diff options
Diffstat (limited to 'src/libffmpeg/libavcodec/dsputil.h')
| -rw-r--r-- | src/libffmpeg/libavcodec/dsputil.h | 51 |
1 files changed, 51 insertions, 0 deletions
diff --git a/src/libffmpeg/libavcodec/dsputil.h b/src/libffmpeg/libavcodec/dsputil.h index dc3bc01e8..df7830564 100644 --- a/src/libffmpeg/libavcodec/dsputil.h +++ b/src/libffmpeg/libavcodec/dsputil.h @@ -38,6 +38,7 @@ //#define DEBUG /* dct code */ typedef short DCTELEM; +typedef int DWTELEM; void fdct_ifast (DCTELEM *data); void fdct_ifast248 (DCTELEM *data); @@ -55,6 +56,8 @@ void ff_fdct_sse2(DCTELEM *block); void ff_h264_idct8_add_c(uint8_t *dst, DCTELEM *block, int stride); void ff_h264_idct_add_c(uint8_t *dst, DCTELEM *block, int stride); +void ff_h264_idct8_dc_add_c(uint8_t *dst, DCTELEM *block, int stride); +void ff_h264_idct_dc_add_c(uint8_t *dst, DCTELEM *block, int stride); void ff_h264_lowres_idct_add_c(uint8_t *dst, int stride, DCTELEM *block); void ff_h264_lowres_idct_put_c(uint8_t *dst, int stride, DCTELEM *block); @@ -76,6 +79,15 @@ void ff_vp3_idct_c(DCTELEM *block/* align 16*/); void ff_vp3_idct_put_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/); void ff_vp3_idct_add_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/); +/* 1/2^n downscaling functions from imgconvert.c */ +void ff_img_copy_plane(uint8_t *dst, int dst_wrap, const uint8_t *src, int src_wrap, int width, int height); +void ff_shrink22(uint8_t *dst, int dst_wrap, const uint8_t *src, int src_wrap, int width, int height); +void ff_shrink44(uint8_t *dst, int dst_wrap, const uint8_t *src, int src_wrap, int width, int height); +void ff_shrink88(uint8_t *dst, int dst_wrap, const uint8_t *src, int src_wrap, int width, int height); + +void ff_gmc_c(uint8_t *dst, uint8_t *src, int stride, int h, int ox, int oy, + int dxx, int dxy, int dyx, int dyy, int shift, int r, int width, int height); + /* minimum alignment rules ;) if u notice errors in the align stuff, need more alignment for some asm code for some cpu or need to use a function with less aligned data then send a mail to the ffmpeg-dev list, ... @@ -134,6 +146,9 @@ static void a(uint8_t *block, const uint8_t *pixels, int line_size, int h){\ typedef int (*me_cmp_func)(void /*MpegEncContext*/ *s, uint8_t *blk1/*align width (8 or 16)*/, uint8_t *blk2/*align 1*/, int line_size, int h)/* __attribute__ ((const))*/; +// for snow slices +typedef struct slice_buffer_s slice_buffer; + /** * DSPContext. */ @@ -262,6 +277,15 @@ typedef struct DSPContext { h264_weight_func weight_h264_pixels_tab[10]; h264_biweight_func biweight_h264_pixels_tab[10]; + /* AVS specific */ + qpel_mc_func put_cavs_qpel_pixels_tab[2][16]; + qpel_mc_func avg_cavs_qpel_pixels_tab[2][16]; + void (*cavs_filter_lv)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); + void (*cavs_filter_lh)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); + void (*cavs_filter_cv)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); + void (*cavs_filter_ch)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); + void (*cavs_idct8_add)(uint8_t *dst, DCTELEM *block, int stride); + me_cmp_func pix_abs[2][4]; /* huffyuv specific */ @@ -333,6 +357,29 @@ typedef struct DSPContext { void (*h264_idct_add)(uint8_t *dst, DCTELEM *block, int stride); void (*h264_idct8_add)(uint8_t *dst, DCTELEM *block, int stride); + void (*h264_idct_dc_add)(uint8_t *dst, DCTELEM *block, int stride); + void (*h264_idct8_dc_add)(uint8_t *dst, DCTELEM *block, int stride); + + /* snow wavelet */ + void (*vertical_compose97i)(DWTELEM *b0, DWTELEM *b1, DWTELEM *b2, DWTELEM *b3, DWTELEM *b4, DWTELEM *b5, int width); + void (*horizontal_compose97i)(DWTELEM *b, int width); + void (*inner_add_yblock)(uint8_t *obmc, const int obmc_stride, uint8_t * * block, int b_w, int b_h, int src_x, int src_y, int src_stride, slice_buffer * sb, int add, uint8_t * dst8); + + void (*prefetch)(void *mem, int stride, int h); + + void (*shrink[4])(uint8_t *dst, int dst_wrap, const uint8_t *src, int src_wrap, int width, int height); + + /* vc1 functions */ + void (*vc1_inv_trans_8x8)(DCTELEM *b); + void (*vc1_inv_trans_8x4)(DCTELEM *b, int n); + void (*vc1_inv_trans_4x8)(DCTELEM *b, int n); + void (*vc1_inv_trans_4x4)(DCTELEM *b, int n); + void (*vc1_v_overlap)(uint8_t* src, int stride, int rnd); + void (*vc1_h_overlap)(uint8_t* src, int stride, int rnd); + /* put 8x8 block with bicubic interpolation and quarterpel precision + * last argument is actually round value instead of height + */ + op_pixels_func put_vc1_mspel_pixels_tab[16]; } DSPContext; void dsputil_static_init(void); @@ -409,6 +456,7 @@ int mm_support(void); #define MM_SSE 0x0008 /* SSE functions */ #define MM_SSE2 0x0010 /* PIV SSE2 functions */ #define MM_3DNOWEXT 0x0020 /* AMD 3DNowExt */ +#define MM_SSE3 0x0040 /* Prescott SSE3 functions */ extern int mm_flags; @@ -531,6 +579,7 @@ struct unaligned_16 { uint16_t l; } __attribute__((packed)); #define LD32(a) (*((uint32_t*)(a))) #define LD64(a) (*((uint64_t*)(a))) +#define ST16(a, b) *((uint16_t*)(a)) = (b) #define ST32(a, b) *((uint32_t*)(a)) = (b) #endif /* !__GNUC__ */ @@ -563,6 +612,8 @@ int ff_fft_init(FFTContext *s, int nbits, int inverse); void ff_fft_permute(FFTContext *s, FFTComplex *z); void ff_fft_calc_c(FFTContext *s, FFTComplex *z); void ff_fft_calc_sse(FFTContext *s, FFTComplex *z); +void ff_fft_calc_3dn(FFTContext *s, FFTComplex *z); +void ff_fft_calc_3dn2(FFTContext *s, FFTComplex *z); void ff_fft_calc_altivec(FFTContext *s, FFTComplex *z); static inline void ff_fft_calc(FFTContext *s, FFTComplex *z) |