我认为 transpose/2-pass 不利于优化 Sobel Operator 代码。Sobel Operator 不是计算函数,因此在这种情况下浪费内存访问进行转置/2-pass 访问并不好。我写了一些 Sobel Operator 测试代码来看看 SSE 能有多快。此代码不处理第一个和最后一个边缘像素,并使用 FPU 计算 sqrt() 值。
Sobel 运算符需要 14 个乘法、1 个平方根、11 个加法、2 个最小/最大、12 个读访问和 1 个写访问运算符。这意味着如果您优化代码,您可以在 20~30 个周期内处理一个组件。
FloatSobel() 函数需要 2113044 个 CPU 周期来处理 256 * 256 图像处理 32.76 周期/组件。我会将此示例代码转换为 SSE。
void FPUSobel()
{
BYTE* image_0 = g_image + g_image_width * 0;
BYTE* image_1 = g_image + g_image_width * 1;
BYTE* image_2 = g_image + g_image_width * 2;
DWORD* screen = g_screen + g_screen_width*1;
for(int y=1; y<g_image_height-1; ++y)
{
for(int x=1; x<g_image_width-1; ++x)
{
float gx = image_0[x-1] * (+1.0f) +
image_0[x+1] * (-1.0f) +
image_1[x-1] * (+2.0f) +
image_1[x+1] * (-2.0f) +
image_2[x-1] * (+1.0f) +
image_2[x+1] * (-1.0f);
float gy = image_0[x-1] * (+1.0f) +
image_0[x+0] * (+2.0f) +
image_0[x+1] * (+1.0f) +
image_2[x-1] * (-1.0f) +
image_2[x+0] * (-2.0f) +
image_2[x+1] * (-1.0f);
int result = (int)min(255.0f, max(0.0f, sqrtf(gx * gx + gy * gy)));
screen[x] = 0x01010101 * result;
}
image_0 += g_image_width;
image_1 += g_image_width;
image_2 += g_image_width;
screen += g_screen_width;
}
}
SseSobel() 函数需要 613220 个 CPU 周期来处理相同的 256*256 图像。它比 FPUSobel() 花费了 9.51 个周期/组件和 3.4 倍。有一些空间需要优化,但速度不会超过 4 倍,因为它使用了 4 路 SIMD。
此函数使用 SoA 方法一次处理 4 个像素。在大多数数组或图像数据中,SoA 优于 AoS,因为您必须转置/洗牌才能使用 AoS。并且 SoA 更容易将通用 C 代码更改为 SSE 代码。
void SseSobel()
{
BYTE* image_0 = g_image + g_image_width * 0;
BYTE* image_1 = g_image + g_image_width * 1;
BYTE* image_2 = g_image + g_image_width * 2;
DWORD* screen = g_screen + g_screen_width*1;
__m128 const_p_one = _mm_set1_ps(+1.0f);
__m128 const_p_two = _mm_set1_ps(+2.0f);
__m128 const_n_one = _mm_set1_ps(-1.0f);
__m128 const_n_two = _mm_set1_ps(-2.0f);
for(int y=1; y<g_image_height-1; ++y)
{
for(int x=1; x<g_image_width-1; x+=4)
{
// load 16 components. (0~6 will be used)
__m128i current_0 = _mm_unpacklo_epi8(_mm_loadu_si128((__m128i*)(image_0+x-1)), _mm_setzero_si128());
__m128i current_1 = _mm_unpacklo_epi8(_mm_loadu_si128((__m128i*)(image_1+x-1)), _mm_setzero_si128());
__m128i current_2 = _mm_unpacklo_epi8(_mm_loadu_si128((__m128i*)(image_2+x-1)), _mm_setzero_si128());
// image_00 = { image_0[x-1], image_0[x+0], image_0[x+1], image_0[x+2] }
__m128 image_00 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(current_0, _mm_setzero_si128()));
// image_01 = { image_0[x+0], image_0[x+1], image_0[x+2], image_0[x+3] }
__m128 image_01 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(_mm_srli_si128(current_0, 2), _mm_setzero_si128()));
// image_02 = { image_0[x+1], image_0[x+2], image_0[x+3], image_0[x+4] }
__m128 image_02 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(_mm_srli_si128(current_0, 4), _mm_setzero_si128()));
__m128 image_10 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(current_1, _mm_setzero_si128()));
__m128 image_12 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(_mm_srli_si128(current_1, 4), _mm_setzero_si128()));
__m128 image_20 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(current_2, _mm_setzero_si128()));
__m128 image_21 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(_mm_srli_si128(current_2, 2), _mm_setzero_si128()));
__m128 image_22 = _mm_cvtepi32_ps(_mm_unpacklo_epi16(_mm_srli_si128(current_2, 4), _mm_setzero_si128()));
__m128 gx = _mm_add_ps( _mm_mul_ps(image_00,const_p_one),
_mm_add_ps( _mm_mul_ps(image_02,const_n_one),
_mm_add_ps( _mm_mul_ps(image_10,const_p_two),
_mm_add_ps( _mm_mul_ps(image_12,const_n_two),
_mm_add_ps( _mm_mul_ps(image_20,const_p_one),
_mm_mul_ps(image_22,const_n_one))))));
__m128 gy = _mm_add_ps( _mm_mul_ps(image_00,const_p_one),
_mm_add_ps( _mm_mul_ps(image_01,const_p_two),
_mm_add_ps( _mm_mul_ps(image_02,const_p_one),
_mm_add_ps( _mm_mul_ps(image_20,const_n_one),
_mm_add_ps( _mm_mul_ps(image_21,const_n_two),
_mm_mul_ps(image_22,const_n_one))))));
__m128 result = _mm_min_ps( _mm_set1_ps(255.0f),
_mm_max_ps( _mm_set1_ps(0.0f),
_mm_sqrt_ps(_mm_add_ps(_mm_mul_ps(gx, gx), _mm_mul_ps(gy,gy))) ));
__m128i pack_32 = _mm_cvtps_epi32(result); //R32,G32,B32,A32
__m128i pack_16 = _mm_packs_epi32(pack_32, pack_32); //R16,G16,B16,A16,R16,G16,B16,A16
__m128i pack_8 = _mm_packus_epi16(pack_16, pack_16); //RGBA,RGBA,RGBA,RGBA
__m128i unpack_2 = _mm_unpacklo_epi8(pack_8, pack_8); //RRGG,BBAA,RRGG,BBAA
__m128i unpack_4 = _mm_unpacklo_epi8(unpack_2, unpack_2); //RRRR,GGGG,BBBB,AAAA
_mm_storeu_si128((__m128i*)(screen+x),unpack_4);
}
image_0 += g_image_width;
image_1 += g_image_width;
image_2 += g_image_width;
screen += g_screen_width;
}
}