|
|
|
@ -6001,6 +6001,7 @@ struct Luv2RGB_b |
|
|
|
|
#elif CV_SSE2 |
|
|
|
|
v_scale = _mm_set1_ps(255.f); |
|
|
|
|
v_zero = _mm_setzero_si128(); |
|
|
|
|
v_alpha = _mm_set1_ps(ColorChannel<uchar>::max()); |
|
|
|
|
haveSIMD = checkHardwareSupport(CV_CPU_SSE2); |
|
|
|
|
#endif |
|
|
|
|
} |
|
|
|
@ -6163,6 +6164,32 @@ struct Luv2RGB_b |
|
|
|
|
if (jr) |
|
|
|
|
dst -= jr, j -= jr; |
|
|
|
|
} |
|
|
|
|
else if (dcn == 4 && haveSIMD) |
|
|
|
|
{ |
|
|
|
|
for ( ; j <= (dn * 3 - 12); j += 12, dst += 16) |
|
|
|
|
{ |
|
|
|
|
__m128 v_buf0 = _mm_mul_ps(_mm_load_ps(buf + j), v_scale); |
|
|
|
|
__m128 v_buf1 = _mm_mul_ps(_mm_load_ps(buf + j + 4), v_scale); |
|
|
|
|
__m128 v_buf2 = _mm_mul_ps(_mm_load_ps(buf + j + 8), v_scale); |
|
|
|
|
|
|
|
|
|
__m128 v_ba0 = _mm_unpackhi_ps(v_buf0, v_alpha); |
|
|
|
|
__m128 v_ba1 = _mm_unpacklo_ps(v_buf2, v_alpha); |
|
|
|
|
|
|
|
|
|
__m128i v_src0 = _mm_cvtps_epi32(_mm_shuffle_ps(v_buf0, v_ba0, 0x44)); |
|
|
|
|
__m128i v_src1 = _mm_shuffle_epi32(_mm_cvtps_epi32(_mm_shuffle_ps(v_ba0, v_buf1, 0x4e)), 0x78); |
|
|
|
|
__m128i v_src2 = _mm_cvtps_epi32(_mm_shuffle_ps(v_buf1, v_ba1, 0x4e)); |
|
|
|
|
__m128i v_src3 = _mm_shuffle_epi32(_mm_cvtps_epi32(_mm_shuffle_ps(v_ba1, v_buf2, 0xee)), 0x78); |
|
|
|
|
|
|
|
|
|
__m128i v_dst0 = _mm_packs_epi32(v_src0, v_src1); |
|
|
|
|
__m128i v_dst1 = _mm_packs_epi32(v_src2, v_src3); |
|
|
|
|
|
|
|
|
|
_mm_storeu_si128((__m128i *)dst, _mm_packus_epi16(v_dst0, v_dst1)); |
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
int jr = j % 3; |
|
|
|
|
if (jr) |
|
|
|
|
dst -= jr, j -= jr; |
|
|
|
|
} |
|
|
|
|
#endif |
|
|
|
|
|
|
|
|
|
for( ; j < dn*3; j += 3, dst += dcn ) |
|
|
|
@ -6184,6 +6211,7 @@ struct Luv2RGB_b |
|
|
|
|
uint8x8_t v_alpha; |
|
|
|
|
#elif CV_SSE2 |
|
|
|
|
__m128 v_scale; |
|
|
|
|
__m128 v_alpha; |
|
|
|
|
__m128i v_zero; |
|
|
|
|
bool haveSIMD; |
|
|
|
|
#endif |
|
|
|
|