给定一个灰度的 cv::Mat (CV_8UC1),我想返回另一个包含元素平方根的 cv::Mat (CV_32FC1),并且我想使用 SSE2 指令集来完成。但是在将 8 位值转换为 32 浮点值以执行平方根时,我遇到了一些问题。我真的很感激任何帮助。这是我的代码(它不会给出正确的值):
uchar *source = (uchar *)cv::alignPtr(image.data, 16);
float *sqDataPtr = cv::alignPtr((float *)Squared.data, 16);
for (x = 0; x < (pixels - 16); x += 16) {
__m128i a0 = _mm_load_si128((__m128i *)(source + x));
__m128i first8 = _mm_unpacklo_epi8(a0, _mm_set1_epi8(0));
__m128i last8 = _mm_unpackhi_epi8(a0, _mm_set1_epi8(0));
__m128i first4i = _mm_unpacklo_epi16(first8, _mm_set1_epi16(0));
__m128i second4i = _mm_unpackhi_epi16(first8, _mm_set1_epi16(0));
__m128 first4 = _mm_cvtepi32_ps(first4i);
__m128 second4 = _mm_cvtepi32_ps(second4i);
__m128i third4i = _mm_unpacklo_epi16(last8, _mm_set1_epi16(0));
__m128i fourth4i = _mm_unpackhi_epi16(last8, _mm_set1_epi16(0));
__m128 third4 = _mm_cvtepi32_ps(third4i);
__m128 fourth4 = _mm_cvtepi32_ps(fourth4i);
// Store
_mm_store_ps(sqDataPtr + x, _mm_sqrt_ps(first4));
_mm_store_ps(sqDataPtr + x + 4, _mm_sqrt_ps(second4));
_mm_store_ps(sqDataPtr + x + 8, _mm_sqrt_ps(third4));
_mm_store_ps(sqDataPtr + x + 12, _mm_sqrt_ps(fourth4));
}