Skip to main content

cross_block_alignr_256x2

fearless_simd::generated::avx2

Function cross_block_alignr_256x2 

Source 
unsafe fn cross_block_alignr_256x2(
    a: [__m256i; 2],
    b: [__m256i; 2],
    shift_bytes: usize,
) -> [__m256i; 2]
Expand description

Concatenates b and a (each 2 x __m256i = 4 blocks) and extracts 4 blocks starting at byte offset shift_bytes. Extracts from [b : a] (b in low bytes, a in high bytes), matching alignr semantics.