This type is the same as the __m128i type defined by Intel,
representing a 128-bit SIMD register. Usage of this type typically
corresponds to the sse and up target features for x86/x86_64.
Internally this type may be viewed as:
i8x16 - sixteen i8 variables packed together
i16x8 - eight i16 variables packed together
i32x4 - four i32 variables packed together
i64x2 - two i64 variables packed together
(as well as unsigned versions). Each intrinsic may interpret the
internal bits differently, check the documentation of the intrinsic
to see how it’s being used.
The in-memory representation of this type is the same as the one of an
equivalent array (i.e. the in-memory order of elements is the same, and
there is no padding); however, the alignment is different and equal to
the size of the type. Note that the ABI for function calls may not be
the same.
Note that this means that an instance of __m128i typically just means
a “bag of bits” which is left up to interpretation at the point of use.
Most intrinsics using __m128i are prefixed with _mm_ and the
integer types tend to correspond to suffixes like “epi8” or “epi32”.
#[cfg(target_arch = "x86")]
use std::arch::x86::*;
#[cfg(target_arch = "x86_64")]
use std::arch::x86_64::*;
let all_bytes_zero = _mm_setzero_si128();
let all_bytes_one = _mm_set1_epi8(1);
let four_i32 = _mm_set_epi32(1, 2, 3, 4);