Compiler Explorer

Source code

#![feature(stdsimd)]
use std::arch::x86_64::*;

// #[inline]
pub fn vec_sum_simd_direct_loop(src: &[i32]) -> i32 {
    #[cfg(debug_assertions)]
    assert!(src.as_ptr() as u64 % 64 == 0);
    #[cfg(debug_assertions)]
    assert!(src.len() % (std::mem::size_of::<__m256i>() / std::mem::size_of::<i32>()) == 0);

let p_src = src.as_ptr();
    let batch_size = std::mem::size_of::<__m256i>() / std::mem::size_of::<i32>();

#[cfg(debug_assertions)]
    assert!(src.len() % batch_size == 0);

let result: i32;
    unsafe {
        let mut offset: isize = 0;
        let total: isize = src.len() as isize;
        let mut curr_sum = _mm256_setzero_si256();

while offset < total {
            let curr = _mm256_load_epi32(p_src.offset(offset));
            curr_sum = _mm256_add_epi32(curr_sum, curr);
            offset += 8;
        }

// this can be reduced with hadd.
        let a0 = _mm256_extract_epi32::<0>(curr_sum);
        let a1 = _mm256_extract_epi32::<1>(curr_sum);
        let a2 = _mm256_extract_epi32::<2>(curr_sum);
        let a3 = _mm256_extract_epi32::<3>(curr_sum);
        let a4 = _mm256_extract_epi32::<4>(curr_sum);
        let a5 = _mm256_extract_epi32::<5>(curr_sum);
        let a6 = _mm256_extract_epi32::<6>(curr_sum);
        let a7 = _mm256_extract_epi32::<7>(curr_sum);

result = a0 + a1 + a2 + a3 + a4 + a5 + a6 + a7;
    }

result
}