c – 快速计算__m128i寄存器中的设置位数

我应该计算__m128i寄存器的设置位数.
特别是,我应该使用以下方法编写两个能够计算寄存器位数的函数.

>寄存器的设定位总数.
>寄存器的每个字节的设置位数.

是否有可以完全或部分执行上述操作的内在功能？

解决方法:

以下是我在旧项目(there is a research paper about it)中使用的一些代码.下面的函数popcnt8计算每​​个字节中设置的位数.

仅SSE2版本(基于Hacker’s Delight book中的算法3)：

static const __m128i popcount_mask1 = _mm_set1_epi8(0x77);
static const __m128i popcount_mask2 = _mm_set1_epi8(0x0F);
static inline __m128i popcnt8(__m128i x) {
    __m128i n;
    // Count bits in each 4-bit field.
    n = _mm_srli_epi64(x, 1);
    n = _mm_and_si128(popcount_mask1, n);
    x = _mm_sub_epi8(x, n);
    n = _mm_srli_epi64(n, 1);
    n = _mm_and_si128(popcount_mask1, n);
    x = _mm_sub_epi8(x, n);
    n = _mm_srli_epi64(n, 1);
    n = _mm_and_si128(popcount_mask1, n);
    x = _mm_sub_epi8(x, n);
    x = _mm_add_epi8(x, _mm_srli_epi16(x, 4));
    x = _mm_and_si128(popcount_mask2, x);
    return x;
}

SSSE3版本(由于Wojciech Mula)：

static const __m128i popcount_mask = _mm_set1_epi8(0x0F);
static const __m128i popcount_table = _mm_setr_epi8(0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4);
static inline __m128i popcnt8(__m128i n) {
    const __m128i pcnt0 = _mm_shuffle_epi8(popcount_table, _mm_and_si128(n, popcount_mask));
    const __m128i pcnt1 = _mm_shuffle_epi8(popcount_table, _mm_and_si128(_mm_srli_epi16(n, 4), popcount_mask));
    return _mm_add_epi8(pcnt0, pcnt1);
}

XOP版本(相当于SSSE3,但使用XOP指令,这些指令在AMD Bulldozer上更快)

static const __m128i popcount_mask = _mm_set1_epi8(0x0F);
static const __m128i popcount_table = _mm_setr_epi8(0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4);
static const __m128i popcount_shift = _mm_set1_epi8(-4);
static inline __m128i popcount8(__m128i n) {
    const __m128i pcnt0 = _mm_perm_epi8(popcount_table, popcount_table, _mm_and_si128(n, popcount_mask));
    const __m128i pcnt1 = _mm_perm_epi8(popcount_table, popcount_table, _mm_shl_epi8(n, popcount_shift));
    return _mm_add_epi8(pcnt0, pcnt1);
}

下面的函数popcnt64计算SSE寄存器的低64位和高64位部分的位数：

SSE2版本：

static inline __m128i popcnt64(__m128i n) {
    const __m128i cnt8 = popcnt8(n);
    return _mm_sad_epu8(cnt8, _mm_setzero_si128());
}

XOP版本：

static inline __m128i popcnt64(__m128i n) {
    const __m128i cnt8 = popcnt8(n);
    return _mm_haddq_epi8(cnt8);
}

最后,下面的函数popcnt128计算整个128位寄存器中的位数：

static inline int popcnt128(__m128i n) {
    const __m128i cnt64 = popcnt64(n);
    const __m128i cnt64_hi = _mm_unpackhi_epi64(cnt64, cnt64);
    const __m128i cnt128 = _mm_add_epi32(cnt64, cnt64_hi);
    return _mm_cvtsi128_si32(cnt128);
}

但是,实现popcnt128的更有效方法是使用硬件POPCNT指令(在支持它的处理器上)：

static inline int popcnt128(__m128i n) {
    const __m128i n_hi = _mm_unpackhi_epi64(n, n);
    #ifdef _MSC_VER
        return __popcnt64(_mm_cvtsi128_si64(n)) + __popcnt64(_mm_cvtsi128_si64(n_hi));
    #else
        return __popcntq(_mm_cvtsi128_si64(n)) + __popcntq(_mm_cvtsi128_si64(n_hi));
    #endif
}

标签：c-3,sse2,c,sse,simd
来源： https://codeday.me/bug/20190928/1827504.html