__m64 b_lo = _mm_mullo_pi16 (_mm_unpacklo_pi8 (b, mm_zero), mm_wb); \
__m64 hi = _mm_add_pi16 (t_hi, b_hi); \
__m64 lo = _mm_add_pi16 (t_lo, b_lo); \
- vx += unit_x; \
/* calculate horizontal weights */ \
__m64 mm_wh = _mm_add_pi16 (mm_addc7, _mm_xor_si64 (mm_xorc7, \
_mm_srli_pi16 (mm_x, \
/* horizontal interpolation */ \
__m64 p = _mm_unpacklo_pi16 (lo, hi); \
__m64 q = _mm_unpackhi_pi16 (lo, hi); \
+ vx += unit_x; \
lo = _mm_madd_pi16 (p, mm_wh); \
hi = _mm_madd_pi16 (q, mm_wh); \
mm_x = _mm_add_pi16 (mm_x, mm_ux); \
#define BILINEAR_INTERPOLATE_ONE_PIXEL_HELPER(pix, phase) \
do { \
__m128i xmm_wh, xmm_a, xmm_b; \
- (void)xmm_ux4; /* suppress warning: unused variable 'xmm_ux4' */ \
/* fetch 2x2 pixel block into sse2 registers */ \
__m128i tltr = _mm_loadl_epi64 ((__m128i *)&src_top[vx >> 16]); \
__m128i blbr = _mm_loadl_epi64 ((__m128i *)&src_bottom[vx >> 16]); \
+ (void)xmm_ux4; /* suppress warning: unused variable 'xmm_ux4' */ \
vx += unit_x; \
/* vertical interpolation */ \
xmm_a = _mm_mullo_epi16 (_mm_unpacklo_epi8 (tltr, xmm_zero), xmm_wt); \