powturbo

size_t memcount_sse2(const void *s, int c, size_t n) {    
    __m128i cv = _mm_set1_epi8(c), sum = _mm_setzero_si128(), acr0,acr1,acr2,acr3;
    const char *p,*pe;						    											   
	for(p = s; p != (char *)s+(n- (n % (252*16)));) { 
	  for(acr0 = acr1 = acr2 = acr3 = _mm_setzero_si128(),pe = p+252*16; p != pe; p += 64) { 
		acr0 = _mm_add_epi8(acr0, _mm_cmpeq_epi8(cv, _mm_loadu_si128((const __m128i *)p))); 
		acr1 = _mm_add_epi8(acr1, _mm_cmpeq_epi8(cv, _mm_loadu_si128((const __m128i *)(p+16)))); 
		acr2 = _mm_add_epi8(acr2, _mm_cmpeq_epi8(cv, _mm_loadu_si128((const __m128i *)(p+32)))); 
		acr3 = _mm_add_epi8(acr3, _mm_cmpeq_epi8(cv, _mm_loadu_si128((const __m128i *)(p+48)))); __builtin_prefetch(p+1024);
	  }

powturbo

size_t memcount_avx2(const void *s, int c, size_t n) {    
    __m256i cv = _mm256_set1_epi8(c), zv = _mm256_setzero_si256(), sum = zv, acr0,acr1,acr2,acr3;
    const char *p,*pe;						    											   
	for(p = s; p != (char *)s+(n- (n % (252*32)));) { 
	  for(acr0 = acr1 = acr2 = acr3 = zv,pe = p+252*32; p != pe; p += 128) { 
		acr0 = _mm256_add_epi8(acr0, _mm256_cmpeq_epi8(cv, _mm256_lddqu_si256((const __m256i *)p))); 
		acr1 = _mm256_add_epi8(acr1, _mm256_cmpeq_epi8(cv, _mm256_lddqu_si256((const __m256i *)(p+32)))); 
		acr2 = _mm256_add_epi8(acr2, _mm256_cmpeq_epi8(cv, _mm256_lddqu_si256((const __m256i *)(p+64)))); 
		acr3 = _mm256_add_epi8(acr3, _mm256_cmpeq_epi8(cv, _mm256_lddqu_si256((const __m256i *)(p+96)))); __builtin_prefetch(p+1024);
	  }