|
clang
5.0.0
|
Go to the source code of this file.
Macros | |
| #define | __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("sse2"))) |
| #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. More... | |
| #define | _mm_bslli_si128(a, imm) _mm_slli_si128((a), (imm)) |
| #define | _mm_srli_si128(a, imm) |
| Right-shifts the 128-bit integer vector operand by the specified number of bytes. More... | |
| #define | _mm_bsrli_si128(a, imm) _mm_srli_si128((a), (imm)) |
| #define | _mm_shuffle_epi32(a, 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. More... | |
| #define | _mm_shufflelo_epi16(a, 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. More... | |
| #define | _mm_shufflehi_epi16(a, 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. More... | |
| #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. More... | |
| #define | _MM_SHUFFLE2(x, y) (((x) << 1) | (y)) |
| #define | _MM_DENORMALS_ZERO_ON (0x0040) |
| #define | _MM_DENORMALS_ZERO_OFF (0x0000) |
| #define | _MM_DENORMALS_ZERO_MASK (0x0040) |
| #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))) |
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. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_add_pd (__m128d __a, __m128d __b) |
| Adds two 128-bit vectors of [2 x double]. More... | |
| 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. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_sub_pd (__m128d __a, __m128d __b) |
| Subtracts two 128-bit vectors of [2 x double]. More... | |
| 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. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_mul_pd (__m128d __a, __m128d __b) |
| Multiplies two 128-bit vectors of [2 x double]. More... | |
| 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. More... | |
| 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]. More... | |
| 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. More... | |
| 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]. More... | |
| 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. More... | |
| 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 the vector containing the lesser of each pair of values. More... | |
| 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. More... | |
| 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 the vector containing the greater of each pair of values. More... | |
| 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]. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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 32-bit integer values, returned in the lower 64 bits of a 128-bit vector of [4 x i32]. More... | |
| 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 integer value, truncating the result when it is inexact. More... | |
| 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]. More... | |
| 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 32-bit integer values, returned in a 64-bit vector of [2 x i32]. More... | |
| 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]. More... | |
| 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. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_undefined_pd (void) |
| Constructs a 128-bit floating-point vector of [2 x double] with unspecified content. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_set_sd (double __w) |
| Constructs a 128-bit floating-point vector of [2 x double]. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_setzero_pd (void) |
| Constructs a 128-bit floating-point vector of [2 x double] initialized to zero. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_move_sd (__m128d __a, __m128d __b) |
| Constructs a 128-bit floating-point vector of [2 x double]. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| static __inline__ void __DEFAULT_FN_ATTRS | _mm_store_pd1 (double *__dp, __m128d __a) |
| Stores a 128-bit vector of [2 x double] into an aligned memory location. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_avg_epu8 (__m128i __a, __m128i __b) |
| Computes the rounded avarages 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]. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_avg_epu16 (__m128i __a, __m128i __b) |
| Computes the rounded avarages 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]. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_sub_epi8 (__m128i __a, __m128i __b) |
| Subtracts the corresponding 8-bit integer values in the operands. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_sub_epi16 (__m128i __a, __m128i __b) |
| Subtracts the corresponding 16-bit integer values in the operands. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_sub_epi32 (__m128i __a, __m128i __b) |
| Subtracts the corresponding 32-bit integer values in the operands. More... | |
| 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. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_sub_epi64 (__m128i __a, __m128i __b) |
| Subtracts the corresponding elements of two [2 x i64] vectors. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_subs_epi8 (__m128i __a, __m128i __b) |
| Subtracts corresponding 8-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_subs_epi16 (__m128i __a, __m128i __b) |
| Subtracts corresponding 16-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_subs_epu8 (__m128i __a, __m128i __b) |
| Subtracts corresponding 8-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_subs_epu16 (__m128i __a, __m128i __b) |
| Subtracts corresponding 16-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_and_si128 (__m128i __a, __m128i __b) |
| Performs a bitwise AND of two 128-bit integer vectors. More... | |
| 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. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_or_si128 (__m128i __a, __m128i __b) |
| Performs a bitwise OR of two 128-bit integer vectors. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_xor_si128 (__m128i __a, __m128i __b) |
| Performs a bitwise exclusive OR of two 128-bit integer vectors. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_cvttps_epi32 (__m128 __a) |
| Converts a vector of [4 x float] into a vector of [4 x i32], truncating the result when it is inexact. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_loadu_si128 (__m128i const *__p) |
| Moves packed integer values from an unaligned 128-bit memory location to elements in a 128-bit integer vector. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_loadl_epi64 (__m128i 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. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_undefined_si128 (void) |
| Generates a 128-bit vector of [4 x i32] with unspecified content. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_setzero_si128 (void) |
| Creates a 128-bit integer vector initialized to zero. More... | |
| 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. More... | |
| static __inline__ void __DEFAULT_FN_ATTRS | _mm_storeu_si128 (__m128i *__p, __m128i __b) |
| Stores a 128-bit integer vector to an unaligned memory location. More... | |
| 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. More... | |
| static __inline__ void __DEFAULT_FN_ATTRS | _mm_storel_epi64 (__m128i *__p, __m128i __a) |
| Stores the lower 64 bits of a 128-bit integer vector of [2 x i64] to a memory location. More... | |
| static __inline__ void __DEFAULT_FN_ATTRS | _mm_stream_pd (double *__p, __m128d __a) |
| Stores a 128-bit floating point vector of [2 x double] to a 128-bit aligned memory location. More... | |
| static __inline__ void __DEFAULT_FN_ATTRS | _mm_stream_si128 (__m128i *__p, __m128i __a) |
| Stores a 128-bit integer vector to a 128-bit aligned memory location. More... | |
| static __inline__ void __DEFAULT_FN_ATTRS | _mm_stream_si32 (int *__p, int __a) |
| Stores a 32-bit integer value in the specified memory location. More... | |
| void | _mm_clflush (void const *__p) |
| The cache line containing __p is flushed and invalidated from all caches in the coherency domain. More... | |
| 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. More... | |
| 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. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_packs_epi16 (__m128i __a, __m128i __b) |
| Converts 16-bit signed integers from both 128-bit integer vector operands into 8-bit signed integers, and packs the results into the destination. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_packs_epi32 (__m128i __a, __m128i __b) |
| Converts 32-bit signed integers from both 128-bit integer vector operands into 16-bit signed integers, and packs the results into the destination. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_packus_epi16 (__m128i __a, __m128i __b) |
| Converts 16-bit signed integers from both 128-bit integer vector operands into 8-bit unsigned integers, and packs the results into the destination. More... | |
| static __inline__ int __DEFAULT_FN_ATTRS | _mm_extract_epi16 (__m128i __a, int __imm) |
| Extracts 16 bits from a 128-bit integer vector of [8 x i16], using the immediate-value parameter as a selector. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_insert_epi16 (__m128i __a, int __b, int __imm) |
| Constructs a 128-bit integer vector by first making a copy of the 128-bit integer vector parameter, and then inserting the lower 16 bits of an integer parameter into an offset specified by the immediate-value parameter. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| static __inline__ __m128i __DEFAULT_FN_ATTRS | _mm_unpackhi_epi64 (__m128i __a, __m128i __b) |
| Unpacks the high-order (odd-indexed) values from two 128-bit vectors of [2 x i64] and interleaves them into a 128-bit vector of [2 x i64]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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]. More... | |
| 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. More... | |
| 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. More... | |
| 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. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_unpackhi_pd (__m128d __a, __m128d __b) |
| Unpacks the high-order (odd-indexed) values from two 128-bit vectors of [2 x double] and interleaves them into a 128-bit vector of [2 x double]. More... | |
| static __inline__ __m128d __DEFAULT_FN_ATTRS | _mm_unpacklo_pd (__m128d __a, __m128d __b) |
| Unpacks the low-order (even-indexed) values from two 128-bit vectors of [2 x double] and interleaves them into a 128-bit vector of [2 x double]. More... | |
| 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. More... | |
| 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]. More... | |
| 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. More... | |
| 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]. More... | |
| 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. More... | |
| 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]. More... | |
| 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]. More... | |
| void | _mm_pause (void) |
| Indicates that a spin loop is being executed for the purposes of optimizing power consumption during the loop. More... | |
| #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("sse2"))) |
Definition at line 50 of file emmintrin.h.
Referenced by _mm_movpi64_epi64().
| #define _mm_bslli_si128 | ( | a, | |
| imm | |||
| ) | _mm_slli_si128((a), (imm)) |
Definition at line 2794 of file emmintrin.h.
| #define _mm_bsrli_si128 | ( | a, | |
| imm | |||
| ) | _mm_srli_si128((a), (imm)) |
Definition at line 3029 of file emmintrin.h.
| #define _MM_DENORMALS_ZERO_MASK (0x0040) |
Definition at line 4923 of file emmintrin.h.
| #define _MM_DENORMALS_ZERO_OFF (0x0000) |
Definition at line 4921 of file emmintrin.h.
| #define _MM_DENORMALS_ZERO_ON (0x0040) |
Definition at line 4920 of file emmintrin.h.
| #define _MM_GET_DENORMALS_ZERO_MODE | ( | ) | (_mm_getcsr() & _MM_DENORMALS_ZERO_MASK) |
Definition at line 4925 of file emmintrin.h.
| #define _mm_load_pd1 | ( | dp | ) | _mm_load1_pd(dp) |
Definition at line 1605 of file emmintrin.h.
| #define _MM_SET_DENORMALS_ZERO_MODE | ( | x | ) | (_mm_setcsr((_mm_getcsr() & ~_MM_DENORMALS_ZERO_MASK) | (x))) |
Definition at line 4926 of file emmintrin.h.
| #define _MM_SHUFFLE2 | ( | x, | |
| y | |||
| ) | (((x) << 1) | (y)) |
Definition at line 4918 of file emmintrin.h.
| #define _mm_shuffle_epi32 | ( | a, | |
| 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. |
Definition at line 4366 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. |
Definition at line 4793 of file emmintrin.h.
| #define _mm_shufflehi_epi16 | ( | a, | |
| 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. |
Definition at line 4433 of file emmintrin.h.
| #define _mm_shufflelo_epi16 | ( | a, | |
| 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. |
Definition at line 4399 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 2773 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 3008 of file emmintrin.h.
| typedef signed char __v16qs __attribute__((__vector_size__(16))) |
Definition at line 29 of file emmintrin.h.
|
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 2092 of file emmintrin.h.
References __b.
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 2114 of file emmintrin.h.
References __b.
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 2154 of file emmintrin.h.
References __b.
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 2070 of file emmintrin.h.
References __b.
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 87 of file emmintrin.h.
References __b.
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 68 of file emmintrin.h.
|
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 2132 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 7FFFh are saturated to 7FFFh. Negative sums less than 8000h are saturated to 8000h.
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 2197 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 7Fh are saturated to 7Fh. Negative sums less than 80h are saturated to 80h.
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 2175 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 FFFFh are saturated to FFFFh. Negative sums are saturated to 0000h.
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 2239 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 FFh are saturated to FFh. Negative sums are saturated to 00h.
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 2218 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 362 of file emmintrin.h.
References __b.
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 2696 of file emmintrin.h.
References __b.
Referenced by _mm_mask_and_epi32(), and _mm_mask_and_epi64().
|
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 383 of file emmintrin.h.
References __b.
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 2716 of file emmintrin.h.
References __b.
Referenced by _mm_mask_andnot_epi32(), and _mm_mask_andnot_epi64().
|
static |
Computes the rounded avarages 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 2279 of file emmintrin.h.
Referenced by _mm_mask_avg_epu16(), and _mm_maskz_avg_epu16().
|
static |
Computes the rounded avarages 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 2259 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 4810 of file emmintrin.h.
|
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 4827 of file emmintrin.h.
|
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 4844 of file emmintrin.h.
|
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 4861 of file emmintrin.h.
|
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 4895 of file emmintrin.h.
|
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 4878 of file emmintrin.h.
| 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 yields 0h for false, FFFFh 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 3179 of file emmintrin.h.
References __b.
|
static |
Compares each of the corresponding 32-bit values of the 128-bit integer vectors for equality.
Each comparison yields 0h for false, FFFFFFFFh 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 3198 of file emmintrin.h.
References __b.
|
static |
Compares each of the corresponding 8-bit values of the 128-bit integer vectors for equality.
Each comparison yields 0h for false, FFh 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 3160 of file emmintrin.h.
References __b.
Referenced by ComputeLineNumbers().
|
static |
Compares each of the corresponding double-precision values of the 128-bit vectors of [2 x double] for equality.
Each comparison yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 696 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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 521 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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 797 of file emmintrin.h.
References __c.
|
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 yields 0h for false, FFFFh 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 3241 of file emmintrin.h.
References __b.
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 yields 0h for false, FFFFFFFFh 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 3262 of file emmintrin.h.
References __b.
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 yields 0h for false, FFh 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 3218 of file emmintrin.h.
References __b.
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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 500 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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 771 of file emmintrin.h.
References __c.
|
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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 479 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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 746 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 yields 0h for false, FFFFh 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 3304 of file emmintrin.h.
References _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 yields 0h for false, FFFFFFFFh 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 3325 of file emmintrin.h.
References _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 yields 0h for false, FFh 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 3283 of file emmintrin.h.
References _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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 458 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 yields 0h for false, FFFFFFFFFFFFFFFFh for true.
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 721 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 589 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 878 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 673 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 979 of file emmintrin.h.
References __c.
|
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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 652 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 953 of file emmintrin.h.
References __c.
|
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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 631 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 928 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 610 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 yields 0h for false, FFFFFFFFFFFFFFFFh for 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 903 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 yields 0h for false, FFFFFFFFFFFFFFFFh 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 yields 0h for false, FFFFFFFFFFFFFFFFh 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 825 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 yields 0h for false, FFFFFFFFFFFFFFFFh 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 568 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 yields 0h for false, FFFFFFFFFFFFFFFFh 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 853 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 yields 0 for false, 1 for true.
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 1001 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 yields 0 for false, 1 for true.
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 1097 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 yields 0 for false, 1 for true.
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 1073 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 yields 0 for false, 1 for true.
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 1049 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 yields 0 for false, 1 for true.
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 1025 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 yields 0 for false, 1 for true.
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 1121 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 1337 of file emmintrin.h.
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 3401 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 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.
This intrinsic corresponds to the VCVTPD2DQ / CVTPD2DQ instruction.
| __a | A 128-bit vector of [2 x double]. |
Definition at line 1357 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 32-bit integer values, returned in a 64-bit vector of [2 x i32].
This intrinsic corresponds to the CVTPD2PI instruction.
| __a | A 128-bit vector of [2 x double]. |
Definition at line 1507 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 1294 of file emmintrin.h.
|
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 1544 of file emmintrin.h.
|
static |
Converts a vector of [4 x float] into a vector of [4 x i32].
This intrinsic corresponds to the VCVTPS2DQ / CVTPS2DQ instruction.
| __a | A 128-bit vector of [4 x float]. |
Definition at line 3417 of file emmintrin.h.
|
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 1314 of file emmintrin.h.
|
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 1561 of file emmintrin.h.
|
static |
Converts the low-order element of a 128-bit vector of [2 x double] into a 32-bit signed integer value.
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 1374 of file emmintrin.h.
|
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 1399 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 3485 of file emmintrin.h.
References __b.
|
static |
Converts a 32-bit signed integer value, in the second parameter, into a double-precision floating-point value, returned in the lower 64 bits of a 128-bit vector of [2 x double].
The upper 64 bits of the result vector are copied from the upper 64 bits of the first parameter.
This intrinsic corresponds to the VCVTSI2SD / CVTSI2SD instruction.
| __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 1422 of file emmintrin.h.
References __b.
|
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 3450 of file emmintrin.h.
|
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 1448 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 32-bit integer values, returned in the lower 64 bits of a 128-bit vector of [4 x i32].
If the result of either conversion is inexact, the result is truncated (rounded towards zero) regardless of the current MXCSR setting. The upper 64 bits of the result vector are set to zero.
This intrinsic corresponds to the VCVTTPD2DQ / CVTTPD2DQ instruction.
| __a | A 128-bit vector of [2 x double]. |
Definition at line 1472 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 32-bit integer values, returned in a 64-bit vector of [2 x i32].
If the result of either conversion is inexact, the result is truncated (rounded towards zero) regardless of the current MXCSR setting.
This intrinsic corresponds to the CVTTPD2PI instruction.
| __a | A 128-bit vector of [2 x double]. |
Definition at line 1527 of file emmintrin.h.
|
static |
Converts a vector of [4 x float] into a vector of [4 x i32], truncating the result when it is inexact.
This intrinsic corresponds to the VCVTTPS2DQ / CVTTPS2DQ instruction.
| __a | A 128-bit vector of [4 x float]. |
Definition at line 3434 of file emmintrin.h.
|
static |
Converts the low-order element of a [2 x double] vector into a 32-bit signed integer value, truncating the result when it is inexact.
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 1490 of file emmintrin.h.
|
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 213 of file emmintrin.h.
References __b.
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 193 of file emmintrin.h.
|
static |
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 4286 of file emmintrin.h.
References __b.
|
static |
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 4313 of file emmintrin.h.
| 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 1596 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 1578 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 1681 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 3521 of file emmintrin.h.
References __p.
|
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 1708 of file emmintrin.h.
|
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 3558 of file emmintrin.h.
|
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 1735 of file emmintrin.h.
|
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 1622 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 1640 of file emmintrin.h.
Referenced by _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 3537 of file emmintrin.h.
Referenced by _mm256_loadu2_m128i().
|
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 1660 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 2305 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 date 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 4031 of file emmintrin.h.
|
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 2325 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 2345 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 the vector containing the greater of each pair of values.
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 344 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.
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 324 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 2365 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 2385 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 the vector containing the lesser of each pair of values.
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 300 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.
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 4702 of file emmintrin.h.
|
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 1889 of file emmintrin.h.
|
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 4333 of file emmintrin.h.
Referenced by ComputeLineNumbers().
|
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 4763 of file emmintrin.h.
|
static |
Returns the lower 64 bits of a 128-bit integer vector as a 64-bit integer.
This intrinsic has no corresponding instruction.
| __a | A 128-bit integer vector operand. The lower 64 bits are moved to the destination. |
Definition at line 4667 of file emmintrin.h.
|
static |
Moves the 64-bit operand to a 128-bit integer vector, zeroing the upper bits.
This intrinsic corresponds to the VMOVQ / MOVQ / MOVD instruction.
| __a | A 64-bit value. |
Definition at line 4684 of file emmintrin.h.
References __DEFAULT_FN_ATTRS.
|
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 2483 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 170 of file emmintrin.h.
References __b.
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 151 of file emmintrin.h.
|
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 2464 of file emmintrin.h.
|
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 2405 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 2425 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 2445 of file emmintrin.h.
References __b.
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.
References __b.
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 2733 of file emmintrin.h.
References __b.
Referenced by _mm_mask_or_epi32(), _mm_mask_or_epi64(), and ComputeLineNumbers().
|
static |
Converts 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]. Each 16-bit element is treated as a signed integer and is converted to a 8-bit signed integer with saturation. Values greater than 0x7F are saturated to 0x7F. Values less than 0x80 are saturated to 0x80. 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]. Each 16-bit element is treated as a signed integer and is converted to a 8-bit signed integer with saturation. Values greater than 0x7F are saturated to 0x7F. Values less than 0x80 are saturated to 0x80. The converted [8 x i8] values are written to the higher 64 bits of the result. |
Definition at line 4202 of file emmintrin.h.
Referenced by _mm_mask_packs_epi16(), and _mm_maskz_packs_epi16().
|
static |
Converts 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]. Each 32-bit element is treated as a signed integer and is converted to a 16-bit signed integer with saturation. Values greater than 0x7FFF are saturated to 0x7FFF. Values less than 0x8000 are saturated to 0x8000. 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]. Each 32-bit element is treated as a signed integer and is converted to a 16-bit signed integer with saturation. Values greater than 0x7FFF are saturated to 0x7FFF. Values less than 0x8000 are saturated to 0x8000. The converted [4 x i16] values are written to the higher 64 bits of the result. |
Definition at line 4230 of file emmintrin.h.
Referenced by _mm_mask_packs_epi32(), and _mm_maskz_packs_epi32().
|
static |
Converts 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]. Each 16-bit element is treated as a signed integer and is converted to an 8-bit unsigned integer with saturation. Values greater than 0xFF are saturated to 0xFF. Values less than 0x00 are saturated to 0x00. 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]. Each 16-bit element is treated as a signed integer and is converted to an 8-bit unsigned integer with saturation. Values greater than 0xFF are saturated to 0xFF. Values less than 0x00 are saturated to 0x00. The converted [8 x i8] values are written to the higher 64 bits of the result. |
Definition at line 4258 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 2505 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 3812 of file emmintrin.h.
|
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 3793 of file emmintrin.h.
|
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 3774 of file emmintrin.h.
|
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 3755 of file emmintrin.h.
|
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 3831 of file emmintrin.h.
References __b.
Referenced by ComputeLineNumbers().
|
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 1794 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 3688 of file emmintrin.h.
|
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 3648 of file emmintrin.h.
|
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 3620 of file emmintrin.h.
|
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 3598 of file emmintrin.h.
|
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 3736 of file emmintrin.h.
|
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 1832 of file emmintrin.h.
References __x.
|
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 1812 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 3906 of file emmintrin.h.
|
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 3875 of file emmintrin.h.
|
static |
Constructs a 128-bit integer vector, initialized in reverse order with the specified 64-bit integral values.
This intrinsic corresponds to the VPUNPCKLQDQ / PUNPCKLQDQ 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 3852 of file emmintrin.h.
|
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 3953 of file emmintrin.h.
|
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 1853 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 1868 of file emmintrin.h.
Referenced by _mm256_zextpd128_pd256(), _mm512_zextpd128_pd512(), _mm_cvtepi64_pd(), _mm_cvtepu64_pd(), _mm_getexp_pd(), _mm_getexp_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_getexp_pd(), _mm_maskz_getexp_sd(), _mm_maskz_getexp_ss(), _mm_maskz_load_pd(), _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_movedup_pd(), _mm_maskz_mul_pd(), _mm_maskz_mul_sd(), _mm_maskz_or_pd(), _mm_maskz_permutevar_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_ps(), _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 3967 of file emmintrin.h.
Referenced by _mm256_cvtepi16_epi8(), _mm256_cvtepi32_epi16(), _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_cvtps_ph(), _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_abs_epi64(), _mm_cvtepi16_epi8(), _mm_cvtepi32_epi16(), _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_lzcnt_epi32(), _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_epi32(), _mm_maskz_compress_epi64(), _mm_maskz_conflict_epi32(), _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_cvtps_ph(), _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_expand_epi32(), _mm_maskz_expand_epi64(), _mm_maskz_expandloadu_epi32(), _mm_maskz_expandloadu_epi64(), _mm_maskz_load_epi32(), _mm_maskz_loadu_epi32(), _mm_maskz_loadu_epi64(), _mm_maskz_loadu_epi8(), _mm_maskz_lzcnt_epi32(), _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_epi32(), _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_permutexvar_epi16(), _mm_maskz_permutexvar_epi8(), _mm_maskz_rolv_epi32(), _mm_maskz_rorv_epi32(), _mm_maskz_set1_epi16(), _mm_maskz_set1_epi8(), _mm_maskz_shuffle_epi8(), _mm_maskz_sll_epi16(), _mm_maskz_sll_epi32(), _mm_maskz_slli_epi16(), _mm_maskz_slli_epi32(), _mm_maskz_sllv_epi16(), _mm_maskz_sllv_epi32(), _mm_maskz_sra_epi16(), _mm_maskz_sra_epi32(), _mm_maskz_srai_epi16(), _mm_maskz_srai_epi32(), _mm_maskz_srav_epi16(), _mm_maskz_srav_epi32(), _mm_maskz_srl_epi16(), _mm_maskz_srl_epi32(), _mm_maskz_srli_epi16(), _mm_maskz_srli_epi32(), _mm_maskz_srlv_epi16(), _mm_maskz_srlv_epi32(), _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_epi8(), _mm_maskz_unpacklo_epi16(), _mm_maskz_unpacklo_epi32(), _mm_maskz_unpacklo_epi8(), _mm_maskz_xor_epi32(), _mm_maskz_xor_epi64(), _mm_max_epi64(), _mm_max_epu64(), _mm_min_epi64(), _mm_min_epu64(), _mm_rolv_epi32(), and _mm_rorv_epi32().
|
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 2830 of file emmintrin.h.
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 2868 of file emmintrin.h.
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 2906 of file emmintrin.h.
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 2811 of file emmintrin.h.
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 2849 of file emmintrin.h.
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 2887 of file emmintrin.h.
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.
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 238 of file emmintrin.h.
References __c.
|
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 2946 of file emmintrin.h.
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 2986 of file emmintrin.h.
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 2926 of file emmintrin.h.
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 2966 of file emmintrin.h.
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 3065 of file emmintrin.h.
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 3103 of file emmintrin.h.
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 3141 of file emmintrin.h.
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 3046 of file emmintrin.h.
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 3084 of file emmintrin.h.
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 3122 of file emmintrin.h.
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 1947 of file emmintrin.h.
References _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 1928 of file emmintrin.h.
Referenced by _mm_store1_pd().
|
static |
Stores a 128-bit vector of [2 x double] into 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. |
| __a | A 128-bit vector of [2 x double] containing the values to be stored. |
Definition at line 1966 of file emmintrin.h.
References _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 1906 of file emmintrin.h.
|
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 3985 of file emmintrin.h.
References __b.
|
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 2025 of file emmintrin.h.
|
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 4050 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 2045 of file emmintrin.h.
|
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 2007 of file emmintrin.h.
|
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 1984 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 4001 of file emmintrin.h.
References __b.
Referenced by _mm256_storeu2_m128i().
|
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 4073 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 4092 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. |
Definition at line 4111 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 2541 of file emmintrin.h.
References __b.
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 2559 of file emmintrin.h.
References __b.
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 2596 of file emmintrin.h.
References __b.
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 2523 of file emmintrin.h.
References __b.
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 129 of file emmintrin.h.
References __b.
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 110 of file emmintrin.h.
|
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 2578 of file emmintrin.h.
|
static |
Subtracts corresponding 16-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination.
Differences greater than 7FFFh are saturated to 7FFFh, and values less than 8000h are saturated to 8000h.
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 2638 of file emmintrin.h.
Referenced by _mm_mask_subs_epi16(), and _mm_maskz_subs_epi16().
|
static |
Subtracts corresponding 8-bit signed integer values in the input and returns the differences in the corresponding bytes in the destination.
Differences greater than 7Fh are saturated to 7Fh, and differences less than 80h are saturated to 80h.
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 2617 of file emmintrin.h.
Referenced by _mm_mask_subs_epi8(), and _mm_maskz_subs_epi8().
|
static |
Subtracts corresponding 16-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination.
Differences less than 0000h are saturated to 0000h.
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 2678 of file emmintrin.h.
Referenced by _mm_mask_subs_epu16(), and _mm_maskz_subs_epu16().
|
static |
Subtracts corresponding 8-bit unsigned integer values in the input and returns the differences in the corresponding bytes in the destination.
Differences less than 00h are saturated to 00h.
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 2658 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 yields 0 for false, 1 for true.
If either of the two lower double-precision values is NaN, 1 is returned.
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 1145 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 yields 0 for false, 1 for true. If either of the two lower double-precision values is NaN, 0 is returned.
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 1249 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 yields 0 for false, 1 for true. If either of the two lower double-precision values is NaN, 0 is returned.
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 1223 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 yields 0 for false, 1 for true. If either of the two lower double-precision values is NaN, 1 is returned.
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 1197 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 yields 0 for false, 1 for true. If either of the two lower double-precision values is NaN, 1 is returned.
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 1171 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 yields 0 for false, 1 for true. If either of the two lower double-precision values is NaN, 0 is returned.
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 1275 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 1756 of file emmintrin.h.
Referenced by _mm512_broadcastsd_pd().
|
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 3576 of file emmintrin.h.
Referenced by _mm256_cvtepi32_epi8(), _mm256_cvtepi64_epi16(), _mm256_cvtepi64_epi32(), _mm256_cvtepi64_epi8(), _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_broadcastb_epi8(), _mm512_broadcastd_epi32(), _mm512_broadcastq_epi64(), _mm512_broadcastw_epi16(), _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_broadcast_i32x2(), _mm_conflict_epi32(), _mm_conflict_epi64(), _mm_cvtepi32_epi8(), _mm_cvtepi64_epi16(), _mm_cvtepi64_epi32(), _mm_cvtepi64_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(), _mm_cvtusepi64_epi8(), _mm_multishift_epi64_epi8(), _mm_permutexvar_epi16(), and _mm_permutexvar_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 4499 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 4522 of file emmintrin.h.
Referenced by _mm_mask_unpackhi_epi32(), and _mm_maskz_unpackhi_epi32().
|
static |
Unpacks the high-order (odd-indexed) values 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 4543 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 4472 of file emmintrin.h.
Referenced by _mm_mask_unpackhi_epi8(), and _mm_maskz_unpackhi_epi8().
|
static |
Unpacks the high-order (odd-indexed) values 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 4723 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 4606 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 4629 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 4650 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 4578 of file emmintrin.h.
Referenced by _mm_mask_unpacklo_epi8(), and _mm_maskz_unpacklo_epi8().
|
static |
Unpacks the low-order (even-indexed) values 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 4744 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 419 of file emmintrin.h.
References __b.
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 2751 of file emmintrin.h.
References __b.
Referenced by _mm_mask_xor_epi32(), and _mm_mask_xor_epi64().
1.8.6