count
	)

static

Right-shifts each of 16-bit values in the 128-bit integer vector operand by the specified number of bits.

High-order bits are cleared.

This intrinsic corresponds to the VPSRLW / PSRLW instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 2984 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srl_epi16(), and _mm_maskz_srl_epi16().

◆ _mm_srl_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srl_epi32	(	__m128i	__a,
		__m128i	__count
	)

static

Right-shifts each of 32-bit values in the 128-bit integer vector operand by the specified number of bits.

High-order bits are cleared.

This intrinsic corresponds to the VPSRLD / PSRLD instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 3020 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srl_epi32(), and _mm_maskz_srl_epi32().

◆ _mm_srl_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srl_epi64	(	__m128i	__a,
		__m128i	__count
	)

static

Right-shifts each of 64-bit values in the 128-bit integer vector operand by the specified number of bits.

High-order bits are cleared.

This intrinsic corresponds to the VPSRLQ / PSRLQ instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	A 128-bit integer vector in which bits [63:0] specify the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 3056 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srl_epi64(), and _mm_maskz_srl_epi64().

◆ _mm_srli_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srli_epi16	(	__m128i	__a,
		int	__count
	)

static

Right-shifts each of 16-bit values in the 128-bit integer vector operand by the specified number of bits.

High-order bits are cleared.

This intrinsic corresponds to the VPSRLW / PSRLW instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 2966 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srli_epi16(), and _mm_maskz_srli_epi16().

◆ _mm_srli_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srli_epi32	(	__m128i	__a,
		int	__count
	)

static

Right-shifts each of 32-bit values in the 128-bit integer vector operand by the specified number of bits.

High-order bits are cleared.

This intrinsic corresponds to the VPSRLD / PSRLD instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 3002 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srli_epi32(), and _mm_maskz_srli_epi32().

◆ _mm_srli_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_srli_epi64	(	__m128i	__a,
		int	__count
	)

static

Right-shifts each of 64-bit values in the 128-bit integer vector operand by the specified number of bits.

High-order bits are cleared.

This intrinsic corresponds to the VPSRLQ / PSRLQ instruction.

Parameters

__a	A 128-bit integer vector containing the source operand.
__count	An integer value specifying the number of bits to right-shift each value in operand __a.

Returns: A 128-bit integer vector containing the right-shifted values.

Definition at line 3038 of file emmintrin.h.

References __a.

Referenced by _mm_mask_srli_epi64(), and _mm_maskz_srli_epi64().

◆ _mm_store1_pd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_store1_pd	(	double *	__dp,
		__m128d	__a
	)

static

Moves the lower 64 bits of a 128-bit vector of [2 x double] twice to the upper and lower 64 bits of a memory location.

This intrinsic corresponds to the VMOVDDUP + VMOVAPD / MOVLHPS + MOVAPS instruction.

Parameters

__dp	A pointer to a memory location that can store two double-precision values.
__a	A 128-bit vector of [2 x double] whose lower 64 bits are copied to each of the values in __dp.

Definition at line 1933 of file emmintrin.h.

References __a, and _mm_store_pd().

Referenced by _mm_store_pd1().

◆ _mm_store_pd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_store_pd	(	double *	__dp,
		__m128d	__a
	)

static

Moves packed double-precision values from a 128-bit vector of [2 x double] to a memory location.

This intrinsic corresponds to the VMOVAPD / MOVAPS instruction.

Parameters

__dp	A pointer to an aligned memory location that can store two double-precision values.
__a	A packed 128-bit vector of [2 x double] containing the values to be moved.

Definition at line 1914 of file emmintrin.h.

References __a.

Referenced by _mm_store1_pd().

◆ _mm_store_pd1()

static __inline__ void __DEFAULT_FN_ATTRS _mm_store_pd1	(	double *	__dp,
		__m128d	__a
	)

static

Moves the lower 64 bits of a 128-bit vector of [2 x double] twice to the upper and lower 64 bits of a memory location.

This intrinsic corresponds to the VMOVDDUP + VMOVAPD / MOVLHPS + MOVAPS instruction.

Parameters

__dp	A pointer to a memory location that can store two double-precision values.
__a	A 128-bit vector of [2 x double] whose lower 64 bits are copied to each of the values in __dp.

Definition at line 1953 of file emmintrin.h.

References __a, and _mm_store1_pd().

◆ _mm_store_sd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_store_sd	(	double *	__dp,
		__m128d	__a
	)

static

Stores the lower 64 bits of a 128-bit vector of [2 x double] to a memory location.

This intrinsic corresponds to the VMOVSD / MOVSD instruction.

Parameters

__dp	A pointer to a 64-bit memory location.
__a	A 128-bit vector of [2 x double] containing the value to be stored.

Definition at line 1893 of file emmintrin.h.

References __a.

◆ _mm_store_si128()

static __inline__ void __DEFAULT_FN_ATTRS _mm_store_si128	(	__m128i *	__p,
		__m128i	__b
	)

static

Stores a 128-bit integer vector to a memory location aligned on a 128-bit boundary.

This intrinsic corresponds to the VMOVAPS / MOVAPS instruction.

Parameters

__p	A pointer to an aligned memory location that will receive the integer values.
__b	A 128-bit integer vector containing the values to be moved.

Definition at line 3874 of file emmintrin.h.

References __b, and __p.

◆ _mm_storeh_pd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storeh_pd	(	double *	__dp,
		__m128d	__a
	)

static

Stores the upper 64 bits of a 128-bit vector of [2 x double] to a memory location.

This intrinsic corresponds to the VMOVHPD / MOVHPD instruction.

Parameters

__dp	A pointer to a 64-bit memory location.
__a	A 128-bit vector of [2 x double] containing the value to be stored.

Definition at line 2009 of file emmintrin.h.

References __a.

◆ _mm_storel_epi64()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storel_epi64	(	__m128i_u *	__p,
		__m128i	__a
	)

static

Stores the lower 64 bits of a 128-bit integer vector of [2 x i64] to a memory location.

This intrinsic corresponds to the VMOVLPS / MOVLPS instruction.

Parameters

__p	A pointer to a 64-bit memory location that will receive the lower 64 bits of the integer vector parameter.
__a	A 128-bit integer vector of [2 x i64]. The lower 64 bits contain the value to be stored.

Definition at line 3997 of file emmintrin.h.

References __a, and __p.

◆ _mm_storel_pd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storel_pd	(	double *	__dp,
		__m128d	__a
	)

static

Stores the lower 64 bits of a 128-bit vector of [2 x double] to a memory location.

This intrinsic corresponds to the VMOVLPD / MOVLPD instruction.

Parameters

__dp	A pointer to a 64-bit memory location.
__a	A 128-bit vector of [2 x double] containing the value to be stored.

Definition at line 2028 of file emmintrin.h.

References __a.

◆ _mm_storer_pd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storer_pd	(	double *	__dp,
		__m128d	__a
	)

static

Stores two double-precision values, in reverse order, from a 128-bit vector of [2 x double] to a 16-byte aligned memory location.

This intrinsic corresponds to a shuffling instruction followed by a VMOVAPD / MOVAPD instruction.

Parameters

__dp	A pointer to a 16-byte aligned memory location that can store two double-precision values.
__a	A 128-bit vector of [2 x double] containing the values to be reversed and stored.

Definition at line 1992 of file emmintrin.h.

References __a.

◆ _mm_storeu_pd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storeu_pd	(	double *	__dp,
		__m128d	__a
	)

static

Stores a 128-bit vector of [2 x double] into an unaligned memory location.

This intrinsic corresponds to the VMOVUPD / MOVUPD instruction.

Parameters

__dp	A pointer to a 128-bit memory location. The address of the memory location does not have to be aligned.
__a	A 128-bit vector of [2 x double] containing the values to be stored.

Definition at line 1970 of file emmintrin.h.

References __a, and __v.

Referenced by _mm256_storeu2_m128d().

◆ _mm_storeu_si128()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storeu_si128	(	__m128i_u *	__p,
		__m128i	__b
	)

static

Stores a 128-bit integer vector to an unaligned memory location.

This intrinsic corresponds to the VMOVUPS / MOVUPS instruction.

Parameters

__p	A pointer to a memory location that will receive the integer values.
__b	A 128-bit integer vector containing the values to be moved.

Definition at line 3889 of file emmintrin.h.

References __b, __p, and __v.

Referenced by _mm256_storeu2_m128i().

◆ _mm_storeu_si16()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storeu_si16	(	void *	__p,
		__m128i	__b
	)

static

Stores a 16-bit integer value from the low element of a 128-bit integer vector.

This intrinsic does not correspond to a specific instruction.

Parameters

__p	A pointer to a 16-bit memory location. The address of the memory location does not have to be aligned.
__b	A 128-bit integer vector containing the value to be stored.

Definition at line 3949 of file emmintrin.h.

References __b, __p, and __v.

◆ _mm_storeu_si32()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storeu_si32	(	void *	__p,
		__m128i	__b
	)

static

Stores a 32-bit integer value from the low element of a 128-bit integer vector.

This intrinsic corresponds to the VMOVD / MOVD instruction.

Parameters

__p	A pointer to a 32-bit memory location. The address of the memory location does not have to be aligned.
__b	A 128-bit integer vector containing the value to be stored.

Definition at line 3929 of file emmintrin.h.

References __b, __p, and __v.

◆ _mm_storeu_si64()

static __inline__ void __DEFAULT_FN_ATTRS _mm_storeu_si64	(	void *	__p,
		__m128i	__b
	)

static

Stores a 64-bit integer value from the low element of a 128-bit integer vector.

This intrinsic corresponds to the VMOVQ / MOVQ instruction.

Parameters

__p	A pointer to a 64-bit memory location. The address of the memory location does not have to be aligned.
__b	A 128-bit integer vector containing the value to be stored.

Definition at line 3909 of file emmintrin.h.

References __b, __p, and __v.

◆ _mm_stream_pd()

static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_pd	(	void *	__p,
		__m128d	__a
	)

static

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).

This intrinsic corresponds to the VMOVNTPS / MOVNTPS instruction.

Parameters

__p	A pointer to the 128-bit aligned memory location used to store the value.
__a	A vector of [2 x double] containing the 64-bit values to be stored.

Definition at line 4019 of file emmintrin.h.

References __a, and __p.

◆ _mm_stream_si128()

static __inline__ void __DEFAULT_FN_ATTRS _mm_stream_si128	(	void *	__p,
		__m128i	__a
	)

static

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).

This intrinsic corresponds to the VMOVNTPS / MOVNTPS instruction.

Parameters

__p	A pointer to the 128-bit aligned memory location used to store the value.
__a	A 128-bit integer vector containing the values to be stored.

Definition at line 4037 of file emmintrin.h.

References __a, and __p.

◆ _mm_sub_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sub_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts the corresponding 16-bit integer values in the operands.

This intrinsic corresponds to the VPSUBW / PSUBW instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the differences of the values in the operands.

Definition at line 2507 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_sub_epi16(), and _mm_maskz_sub_epi16().

◆ _mm_sub_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sub_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts the corresponding 32-bit integer values in the operands.

This intrinsic corresponds to the VPSUBD / PSUBD instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the differences of the values in the operands.

Definition at line 2524 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_sub_epi32(), and _mm_maskz_sub_epi32().

◆ _mm_sub_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sub_epi64	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts the corresponding elements of two [2 x i64] vectors.

This intrinsic corresponds to the VPSUBQ / PSUBQ instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the differences of the values in the operands.

Definition at line 2559 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_sub_epi64(), and _mm_maskz_sub_epi64().

◆ _mm_sub_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_sub_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts the corresponding 8-bit integer values in the operands.

This intrinsic corresponds to the VPSUBB / PSUBB instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the differences of the values in the operands.

Definition at line 2490 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_sub_epi8(), and _mm_maskz_sub_epi8().

◆ _mm_sub_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_sub_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Subtracts two 128-bit vectors of [2 x double].

This intrinsic corresponds to the VSUBPD / SUBPD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing the minuend.
__b	A 128-bit vector of [2 x double] containing the subtrahend.

Returns: A 128-bit vector of [2 x double] containing the differences between both operands.

Definition at line 132 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_sub_pd(), and _mm_maskz_sub_pd().

◆ _mm_sub_sd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_sub_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Subtracts the lower double-precision value of the second operand from the lower double-precision value of the first operand and returns the difference in the lower 64 bits of the result.

The upper 64 bits of the result are copied from the upper double-precision value of the first operand.

This intrinsic corresponds to the VSUBSD / SUBSD instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing the minuend.
__b	A 128-bit vector of [2 x double] containing the subtrahend.

Returns: A 128-bit vector of [2 x double] whose lower 64 bits contain the difference of the lower 64 bits of both operands. The upper 64 bits are copied from the upper 64 bits of the first source operand.

Definition at line 114 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_sub_sd(), and _mm_maskz_sub_sd().

◆ _mm_sub_si64()

static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX _mm_sub_si64	(	__m64	__a,
		__m64	__b
	)

static

Subtracts signed or unsigned 64-bit integer values and writes the difference to the corresponding bits in the destination.

This intrinsic corresponds to the PSUBQ instruction.

Parameters

__a	A 64-bit integer vector containing the minuend.
__b	A 64-bit integer vector containing the subtrahend.

Returns: A 64-bit integer vector containing the difference of the values in the operands.

Definition at line 2542 of file emmintrin.h.

References __a, and __b.

◆ _mm_subs_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_subs_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts, with saturation, corresponding 16-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination.

Differences greater than 0x7FFF are saturated to 0x7FFF, and values less than 0x8000 are saturated to 0x8000.

This intrinsic corresponds to the VPSUBSW / PSUBSW instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the differences of the values in the operands.

Definition at line 2603 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_subs_epi16(), and _mm_maskz_subs_epi16().

◆ _mm_subs_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_subs_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts, with saturation, corresponding 8-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination.

Differences greater than 0x7F are saturated to 0x7F, and differences less than 0x80 are saturated to 0x80.

This intrinsic corresponds to the VPSUBSB / PSUBSB instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the differences of the values in the operands.

Definition at line 2581 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_subs_epi8(), and _mm_maskz_subs_epi8().

◆ _mm_subs_epu16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_subs_epu16	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts, with saturation, corresponding 16-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination.

Differences less than 0x0000 are saturated to 0x0000.

This intrinsic corresponds to the VPSUBUSW / PSUBUSW instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the unsigned integer differences of the values in the operands.

Definition at line 2645 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_subs_epu16(), and _mm_maskz_subs_epu16().

◆ _mm_subs_epu8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_subs_epu8	(	__m128i	__a,
		__m128i	__b
	)

static

Subtracts, with saturation, corresponding 8-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination.

Differences less than 0x00 are saturated to 0x00.

This intrinsic corresponds to the VPSUBUSB / PSUBUSB instruction.

Parameters

__a	A 128-bit integer vector containing the minuends.
__b	A 128-bit integer vector containing the subtrahends.

Returns: A 128-bit integer vector containing the unsigned integer differences of the values in the operands.

Definition at line 2624 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_subs_epu8(), and _mm_maskz_subs_epu8().

◆ _mm_ucomieq_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_ucomieq_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] for equality.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VUCOMISD / UCOMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1138 of file emmintrin.h.

References __a, and __b.

◆ _mm_ucomige_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_ucomige_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than or equal to the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VUCOMISD / UCOMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1234 of file emmintrin.h.

References __a, and __b.

◆ _mm_ucomigt_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_ucomigt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is greater than the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VUCOMISD / UCOMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1210 of file emmintrin.h.

References __a, and __b.

◆ _mm_ucomile_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_ucomile_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than or equal to the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VUCOMISD / UCOMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1186 of file emmintrin.h.

References __a, and __b.

◆ _mm_ucomilt_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_ucomilt_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is less than the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 0.

This intrinsic corresponds to the VUCOMISD / UCOMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison results.

Definition at line 1162 of file emmintrin.h.

References __a, and __b.

◆ _mm_ucomineq_sd()

static __inline__ int __DEFAULT_FN_ATTRS _mm_ucomineq_sd	(	__m128d	__a,
		__m128d	__b
	)

static

Compares the lower double-precision floating-point values in each of the two 128-bit floating-point vectors of [2 x double] to determine if the value in the first parameter is unequal to the corresponding value in the second parameter.

The comparison returns 0 for false, 1 for true. If either value in a comparison is NaN, returns 1.

This intrinsic corresponds to the VUCOMISD / UCOMISD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __b.
__b	A 128-bit vector of [2 x double]. The lower double-precision value is compared to the lower double-precision value of __a.

Returns: An integer containing the comparison result.

Definition at line 1258 of file emmintrin.h.

References __a, and __b.

◆ _mm_undefined_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_undefined_pd ( void )

static

Constructs a 128-bit floating-point vector of [2 x double] with unspecified content.

This could be used as an argument to another intrinsic function where the argument is required but the value is not actually used.

This intrinsic has no corresponding instruction.

Returns: A 128-bit floating-point vector of [2 x double] with unspecified content.

Definition at line 1755 of file emmintrin.h.

◆ _mm_undefined_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_undefined_si128 ( void )

static

Generates a 128-bit vector of [4 x i32] with unspecified content.

This could be used as an argument to another intrinsic function where the argument is required but the value is not actually used.

This intrinsic has no corresponding instruction.

Returns: A 128-bit vector of [4 x i32] with unspecified content.

Definition at line 3477 of file emmintrin.h.

Referenced by _mm256_cvtsepi32_epi16(), _mm256_cvtsepi32_epi8(), _mm256_cvtsepi64_epi16(), _mm256_cvtsepi64_epi32(), _mm256_cvtsepi64_epi8(), _mm256_cvtusepi32_epi16(), _mm256_cvtusepi32_epi8(), _mm256_cvtusepi64_epi16(), _mm256_cvtusepi64_epi32(), _mm256_cvtusepi64_epi8(), _mm512_cvtepi32_epi8(), _mm512_cvtepi64_epi16(), _mm512_cvtepi64_epi8(), _mm512_cvtsepi32_epi8(), _mm512_cvtsepi64_epi16(), _mm512_cvtsepi64_epi8(), _mm512_cvtusepi32_epi8(), _mm512_cvtusepi64_epi16(), _mm512_cvtusepi64_epi8(), _mm_cvtsepi32_epi8(), _mm_cvtsepi64_epi16(), _mm_cvtsepi64_epi32(), _mm_cvtsepi64_epi8(), _mm_cvtusepi32_epi16(), _mm_cvtusepi32_epi8(), _mm_cvtusepi64_epi16(), _mm_cvtusepi64_epi32(), and _mm_cvtusepi64_epi8().

◆ _mm_unpackhi_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpackhi_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the high-order (index 4-7) values from two 128-bit vectors of [8 x i16] and interleaves them into a 128-bit vector of [8 x i16].

This intrinsic corresponds to the VPUNPCKHWD / PUNPCKHWD instruction.

Parameters

__a	A 128-bit vector of [8 x i16]. Bits [79:64] are written to bits [15:0] of the result. Bits [95:80] are written to bits [47:32] of the result. Bits [111:96] are written to bits [79:64] of the result. Bits [127:112] are written to bits [111:96] of the result.
__b	A 128-bit vector of [8 x i16]. Bits [79:64] are written to bits [31:16] of the result. Bits [95:80] are written to bits [63:48] of the result. Bits [111:96] are written to bits [95:80] of the result. Bits [127:112] are written to bits [127:112] of the result.

Returns: A 128-bit vector of [8 x i16] containing the interleaved values.

Definition at line 4424 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpackhi_epi16(), and _mm_maskz_unpackhi_epi16().

◆ _mm_unpackhi_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpackhi_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the high-order (index 2,3) values from two 128-bit vectors of [4 x i32] and interleaves them into a 128-bit vector of [4 x i32].

This intrinsic corresponds to the VPUNPCKHDQ / PUNPCKHDQ instruction.

Parameters

__a	A 128-bit vector of [4 x i32]. Bits [95:64] are written to bits [31:0] of the destination. Bits [127:96] are written to bits [95:64] of the destination.
__b	A 128-bit vector of [4 x i32]. Bits [95:64] are written to bits [64:32] of the destination. Bits [127:96] are written to bits [127:96] of the destination.

Returns: A 128-bit vector of [4 x i32] containing the interleaved values.

Definition at line 4447 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpackhi_epi32(), and _mm_maskz_unpackhi_epi32().

◆ _mm_unpackhi_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpackhi_epi64	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the high-order 64-bit elements from two 128-bit vectors of [2 x i64] and interleaves them into a 128-bit vector of [2 x i64].

This intrinsic corresponds to the VPUNPCKHQDQ / PUNPCKHQDQ instruction.

Parameters

__a	A 128-bit vector of [2 x i64]. Bits [127:64] are written to bits [63:0] of the destination.
__b	A 128-bit vector of [2 x i64]. Bits [127:64] are written to bits [127:64] of the destination.

Returns: A 128-bit vector of [2 x i64] containing the interleaved values.

Definition at line 4468 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpackhi_epi64(), and _mm_maskz_unpackhi_epi64().

◆ _mm_unpackhi_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpackhi_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the high-order (index 8-15) values from two 128-bit vectors of [16 x i8] and interleaves them into a 128-bit vector of [16 x i8].

This intrinsic corresponds to the VPUNPCKHBW / PUNPCKHBW instruction.

Parameters

__a A 128-bit vector of [16 x i8]. Bits [71:64] are written to bits [7:0] of the result.
Bits [79:72] are written to bits [23:16] of the result.
Bits [87:80] are written to bits [39:32] of the result.
Bits [95:88] are written to bits [55:48] of the result.
Bits [103:96] are written to bits [71:64] of the result.
Bits [111:104] are written to bits [87:80] of the result.
Bits [119:112] are written to bits [103:96] of the result.
Bits [127:120] are written to bits [119:112] of the result.

__b A 128-bit vector of [16 x i8].
Bits [71:64] are written to bits [15:8] of the result.
Bits [79:72] are written to bits [31:24] of the result.
Bits [87:80] are written to bits [47:40] of the result.
Bits [95:88] are written to bits [63:56] of the result.
Bits [103:96] are written to bits [79:72] of the result.
Bits [111:104] are written to bits [95:88] of the result.
Bits [119:112] are written to bits [111:104] of the result.
Bits [127:120] are written to bits [127:120] of the result.

Returns: A 128-bit vector of [16 x i8] containing the interleaved values.

Definition at line 4396 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpackhi_epi8(), and _mm_maskz_unpackhi_epi8().

◆ _mm_unpackhi_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_unpackhi_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Unpacks the high-order 64-bit elements from two 128-bit vectors of [2 x double] and interleaves them into a 128-bit vector of [2 x double].

This intrinsic corresponds to the VUNPCKHPD / UNPCKHPD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. Bits [127:64] are written to bits [63:0] of the destination.
__b	A 128-bit vector of [2 x double]. Bits [127:64] are written to bits [127:64] of the destination.

Returns: A 128-bit vector of [2 x double] containing the interleaved values.

Definition at line 4641 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpackhi_pd(), and _mm_maskz_unpackhi_pd().

◆ _mm_unpacklo_epi16()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpacklo_epi16	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the low-order (index 0-3) values from each of the two 128-bit vectors of [8 x i16] and interleaves them into a 128-bit vector of [8 x i16].

This intrinsic corresponds to the VPUNPCKLWD / PUNPCKLWD instruction.

Parameters

__a	A 128-bit vector of [8 x i16]. Bits [15:0] are written to bits [15:0] of the result. Bits [31:16] are written to bits [47:32] of the result. Bits [47:32] are written to bits [79:64] of the result. Bits [63:48] are written to bits [111:96] of the result.
__b	A 128-bit vector of [8 x i16]. Bits [15:0] are written to bits [31:16] of the result. Bits [31:16] are written to bits [63:48] of the result. Bits [47:32] are written to bits [95:80] of the result. Bits [63:48] are written to bits [127:112] of the result.

Returns: A 128-bit vector of [8 x i16] containing the interleaved values.

Definition at line 4531 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpacklo_epi16(), and _mm_maskz_unpacklo_epi16().

◆ _mm_unpacklo_epi32()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpacklo_epi32	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the low-order (index 0,1) values from two 128-bit vectors of [4 x i32] and interleaves them into a 128-bit vector of [4 x i32].

This intrinsic corresponds to the VPUNPCKLDQ / PUNPCKLDQ instruction.

Parameters

__a	A 128-bit vector of [4 x i32]. Bits [31:0] are written to bits [31:0] of the destination. Bits [63:32] are written to bits [95:64] of the destination.
__b	A 128-bit vector of [4 x i32]. Bits [31:0] are written to bits [64:32] of the destination. Bits [63:32] are written to bits [127:96] of the destination.

Returns: A 128-bit vector of [4 x i32] containing the interleaved values.

Definition at line 4554 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpacklo_epi32(), and _mm_maskz_unpacklo_epi32().

◆ _mm_unpacklo_epi64()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpacklo_epi64	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the low-order 64-bit elements from two 128-bit vectors of [2 x i64] and interleaves them into a 128-bit vector of [2 x i64].

This intrinsic corresponds to the VPUNPCKLQDQ / PUNPCKLQDQ instruction.

Parameters

__a	A 128-bit vector of [2 x i64]. Bits [63:0] are written to bits [63:0] of the destination.
__b	A 128-bit vector of [2 x i64]. Bits [63:0] are written to bits [127:64] of the destination.

Returns: A 128-bit vector of [2 x i64] containing the interleaved values.

Definition at line 4575 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpacklo_epi64(), and _mm_maskz_unpacklo_epi64().

◆ _mm_unpacklo_epi8()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_unpacklo_epi8	(	__m128i	__a,
		__m128i	__b
	)

static

Unpacks the low-order (index 0-7) values from two 128-bit vectors of [16 x i8] and interleaves them into a 128-bit vector of [16 x i8].

This intrinsic corresponds to the VPUNPCKLBW / PUNPCKLBW instruction.

Parameters

__a A 128-bit vector of [16 x i8].
Bits [7:0] are written to bits [7:0] of the result.
Bits [15:8] are written to bits [23:16] of the result.
Bits [23:16] are written to bits [39:32] of the result.
Bits [31:24] are written to bits [55:48] of the result.
Bits [39:32] are written to bits [71:64] of the result.
Bits [47:40] are written to bits [87:80] of the result.
Bits [55:48] are written to bits [103:96] of the result.
Bits [63:56] are written to bits [119:112] of the result.

__b A 128-bit vector of [16 x i8]. Bits [7:0] are written to bits [15:8] of the result.
Bits [15:8] are written to bits [31:24] of the result.
Bits [23:16] are written to bits [47:40] of the result.
Bits [31:24] are written to bits [63:56] of the result.
Bits [39:32] are written to bits [79:72] of the result.
Bits [47:40] are written to bits [95:88] of the result.
Bits [55:48] are written to bits [111:104] of the result.
Bits [63:56] are written to bits [127:120] of the result.

Returns: A 128-bit vector of [16 x i8] containing the interleaved values.

Definition at line 4502 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpacklo_epi8(), and _mm_maskz_unpacklo_epi8().

◆ _mm_unpacklo_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_unpacklo_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Unpacks the low-order 64-bit elements from two 128-bit vectors of [2 x double] and interleaves them into a 128-bit vector of [2 x double].

This intrinsic corresponds to the VUNPCKLPD / UNPCKLPD instruction.

Parameters

__a	A 128-bit vector of [2 x double]. Bits [63:0] are written to bits [63:0] of the destination.
__b	A 128-bit vector of [2 x double]. Bits [63:0] are written to bits [127:64] of the destination.

Returns: A 128-bit vector of [2 x double] containing the interleaved values.

Definition at line 4661 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_unpacklo_pd(), and _mm_maskz_unpacklo_pd().

◆ _mm_xor_pd()

static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_xor_pd	(	__m128d	__a,
		__m128d	__b
	)

static

Performs a bitwise XOR of two 128-bit vectors of [2 x double].

This intrinsic corresponds to the VPXOR / PXOR instruction.

Parameters

__a	A 128-bit vector of [2 x double] containing one of the source operands.
__b	A 128-bit vector of [2 x double] containing one of the source operands.

Returns: A 128-bit vector of [2 x double] containing the bitwise XOR of the values between both operands.

Definition at line 415 of file emmintrin.h.

References __a, and __b.

Referenced by _mm_mask_xor_pd(), and _mm_maskz_xor_pd().

◆ _mm_xor_si128()

static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_xor_si128	(	__m128i	__a,
		__m128i	__b
	)

static

Performs a bitwise exclusive OR of two 128-bit integer vectors.

This intrinsic corresponds to the VPXOR / PXOR instruction.

Parameters

__a	A 128-bit integer vector containing one of the source operands.
__b	A 128-bit integer vector containing one of the source operands.

Returns: A 128-bit integer vector containing the bitwise exclusive OR of the values in both operands.

Definition at line 2714 of file emmintrin.h.

References __a, and __b.

Variable Documentation

◆ __a

__inline__ void int __a

Initial value:

{

__builtin_ia32_movnti((int *)__p, __a)

__p

static __inline__ uint32_t volatile uint32_t * __p

Definition: arm_acle.h:80

__a

static __inline__ void int __a

Definition: emmintrin.h:4057

Definition at line 4057 of file emmintrin.h.

Referenced by __all(), __any(), __attribute__(), __ballot(), __blcfill_u32(), __blci_u32(), __blcic_u32(), __blcmsk_u32(), __blcs_u32(), __blsfill_u32(), __blsic_u32(), __bool2mask(), __brev(), __brevll(), __byte_perm(), __clz(), __clzll(), __cosf(), __dadd_rd(), __dadd_rn(), __dadd_ru(), __dadd_rz(), __ddiv_rd(), __ddiv_rn(), __ddiv_ru(), __ddiv_rz(), __DEPRECATED_FN_ATTRS(), __divdc3(), __divsc3(), __dmul_rd(), __dmul_rn(), __dmul_ru(), __dmul_rz(), __double2float_rd(), __double2float_rn(), __double2float_ru(), __double2float_rz(), __double2hiint(), __double2int_rd(), __double2int_rn(), __double2int_ru(), __double2int_rz(), __double2ll_rd(), __double2ll_rn(), __double2ll_ru(), __double2ll_rz(), __double2loint(), __double2uint_rd(), __double2uint_rn(), __double2uint_ru(), __double2uint_rz(), __double2ull_rd(), __double2ull_rn(), __double2ull_ru(), __double2ull_rz(), __double_as_longlong(), __drcp_rd(), __drcp_rn(), __drcp_ru(), __drcp_rz(), __dsqrt_rd(), __dsqrt_rn(), __dsqrt_ru(), __dsqrt_rz(), __dsub_rd(), __dsub_rn(), __dsub_ru(), __dsub_rz(), __exp10f(), __expf(), __fadd_rd(), __fadd_rn(), __fadd_ru(), __fadd_rz(), __fdiv_rd(), __fdiv_rn(), __fdiv_ru(), __fdiv_rz(), __fdividef(), __ffs(), __ffsll(), __finite(), __finitef(), __float2int_rd(), __float2int_rn(), __float2int_ru(), __float2int_rz(), __float2ll_rd(), __float2ll_rn(), __float2ll_ru(), __float2ll_rz(), __float2uint_rd(), __float2uint_rn(), __float2uint_ru(), __float2uint_rz(), __float2ull_rd(), __float2ull_rn(), __float2ull_ru(), __float2ull_rz(), __float_as_int(), __float_as_uint(), __fma_rd(), __fma_rn(), __fma_ru(), __fma_rz(), __fmaf_ieee_rd(), __fmaf_ieee_rn(), __fmaf_ieee_ru(), __fmaf_ieee_rz(), __fmaf_rd(), __fmaf_rn(), __fmaf_ru(), __fmaf_rz(), __fmul_rd(), __fmul_rn(), __fmul_ru(), __fmul_rz(), __frcp_rd(), __frcp_rn(), __frcp_ru(), __frcp_rz(), __frsqrt_rn(), __fsqrt_rd(), __fsqrt_rn(), __fsqrt_ru(), __fsqrt_rz(), __fsub_rd(), __fsub_rn(), __fsub_ru(), __fsub_rz(), __hadd(), __hiloint2double(), __int2double_rn(), __int2float_rd(), __int2float_rn(), __int2float_ru(), __int2float_rz(), __int_as_float(), __isfinited(), __isinf(), __isinff(), __isnan(), __isnanf(), __ll2double_rd(), __ll2double_rn(), __ll2double_ru(), __ll2double_rz(), __ll2float_rd(), __ll2float_rn(), __ll2float_ru(), __ll2float_rz(), __log10f(), __log2f(), __logf(), __longlong_as_double(), __mul24(), __mul64hi(), __muldc3(), __mulhi(), __mulsc3(), __popc(), __popcll(), __powf(), __rhadd(), __sad(), __saturatef(), __signbitd(), __signbitf(), __sincosf(), __sinf(), __syncthreads_and(), __syncthreads_count(), __syncthreads_or(), __t1mskc_u32(), __tanf(), __tzmsk_u32(), __uhadd(), __uint2double_rn(), __uint2float_rd(), __uint2float_rn(), __uint2float_ru(), __uint2float_rz(), __uint_as_float(), __ull2double_rd(), __ull2double_rn(), __ull2double_ru(), __ull2double_rz(), __ull2float_rd(), __ull2float_rn(), __ull2float_ru(), __ull2float_rz(), __umul24(), __umul64hi(), __umulhi(), __urhadd(), __usad(), __vabs2(), __vabs4(), __vabsdiffs2(), __vabsdiffs4(), __vabsdiffu2(), __vabsdiffu4(), __vabsss2(), __vabsss4(), __vadd2(), __vadd4(), __vaddss2(), __vaddss4(), __vaddus2(), __vaddus4(), __vavgs2(), __vavgs4(), __vavgu2(), __vavgu4(), __vcmpeq2(), __vcmpeq4(), __vcmpges2(), __vcmpges4(), __vcmpgeu2(), __vcmpgeu4(), __vcmpgts2(), __vcmpgts4(), __vcmpgtu2(), __vcmpgtu4(), __vcmples2(), __vcmples4(), __vcmpleu2(), __vcmpleu4(), __vcmplts2(), __vcmplts4(), __vcmpltu2(), __vcmpltu4(), __vcmpne2(), __vcmpne4(), __vhaddu2(), __vhaddu4(), __vmaxs2(), __vmaxs4(), __vmaxu2(), __vmaxu4(), __vmins2(), __vmins4(), __vminu2(), __vminu4(), __vneg2(), __vneg4(), __vnegss2(), __vnegss4(), __vsads2(), __vsads4(), __vsadu2(), __vsadu4(), __vseteq2(), __vseteq4(), __vsetges2(), __vsetges4(), __vsetgeu2(), __vsetgeu4(), __vsetgts2(), __vsetgts4(), __vsetgtu2(), __vsetgtu4(), __vsetles2(), __vsetles4(), __vsetleu2(), __vsetleu4(), __vsetlts2(), __vsetlts4(), __vsetltu2(), __vsetltu4(), __vsetne2(), __vsetne4(), __vsub2(), __vsub4(), __vsubss2(), __vsubss4(), __vsubus2(), __vsubus4(), _cvtsh_ss(), _inc_ssp(), _incsspd(), _mm256_2intersect_epi32(), _mm256_2intersect_epi64(), _mm256_abs_epi16(), _mm256_abs_epi32(), _mm256_abs_epi8(), _mm256_add_epi16(), _mm256_add_epi32(), _mm256_add_epi64(), _mm256_add_epi8(), _mm256_add_pd(), _mm256_add_ps(), _mm256_adds_epi16(), _mm256_adds_epi8(), _mm256_adds_epu16(), _mm256_adds_epu8(), _mm256_addsub_pd(), _mm256_addsub_ps(), _mm256_and_epi32(), _mm256_and_epi64(), _mm256_and_pd(), _mm256_and_ps(), _mm256_and_si256(), _mm256_andnot_pd(), _mm256_andnot_ps(), _mm256_andnot_si256(), _mm256_avg_epu16(), _mm256_avg_epu8(), _mm256_blendv_pd(), _mm256_blendv_ps(), _mm256_broadcast_pd(), _mm256_broadcast_ps(), _mm256_broadcast_sd(), _mm256_broadcast_ss(), _mm256_castpd128_pd256(), _mm256_castpd256_pd128(), _mm256_castpd_ps(), _mm256_castpd_si256(), _mm256_castps128_ps256(), _mm256_castps256_ps128(), _mm256_castps_pd(), _mm256_castps_si256(), _mm256_castsi128_si256(), _mm256_castsi256_pd(), _mm256_castsi256_ps(), _mm256_castsi256_si128(), _mm256_cmpeq_epi16(), _mm256_cmpeq_epi32(), _mm256_cmpeq_epi64(), _mm256_cmpeq_epi8(), _mm256_cmpgt_epi16(), _mm256_cmpgt_epi32(), _mm256_cmpgt_epi64(), _mm256_cmpgt_epi8(), _mm256_cvtepi32_pd(), _mm256_cvtepi32_ps(), _mm256_cvtpd_epi32(), _mm256_cvtpd_ps(), _mm256_cvtph_ps(), _mm256_cvtps_epi32(), _mm256_cvtps_pd(), _mm256_cvtsd_f64(), _mm256_cvtsi256_si32(), _mm256_cvtss_f32(), _mm256_cvttpd_epi32(), _mm256_cvttps_epi32(), _mm256_div_pd(), _mm256_div_ps(), _mm256_hadd_epi16(), _mm256_hadd_epi32(), _mm256_hadd_pd(), _mm256_hadd_ps(), _mm256_hadds_epi16(), _mm256_hsub_epi16(), _mm256_hsub_epi32(), _mm256_hsub_pd(), _mm256_hsub_ps(), _mm256_hsubs_epi16(), _mm256_madd_epi16(), _mm256_maddubs_epi16(), _mm256_maskstore_pd(), _mm256_maskstore_ps(), _mm256_max_epi16(), _mm256_max_epi32(), _mm256_max_epi8(), _mm256_max_epu16(), _mm256_max_epu32(), _mm256_max_epu8(), _mm256_max_pd(), _mm256_max_ps(), _mm256_min_epi16(), _mm256_min_epi32(), _mm256_min_epi8(), _mm256_min_epu16(), _mm256_min_epu32(), _mm256_min_epu8(), _mm256_min_pd(), _mm256_min_ps(), _mm256_movedup_pd(), _mm256_movehdup_ps(), _mm256_moveldup_ps(), _mm256_movemask_epi8(), _mm256_movemask_pd(), _mm256_movemask_ps(), _mm256_mul_epi32(), _mm256_mul_epu32(), _mm256_mul_pd(), _mm256_mul_ps(), _mm256_mulhi_epi16(), _mm256_mulhi_epu16(), _mm256_mulhrs_epi16(), _mm256_mullo_epi16(), _mm256_mullo_epi32(), _mm256_or_epi32(), _mm256_or_epi64(), _mm256_or_pd(), _mm256_or_ps(), _mm256_or_si256(), _mm256_packs_epi16(), _mm256_packs_epi32(), _mm256_packus_epi16(), _mm256_permutevar8x32_epi32(), _mm256_permutevar8x32_ps(), _mm256_permutevar_pd(), _mm256_permutevar_ps(), _mm256_rcp_ps(), _mm256_rsqrt_ps(), _mm256_sad_epu8(), _mm256_set_epi64x(), _mm256_set_pd(), _mm256_set_ps(), _mm256_setr_epi64x(), _mm256_setr_pd(), _mm256_setr_ps(), _mm256_shuffle_epi8(), _mm256_sign_epi16(), _mm256_sign_epi32(), _mm256_sign_epi8(), _mm256_sll_epi16(), _mm256_sll_epi32(), _mm256_sll_epi64(), _mm256_slli_epi16(), _mm256_slli_epi32(), _mm256_slli_epi64(), _mm256_sqrt_pd(), _mm256_sqrt_ps(), _mm256_sra_epi16(), _mm256_sra_epi32(), _mm256_srai_epi16(), _mm256_srai_epi32(), _mm256_srl_epi16(), _mm256_srl_epi32(), _mm256_srl_epi64(), _mm256_srli_epi16(), _mm256_srli_epi32(), _mm256_srli_epi64(), _mm256_store_pd(), _mm256_store_ps(), _mm256_store_si256(), _mm256_storeu2_m128(), _mm256_storeu2_m128d(), _mm256_storeu2_m128i(), _mm256_storeu_pd(), _mm256_storeu_ps(), _mm256_storeu_si256(), _mm256_stream_pd(), _mm256_stream_ps(), _mm256_stream_si256(), _mm256_sub_epi16(), _mm256_sub_epi32(), _mm256_sub_epi64(), _mm256_sub_epi8(), _mm256_sub_pd(), _mm256_sub_ps(), _mm256_subs_epi16(), _mm256_subs_epi8(), _mm256_subs_epu16(), _mm256_subs_epu8(), _mm256_testc_pd(), _mm256_testc_ps(), _mm256_testc_si256(), _mm256_testnzc_pd(), _mm256_testnzc_ps(), _mm256_testnzc_si256(), _mm256_testz_pd(), _mm256_testz_ps(), _mm256_testz_si256(), _mm256_unpackhi_epi16(), _mm256_unpackhi_epi32(), _mm256_unpackhi_epi64(), _mm256_unpackhi_epi8(), _mm256_unpackhi_pd(), _mm256_unpackhi_ps(), _mm256_unpacklo_epi16(), _mm256_unpacklo_epi32(), _mm256_unpacklo_epi64(), _mm256_unpacklo_epi8(), _mm256_unpacklo_pd(), _mm256_unpacklo_ps(), _mm256_xor_epi32(), _mm256_xor_epi64(), _mm256_xor_pd(), _mm256_xor_ps(), _mm256_xor_si256(), _mm256_zextpd128_pd256(), _mm256_zextps128_ps256(), _mm256_zextsi128_si256(), _mm512_2intersect_epi32(), _mm512_2intersect_epi64(), _mm512_add_pd(), _mm512_add_ps(), _mm512_and_epi32(), _mm512_and_epi64(), _mm512_and_si512(), _mm512_castpd256_pd512(), _mm512_castpd512_pd128(), _mm512_castps256_ps512(), _mm512_castps512_ps128(), _mm512_cvtsd_f64(), _mm512_cvtss_f32(), _mm512_cvttpd_epi32(), _mm512_cvttps_epi32(), _mm512_div_pd(), _mm512_div_ps(), _mm512_int2mask(), _mm512_mask2int(), _mm512_mask_and_epi32(), _mm512_mask_and_epi64(), _mm512_mask_or_epi32(), _mm512_mask_or_epi64(), _mm512_mask_xor_epi32(), _mm512_mask_xor_epi64(), _mm512_maskz_and_epi32(), _mm512_maskz_and_epi64(), _mm512_maskz_or_epi32(), _mm512_maskz_or_epi64(), _mm512_maskz_xor_epi32(), _mm512_maskz_xor_epi64(), _mm512_mul_pd(), _mm512_mul_ps(), _mm512_or_epi32(), _mm512_or_epi64(), _mm512_or_si512(), _mm512_sub_pd(), _mm512_sub_ps(), _mm512_unpackhi_pd(), _mm512_unpackhi_ps(), _mm512_unpacklo_pd(), _mm512_unpacklo_ps(), _mm512_xor_epi32(), _mm512_xor_epi64(), _mm512_xor_si512(), _mm512_zextpd128_pd512(), _mm512_zextpd256_pd512(), _mm512_zextps128_ps512(), _mm512_zextps256_ps512(), _mm512_zextsi128_si512(), _mm512_zextsi256_si512(), _mm_2intersect_epi32(), _mm_2intersect_epi64(), _mm_abs_epi16(), _mm_abs_epi32(), _mm_abs_epi8(), _mm_abs_pi16(), _mm_abs_pi32(), _mm_abs_pi8(), _mm_add_epi16(), _mm_add_epi32(), _mm_add_epi64(), _mm_add_epi8(), _mm_add_pd(), _mm_add_ps(), _mm_add_sd(), _mm_add_si64(), _mm_add_ss(), _mm_adds_epi16(), _mm_adds_epi8(), _mm_adds_epu16(), _mm_adds_epu8(), _mm_addsub_pd(), _mm_addsub_ps(), _mm_and_epi32(), _mm_and_epi64(), _mm_and_pd(), _mm_and_ps(), _mm_and_si128(), _mm_andnot_pd(), _mm_andnot_ps(), _mm_andnot_si128(), _mm_avg_epu16(), _mm_avg_epu8(), _mm_avg_pu16(), _mm_avg_pu8(), _mm_broadcast_ss(), _mm_broadcastsd_pd(), _mm_castpd_ps(), _mm_castpd_si128(), _mm_castps_pd(), _mm_castps_si128(), _mm_castsi128_pd(), _mm_castsi128_ps(), _mm_cmpeq_epi16(), _mm_cmpeq_epi32(), _mm_cmpeq_epi8(), _mm_cmpeq_pd(), _mm_cmpeq_ps(), _mm_cmpeq_sd(), _mm_cmpeq_ss(), _mm_cmpge_pd(), _mm_cmpge_ps(), _mm_cmpge_sd(), _mm_cmpge_ss(), _mm_cmpgt_epi16(), _mm_cmpgt_epi32(), _mm_cmpgt_epi8(), _mm_cmpgt_pd(), _mm_cmpgt_ps(), _mm_cmpgt_sd(), _mm_cmpgt_ss(), _mm_cmple_pd(), _mm_cmple_ps(), _mm_cmple_sd(), _mm_cmple_ss(), _mm_cmplt_epi16(), _mm_cmplt_epi32(), _mm_cmplt_epi8(), _mm_cmplt_pd(), _mm_cmplt_ps(), _mm_cmplt_sd(), _mm_cmplt_ss(), _mm_cmpneq_pd(), _mm_cmpneq_ps(), _mm_cmpneq_sd(), _mm_cmpneq_ss(), _mm_cmpnge_pd(), _mm_cmpnge_ps(), _mm_cmpnge_sd(), _mm_cmpnge_ss(), _mm_cmpngt_pd(), _mm_cmpngt_ps(), _mm_cmpngt_sd(), _mm_cmpngt_ss(), _mm_cmpnle_pd(), _mm_cmpnle_ps(), _mm_cmpnle_sd(), _mm_cmpnle_ss(), _mm_cmpnlt_pd(), _mm_cmpnlt_ps(), _mm_cmpnlt_sd(), _mm_cmpnlt_ss(), _mm_cmpord_pd(), _mm_cmpord_ps(), _mm_cmpord_sd(), _mm_cmpord_ss(), _mm_cmpunord_pd(), _mm_cmpunord_ps(), _mm_cmpunord_sd(), _mm_cmpunord_ss(), _mm_comieq_sd(), _mm_comieq_ss(), _mm_comige_sd(), _mm_comige_ss(), _mm_comigt_sd(), _mm_comigt_ss(), _mm_comile_sd(), _mm_comile_ss(), _mm_comilt_sd(), _mm_comilt_ss(), _mm_comineq_sd(), _mm_comineq_ss(), _mm_cvt_pi2ps(), _mm_cvt_ps2pi(), _mm_cvt_si2ss(), _mm_cvt_ss2si(), _mm_cvtepi32_pd(), _mm_cvtepi32_ps(), _mm_cvtpd_epi32(), _mm_cvtpd_pi32(), _mm_cvtpd_ps(), _mm_cvtph_ps(), _mm_cvtpi16_ps(), _mm_cvtpi32_pd(), _mm_cvtpi32_ps(), _mm_cvtpi32x2_ps(), _mm_cvtpi8_ps(), _mm_cvtps_epi32(), _mm_cvtps_pd(), _mm_cvtps_pi16(), _mm_cvtps_pi32(), _mm_cvtps_pi8(), _mm_cvtpu16_ps(), _mm_cvtpu8_ps(), _mm_cvtsd_f64(), _mm_cvtsd_si32(), _mm_cvtsd_ss(), _mm_cvtsi128_si32(), _mm_cvtsi128_si64(), _mm_cvtsi32_sd(), _mm_cvtsi32_si128(), _mm_cvtsi32_ss(), _mm_cvtsi64_si128(), _mm_cvtss_f32(), _mm_cvtss_sd(), _mm_cvtss_si32(), _mm_cvtt_ps2pi(), _mm_cvtt_ss2si(), _mm_cvttpd_epi32(), _mm_cvttpd_pi32(), _mm_cvttps_epi32(), _mm_cvttps_pi32(), _mm_cvttsd_si32(), _mm_cvttss_si32(), _mm_div_pd(), _mm_div_ps(), _mm_div_sd(), _mm_div_ss(), _mm_hadd_epi16(), _mm_hadd_epi32(), _mm_hadd_pd(), _mm_hadd_pi16(), _mm_hadd_pi32(), _mm_hadd_ps(), _mm_hadds_epi16(), _mm_hadds_pi16(), _mm_hsub_epi16(), _mm_hsub_epi32(), _mm_hsub_pd(), _mm_hsub_pi16(), _mm_hsub_pi32(), _mm_hsub_ps(), _mm_hsubs_epi16(), _mm_hsubs_pi16(), _mm_loadh_pd(), _mm_loadh_pi(), _mm_loadl_pd(), _mm_loadl_pi(), _mm_loadr_ps(), _mm_loadu_si16(), _mm_loadu_si32(), _mm_loadu_si64(), _mm_madd_epi16(), _mm_maddubs_epi16(), _mm_maddubs_pi16(), _mm_maskstore_pd(), _mm_maskstore_ps(), _mm_max_epi16(), _mm_max_epu8(), _mm_max_pd(), _mm_max_pi16(), _mm_max_ps(), _mm_max_pu8(), _mm_max_sd(), _mm_max_ss(), _mm_min_epi16(), _mm_min_epu8(), _mm_min_pd(), _mm_min_pi16(), _mm_min_ps(), _mm_min_pu8(), _mm_min_sd(), _mm_min_ss(), _mm_move_epi64(), _mm_move_sd(), _mm_move_ss(), _mm_movedup_pd(), _mm_movehdup_ps(), _mm_movehl_ps(), _mm_moveldup_ps(), _mm_movelh_ps(), _mm_movemask_epi8(), _mm_movemask_pd(), _mm_movemask_pi8(), _mm_movemask_ps(), _mm_movepi64_pi64(), _mm_movpi64_epi64(), _mm_mul_epu32(), _mm_mul_pd(), _mm_mul_ps(), _mm_mul_sd(), _mm_mul_ss(), _mm_mul_su32(), _mm_mulhi_epi16(), _mm_mulhi_epu16(), _mm_mulhi_pu16(), _mm_mulhrs_epi16(), _mm_mulhrs_pi16(), _mm_mullo_epi16(), _mm_or_epi32(), _mm_or_epi64(), _mm_or_pd(), _mm_or_ps(), _mm_or_si128(), _mm_packs_epi16(), _mm_packs_epi32(), _mm_packus_epi16(), _mm_permutevar_pd(), _mm_permutevar_ps(), _mm_rcp_ps(), _mm_rcp_ss(), _mm_rsqrt_ps(), _mm_rsqrt_ss(), _mm_sad_epu8(), _mm_sad_pu8(), _mm_shuffle_epi8(), _mm_shuffle_pi8(), _mm_sign_epi16(), _mm_sign_epi32(), _mm_sign_epi8(), _mm_sign_pi16(), _mm_sign_pi32(), _mm_sign_pi8(), _mm_sll_epi16(), _mm_sll_epi32(), _mm_sll_epi64(), _mm_slli_epi16(), _mm_slli_epi32(), _mm_slli_epi64(), _mm_sqrt_pd(), _mm_sqrt_ps(), _mm_sqrt_sd(), _mm_sqrt_ss(), _mm_sra_epi16(), _mm_sra_epi32(), _mm_srai_epi16(), _mm_srai_epi32(), _mm_srl_epi16(), _mm_srl_epi32(), _mm_srl_epi64(), _mm_srli_epi16(), _mm_srli_epi32(), _mm_srli_epi64(), _mm_store1_pd(), _mm_store1_ps(), _mm_store_pd(), _mm_store_pd1(), _mm_store_ps(), _mm_store_ps1(), _mm_store_sd(), _mm_store_ss(), _mm_storeh_pd(), _mm_storeh_pi(), _mm_storel_epi64(), _mm_storel_pd(), _mm_storel_pi(), _mm_storer_pd(), _mm_storer_ps(), _mm_storeu_pd(), _mm_storeu_ps(), _mm_stream_pd(), _mm_stream_pi(), _mm_stream_ps(), _mm_stream_sd(), _mm_stream_si128(), _mm_stream_ss(), _mm_sub_epi16(), _mm_sub_epi32(), _mm_sub_epi64(), _mm_sub_epi8(), _mm_sub_pd(), _mm_sub_ps(), _mm_sub_sd(), _mm_sub_si64(), _mm_sub_ss(), _mm_subs_epi16(), _mm_subs_epi8(), _mm_subs_epu16(), _mm_subs_epu8(), _mm_testc_pd(), _mm_testc_ps(), _mm_testnzc_pd(), _mm_testnzc_ps(), _mm_testz_pd(), _mm_testz_ps(), _mm_ucomieq_sd(), _mm_ucomieq_ss(), _mm_ucomige_sd(), _mm_ucomige_ss(), _mm_ucomigt_sd(), _mm_ucomigt_ss(), _mm_ucomile_sd(), _mm_ucomile_ss(), _mm_ucomilt_sd(), _mm_ucomilt_ss(), _mm_ucomineq_sd(), _mm_ucomineq_ss(), _mm_unpackhi_epi16(), _mm_unpackhi_epi32(), _mm_unpackhi_epi64(), _mm_unpackhi_epi8(), _mm_unpackhi_pd(), _mm_unpackhi_ps(), _mm_unpacklo_epi16(), _mm_unpacklo_epi32(), _mm_unpacklo_epi64(), _mm_unpacklo_epi8(), _mm_unpacklo_pd(), _mm_unpacklo_ps(), _mm_xor_epi32(), _mm_xor_epi64(), _mm_xor_pd(), _mm_xor_ps(), _mm_xor_si128(), _rdsspd(), _wrssd(), _wrussd(), abs(), acos(), acosf(), acosh(), acoshf(), asin(), asinf(), asinh(), asinhf(), atan(), atan2(), atan2f(), atanf(), atanh(), atanhf(), cbrt(), cbrtf(), ceil(), ceilf(), copysign(), copysignf(), cos(), cosf(), cosh(), coshf(), cospi(), cospif(), cyl_bessel_i0(), cyl_bessel_i0f(), cyl_bessel_i1(), cyl_bessel_i1f(), erf(), erfc(), erfcf(), erfcinv(), erfcinvf(), erfcx(), erfcxf(), erff(), erfinv(), erfinvf(), exp(), exp10(), exp10f(), exp2(), exp2f(), expf(), expm1(), expm1f(), fabs(), fabsf(), fdim(), fdimf(), fdivide(), fdividef(), fma(), fmaf(), fmax(), fmaxf(), fmin(), fminf(), fmod(), fmodf(), frexp(), frexpf(), hypot(), hypotf(), ilogb(), ilogbf(), j0(), j0f(), j1(), j1f(), jn(), jnf(), labs(), ldexp(), ldexpf(), lgamma(), lgammaf(), llabs(), llmax(), llmin(), llrint(), llrintf(), llround(), llroundf(), log(), log10(), log10f(), log1p(), log1pf(), log2(), log2f(), logb(), logbf(), logf(), lrint(), lrintf(), lround(), lroundf(), max(), memcpy(), memset(), min(), modf(), modff(), nearbyint(), nearbyintf(), nextafter(), nextafterf(), norm(), norm3d(), norm3df(), norm4d(), norm4df(), normcdf(), normcdff(), normcdfinv(), normcdfinvf(), normf(), pow(), powf(), powi(), powif(), rcbrt(), rcbrtf(), remainder(), remainderf(), remquo(), remquof(), rhypot(), rhypotf(), rint(), rintf(), rnorm(), rnorm3d(), rnorm3df(), rnorm4d(), rnorm4df(), rnormf(), round(), roundf(), rsqrt(), rsqrtf(), scalbln(), scalblnf(), scalbn(), scalbnf(), sin(), sincos(), sincosf(), sincospi(), sincospif(), sinf(), sinh(), sinhf(), sinpi(), sinpif(), sqrt(), sqrtf(), tan(), tanf(), tanh(), tanhf(), tgamma(), tgammaf(), trunc(), truncf(), ullmax(), ullmin(), umax(), umin(), vec_abs(), vec_abss(), vec_add(), vec_addc(), vec_adde(), vec_adds(), vec_all_eq(), vec_all_ge(), vec_all_gt(), vec_all_le(), vec_all_lt(), vec_all_nan(), vec_all_ne(), vec_all_nge(), vec_all_ngt(), vec_all_nle(), vec_all_nlt(), vec_all_numeric(), vec_and(), vec_andc(), vec_any_eq(), vec_any_ge(), vec_any_gt(), vec_any_le(), vec_any_lt(), vec_any_nan(), vec_any_ne(), vec_any_nge(), vec_any_ngt(), vec_any_nle(), vec_any_nlt(), vec_any_numeric(), vec_avg(), vec_ceil(), vec_cmpeq(), vec_cmpge(), vec_cmpgt(), vec_cmple(), vec_cmplt(), vec_cmpne(), vec_div(), vec_extract(), vec_float(), vec_floor(), vec_insert(), vec_ld(), vec_lde(), vec_ldl(), vec_lvebx(), vec_lvehx(), vec_lvewx(), vec_lvlx(), vec_lvlxl(), vec_lvrx(), vec_lvrxl(), vec_lvsl(), vec_lvsr(), vec_lvx(), vec_lvxl(), vec_madd(), vec_max(), vec_mergeh(), vec_mergel(), vec_min(), vec_mladd(), vec_msum(), vec_msums(), vec_mtvscr(), vec_mul(), vec_mule(), vec_mulo(), vec_nabs(), vec_neg(), vec_nmsub(), vec_nor(), vec_or(), vec_pack(), vec_packs(), vec_packsu(), vec_perm(), vec_promote(), vec_re(), vec_recipdiv(), vec_revb(), vec_reve(), vec_rl(), vec_round(), vec_roundm(), vec_roundp(), vec_roundz(), vec_rsqrt(), vec_rsqrte(), vec_sel(), vec_signed(), vec_sl(), vec_sld(), vec_sldw(), vec_sll(), vec_slo(), vec_splat(), vec_splat_s16(), vec_splat_s32(), vec_splat_s8(), vec_splat_u16(), vec_splat_u32(), vec_splat_u8(), vec_splats(), vec_sr(), vec_sra(), vec_srl(), vec_sro(), vec_st(), vec_ste(), vec_stl(), vec_stvebx(), vec_stvehx(), vec_stvewx(), vec_stvlx(), vec_stvlxl(), vec_stvrx(), vec_stvrxl(), vec_stvx(), vec_stvxl(), vec_sub(), vec_subc(), vec_sube(), vec_subs(), vec_sum4s(), vec_trunc(), vec_unpackh(), vec_unpackl(), vec_unsigned(), vec_vaddsbs(), vec_vaddshs(), vec_vaddsws(), vec_vaddubm(), vec_vaddubs(), vec_vadduhm(), vec_vadduhs(), vec_vadduwm(), vec_vadduws(), vec_vand(), vec_vandc(), vec_vmaxsb(), vec_vmaxsh(), vec_vmaxsw(), vec_vmaxub(), vec_vmaxuh(), vec_vmaxuw(), vec_vminsb(), vec_vminsh(), vec_vminsw(), vec_vminub(), vec_vminuh(), vec_vminuw(), vec_vmladduhm(), vec_vmrghb(), vec_vmrghh(), vec_vmrghw(), vec_vmrglb(), vec_vmrglh(), vec_vmrglw(), vec_vnor(), vec_vor(), vec_vperm(), vec_vpkshus(), vec_vpkswus(), vec_vpkuhum(), vec_vpkuwum(), vec_vrlb(), vec_vrlh(), vec_vrlw(), vec_vsel(), vec_vsl(), vec_vslb(), vec_vsldoi(), vec_vslh(), vec_vslo(), vec_vslw(), vec_vspltb(), vec_vsplth(), vec_vspltisb(), vec_vspltish(), vec_vspltisw(), vec_vspltw(), vec_vsr(), vec_vsrab(), vec_vsrah(), vec_vsraw(), vec_vsrb(), vec_vsrh(), vec_vsro(), vec_vsrw(), vec_vsubsbs(), vec_vsubshs(), vec_vsubsws(), vec_vsububm(), vec_vsububs(), vec_vsubuhm(), vec_vsubuhs(), vec_vsubuwm(), vec_vsubuws(), vec_vupkhsb(), vec_vupkhsh(), vec_vupklsb(), vec_vupklsh(), vec_vxor(), vec_xor(), wasm_f32x4_abs(), wasm_f32x4_add(), wasm_f32x4_ceil(), wasm_f32x4_convert_i32x4(), wasm_f32x4_convert_u32x4(), wasm_f32x4_demote_f64x2_zero(), wasm_f32x4_div(), wasm_f32x4_eq(), wasm_f32x4_extract_lane(), wasm_f32x4_floor(), wasm_f32x4_ge(), wasm_f32x4_gt(), wasm_f32x4_le(), wasm_f32x4_lt(), wasm_f32x4_max(), wasm_f32x4_min(), wasm_f32x4_mul(), wasm_f32x4_ne(), wasm_f32x4_nearest(), wasm_f32x4_neg(), wasm_f32x4_pmax(), wasm_f32x4_pmin(), wasm_f32x4_relaxed_madd(), wasm_f32x4_relaxed_max(), wasm_f32x4_relaxed_min(), wasm_f32x4_relaxed_nmadd(), wasm_f32x4_replace_lane(), wasm_f32x4_splat(), wasm_f32x4_sqrt(), wasm_f32x4_sub(), wasm_f32x4_trunc(), wasm_f64x2_abs(), wasm_f64x2_add(), wasm_f64x2_ceil(), wasm_f64x2_convert_low_i32x4(), wasm_f64x2_convert_low_u32x4(), wasm_f64x2_div(), wasm_f64x2_eq(), wasm_f64x2_extract_lane(), wasm_f64x2_floor(), wasm_f64x2_ge(), wasm_f64x2_gt(), wasm_f64x2_le(), wasm_f64x2_lt(), wasm_f64x2_max(), wasm_f64x2_min(), wasm_f64x2_mul(), wasm_f64x2_ne(), wasm_f64x2_nearest(), wasm_f64x2_neg(), wasm_f64x2_pmax(), wasm_f64x2_pmin(), wasm_f64x2_promote_low_f32x4(), wasm_f64x2_relaxed_madd(), wasm_f64x2_relaxed_max(), wasm_f64x2_relaxed_min(), wasm_f64x2_relaxed_nmadd(), wasm_f64x2_replace_lane(), wasm_f64x2_splat(), wasm_f64x2_sqrt(), wasm_f64x2_sub(), wasm_f64x2_trunc(), wasm_i16x8_abs(), wasm_i16x8_add(), wasm_i16x8_add_sat(), wasm_i16x8_all_true(), wasm_i16x8_bitmask(), wasm_i16x8_eq(), wasm_i16x8_extadd_pairwise_i8x16(), wasm_i16x8_extend_high_i8x16(), wasm_i16x8_extend_low_i8x16(), wasm_i16x8_extmul_high_i8x16(), wasm_i16x8_extmul_low_i8x16(), wasm_i16x8_extract_lane(), wasm_i16x8_ge(), wasm_i16x8_gt(), wasm_i16x8_le(), wasm_i16x8_lt(), wasm_i16x8_max(), wasm_i16x8_min(), wasm_i16x8_mul(), wasm_i16x8_narrow_i32x4(), wasm_i16x8_ne(), wasm_i16x8_neg(), wasm_i16x8_q15mulr_sat(), wasm_i16x8_relaxed_dot_i8x16_i7x16(), wasm_i16x8_relaxed_laneselect(), wasm_i16x8_relaxed_q15mulr(), wasm_i16x8_replace_lane(), wasm_i16x8_shl(), wasm_i16x8_shr(), wasm_i16x8_splat(), wasm_i16x8_sub(), wasm_i16x8_sub_sat(), wasm_i32x4_abs(), wasm_i32x4_add(), wasm_i32x4_all_true(), wasm_i32x4_bitmask(), wasm_i32x4_dot_i16x8(), wasm_i32x4_eq(), wasm_i32x4_extadd_pairwise_i16x8(), wasm_i32x4_extend_high_i16x8(), wasm_i32x4_extend_low_i16x8(), wasm_i32x4_extmul_high_i16x8(), wasm_i32x4_extmul_low_i16x8(), wasm_i32x4_extract_lane(), wasm_i32x4_ge(), wasm_i32x4_gt(), wasm_i32x4_le(), wasm_i32x4_lt(), wasm_i32x4_max(), wasm_i32x4_min(), wasm_i32x4_mul(), wasm_i32x4_ne(), wasm_i32x4_neg(), wasm_i32x4_relaxed_dot_i8x16_i7x16_add(), wasm_i32x4_relaxed_laneselect(), wasm_i32x4_relaxed_trunc_f32x4(), wasm_i32x4_relaxed_trunc_f64x2_zero(), wasm_i32x4_replace_lane(), wasm_i32x4_shl(), wasm_i32x4_shr(), wasm_i32x4_splat(), wasm_i32x4_sub(), wasm_i32x4_trunc_sat_f32x4(), wasm_i32x4_trunc_sat_f64x2_zero(), wasm_i64x2_abs(), wasm_i64x2_add(), wasm_i64x2_all_true(), wasm_i64x2_bitmask(), wasm_i64x2_eq(), wasm_i64x2_extend_high_i32x4(), wasm_i64x2_extend_low_i32x4(), wasm_i64x2_extmul_high_i32x4(), wasm_i64x2_extmul_low_i32x4(), wasm_i64x2_extract_lane(), wasm_i64x2_ge(), wasm_i64x2_gt(), wasm_i64x2_le(), wasm_i64x2_lt(), wasm_i64x2_mul(), wasm_i64x2_ne(), wasm_i64x2_neg(), wasm_i64x2_relaxed_laneselect(), wasm_i64x2_replace_lane(), wasm_i64x2_shl(), wasm_i64x2_shr(), wasm_i64x2_splat(), wasm_i64x2_sub(), wasm_i8x16_abs(), wasm_i8x16_add(), wasm_i8x16_add_sat(), wasm_i8x16_all_true(), wasm_i8x16_bitmask(), wasm_i8x16_eq(), wasm_i8x16_extract_lane(), wasm_i8x16_ge(), wasm_i8x16_gt(), wasm_i8x16_le(), wasm_i8x16_lt(), wasm_i8x16_max(), wasm_i8x16_min(), wasm_i8x16_narrow_i16x8(), wasm_i8x16_ne(), wasm_i8x16_neg(), wasm_i8x16_popcnt(), wasm_i8x16_relaxed_laneselect(), wasm_i8x16_relaxed_swizzle(), wasm_i8x16_replace_lane(), wasm_i8x16_shl(), wasm_i8x16_shr(), wasm_i8x16_splat(), wasm_i8x16_sub(), wasm_i8x16_sub_sat(), wasm_i8x16_swizzle(), wasm_u16x8_add_sat(), wasm_u16x8_avgr(), wasm_u16x8_extadd_pairwise_u8x16(), wasm_u16x8_extend_high_u8x16(), wasm_u16x8_extend_low_u8x16(), wasm_u16x8_extmul_high_u8x16(), wasm_u16x8_extmul_low_u8x16(), wasm_u16x8_extract_lane(), wasm_u16x8_ge(), wasm_u16x8_gt(), wasm_u16x8_le(), wasm_u16x8_lt(), wasm_u16x8_max(), wasm_u16x8_min(), wasm_u16x8_narrow_i32x4(), wasm_u16x8_replace_lane(), wasm_u16x8_shr(), wasm_u16x8_splat(), wasm_u16x8_sub_sat(), wasm_u32x4_extadd_pairwise_u16x8(), wasm_u32x4_extend_high_u16x8(), wasm_u32x4_extend_low_u16x8(), wasm_u32x4_extmul_high_u16x8(), wasm_u32x4_extmul_low_u16x8(), wasm_u32x4_extract_lane(), wasm_u32x4_ge(), wasm_u32x4_gt(), wasm_u32x4_le(), wasm_u32x4_lt(), wasm_u32x4_max(), wasm_u32x4_min(), wasm_u32x4_relaxed_trunc_f32x4(), wasm_u32x4_relaxed_trunc_f64x2_zero(), wasm_u32x4_replace_lane(), wasm_u32x4_shr(), wasm_u32x4_splat(), wasm_u32x4_trunc_sat_f32x4(), wasm_u32x4_trunc_sat_f64x2_zero(), wasm_u64x2_extend_high_u32x4(), wasm_u64x2_extend_low_u32x4(), wasm_u64x2_extmul_high_u32x4(), wasm_u64x2_extmul_low_u32x4(), wasm_u64x2_extract_lane(), wasm_u64x2_replace_lane(), wasm_u64x2_shr(), wasm_u64x2_splat(), wasm_u8x16_add_sat(), wasm_u8x16_avgr(), wasm_u8x16_extract_lane(), wasm_u8x16_ge(), wasm_u8x16_gt(), wasm_u8x16_le(), wasm_u8x16_lt(), wasm_u8x16_max(), wasm_u8x16_min(), wasm_u8x16_narrow_i16x8(), wasm_u8x16_replace_lane(), wasm_u8x16_shr(), wasm_u8x16_splat(), wasm_u8x16_sub_sat(), wasm_v128_and(), wasm_v128_andnot(), wasm_v128_any_true(), wasm_v128_bitselect(), wasm_v128_or(), wasm_v128_store(), wasm_v128_xor(), y0(), y0f(), y1(), y1f(), yn(), and ynf().

Macros

Typedefs

Functions

Variables

Macro Definition Documentation

◆ __DEFAULT_FN_ATTRS

◆ __DEFAULT_FN_ATTRS_MMX

◆ _mm_bslli_si128

◆ _mm_bsrli_si128

◆ _mm_cmp_pd

◆ _mm_cmp_sd

◆ _MM_DENORMALS_ZERO_MASK

◆ _MM_DENORMALS_ZERO_OFF

◆ _MM_DENORMALS_ZERO_ON

◆ _mm_extract_epi16

◆ _MM_GET_DENORMALS_ZERO_MODE

◆ _mm_insert_epi16

◆ _mm_load_pd1

◆ _MM_SET_DENORMALS_ZERO_MODE

◆ _MM_SHUFFLE2

◆ _mm_shuffle_epi32

◆ _mm_shuffle_pd

◆ _mm_shufflehi_epi16

◆ _mm_shufflelo_epi16

◆ _mm_slli_si128

◆ _mm_srli_si128

Typedef Documentation

◆ __attribute__

Function Documentation

◆ __attribute__()

◆ _mm_add_epi16()

◆ _mm_add_epi32()

◆ _mm_add_epi64()

◆ _mm_add_epi8()

◆ _mm_add_pd()

◆ _mm_add_sd()

◆ _mm_add_si64()

◆ _mm_adds_epi16()

◆ _mm_adds_epi8()

◆ _mm_adds_epu16()

◆ _mm_adds_epu8()

◆ _mm_and_pd()

◆ _mm_and_si128()

◆ _mm_andnot_pd()

◆ _mm_andnot_si128()

◆ _mm_avg_epu16()

◆ _mm_avg_epu8()

◆ _mm_castpd_ps()

◆ _mm_castpd_si128()

◆ _mm_castps_pd()

◆ _mm_castps_si128()

◆ _mm_castsi128_pd()

◆ _mm_castsi128_ps()

◆ _mm_clflush()

◆ _mm_cmpeq_epi16()

◆ _mm_cmpeq_epi32()

◆ _mm_cmpeq_epi8()

◆ _mm_cmpeq_pd()

◆ _mm_cmpeq_sd()

◆ _mm_cmpge_pd()

◆ _mm_cmpge_sd()

◆ _mm_cmpgt_epi16()

◆ _mm_cmpgt_epi32()

◆ _mm_cmpgt_epi8()

◆ _mm_cmpgt_pd()

◆ _mm_cmpgt_sd()

◆ _mm_cmple_pd()

◆ _mm_cmple_sd()

◆ _mm_cmplt_epi16()

◆ _mm_cmplt_epi32()

◆ _mm_cmplt_epi8()

◆ _mm_cmplt_pd()

◆ _mm_cmplt_sd()

◆ _mm_cmpneq_pd()

◆ _mm_cmpneq_sd()

◆ _mm_cmpnge_pd()

◆ _mm_cmpnge_sd()

◆ _mm_cmpngt_pd()

◆ _mm_cmpngt_sd()

◆ _mm_cmpnle_pd()

◆ attribute

◆ attribute()