[−][src]Macro safe_arch::blend_imm_i32_m256i
This is supported with target feature
avx2
only.Blends the i32
lanes according to the immediate value.
- Each bit in
0..=7
should be set for$b
and unset for$a
let a = m256i::from([5_i32; 8]); let b = m256i::from([10_i32; 8]); // let c: [i32; 8] = blend_imm_i32_m256i!(a, b, 0b11001000).into(); assert_eq!(c, [5, 5, 5, 10, 5, 5, 10, 10]);
- Intrinsic:
_mm256_blend_epi32
- Assembly:
vpblendd ymm, ymm, ymm, imm8