Compiler Explorer

Source code

#include <immintrin.h>
#include <stdint.h>

static inline
__m256i hsum_epu8_epu64(__m256i v) {
    return _mm256_sad_epu8(v, _mm256_setzero_si256());  // SAD against zero is a handy trick
}

static inline
uint64_t hsum_epu64_scalar(__m256i v) {
    __m128i lo = _mm256_castsi256_si128(v);
    __m128i hi = _mm256_extracti128_si256(v, 1);
    __m128i sum2x64 = _mm_add_epi64(lo, hi);   // narrow to 128

hi = _mm_unpackhi_epi64(sum2x64, sum2x64);
    __m128i sum = _mm_add_epi64(hi, sum2x64);  // narrow to 64
    return _mm_cvtsi128_si64(sum);
}

unsigned long long char_count_AVX2(char const* vector, size_t size, char c)
{
    __m256i C=_mm256_set1_epi8(c);
    
    // todo: count elements and increment `vector` until it is aligned to 256bytes, or at least 32
    __m256i const * simd_vector = (__m256i const *) vector;
     // *simd_vector is an alignment-required load, unlike _mm256_loadu_si256()
    
    __m256i sum64 = _mm256_setzero_si256();
    size_t unrolled_size_limit = size - 4*255*32 + 1;
    for(size_t k=0; k<unrolled_size_limit ; k+=4*255*32) // outer loop: TODO
    {
        __m256i counter[4]; // multiple counter registers to hide latencies
        for(int j=0; j<4; j++)
            counter[j]=_mm256_setzero_si256();
        // inner loop: make sure that you don't go beyond the data you can read
        for(int i=0; i<255; ++i)
        {   // or limit this inner loop to ~22 to avoid branch mispredicts
            for(int j=0; j<4; ++j)
            {
                counter[j]=_mm256_sub_epi8(counter[j],           // count -= 0 or -1
                                           _mm256_cmpeq_epi8(*simd_vector, C));
                ++simd_vector;
            }
        }

// only need one outer accumulator: OoO exec hides the latency of adding into it
        sum64 = _mm256_add_epi64(sum64, hsum_epu8_epu64(counter[0]));
        sum64 = _mm256_add_epi64(sum64, hsum_epu8_epu64(counter[1]));
        sum64 = _mm256_add_epi64(sum64, hsum_epu8_epu64(counter[2]));
        sum64 = _mm256_add_epi64(sum64, hsum_epu8_epu64(counter[3]));
    }

uint64_t sum = hsum_epu64_scalar(sum64);

// TODO add up remaining bytes with sum.
    // Including a rolled-up vector loop before going scalar
    //  because we're potentially a *long* way from the end

// Maybe put some logic into the main loop to shorten the 255 inner iterations
    // if we're close to the end.  A little bit of scalar work there shouldn't hurt every 255 iters.

return sum;
}