Compiler Explorer

Source code

#![feature(stdsimd)]
#![feature(test)]

use std::arch::x86_64::*;

pub unsafe fn overlay_chunk_avx2(this_chunk: &mut [u8], image_chunk: &[u8], c1: __m256i, c2: __m256i) {
    let this_ptr = this_chunk.as_mut_ptr() as *mut __m128i;
    let image_ptr = image_chunk.as_ptr() as *const __m128i;

let this_argb = _mm_loadu_si128(this_ptr);
    let image_argb = _mm_loadu_si128(image_ptr);

let this_u16 = _mm256_cvtepu8_epi16(this_argb);
    let image_u16 = _mm256_cvtepu8_epi16(image_argb);

let image_alpha = _mm256_shuffle_epi8(image_u16, c1);
    let image_inv_alpha = _mm256_sub_epi8(c2, image_alpha);

let this_blended = _mm256_mullo_epi16(this_u16, image_inv_alpha);
    let image_blended = _mm256_mullo_epi16(image_u16, image_alpha);

let blended = _mm256_add_epi16(this_blended, image_blended);
    let divided = _mm256_srli_epi16(blended, 8);

let lo_lane = _mm256_castsi256_si128(divided);
    let hi_lane = _mm256_extracti128_si256(divided, 1);

let divided_u8 = _mm_packus_epi16(lo_lane, hi_lane);

_mm_storeu_si128(this_ptr, divided_u8);
}

pub unsafe fn overlay_chunk_avx512(this_chunk: &mut [u8], image_chunk: &[u8], c1: __m512i, c2: __m512i) {
    let this_ptr = this_chunk.as_mut_ptr() as *mut i8;
    let image_ptr = image_chunk.as_ptr() as *const i8;

let this_argb = _mm256_loadu_epi8(this_ptr);
    let image_argb = _mm256_loadu_epi8(image_ptr);

let this_u16 = _mm512_cvtepu8_epi16(this_argb);
    let image_u16 = _mm512_cvtepu8_epi16(image_argb);

let image_alpha = _mm512_shuffle_epi8(image_u16, c1);
    let image_inv_alpha = _mm512_sub_epi8(c2, image_alpha);

let this_blended = _mm512_mullo_epi16(this_u16, image_inv_alpha);
    let image_blended = _mm512_mullo_epi16(image_u16, image_alpha);

let blended = _mm512_add_epi16(this_blended, image_blended);

let divided = _mm512_srli_epi16(blended, 8);
    let divided_u8 = _mm512_cvtepi16_epi8(divided);

_mm256_storeu_epi8(this_ptr, divided_u8);
}