This type is the same as the __m256d type defined by Intel,
representing a 256-bit SIMD register which internally is consisted of
four packed f64 instances. Usage of this type typically corresponds
to the avx and up target features for x86/x86_64.
Note that unlike __m256i, the integer version of the 256-bit
registers, this __m256d type has one interpretation. Each instance
of __m256d always corresponds to f64x4, or four f64 types packed
together.
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.
Most intrinsics using __m256d are prefixed with _mm256_ and are
suffixed with “pd” (or otherwise contain “pd”). Not to be confused with
“ps” which is used for __m256.
#[cfg(target_arch = "x86")]
use std::arch::x86::*;
#[cfg(target_arch = "x86_64")]
use std::arch::x86_64::*;
let four_zeros = _mm256_setzero_pd();
let four_ones = _mm256_set1_pd(1.0);
let four_floats = _mm256_set_pd(1.0, 2.0, 3.0, 4.0);