|
|
|
@ -33,17 +33,17 @@ void ff_put_pixels4_mmxext(uint8_t *block, const uint8_t *pixels, |
|
|
|
|
ptrdiff_t line_size, int h); |
|
|
|
|
void ff_avg_pixels4_mmxext(uint8_t *block, const uint8_t *pixels, |
|
|
|
|
ptrdiff_t line_size, int h); |
|
|
|
|
void ff_put_pixels4_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, |
|
|
|
|
void ff_put_pixels4_l2_mmxext(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, |
|
|
|
|
int dstStride, int src1Stride, int h); |
|
|
|
|
void ff_avg_pixels4_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, |
|
|
|
|
void ff_avg_pixels4_l2_mmxext(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, |
|
|
|
|
int dstStride, int src1Stride, int h); |
|
|
|
|
void ff_put_pixels8_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, |
|
|
|
|
void ff_put_pixels8_l2_mmxext(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, |
|
|
|
|
int dstStride, int src1Stride, int h); |
|
|
|
|
void ff_avg_pixels8_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, |
|
|
|
|
void ff_avg_pixels8_l2_mmxext(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, |
|
|
|
|
int dstStride, int src1Stride, int h); |
|
|
|
|
void ff_put_pixels16_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, |
|
|
|
|
void ff_put_pixels16_l2_mmxext(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, |
|
|
|
|
int dstStride, int src1Stride, int h); |
|
|
|
|
void ff_avg_pixels16_l2_mmxext(uint8_t *dst, uint8_t *src1, uint8_t *src2, |
|
|
|
|
void ff_avg_pixels16_l2_mmxext(uint8_t *dst, const uint8_t *src1, const uint8_t *src2, |
|
|
|
|
int dstStride, int src1Stride, int h); |
|
|
|
|
#define ff_put_pixels8_l2_sse2 ff_put_pixels8_l2_mmxext |
|
|
|
|
#define ff_avg_pixels8_l2_sse2 ff_avg_pixels8_l2_mmxext |
|
|
|
@ -54,29 +54,29 @@ CALL_2X_PIXELS(ff_avg_pixels16_mmxext, ff_avg_pixels8_mmxext, 8) |
|
|
|
|
CALL_2X_PIXELS(ff_put_pixels16_mmxext, ff_put_pixels8_mmxext, 8) |
|
|
|
|
|
|
|
|
|
#define DEF_QPEL(OPNAME)\ |
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_h_lowpass_mmxext(uint8_t *dst, uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_mmxext(uint8_t *dst, uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_ssse3(uint8_t *dst, uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_h_lowpass_l2_mmxext(uint8_t *dst, uint8_t *src, uint8_t *src2, int dstStride, int src2Stride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_l2_mmxext(uint8_t *dst, uint8_t *src, uint8_t *src2, int dstStride, int src2Stride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_l2_ssse3(uint8_t *dst, uint8_t *src, uint8_t *src2, int dstStride, int src2Stride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_v_lowpass_mmxext(uint8_t *dst, uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_v_lowpass_op_mmxext(uint8_t *dst, uint8_t *src, int dstStride, int srcStride, int h);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_v_lowpass_sse2(uint8_t *dst, uint8_t *src, int dstStride, int srcStride, int h);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_hv_lowpass_v_mmxext(uint8_t *src, int16_t *tmp, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_h_lowpass_mmxext(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_mmxext(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_ssse3(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_h_lowpass_l2_mmxext(uint8_t *dst, const uint8_t *src, const uint8_t *src2, int dstStride, int src2Stride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_l2_mmxext(uint8_t *dst, const uint8_t *src, const uint8_t *src2, int dstStride, int src2Stride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8_h_lowpass_l2_ssse3(uint8_t *dst, const uint8_t *src, const uint8_t *src2, int dstStride, int src2Stride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_v_lowpass_mmxext(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_v_lowpass_op_mmxext(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_v_lowpass_sse2(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_hv_lowpass_v_mmxext(const uint8_t *src, int16_t *tmp, int srcStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel4_hv_lowpass_h_mmxext(int16_t *tmp, uint8_t *dst, int dstStride);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_hv1_lowpass_op_mmxext(uint8_t *src, int16_t *tmp, int srcStride, int size);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_hv1_lowpass_op_sse2(uint8_t *src, int16_t *tmp, int srcStride, int size);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_hv1_lowpass_op_mmxext(const uint8_t *src, int16_t *tmp, int srcStride, int size);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_hv1_lowpass_op_sse2(const uint8_t *src, int16_t *tmp, int srcStride, int size);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_hv2_lowpass_op_mmxext(uint8_t *dst, int16_t *tmp, int dstStride, int unused, int h);\
|
|
|
|
|
void ff_ ## OPNAME ## _h264_qpel8or16_hv2_lowpass_ssse3(uint8_t *dst, int16_t *tmp, int dstStride, int tmpStride, int size);\
|
|
|
|
|
void ff_ ## OPNAME ## _pixels4_l2_shift5_mmxext(uint8_t *dst, int16_t *src16, uint8_t *src8, int dstStride, int src8Stride, int h);\
|
|
|
|
|
void ff_ ## OPNAME ## _pixels8_l2_shift5_mmxext(uint8_t *dst, int16_t *src16, uint8_t *src8, int dstStride, int src8Stride, int h); |
|
|
|
|
void ff_ ## OPNAME ## _pixels4_l2_shift5_mmxext(uint8_t *dst, const int16_t *src16, const uint8_t *src8, int dstStride, int src8Stride, int h);\
|
|
|
|
|
void ff_ ## OPNAME ## _pixels8_l2_shift5_mmxext(uint8_t *dst, const int16_t *src16, const uint8_t *src8, int dstStride, int src8Stride, int h); |
|
|
|
|
|
|
|
|
|
DEF_QPEL(avg) |
|
|
|
|
DEF_QPEL(put) |
|
|
|
|
|
|
|
|
|
#define QPEL_H264(OPNAME, OP, MMX)\ |
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel4_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel4_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
int w=3;\
|
|
|
|
|
src -= 2*srcStride+2;\
|
|
|
|
|
while(w--){\
|
|
|
|
@ -88,14 +88,14 @@ static av_always_inline void ff_ ## OPNAME ## h264_qpel4_hv_lowpass_ ## MMX(uint |
|
|
|
|
ff_ ## OPNAME ## h264_qpel4_hv_lowpass_h_mmxext(tmp, dst, dstStride);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(uint8_t *dst, uint8_t *src, int dstStride, int srcStride, int h){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride, int h){\
|
|
|
|
|
src -= 2*srcStride;\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_op_mmxext(dst, src, dstStride, srcStride, h);\
|
|
|
|
|
src += 4;\
|
|
|
|
|
dst += 4;\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_op_mmxext(dst, src, dstStride, srcStride, h);\
|
|
|
|
|
}\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_hv1_lowpass_ ## MMX(int16_t *tmp, uint8_t *src, int tmpStride, int srcStride, int size){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_hv1_lowpass_ ## MMX(int16_t *tmp, const uint8_t *src, int tmpStride, int srcStride, int size){\
|
|
|
|
|
int w = (size+8)>>2;\
|
|
|
|
|
src -= 2*srcStride+2;\
|
|
|
|
|
while(w--){\
|
|
|
|
@ -113,15 +113,15 @@ static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_hv2_lowpass_ ## MMX |
|
|
|
|
}while(w--);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_v_lowpass_ ## MMX(uint8_t *dst, uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_v_lowpass_ ## MMX(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(dst , src , dstStride, srcStride, 8);\
|
|
|
|
|
}\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_v_lowpass_ ## MMX(uint8_t *dst, uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_v_lowpass_ ## MMX(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(dst , src , dstStride, srcStride, 16);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(dst+8, src+8, dstStride, srcStride, 16);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_ ## MMX(uint8_t *dst, uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_ ## MMX(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_ ## MMX(dst , src , dstStride, srcStride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_ ## MMX(dst+8, src+8, dstStride, srcStride);\
|
|
|
|
|
src += 8*srcStride;\
|
|
|
|
@ -130,7 +130,7 @@ static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_ ## MMX(uint |
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_ ## MMX(dst+8, src+8, dstStride, srcStride);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_l2_ ## MMX(uint8_t *dst, uint8_t *src, uint8_t *src2, int dstStride, int src2Stride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_l2_ ## MMX(uint8_t *dst, const uint8_t *src, const uint8_t *src2, int dstStride, int src2Stride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_l2_ ## MMX(dst , src , src2 , dstStride, src2Stride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_l2_ ## MMX(dst+8, src+8, src2+8, dstStride, src2Stride);\
|
|
|
|
|
src += 8*dstStride;\
|
|
|
|
@ -140,19 +140,19 @@ static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_l2_ ## MMX(u |
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_l2_ ## MMX(dst+8, src+8, src2+8, dstStride, src2Stride);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, uint8_t *src, int dstStride, int tmpStride, int srcStride, int size){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride, int size){\
|
|
|
|
|
ff_put_h264_qpel8or16_hv1_lowpass_ ## MMX(tmp, src, tmpStride, srcStride, size);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_hv2_lowpass_ ## MMX(dst, tmp, dstStride, tmpStride, size);\
|
|
|
|
|
}\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(dst , tmp , src , dstStride, tmpStride, srcStride, 8);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(dst , tmp , src , dstStride, tmpStride, srcStride, 16);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## pixels16_l2_shift5_ ## MMX(uint8_t *dst, int16_t *src16, uint8_t *src8, int dstStride, int src8Stride, int h)\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## pixels16_l2_shift5_ ## MMX(uint8_t *dst, const int16_t *src16, const uint8_t *src8, int dstStride, int src8Stride, int h)\
|
|
|
|
|
{\
|
|
|
|
|
ff_ ## OPNAME ## pixels8_l2_shift5_ ## MMX(dst , src16 , src8 , dstStride, src8Stride, h);\
|
|
|
|
|
ff_ ## OPNAME ## pixels8_l2_shift5_ ## MMX(dst+8, src16+8, src8+8, dstStride, src8Stride, h);\
|
|
|
|
@ -162,12 +162,12 @@ static av_always_inline void ff_ ## OPNAME ## pixels16_l2_shift5_ ## MMX(uint8_t |
|
|
|
|
#if ARCH_X86_64 |
|
|
|
|
#define QPEL_H264_H16_XMM(OPNAME, OP, MMX)\ |
|
|
|
|
|
|
|
|
|
void ff_avg_h264_qpel16_h_lowpass_l2_ssse3(uint8_t *dst, uint8_t *src, uint8_t *src2, int dstStride, int src2Stride); |
|
|
|
|
void ff_put_h264_qpel16_h_lowpass_l2_ssse3(uint8_t *dst, uint8_t *src, uint8_t *src2, int dstStride, int src2Stride); |
|
|
|
|
void ff_avg_h264_qpel16_h_lowpass_l2_ssse3(uint8_t *dst, const uint8_t *src, const uint8_t *src2, int dstStride, int src2Stride); |
|
|
|
|
void ff_put_h264_qpel16_h_lowpass_l2_ssse3(uint8_t *dst, const uint8_t *src, const uint8_t *src2, int dstStride, int src2Stride); |
|
|
|
|
|
|
|
|
|
#else // ARCH_X86_64
|
|
|
|
|
#define QPEL_H264_H16_XMM(OPNAME, OP, MMX)\ |
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_l2_ ## MMX(uint8_t *dst, uint8_t *src, uint8_t *src2, int dstStride, int src2Stride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_l2_ ## MMX(uint8_t *dst, const uint8_t *src, const uint8_t *src2, int dstStride, int src2Stride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_l2_ ## MMX(dst , src , src2 , dstStride, src2Stride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_l2_ ## MMX(dst+8, src+8, src2+8, dstStride, src2Stride);\
|
|
|
|
|
src += 8*dstStride;\
|
|
|
|
@ -180,7 +180,7 @@ static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_l2_ ## MMX(u |
|
|
|
|
|
|
|
|
|
#define QPEL_H264_H_XMM(OPNAME, OP, MMX)\ |
|
|
|
|
QPEL_H264_H16_XMM(OPNAME, OP, MMX)\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_ ## MMX(uint8_t *dst, uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_ ## MMX(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_ ## MMX(dst , src , dstStride, srcStride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8_h_lowpass_ ## MMX(dst+8, src+8, dstStride, srcStride);\
|
|
|
|
|
src += 8*srcStride;\
|
|
|
|
@ -190,16 +190,16 @@ static av_always_inline void ff_ ## OPNAME ## h264_qpel16_h_lowpass_ ## MMX(uint |
|
|
|
|
}\
|
|
|
|
|
|
|
|
|
|
#define QPEL_H264_V_XMM(OPNAME, OP, MMX)\ |
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_v_lowpass_ ## MMX(uint8_t *dst, uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_v_lowpass_ ## MMX(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(dst , src , dstStride, srcStride, 8);\
|
|
|
|
|
}\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_v_lowpass_ ## MMX(uint8_t *dst, uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_v_lowpass_ ## MMX(uint8_t *dst, const uint8_t *src, int dstStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(dst , src , dstStride, srcStride, 16);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_v_lowpass_ ## MMX(dst+8, src+8, dstStride, srcStride, 16);\
|
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
static av_always_inline void put_h264_qpel8or16_hv1_lowpass_sse2(int16_t *tmp, |
|
|
|
|
uint8_t *src, |
|
|
|
|
const uint8_t *src, |
|
|
|
|
int tmpStride, |
|
|
|
|
int srcStride, |
|
|
|
|
int size) |
|
|
|
@ -214,14 +214,14 @@ static av_always_inline void put_h264_qpel8or16_hv1_lowpass_sse2(int16_t *tmp, |
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
#define QPEL_H264_HV_XMM(OPNAME, OP, MMX)\ |
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, uint8_t *src, int dstStride, int tmpStride, int srcStride, int size){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride, int size){\
|
|
|
|
|
put_h264_qpel8or16_hv1_lowpass_sse2(tmp, src, tmpStride, srcStride, size);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_hv2_lowpass_ ## MMX(dst, tmp, dstStride, tmpStride, size);\
|
|
|
|
|
}\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel8_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(dst, tmp, src, dstStride, tmpStride, srcStride, 8);\
|
|
|
|
|
}\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
static av_always_inline void ff_ ## OPNAME ## h264_qpel16_hv_lowpass_ ## MMX(uint8_t *dst, int16_t *tmp, const uint8_t *src, int dstStride, int tmpStride, int srcStride){\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel8or16_hv_lowpass_ ## MMX(dst, tmp, src, dstStride, tmpStride, srcStride, 16);\
|
|
|
|
|
}\
|
|
|
|
|
|
|
|
|
@ -244,12 +244,12 @@ H264_MC_V(OPNAME, SIZE, MMX, ALIGN)\ |
|
|
|
|
H264_MC_H(OPNAME, SIZE, MMX, ALIGN)\
|
|
|
|
|
H264_MC_HV(OPNAME, SIZE, MMX, ALIGN)\
|
|
|
|
|
|
|
|
|
|
static void put_h264_qpel16_mc00_sse2 (uint8_t *dst, uint8_t *src, |
|
|
|
|
static void put_h264_qpel16_mc00_sse2 (uint8_t *dst, const uint8_t *src, |
|
|
|
|
ptrdiff_t stride) |
|
|
|
|
{ |
|
|
|
|
ff_put_pixels16_sse2(dst, src, stride, 16); |
|
|
|
|
} |
|
|
|
|
static void avg_h264_qpel16_mc00_sse2 (uint8_t *dst, uint8_t *src, |
|
|
|
|
static void avg_h264_qpel16_mc00_sse2 (uint8_t *dst, const uint8_t *src, |
|
|
|
|
ptrdiff_t stride) |
|
|
|
|
{ |
|
|
|
|
ff_avg_pixels16_sse2(dst, src, stride, 16); |
|
|
|
@ -258,41 +258,41 @@ static void avg_h264_qpel16_mc00_sse2 (uint8_t *dst, uint8_t *src, |
|
|
|
|
#define avg_h264_qpel8_mc00_sse2 avg_h264_qpel8_mc00_mmxext |
|
|
|
|
|
|
|
|
|
#define H264_MC_C(OPNAME, SIZE, MMX, ALIGN) \ |
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc00_ ## MMX (uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc00_ ## MMX (uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
ff_ ## OPNAME ## pixels ## SIZE ## _ ## MMX(dst, src, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
|
|
|
|
|
#define H264_MC_H(OPNAME, SIZE, MMX, ALIGN) \ |
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc10_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc10_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src, src, stride, stride);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc20_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc20_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_ ## MMX(dst, src, stride, stride);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc30_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc30_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src, src+1, stride, stride);\
|
|
|
|
|
}\
|
|
|
|
|
|
|
|
|
|
#define H264_MC_V(OPNAME, SIZE, MMX, ALIGN) \ |
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc01_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc01_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*SIZE];\
|
|
|
|
|
ff_put_h264_qpel ## SIZE ## _v_lowpass_ ## MMX(temp, src, SIZE, stride);\
|
|
|
|
|
ff_ ## OPNAME ## pixels ## SIZE ## _l2_ ## MMX(dst, src, temp, stride, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc02_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc02_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _v_lowpass_ ## MMX(dst, src, stride, stride);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc03_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc03_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*SIZE];\
|
|
|
|
|
ff_put_h264_qpel ## SIZE ## _v_lowpass_ ## MMX(temp, src, SIZE, stride);\
|
|
|
|
@ -300,41 +300,41 @@ static void OPNAME ## h264_qpel ## SIZE ## _mc03_ ## MMX(uint8_t *dst, uint8_t * |
|
|
|
|
}\
|
|
|
|
|
|
|
|
|
|
#define H264_MC_HV(OPNAME, SIZE, MMX, ALIGN) \ |
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc11_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc11_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*SIZE];\
|
|
|
|
|
ff_put_h264_qpel ## SIZE ## _v_lowpass_ ## MMX(temp, src, SIZE, stride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src, temp, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc31_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc31_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*SIZE];\
|
|
|
|
|
ff_put_h264_qpel ## SIZE ## _v_lowpass_ ## MMX(temp, src+1, SIZE, stride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src, temp, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc13_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc13_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*SIZE];\
|
|
|
|
|
ff_put_h264_qpel ## SIZE ## _v_lowpass_ ## MMX(temp, src, SIZE, stride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src+stride, temp, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc33_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc33_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*SIZE];\
|
|
|
|
|
ff_put_h264_qpel ## SIZE ## _v_lowpass_ ## MMX(temp, src+1, SIZE, stride);\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src+stride, temp, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc22_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc22_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint16_t, temp)[SIZE*(SIZE<8?12:24)];\
|
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _hv_lowpass_ ## MMX(dst, temp, src, stride, SIZE, stride);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc21_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc21_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*(SIZE<8?12:24)*2 + SIZE*SIZE];\
|
|
|
|
|
uint8_t * const halfHV= temp;\
|
|
|
|
@ -344,7 +344,7 @@ static void OPNAME ## h264_qpel ## SIZE ## _mc21_ ## MMX(uint8_t *dst, uint8_t * |
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src, halfHV, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc23_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc23_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*(SIZE<8?12:24)*2 + SIZE*SIZE];\
|
|
|
|
|
uint8_t * const halfHV= temp;\
|
|
|
|
@ -354,7 +354,7 @@ static void OPNAME ## h264_qpel ## SIZE ## _mc23_ ## MMX(uint8_t *dst, uint8_t * |
|
|
|
|
ff_ ## OPNAME ## h264_qpel ## SIZE ## _h_lowpass_l2_ ## MMX(dst, src+stride, halfHV, stride, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc12_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc12_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*(SIZE<8?12:24)*2 + SIZE*SIZE];\
|
|
|
|
|
uint8_t * const halfHV= temp;\
|
|
|
|
@ -364,7 +364,7 @@ static void OPNAME ## h264_qpel ## SIZE ## _mc12_ ## MMX(uint8_t *dst, uint8_t * |
|
|
|
|
ff_ ## OPNAME ## pixels ## SIZE ## _l2_shift5_mmxext(dst, halfV+2, halfHV, stride, SIZE, SIZE);\
|
|
|
|
|
}\
|
|
|
|
|
\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc32_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
static void OPNAME ## h264_qpel ## SIZE ## _mc32_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride)\
|
|
|
|
|
{\
|
|
|
|
|
DECLARE_ALIGNED(ALIGN, uint8_t, temp)[SIZE*(SIZE<8?12:24)*2 + SIZE*SIZE];\
|
|
|
|
|
uint8_t * const halfHV= temp;\
|
|
|
|
@ -409,7 +409,7 @@ H264_MC_816(H264_MC_HV, ssse3) |
|
|
|
|
//10bit
|
|
|
|
|
#define LUMA_MC_OP(OP, NUM, DEPTH, TYPE, OPT) \ |
|
|
|
|
void ff_ ## OP ## _h264_qpel ## NUM ## _ ## TYPE ## _ ## DEPTH ## _ ## OPT \
|
|
|
|
|
(uint8_t *dst, uint8_t *src, ptrdiff_t stride); |
|
|
|
|
(uint8_t *dst, const uint8_t *src, ptrdiff_t stride); |
|
|
|
|
|
|
|
|
|
#define LUMA_MC_ALL(DEPTH, TYPE, OPT) \ |
|
|
|
|
LUMA_MC_OP(put, 4, DEPTH, TYPE, OPT) \
|
|
|
|
@ -466,7 +466,7 @@ LUMA_MC_816(10, mc23, sse2) |
|
|
|
|
LUMA_MC_816(10, mc33, sse2) |
|
|
|
|
|
|
|
|
|
#define QPEL16_OPMC(OP, MC, MMX)\ |
|
|
|
|
void ff_ ## OP ## _h264_qpel16_ ## MC ## _10_ ## MMX(uint8_t *dst, uint8_t *src, ptrdiff_t stride){\
|
|
|
|
|
void ff_ ## OP ## _h264_qpel16_ ## MC ## _10_ ## MMX(uint8_t *dst, const uint8_t *src, ptrdiff_t stride){\
|
|
|
|
|
ff_ ## OP ## _h264_qpel8_ ## MC ## _10_ ## MMX(dst , src , stride);\
|
|
|
|
|
ff_ ## OP ## _h264_qpel8_ ## MC ## _10_ ## MMX(dst+16, src+16, stride);\
|
|
|
|
|
src += 8*stride;\
|
|
|
|
|