使用 sse 内在函数对 (A)RGB32 图像进行最快 50% 缩放

我想在 C++ 中尽可能快地缩小图像。本文 http://blog.qt.io/blog/2009/01/20/50-scaling-of-argb32-image/描述如何有效地将 32 位 RGB 图像平均降低 50%。它速度快而且看起来不错。

我尝试使用 sse 内在函数修改该方法。无论启用或不启用 SSE，下面的代码都可以工作。但令人惊讶的是，加速效果可以忽略不计。

任何人都可以找到改进 SSE 代码的方法吗？创建变量 shuffle1 和 shuffle2 的两行似乎是候选者（使用一些巧妙的移位或类似方法）。

/*
 * Calculates the average of two rgb32 pixels.
 */
inline static uint32_t avg(uint32_t a, uint32_t b)
{
    return (((a^b) & 0xfefefefeUL) >> 1) + (a&b);
}

/*
 * Calculates the average of four rgb32 pixels.
 */
inline static uint32_t avg(const uint32_t a[2], const uint32_t b[2])
{
    return avg(avg(a[0], a[1]), avg(b[0], b[1]));
}

/*
 * Calculates the average of two rows of rgb32 pixels.
 */
void average2Rows(const uint32_t* src_row1, const uint32_t* src_row2, uint32_t* dst_row, int w)
{
#if !defined(__SSE)
        for (int x = w; x; --x, dst_row++, src_row1 += 2, src_row2 += 2)
            * dst_row = avg(src_row1, src_row2);
#else
        for (int x = w; x; x-=4, dst_row+=4, src_row1 += 8, src_row2 += 8)
        {
            __m128i left  = _mm_avg_epu8(_mm_load_si128((__m128i const*)src_row1), _mm_load_si128((__m128i const*)src_row2));
            __m128i right = _mm_avg_epu8(_mm_load_si128((__m128i const*)(src_row1+4)), _mm_load_si128((__m128i const*)(src_row2+4)));

            __m128i shuffle1 = _mm_set_epi32( right.m128i_u32[2], right.m128i_u32[0], left.m128i_u32[2], left.m128i_u32[0]);
            __m128i shuffle2 = _mm_set_epi32( right.m128i_u32[3], right.m128i_u32[1], left.m128i_u32[3], left.m128i_u32[1]);

            _mm_store_si128((__m128i *)dst_row, _mm_avg_epu8(shuffle1, shuffle2));
        }
#endif
}

在通用寄存器和 SSE 寄存器之间传输数据非常慢，因此您应该避免执行以下操作：

__m128i shuffle1 = _mm_set_epi32( right.m128i_u32[2], right.m128i_u32[0], left.m128i_u32[2], left.m128i_u32[0]);
__m128i shuffle2 = _mm_set_epi32( right.m128i_u32[3], right.m128i_u32[1], left.m128i_u32[3], left.m128i_u32[1]);

借助相应的洗牌操作对 SSE 寄存器中的值进行洗牌。

这应该是您正在寻找的：

__m128i t0 = _mm_unpacklo_epi32( left, right ); // right.m128i_u32[1] left.m128i_u32[1] right.m128i_u32[0] left.m128i_u32[0]
__m128i t1 = _mm_unpackhi_epi32( left, right ); // right.m128i_u32[3] left.m128i_u32[3] right.m128i_u32[2] left.m128i_u32[2]
__m128i shuffle1 = _mm_unpacklo_epi32( t0, t1 );    // right.m128i_u32[2] right.m128i_u32[0] left.m128i_u32[2] left.m128i_u32[0]
__m128i shuffle2 = _mm_unpackhi_epi32( t0, t1 );    // right.m128i_u32[3] right.m128i_u32[1] left.m128i_u32[3] left.m128i_u32[1]