clang 20.0.0git
|
#include <xmmintrin.h>
Go to the source code of this file.
Macros | |
#define | __DEFAULT_FN_ATTRS |
#define | __trunc64(x) (__m64) __builtin_shufflevector((__v2di)(x), __extension__(__v2di){}, 0) |
#define | __anyext128(x) |
#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 | _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 | _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 | _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 | _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 | _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 | _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 |
#define __anyext128 | ( | x | ) |
Definition at line 58 of file emmintrin.h.
#define __DEFAULT_FN_ATTRS |
Definition at line 52 of file emmintrin.h.
#define __trunc64 | ( | x | ) | (__m64) __builtin_shufflevector((__v2di)(x), __extension__(__v2di){}, 0) |
Definition at line 56 of file emmintrin.h.
#define _mm_bslli_si128 | ( | a, | |
imm | |||
) |
Definition at line 2741 of file emmintrin.h.
#define _mm_bsrli_si128 | ( | a, | |
imm | |||
) |
Definition at line 2950 of file emmintrin.h.
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.
This intrinsic corresponds to the (V)CMPPD
instruction.
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) |
Definition at line 4837 of file emmintrin.h.
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.
This intrinsic corresponds to the (V)CMPSD
instruction.
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) |
Definition at line 4873 of file emmintrin.h.
#define _MM_DENORMALS_ZERO_MASK (0x0040U) |
Definition at line 4903 of file emmintrin.h.
#define _MM_DENORMALS_ZERO_OFF (0x0000U) |
Definition at line 4901 of file emmintrin.h.
#define _MM_DENORMALS_ZERO_ON (0x0040U) |
Definition at line 4900 of file emmintrin.h.
#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.
This intrinsic corresponds to the VPEXTRW / PEXTRW
instruction.
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. |
Definition at line 4220 of file emmintrin.h.
#define _MM_GET_DENORMALS_ZERO_MODE | ( | ) | (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK) |
Definition at line 4905 of file emmintrin.h.
#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.
This intrinsic corresponds to the VPINSRW / PINSRW
instruction.
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. |
Definition at line 4248 of file emmintrin.h.
#define _mm_load_pd1 | ( | dp | ) | _mm_load1_pd(dp) |
Definition at line 1580 of file emmintrin.h.
#define _MM_SET_DENORMALS_ZERO_MODE | ( | x | ) | (_mm_setcsr((_mm_getcsr() & ~_MM_DENORMALS_ZERO_MASK) | (x))) |
Definition at line 4906 of file emmintrin.h.
#define _MM_SHUFFLE2 | ( | x, | |
y | |||
) | (((x) << 1) | (y)) |
Definition at line 4898 of file emmintrin.h.
#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.
This intrinsic corresponds to the VPSHUFD / PSHUFD
instruction.
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] . |
Definition at line 4299 of file emmintrin.h.
#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.
This intrinsic corresponds to the VSHUFPD / SHUFPD
instruction.
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] . |
Definition at line 4711 of file emmintrin.h.
#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.
This intrinsic corresponds to the VPSHUFHW / PSHUFHW
instruction.
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] . |
Definition at line 4365 of file emmintrin.h.
#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.
This intrinsic corresponds to the VPSHUFLW / PSHUFLW
instruction.
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] . |
Definition at line 4332 of file emmintrin.h.
#define _mm_slli_si128 | ( | a, | |
imm | |||
) |
Left-shifts the 128-bit integer vector operand by the specified number of bytes.
Low-order bits are cleared.
This intrinsic corresponds to the VPSLLDQ / PSLLDQ
instruction.
a | A 128-bit integer vector containing the source operand. |
imm | An immediate value specifying the number of bytes to left-shift operand a. |
Definition at line 2737 of file emmintrin.h.
#define _mm_srli_si128 | ( | a, | |
imm | |||
) |
Right-shifts the 128-bit integer vector operand by the specified number of bytes.
High-order bits are cleared.
This intrinsic corresponds to the VPSRLDQ / PSRLDQ
instruction.
a | A 128-bit integer vector containing the source operand. |
imm | An immediate value specifying the number of bytes to right-shift operand a. |
Definition at line 2946 of file emmintrin.h.
typedef signed char __v16qs __attribute__((__vector_size__(16))) |
Definition at line 19 of file emmintrin.h.
|
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.
__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. |
|
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.
__a | A 128-bit vector of [8 x i16]. |
__b | A 128-bit vector of [8 x i16]. |
Definition at line 2076 of file emmintrin.h.
Referenced by _mm_mask_add_epi16(), and _mm_maskz_add_epi16().
|
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.
__a | A 128-bit vector of [4 x i32]. |
__b | A 128-bit vector of [4 x i32]. |
Definition at line 2097 of file emmintrin.h.
Referenced by _mm_mask_add_epi32(), and _mm_maskz_add_epi32().
|
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.
__a | A 128-bit vector of [2 x i64]. |
__b | A 128-bit vector of [2 x i64]. |
Definition at line 2134 of file emmintrin.h.
Referenced by _mm_mask_add_epi64(), and _mm_maskz_add_epi64().
|
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.
__a | A 128-bit vector of [16 x i8]. |
__b | A 128-bit vector of [16 x i8]. |
Definition at line 2055 of file emmintrin.h.
Referenced by _mm_mask_add_epi8(), and _mm_maskz_add_epi8().
|
static |
Adds two 128-bit vectors of [2 x double].
This intrinsic corresponds to the VADDPD / ADDPD
instruction.
__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. |
Definition at line 95 of file emmintrin.h.
Referenced by _mm_mask_add_pd(), and _mm_maskz_add_pd().
|
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.
__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. |
Definition at line 77 of file emmintrin.h.
Referenced by _mm_mask_add_sd(), and _mm_maskz_add_sd().
|
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.
__a | A 64-bit integer. |
__b | A 64-bit integer. |
Definition at line 2114 of file emmintrin.h.
|
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.
__a | A 128-bit signed [8 x i16] vector. |
__b | A 128-bit signed [8 x i16] vector. |
Definition at line 2178 of file emmintrin.h.
Referenced by _mm_mask_adds_epi16(), and _mm_maskz_adds_epi16().
|
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.
__a | A 128-bit signed [16 x i8] vector. |
__b | A 128-bit signed [16 x i8] vector. |
Definition at line 2156 of file emmintrin.h.
Referenced by _mm_mask_adds_epi8(), and _mm_maskz_adds_epi8().
|
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.
__a | A 128-bit unsigned [8 x i16] vector. |
__b | A 128-bit unsigned [8 x i16] vector. |
Definition at line 2222 of file emmintrin.h.
Referenced by _mm_mask_adds_epu16(), and _mm_maskz_adds_epu16().
|
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.
__a | A 128-bit unsigned [16 x i8] vector. |
__b | A 128-bit unsigned [16 x i8] vector. |
Definition at line 2200 of file emmintrin.h.
Referenced by _mm_mask_adds_epu8(), and _mm_maskz_adds_epu8().
|
static |
Performs a bitwise AND of two 128-bit vectors of [2 x double].
This intrinsic corresponds to the VPAND / PAND
instruction.
__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. |
Definition at line 364 of file emmintrin.h.
Referenced by _mm_mask_and_pd(), and _mm_maskz_and_pd().
|
static |
Performs a bitwise AND of two 128-bit integer vectors.
This intrinsic corresponds to the VPAND / PAND
instruction.
__a | A 128-bit integer vector containing one of the source operands. |
__b | A 128-bit integer vector containing one of the source operands. |
Definition at line 2663 of file emmintrin.h.
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().
|
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.
__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. |
Definition at line 384 of file emmintrin.h.
Referenced by _mm_mask_andnot_pd(), and _mm_maskz_andnot_pd().
|
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.
__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. |
Definition at line 2682 of file emmintrin.h.
|
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.
__a | A 128-bit unsigned [8 x i16] vector. |
__b | A 128-bit unsigned [8 x i16] vector. |
Definition at line 2260 of file emmintrin.h.
Referenced by _mm_mask_avg_epu16(), and _mm_maskz_avg_epu16().
|
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.
__a | A 128-bit unsigned [16 x i8] vector. |
__b | A 128-bit unsigned [16 x i8] vector. |
Definition at line 2241 of file emmintrin.h.
Referenced by _mm_mask_avg_epu8(), and _mm_maskz_avg_epu8().
|
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.
__a | A 128-bit floating-point vector of [2 x double]. |
Definition at line 4726 of file emmintrin.h.
References __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.
__a | A 128-bit floating-point vector of [2 x double]. |
Definition at line 4741 of file emmintrin.h.
References __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.
__a | A 128-bit floating-point vector of [4 x float]. |
Definition at line 4756 of file emmintrin.h.
References __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.
__a | A 128-bit floating-point vector of [4 x float]. |
Definition at line 4771 of file emmintrin.h.
References __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.
__a | A 128-bit integer vector. |
Definition at line 4801 of file emmintrin.h.
References __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.
__a | A 128-bit integer vector. |
Definition at line 4786 of file emmintrin.h.
References __a.
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.
__p | A pointer to the memory location used to identify the cache line to be flushed. |
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3095 of file emmintrin.h.
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3114 of file emmintrin.h.
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3076 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 438 of file emmintrin.h.
|
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.
__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. |
Definition at line 695 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 522 of file emmintrin.h.
|
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.
__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. |
Definition at line 796 of file emmintrin.h.
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3156 of file emmintrin.h.
Referenced by _mm_cmplt_epi16().
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3176 of file emmintrin.h.
Referenced by _mm_cmplt_epi32().
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3134 of file emmintrin.h.
Referenced by _mm_cmplt_epi8().
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 501 of file emmintrin.h.
|
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.
__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. |
Definition at line 770 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 480 of file emmintrin.h.
|
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.
__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. |
Definition at line 745 of file emmintrin.h.
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3216 of file emmintrin.h.
References __a, __b, and _mm_cmpgt_epi16().
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3236 of file emmintrin.h.
References __a, __b, and _mm_cmpgt_epi32().
|
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.
__a | A 128-bit integer vector. |
__b | A 128-bit integer vector. |
Definition at line 3196 of file emmintrin.h.
References __a, __b, and _mm_cmpgt_epi8().
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 459 of file emmintrin.h.
|
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.
__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. |
Definition at line 720 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 588 of file emmintrin.h.
|
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.
__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. |
Definition at line 875 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 672 of file emmintrin.h.
|
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.
__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. |
Definition at line 976 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 651 of file emmintrin.h.
|
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.
__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. |
Definition at line 950 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 630 of file emmintrin.h.
|
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.
__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. |
Definition at line 925 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 609 of file emmintrin.h.
|
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.
__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. |
Definition at line 900 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 544 of file emmintrin.h.
|
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.
__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. |
Definition at line 823 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
__b | A 128-bit vector of [2 x double]. |
Definition at line 567 of file emmintrin.h.
|
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.
__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. |
Definition at line 850 of file emmintrin.h.
|
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.
__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. |
Definition at line 999 of file emmintrin.h.
|
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.
__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. |
Definition at line 1095 of file emmintrin.h.
|
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.
__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. |
Definition at line 1071 of file emmintrin.h.
|
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.
__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. |
Definition at line 1047 of file emmintrin.h.
|
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.
__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. |
Definition at line 1023 of file emmintrin.h.
|
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.
__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. |
Definition at line 1119 of file emmintrin.h.
|
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.
__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.
Definition at line 1318 of file emmintrin.h.
References __a.
Referenced by _mm_mask_cvtepi32_pd(), and _mm_maskz_cvtepi32_pd().
|
static |
Converts a vector of [4 x i32] into a vector of [4 x float].
This intrinsic corresponds to the VCVTDQ2PS / CVTDQ2PS
instruction.
__a | A 128-bit integer vector. |
Definition at line 3314 of file emmintrin.h.
References __a.
Referenced by _mm_mask_cvtepi32_ps(), and _mm_maskz_cvtepi32_ps().
|
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.
__a | A 128-bit vector of [2 x double]. |
Definition at line 1340 of file emmintrin.h.
References __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.
__a | A 128-bit vector of [2 x double]. |
Definition at line 1492 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
Definition at line 1279 of file emmintrin.h.
References __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.
__a | A 64-bit vector of [2 x i32]. |
Definition at line 1526 of file emmintrin.h.
References __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.
__a | A 128-bit vector of [4 x float]. |
Definition at line 3332 of file emmintrin.h.
References __a.
Referenced by _mm_mask_cvtps_epi32(), and _mm_maskz_cvtps_epi32().
|
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.
__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. |
Definition at line 1297 of file emmintrin.h.
References __a.
Referenced by _mm_mask_cvtps_pd(), and _mm_maskz_cvtps_pd().
|
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.
__a | A 128-bit vector of [2 x double]. The lower 64 bits are returned. |
Definition at line 1541 of file emmintrin.h.
References __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.
__a | A 128-bit vector of [2 x double]. The lower 64 bits are used in the conversion. |
Definition at line 1359 of file emmintrin.h.
References __a.
|
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.
__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. |
Definition at line 1382 of file emmintrin.h.
|
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.
__a | A vector of [4 x i32]. The least significant 32 bits are moved to the destination. |
Definition at line 3395 of file emmintrin.h.
|
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.
__a | A vector of [2 x i64]. The least significant 64 bits are moved to the destination. |
Definition at line 3411 of file emmintrin.h.
References __a.
|
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.
__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. |
Definition at line 1404 of file emmintrin.h.
|
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.
__a | A 32-bit signed integer operand. |
Definition at line 3365 of file emmintrin.h.
References __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.
__a | A 64-bit signed integer operand containing the value to be converted. |
Definition at line 3380 of file emmintrin.h.
References __a.
|
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.
__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. |
Definition at line 1429 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [2 x double]. |
Definition at line 1453 of file emmintrin.h.
References __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.
__a | A 128-bit vector of [2 x double]. |
Definition at line 1511 of file emmintrin.h.
|
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.
__a | A 128-bit vector of [4 x float]. |
Definition at line 3351 of file emmintrin.h.
References __a.
Referenced by _mm_mask_cvttps_epi32(), and _mm_maskz_cvttps_epi32().
|
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.
__a | A 128-bit vector of [2 x double]. The lower 64 bits are used in the conversion. |
Definition at line 1473 of file emmintrin.h.
References __a.
|
static |
Performs an element-by-element division of two 128-bit vectors of [2 x double].
This intrinsic corresponds to the VDIVPD / DIVPD
instruction.
__a | A 128-bit vector of [2 x double] containing the dividend. |
__b | A 128-bit vector of [2 x double] containing the divisor. |
Definition at line 215 of file emmintrin.h.
Referenced by _mm_mask_div_pd(), and _mm_maskz_div_pd().
|
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.
__a | A 128-bit vector of [2 x double] containing the dividend. |
__b | A 128-bit vector of [2 x double] containing divisor. |
Definition at line 196 of file emmintrin.h.
Referenced by _mm_mask_div_sd(), and _mm_maskz_div_sd().
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.
|
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.
__dp | A pointer to a memory location containing a double-precision value. |
Definition at line 1572 of file emmintrin.h.
|
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.
__dp | A pointer to a 128-bit memory location. The address of the memory location has to be 16-byte aligned. |
Definition at line 1556 of file emmintrin.h.
|
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.
__dp | A pointer to a memory location containing a double-precision value. The address of the memory location does not have to be aligned. |
Definition at line 1687 of file emmintrin.h.
|
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.
__p | An aligned pointer to a memory location containing integer values. |
Definition at line 3426 of file emmintrin.h.
References __p.
Referenced by fastParseASCIIIdentifier().
|
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.
__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. |
Definition at line 1712 of file emmintrin.h.
References __a.
|
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.
__p | A 128-bit vector of [2 x i64]. Bits [63:0] are written to bits [63:0] of the destination. |
Definition at line 3461 of file emmintrin.h.
References __p.
|
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.
__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. |
Definition at line 1738 of file emmintrin.h.
References __a.
|
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.
__dp | A 16-byte aligned pointer to an array of double-precision values to be loaded in reverse order. |
Definition at line 1596 of file emmintrin.h.
|
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.
__dp | A pointer to a 128-bit memory location. The address of the memory location does not have to be aligned. |
Definition at line 1612 of file emmintrin.h.
References __v.
Referenced by _mm256_broadcast_pd(), and _mm256_loadu2_m128d().
|
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.
__p | A pointer to a memory location containing integer values. |
Definition at line 3441 of file emmintrin.h.
Referenced by _mm256_loadu2_m128i(), and fastParseASCIIIdentifier().
|
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.
__a | A pointer to a 16-bit memory location. The address of the memory location does not have to be aligned. |
Definition at line 1668 of file emmintrin.h.
|
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.
__a | A pointer to a 32-bit memory location. The address of the memory location does not have to be aligned. |
Definition at line 1649 of file emmintrin.h.
|
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.
__a | A pointer to a 64-bit memory location. The address of the memory location does not have to be aligned. |
Definition at line 1630 of file emmintrin.h.
|
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.
__a | A 128-bit signed [8 x i16] vector. |
__b | A 128-bit signed [8 x i16] vector. |
Definition at line 2285 of file emmintrin.h.
Referenced by _mm_mask_madd_epi16(), and _mm_maskz_madd_epi16().
|
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.
__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 3979 of file emmintrin.h.
References __p.
|
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.
__a | A 128-bit signed [8 x i16] vector. |
__b | A 128-bit signed [8 x i16] vector. |
Definition at line 2304 of file emmintrin.h.
Referenced by _mm_mask_max_epi16(), and _mm_maskz_max_epi16().
|
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.
__a | A 128-bit unsigned [16 x i8] vector. |
__b | A 128-bit unsigned [16 x i8] vector. |
Definition at line 2323 of file emmintrin.h.
Referenced by _mm_mask_max_epu8(), and _mm_maskz_max_epu8().
|
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.
__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. |
Definition at line 347 of file emmintrin.h.
Referenced by _mm_mask_max_pd(), and _mm_maskz_max_pd().
|
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.
__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. |
Definition at line 326 of file emmintrin.h.
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.
|
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.
__a | A 128-bit signed [8 x i16] vector. |
__b | A 128-bit signed [8 x i16] vector. |
Definition at line 2342 of file emmintrin.h.
Referenced by _mm_mask_min_epi16(), and _mm_maskz_min_epi16().
|
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.
__a | A 128-bit unsigned [16 x i8] vector. |
__b | A 128-bit unsigned [16 x i8] vector. |
Definition at line 2361 of file emmintrin.h.
Referenced by _mm_mask_min_epu8(), and _mm_maskz_min_epu8().
|
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.
__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. |
Definition at line 301 of file emmintrin.h.
Referenced by _mm_mask_min_pd(), and _mm_maskz_min_pd().
|
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.
__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. |
Definition at line 280 of file emmintrin.h.
|
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.
__a | A 128-bit integer vector operand. The lower 64 bits are moved to the destination. |
Definition at line 4623 of file emmintrin.h.
References __a, and _mm_setzero_si128().
|
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.
__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. |
Definition at line 1879 of file emmintrin.h.
Referenced by _mm_mask_move_sd(), and _mm_maskz_move_sd().
|
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.
__a | A 128-bit integer vector containing the values with bits to be extracted. |
Definition at line 4264 of file emmintrin.h.
References __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.
__a | A 128-bit vector of [2 x double] containing the values with sign bits to be extracted. |
Definition at line 4680 of file emmintrin.h.
References __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.
__a | A 128-bit integer vector operand. The lower 64 bits are moved to the destination. |
Definition at line 4592 of file emmintrin.h.
References __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.
__a | A 64-bit value. |
Definition at line 4607 of file emmintrin.h.
References __a.
|
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.
__a | A [2 x i64] vector containing one of the source operands. |
__b | A [2 x i64] vector containing one of the source operands. |
Definition at line 2454 of file emmintrin.h.
Referenced by _mm_mask_mul_epu32(), and _mm_maskz_mul_epu32().
|
static |
Multiplies two 128-bit vectors of [2 x double].
This intrinsic corresponds to the VMULPD / MULPD
instruction.
__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. |
Definition at line 174 of file emmintrin.h.
Referenced by _mm_mask_mul_pd(), and _mm_maskz_mul_pd().
|
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.
__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. |
Definition at line 156 of file emmintrin.h.
Referenced by _mm_mask_mul_sd(), and _mm_maskz_mul_sd().
|
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.
__a | A 64-bit integer containing one of the source operands. |
__b | A 64-bit integer containing one of the source operands. |
Definition at line 2436 of file emmintrin.h.
References __a, __anyext128, __b, and __trunc64.
|
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.
__a | A 128-bit signed [8 x i16] vector. |
__b | A 128-bit signed [8 x i16] vector. |
Definition at line 2380 of file emmintrin.h.
Referenced by _mm_mask_mulhi_epi16(), and _mm_maskz_mulhi_epi16().
|
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.
__a | A 128-bit unsigned [8 x i16] vector. |
__b | A 128-bit unsigned [8 x i16] vector. |
Definition at line 2399 of file emmintrin.h.
Referenced by _mm_mask_mulhi_epu16(), and _mm_maskz_mulhi_epu16().
|
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.
__a | A 128-bit signed [8 x i16] vector. |
__b | A 128-bit signed [8 x i16] vector. |
Definition at line 2418 of file emmintrin.h.
Referenced by _mm_mask_mullo_epi16(), and _mm_maskz_mullo_epi16().
|
static |
Performs a bitwise OR of two 128-bit vectors of [2 x double].
This intrinsic corresponds to the VPOR / POR
instruction.
__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. |
Definition at line 401 of file emmintrin.h.
Referenced by _mm_mask_or_pd(), and _mm_maskz_or_pd().
|
static |
Performs a bitwise OR of two 128-bit integer vectors.
This intrinsic corresponds to the VPOR / POR
instruction.
__a | A 128-bit integer vector containing one of the source operands. |
__b | A 128-bit integer vector containing one of the source operands. |
Definition at line 2698 of file emmintrin.h.
|
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.
__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. |
Definition at line 4143 of file emmintrin.h.
Referenced by _mm_mask_packs_epi16(), and _mm_maskz_packs_epi16().
|
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.
__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. |
Definition at line 4166 of file emmintrin.h.
Referenced by _mm_mask_packs_epi32(), and _mm_maskz_packs_epi32().
|
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.
__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. |
Definition at line 4189 of file emmintrin.h.
Referenced by _mm_mask_packus_epi16(), and _mm_maskz_packus_epi16().
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.
|
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.
__a | A 128-bit integer vector containing one of the source operands. |
__b | A 128-bit integer vector containing one of the source operands. |
Definition at line 2475 of file emmintrin.h.
|
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.
__w | A 16-bit value used to initialize the elements of the destination integer vector. |
Definition at line 3707 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().
|
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.
__i | A 32-bit value used to initialize the elements of the destination integer vector. |
Definition at line 3690 of file emmintrin.h.
References _mm_set_epi32().
Referenced by _mm_broadcastmw_epi32(), _mm_mask_set1_epi32(), and _mm_maskz_set1_epi32().
|
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.
__q | A 64-bit value used to initialize the elements of the destination integer vector. |
Definition at line 3673 of file emmintrin.h.
References _mm_set_epi64().
|
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.
__q | Integer value used to initialize the elements of the destination integer vector. |
Definition at line 3656 of file emmintrin.h.
References _mm_set_epi64x().
Referenced by _mm_broadcastmb_epi64(), _mm_mask_set1_epi64(), and _mm_maskz_set1_epi64().
|
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.
__b | An 8-bit value used to initialize the elements of the destination integer vector. |
Definition at line 3724 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().
|
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.
__w | A double-precision floating-point value used to initialize each vector element of the result. |
Definition at line 1792 of file emmintrin.h.
Referenced by _mm_set_pd1().
|
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.
__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. |
Definition at line 3586 of file emmintrin.h.
Referenced by _mm_set1_epi16(), and _mm_setr_epi16().
|
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.
__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. |
Definition at line 3546 of file emmintrin.h.
Referenced by _mm_set1_epi32(), and _mm_setr_epi32().
|
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.
__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]. |
Definition at line 3519 of file emmintrin.h.
References _mm_set_epi64x().
Referenced by _mm_set1_epi64(), and _mm_setr_epi64().
|
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.
__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]. |
Definition at line 3498 of file emmintrin.h.
Referenced by _mm_set1_epi64x(), and _mm_set_epi64().
|
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.
__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. |
Definition at line 3635 of file emmintrin.h.
Referenced by _mm_set1_epi8(), and _mm_setr_epi8().
|
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.
__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. |
Definition at line 1826 of file emmintrin.h.
|
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.
__w | A double-precision floating-point value used to initialize each vector element of the result. |
Definition at line 1808 of file emmintrin.h.
References _mm_set1_pd().
|
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.
__w | A double-precision floating-point value used to initialize the lower 64 bits of the result. |
Definition at line 1776 of file emmintrin.h.
|
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.
__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. |
Definition at line 3797 of file emmintrin.h.
References _mm_set_epi16().
|
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.
__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. |
Definition at line 3765 of file emmintrin.h.
References _mm_set_epi32().
|
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.
__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. |
Definition at line 3743 of file emmintrin.h.
References _mm_set_epi64().
|
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.
__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. |
Definition at line 3844 of file emmintrin.h.
References _mm_set_epi8().
|
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.
__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. |
Definition at line 1846 of file emmintrin.h.
|
static |
Constructs a 128-bit floating-point vector of [2 x double] initialized to zero.
This intrinsic corresponds to the VXORPS / XORPS
instruction.
Definition at line 1860 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().
|
static |
Creates a 128-bit integer vector initialized to zero.
This intrinsic corresponds to the VXORPS / XORPS
instruction.
Definition at line 3859 of file emmintrin.h.
Referenced by _mm256_cvtpd_epu32(), _mm256_cvtsepi16_epi8(), _mm256_cvttpd_epu32(), _mm256_cvtusepi16_epi8(), _mm256_maskz_cvtepi16_epi8(), _mm256_maskz_cvtepi32_epi16(), _mm256_maskz_cvtepi32_epi8(), _mm256_maskz_cvtepi64_epi16(), _mm256_maskz_cvtepi64_epi32(), _mm256_maskz_cvtepi64_epi8(), _mm256_maskz_cvtpd_epi32(), _mm256_maskz_cvtpd_epu32(), _mm256_maskz_cvtsepi16_epi8(), _mm256_maskz_cvtsepi32_epi16(), _mm256_maskz_cvtsepi32_epi8(), _mm256_maskz_cvtsepi64_epi16(), _mm256_maskz_cvtsepi64_epi32(), _mm256_maskz_cvtsepi64_epi8(), _mm256_maskz_cvttpd_epi32(), _mm256_maskz_cvttpd_epu32(), _mm256_maskz_cvtusepi16_epi8(), _mm256_maskz_cvtusepi32_epi16(), _mm256_maskz_cvtusepi32_epi8(), _mm256_maskz_cvtusepi64_epi16(), _mm256_maskz_cvtusepi64_epi32(), _mm256_maskz_cvtusepi64_epi8(), _mm256_zextsi128_si256(), _mm512_maskz_cvtepi32_epi8(), _mm512_maskz_cvtepi64_epi16(), _mm512_maskz_cvtepi64_epi8(), _mm512_maskz_cvtsepi32_epi8(), _mm512_maskz_cvtsepi64_epi16(), _mm512_maskz_cvtsepi64_epi8(), _mm512_maskz_cvtusepi32_epi8(), _mm512_maskz_cvtusepi64_epi16(), _mm512_maskz_cvtusepi64_epi8(), _mm512_zextsi128_si512(), _mm_cvtpd_epi64(), _mm_cvtpd_epu32(), _mm_cvtpd_epu64(), _mm_cvtps_epi64(), _mm_cvtps_epu32(), _mm_cvtps_epu64(), _mm_cvtsepi16_epi8(), _mm_cvtsepi32_epi16(), _mm_cvttpd_epi64(), _mm_cvttpd_epu32(), _mm_cvttpd_epu64(), _mm_cvttps_epi64(), _mm_cvttps_epu32(), _mm_cvttps_epu64(), _mm_cvtusepi16_epi8(), _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_maskz_abs_epi16(), _mm_maskz_abs_epi32(), _mm_maskz_abs_epi64(), _mm_maskz_abs_epi8(), _mm_maskz_add_epi16(), _mm_maskz_add_epi32(), _mm_maskz_add_epi64(), _mm_maskz_add_epi8(), _mm_maskz_adds_epi16(), _mm_maskz_adds_epi8(), _mm_maskz_adds_epu16(), _mm_maskz_adds_epu8(), _mm_maskz_and_epi32(), _mm_maskz_and_epi64(), _mm_maskz_andnot_epi32(), _mm_maskz_andnot_epi64(), _mm_maskz_avg_epu16(), _mm_maskz_avg_epu8(), _mm_maskz_broadcast_i32x2(), _mm_maskz_broadcastb_epi8(), _mm_maskz_broadcastd_epi32(), _mm_maskz_broadcastq_epi64(), _mm_maskz_broadcastw_epi16(), _mm_maskz_compress_epi16(), _mm_maskz_compress_epi32(), _mm_maskz_compress_epi64(), _mm_maskz_compress_epi8(), _mm_maskz_conflict_epi32(), _mm_maskz_conflict_epi64(), _mm_maskz_cvtepi16_epi32(), _mm_maskz_cvtepi16_epi64(), _mm_maskz_cvtepi16_epi8(), _mm_maskz_cvtepi32_epi16(), _mm_maskz_cvtepi32_epi64(), _mm_maskz_cvtepi32_epi8(), _mm_maskz_cvtepi64_epi16(), _mm_maskz_cvtepi64_epi32(), _mm_maskz_cvtepi64_epi8(), _mm_maskz_cvtepi8_epi16(), _mm_maskz_cvtepi8_epi32(), _mm_maskz_cvtepi8_epi64(), _mm_maskz_cvtepu16_epi32(), _mm_maskz_cvtepu16_epi64(), _mm_maskz_cvtepu32_epi64(), _mm_maskz_cvtepu8_epi16(), _mm_maskz_cvtepu8_epi32(), _mm_maskz_cvtepu8_epi64(), _mm_maskz_cvtpd_epi32(), _mm_maskz_cvtpd_epi64(), _mm_maskz_cvtpd_epu32(), _mm_maskz_cvtpd_epu64(), _mm_maskz_cvtps_epi32(), _mm_maskz_cvtps_epi64(), _mm_maskz_cvtps_epu32(), _mm_maskz_cvtps_epu64(), _mm_maskz_cvtsepi16_epi8(), _mm_maskz_cvtsepi32_epi16(), _mm_maskz_cvtsepi32_epi8(), _mm_maskz_cvtsepi64_epi16(), _mm_maskz_cvtsepi64_epi32(), _mm_maskz_cvtsepi64_epi8(), _mm_maskz_cvttpd_epi32(), _mm_maskz_cvttpd_epi64(), _mm_maskz_cvttpd_epu32(), _mm_maskz_cvttpd_epu64(), _mm_maskz_cvttps_epi32(), _mm_maskz_cvttps_epi64(), _mm_maskz_cvttps_epu32(), _mm_maskz_cvttps_epu64(), _mm_maskz_cvtusepi16_epi8(), _mm_maskz_cvtusepi32_epi16(), _mm_maskz_cvtusepi32_epi8(), _mm_maskz_cvtusepi64_epi16(), _mm_maskz_cvtusepi64_epi32(), _mm_maskz_cvtusepi64_epi8(), _mm_maskz_dpbusd_epi32(), _mm_maskz_dpbusds_epi32(), _mm_maskz_dpwssd_epi32(), _mm_maskz_dpwssds_epi32(), _mm_maskz_expand_epi16(), _mm_maskz_expand_epi32(), _mm_maskz_expand_epi64(), _mm_maskz_expand_epi8(), _mm_maskz_expandloadu_epi16(), _mm_maskz_expandloadu_epi32(), _mm_maskz_expandloadu_epi64(), _mm_maskz_expandloadu_epi8(), _mm_maskz_load_epi32(), _mm_maskz_load_epi64(), _mm_maskz_loadu_epi16(), _mm_maskz_loadu_epi32(), _mm_maskz_loadu_epi64(), _mm_maskz_loadu_epi8(), _mm_maskz_lzcnt_epi32(), _mm_maskz_lzcnt_epi64(), _mm_maskz_madd52hi_epu64(), _mm_maskz_madd52lo_epu64(), _mm_maskz_madd_epi16(), _mm_maskz_maddubs_epi16(), _mm_maskz_max_epi16(), _mm_maskz_max_epi32(), _mm_maskz_max_epi64(), _mm_maskz_max_epi8(), _mm_maskz_max_epu16(), _mm_maskz_max_epu32(), _mm_maskz_max_epu64(), _mm_maskz_max_epu8(), _mm_maskz_min_epi16(), _mm_maskz_min_epi32(), _mm_maskz_min_epi64(), _mm_maskz_min_epi8(), _mm_maskz_min_epu16(), _mm_maskz_min_epu32(), _mm_maskz_min_epu64(), _mm_maskz_min_epu8(), _mm_maskz_mov_epi16(), _mm_maskz_mov_epi32(), _mm_maskz_mov_epi64(), _mm_maskz_mov_epi8(), _mm_maskz_mul_epi32(), _mm_maskz_mul_epu32(), _mm_maskz_mulhi_epi16(), _mm_maskz_mulhi_epu16(), _mm_maskz_mulhrs_epi16(), _mm_maskz_mullo_epi16(), _mm_maskz_mullo_epi32(), _mm_maskz_mullo_epi64(), _mm_maskz_multishift_epi64_epi8(), _mm_maskz_or_epi32(), _mm_maskz_or_epi64(), _mm_maskz_packs_epi16(), _mm_maskz_packs_epi32(), _mm_maskz_packus_epi16(), _mm_maskz_packus_epi32(), _mm_maskz_permutex2var_epi16(), _mm_maskz_permutex2var_epi32(), _mm_maskz_permutex2var_epi64(), _mm_maskz_permutex2var_epi8(), _mm_maskz_permutexvar_epi16(), _mm_maskz_permutexvar_epi8(), _mm_maskz_popcnt_epi16(), _mm_maskz_popcnt_epi32(), _mm_maskz_popcnt_epi64(), _mm_maskz_popcnt_epi8(), _mm_maskz_rolv_epi32(), _mm_maskz_rolv_epi64(), _mm_maskz_rorv_epi32(), _mm_maskz_rorv_epi64(), _mm_maskz_set1_epi16(), _mm_maskz_set1_epi32(), _mm_maskz_set1_epi64(), _mm_maskz_set1_epi8(), _mm_maskz_shldv_epi16(), _mm_maskz_shldv_epi32(), _mm_maskz_shldv_epi64(), _mm_maskz_shrdv_epi16(), _mm_maskz_shrdv_epi32(), _mm_maskz_shrdv_epi64(), _mm_maskz_shuffle_epi8(), _mm_maskz_sll_epi16(), _mm_maskz_sll_epi32(), _mm_maskz_sll_epi64(), _mm_maskz_slli_epi16(), _mm_maskz_slli_epi32(), _mm_maskz_slli_epi64(), _mm_maskz_sllv_epi16(), _mm_maskz_sllv_epi32(), _mm_maskz_sllv_epi64(), _mm_maskz_sra_epi16(), _mm_maskz_sra_epi32(), _mm_maskz_sra_epi64(), _mm_maskz_srai_epi16(), _mm_maskz_srai_epi32(), _mm_maskz_srai_epi64(), _mm_maskz_srav_epi16(), _mm_maskz_srav_epi32(), _mm_maskz_srav_epi64(), _mm_maskz_srl_epi16(), _mm_maskz_srl_epi32(), _mm_maskz_srl_epi64(), _mm_maskz_srli_epi16(), _mm_maskz_srli_epi32(), _mm_maskz_srli_epi64(), _mm_maskz_srlv_epi16(), _mm_maskz_srlv_epi32(), _mm_maskz_srlv_epi64(), _mm_maskz_sub_epi16(), _mm_maskz_sub_epi32(), _mm_maskz_sub_epi64(), _mm_maskz_sub_epi8(), _mm_maskz_subs_epi16(), _mm_maskz_subs_epi8(), _mm_maskz_subs_epu16(), _mm_maskz_subs_epu8(), _mm_maskz_unpackhi_epi16(), _mm_maskz_unpackhi_epi32(), _mm_maskz_unpackhi_epi64(), _mm_maskz_unpackhi_epi8(), _mm_maskz_unpacklo_epi16(), _mm_maskz_unpacklo_epi32(), _mm_maskz_unpacklo_epi64(), _mm_maskz_unpacklo_epi8(), _mm_maskz_xor_epi32(), _mm_maskz_xor_epi64(), _mm_move_epi64(), _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().
|
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.
__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. |
Definition at line 2776 of file emmintrin.h.
References __a.
Referenced by _mm_mask_sll_epi16(), and _mm_maskz_sll_epi16().
|
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.
__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. |
Definition at line 2812 of file emmintrin.h.
References __a.
Referenced by _mm_mask_sll_epi32(), and _mm_maskz_sll_epi32().
|
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.
__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. |
Definition at line 2848 of file emmintrin.h.
References __a.
Referenced by _mm_mask_sll_epi64(), and _mm_maskz_sll_epi64().
|
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.
__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. |
Definition at line 2758 of file emmintrin.h.
References __a.
Referenced by _mm_mask_slli_epi16(), and _mm_maskz_slli_epi16().
|
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.
__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. |
Definition at line 2794 of file emmintrin.h.
References __a.
Referenced by _mm_mask_slli_epi32(), and _mm_maskz_slli_epi32().
|
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.
__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. |
Definition at line 2830 of file emmintrin.h.
References __a.
Referenced by _mm_mask_slli_epi64(), and _mm_maskz_slli_epi64().
|
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.
__a | A 128-bit vector of [2 x double]. |
Definition at line 256 of file emmintrin.h.
References __a.
Referenced by _mm_mask_sqrt_pd(), and _mm_maskz_sqrt_pd().
|
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.
__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. |
Definition at line 239 of file emmintrin.h.
|
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.
__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. |
Definition at line 2886 of file emmintrin.h.
References __a.
Referenced by _mm_mask_sra_epi16(), and _mm_maskz_sra_epi16().
|
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.
__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. |
Definition at line 2924 of file emmintrin.h.
References __a.
Referenced by _mm_mask_sra_epi32(), and _mm_maskz_sra_epi32().
|
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.
__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. |
Definition at line 2867 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srai_epi16(), and _mm_maskz_srai_epi16().
|
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.
__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. |
Definition at line 2905 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srai_epi32(), and _mm_maskz_srai_epi32().
|
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.
__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. |
Definition at line 2985 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srl_epi16(), and _mm_maskz_srl_epi16().
|
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.
__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. |
Definition at line 3021 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srl_epi32(), and _mm_maskz_srl_epi32().
|
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.
__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. |
Definition at line 3057 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srl_epi64(), and _mm_maskz_srl_epi64().
|
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.
__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. |
Definition at line 2967 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srli_epi16(), and _mm_maskz_srli_epi16().
|
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.
__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. |
Definition at line 3003 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srli_epi32(), and _mm_maskz_srli_epi32().
|
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.
__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. |
Definition at line 3039 of file emmintrin.h.
References __a.
Referenced by _mm_mask_srli_epi64(), and _mm_maskz_srli_epi64().
|
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.
__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 1936 of file emmintrin.h.
References __a, and _mm_store_pd().
Referenced by _mm_store_pd1().
|
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.
__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 1917 of file emmintrin.h.
References __a.
Referenced by _mm_store1_pd().
|
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.
__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 1956 of file emmintrin.h.
References __a, and _mm_store1_pd().
|
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.
__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 1896 of file emmintrin.h.
References __a.
|
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.
__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 3875 of file emmintrin.h.
|
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.
__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 2012 of file emmintrin.h.
References __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.
__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 3998 of file emmintrin.h.
|
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.
__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 2031 of file emmintrin.h.
References __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.
__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 1995 of file emmintrin.h.
References __a.
|
static |
Stores a 128-bit vector of [2 x double] into an unaligned memory location.
This intrinsic corresponds to the VMOVUPD / MOVUPD
instruction.
__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 1973 of file emmintrin.h.
Referenced by _mm256_storeu2_m128d().
|
static |
Stores a 128-bit integer vector to an unaligned memory location.
This intrinsic corresponds to the VMOVUPS / MOVUPS
instruction.
__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 3890 of file emmintrin.h.
Referenced by _mm256_storeu2_m128i().
|
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.
__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 3950 of file emmintrin.h.
|
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.
__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 3930 of file emmintrin.h.
|
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.
__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 3910 of file emmintrin.h.
|
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.
__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 4020 of file emmintrin.h.
|
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.
__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 4038 of file emmintrin.h.
|
static |
Subtracts the corresponding 16-bit integer values in the operands.
This intrinsic corresponds to the VPSUBW / PSUBW
instruction.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2509 of file emmintrin.h.
Referenced by _mm_mask_sub_epi16(), and _mm_maskz_sub_epi16().
|
static |
Subtracts the corresponding 32-bit integer values in the operands.
This intrinsic corresponds to the VPSUBD / PSUBD
instruction.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2526 of file emmintrin.h.
Referenced by _mm_mask_sub_epi32(), and _mm_maskz_sub_epi32().
|
static |
Subtracts the corresponding elements of two [2 x i64] vectors.
This intrinsic corresponds to the VPSUBQ / PSUBQ
instruction.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2560 of file emmintrin.h.
Referenced by _mm_mask_sub_epi64(), and _mm_maskz_sub_epi64().
|
static |
Subtracts the corresponding 8-bit integer values in the operands.
This intrinsic corresponds to the VPSUBB / PSUBB
instruction.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2492 of file emmintrin.h.
Referenced by _mm_mask_sub_epi8(), and _mm_maskz_sub_epi8().
|
static |
Subtracts two 128-bit vectors of [2 x double].
This intrinsic corresponds to the VSUBPD / SUBPD
instruction.
__a | A 128-bit vector of [2 x double] containing the minuend. |
__b | A 128-bit vector of [2 x double] containing the subtrahend. |
Definition at line 135 of file emmintrin.h.
Referenced by _mm_mask_sub_pd(), and _mm_maskz_sub_pd().
|
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.
__a | A 128-bit vector of [2 x double] containing the minuend. |
__b | A 128-bit vector of [2 x double] containing the subtrahend. |
Definition at line 117 of file emmintrin.h.
Referenced by _mm_mask_sub_sd(), and _mm_maskz_sub_sd().
|
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.
__a | A 64-bit integer vector containing the minuend. |
__b | A 64-bit integer vector containing the subtrahend. |
Definition at line 2544 of file emmintrin.h.
|
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.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2604 of file emmintrin.h.
Referenced by _mm_mask_subs_epi16(), and _mm_maskz_subs_epi16().
|
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.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2582 of file emmintrin.h.
Referenced by _mm_mask_subs_epi8(), and _mm_maskz_subs_epi8().
|
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.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2646 of file emmintrin.h.
Referenced by _mm_mask_subs_epu16(), and _mm_maskz_subs_epu16().
|
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.
__a | A 128-bit integer vector containing the minuends. |
__b | A 128-bit integer vector containing the subtrahends. |
Definition at line 2625 of file emmintrin.h.
Referenced by _mm_mask_subs_epu8(), and _mm_maskz_subs_epu8().
|
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.
__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. |
Definition at line 1141 of file emmintrin.h.
|
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.
__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. |
Definition at line 1237 of file emmintrin.h.
|
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.
__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. |
Definition at line 1213 of file emmintrin.h.
|
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.
__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. |
Definition at line 1189 of file emmintrin.h.
|
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.
__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. |
Definition at line 1165 of file emmintrin.h.
|
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.
__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. |
Definition at line 1261 of file emmintrin.h.
|
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.
Definition at line 1758 of file emmintrin.h.
|
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.
Definition at line 3478 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().
|
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.
__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. |
Definition at line 4425 of file emmintrin.h.
Referenced by _mm_mask_unpackhi_epi16(), and _mm_maskz_unpackhi_epi16().
|
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.
__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. |
Definition at line 4448 of file emmintrin.h.
Referenced by _mm_mask_unpackhi_epi32(), and _mm_maskz_unpackhi_epi32().
|
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.
__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. |
Definition at line 4469 of file emmintrin.h.
Referenced by _mm_mask_unpackhi_epi64(), and _mm_maskz_unpackhi_epi64().
|
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.
__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. |
Definition at line 4397 of file emmintrin.h.
Referenced by _mm_mask_unpackhi_epi8(), and _mm_maskz_unpackhi_epi8().
|
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.
__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. |
Definition at line 4642 of file emmintrin.h.
Referenced by _mm_mask_unpackhi_pd(), and _mm_maskz_unpackhi_pd().
|
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.
__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. |
Definition at line 4532 of file emmintrin.h.
Referenced by _mm_mask_unpacklo_epi16(), and _mm_maskz_unpacklo_epi16().
|
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.
__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. |
Definition at line 4555 of file emmintrin.h.
Referenced by _mm_mask_unpacklo_epi32(), and _mm_maskz_unpacklo_epi32().
|
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.
__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. |
Definition at line 4576 of file emmintrin.h.
Referenced by _mm_mask_unpacklo_epi64(), and _mm_maskz_unpacklo_epi64().
|
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.
__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. |
Definition at line 4503 of file emmintrin.h.
Referenced by _mm_mask_unpacklo_epi8(), and _mm_maskz_unpacklo_epi8().
|
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.
__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. |
Definition at line 4662 of file emmintrin.h.
Referenced by _mm_mask_unpacklo_pd(), and _mm_maskz_unpacklo_pd().
|
static |
Performs a bitwise XOR of two 128-bit vectors of [2 x double].
This intrinsic corresponds to the VPXOR / PXOR
instruction.
__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. |
Definition at line 418 of file emmintrin.h.
Referenced by _mm_mask_xor_pd(), and _mm_maskz_xor_pd().
|
static |
Performs a bitwise exclusive OR of two 128-bit integer vectors.
This intrinsic corresponds to the VPXOR / PXOR
instruction.
__a | A 128-bit integer vector containing one of the source operands. |
__b | A 128-bit integer vector containing one of the source operands. |
Definition at line 2715 of file emmintrin.h.
__inline__ void int __a |
Definition at line 4058 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().