diff options
Diffstat (limited to 'core/src/fxcodec/fx_libopenjpeg/libopenjpeg20/mct.c')
| -rw-r--r-- | core/src/fxcodec/fx_libopenjpeg/libopenjpeg20/mct.c | 73 |
1 files changed, 36 insertions, 37 deletions
diff --git a/core/src/fxcodec/fx_libopenjpeg/libopenjpeg20/mct.c b/core/src/fxcodec/fx_libopenjpeg/libopenjpeg20/mct.c index 89f82225a0..60ee0969d5 100644 --- a/core/src/fxcodec/fx_libopenjpeg/libopenjpeg20/mct.c +++ b/core/src/fxcodec/fx_libopenjpeg/libopenjpeg20/mct.c @@ -150,43 +150,42 @@ void opj_mct_decode_real( { OPJ_UINT32 i; #ifdef __SSE__ - __m128 vrv, vgu, vgv, vbu; - vrv = _mm_set1_ps(1.402f); - vgu = _mm_set1_ps(0.34413f); - vgv = _mm_set1_ps(0.71414f); - vbu = _mm_set1_ps(1.772f); - for (i = 0; i < (n >> 3); ++i) { - __m128 vy, vu, vv; - __m128 vr, vg, vb; - - vy = _mm_load_ps(c0); - vu = _mm_load_ps(c1); - vv = _mm_load_ps(c2); - vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv)); - vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv)); - vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu)); - _mm_store_ps(c0, vr); - _mm_store_ps(c1, vg); - _mm_store_ps(c2, vb); - c0 += 4; - c1 += 4; - c2 += 4; - - vy = _mm_load_ps(c0); - vu = _mm_load_ps(c1); - vv = _mm_load_ps(c2); - vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv)); - vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv)); - vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu)); - _mm_store_ps(c0, vr); - _mm_store_ps(c1, vg); - _mm_store_ps(c2, vb); - c0 += 4; - c1 += 4; - c2 += 4; - } - n &= 7; - + __m128 vrv, vgu, vgv, vbu; + vrv = _mm_set1_ps(1.402f); + vgu = _mm_set1_ps(0.34413f); + vgv = _mm_set1_ps(0.71414f); + vbu = _mm_set1_ps(1.772f); + for (i = 0; i < (n >> 3); ++i) { + __m128 vy, vu, vv; + __m128 vr, vg, vb; + + vy = _mm_load_ps(c0); + vu = _mm_load_ps(c1); + vv = _mm_load_ps(c2); + vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv)); + vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv)); + vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu)); + _mm_store_ps(c0, vr); + _mm_store_ps(c1, vg); + _mm_store_ps(c2, vb); + c0 += 4; + c1 += 4; + c2 += 4; + + vy = _mm_load_ps(c0); + vu = _mm_load_ps(c1); + vv = _mm_load_ps(c2); + vr = _mm_add_ps(vy, _mm_mul_ps(vv, vrv)); + vg = _mm_sub_ps(_mm_sub_ps(vy, _mm_mul_ps(vu, vgu)), _mm_mul_ps(vv, vgv)); + vb = _mm_add_ps(vy, _mm_mul_ps(vu, vbu)); + _mm_store_ps(c0, vr); + _mm_store_ps(c1, vg); + _mm_store_ps(c2, vb); + c0 += 4; + c1 += 4; + c2 += 4; + } + n &= 7; #endif for(i = 0; i < n; ++i) { OPJ_FLOAT32 y = c0[i]; |