diff options
Diffstat (limited to 'libavcodec/i386/dsputil_mmx.c')
| -rw-r--r-- | libavcodec/i386/dsputil_mmx.c | 90 |
1 files changed, 90 insertions, 0 deletions
diff --git a/libavcodec/i386/dsputil_mmx.c b/libavcodec/i386/dsputil_mmx.c index 30e938312d..c0d5bfcaca 100644 --- a/libavcodec/i386/dsputil_mmx.c +++ b/libavcodec/i386/dsputil_mmx.c @@ -696,6 +696,94 @@ static void h263_h_loop_filter_mmx(uint8_t *src, int stride, int qscale){ } } +/* draw the edges of width 'w' of an image of size width, height + this mmx version can only handle w==8 || w==16 */ +static void draw_edges_mmx(uint8_t *buf, int wrap, int width, int height, int w) +{ + uint8_t *ptr, *last_line; + int i; + + last_line = buf + (height - 1) * wrap; + /* left and right */ + ptr = buf; + if(w==8) + { + asm volatile( + "1: \n\t" + "movd (%0), %%mm0 \n\t" + "punpcklbw %%mm0, %%mm0 \n\t" + "punpcklwd %%mm0, %%mm0 \n\t" + "punpckldq %%mm0, %%mm0 \n\t" + "movq %%mm0, -8(%0) \n\t" + "movq -8(%0, %2), %%mm1 \n\t" + "punpckhbw %%mm1, %%mm1 \n\t" + "punpckhwd %%mm1, %%mm1 \n\t" + "punpckhdq %%mm1, %%mm1 \n\t" + "movq %%mm1, (%0, %2) \n\t" + "add %1, %0 \n\t" + "cmp %3, %0 \n\t" + " jb 1b \n\t" + : "+r" (ptr) + : "r" ((long)wrap), "r" ((long)width), "r" (ptr + wrap*height) + ); + } + else + { + asm volatile( + "1: \n\t" + "movd (%0), %%mm0 \n\t" + "punpcklbw %%mm0, %%mm0 \n\t" + "punpcklwd %%mm0, %%mm0 \n\t" + "punpckldq %%mm0, %%mm0 \n\t" + "movq %%mm0, -8(%0) \n\t" + "movq %%mm0, -16(%0) \n\t" + "movq -8(%0, %2), %%mm1 \n\t" + "punpckhbw %%mm1, %%mm1 \n\t" + "punpckhwd %%mm1, %%mm1 \n\t" + "punpckhdq %%mm1, %%mm1 \n\t" + "movq %%mm1, (%0, %2) \n\t" + "movq %%mm1, 8(%0, %2) \n\t" + "add %1, %0 \n\t" + "cmp %3, %0 \n\t" + " jb 1b \n\t" + : "+r" (ptr) + : "r" ((long)wrap), "r" ((long)width), "r" (ptr + wrap*height) + ); + } + + for(i=0;i<w;i+=4) { + /* top and bottom (and hopefully also the corners) */ + ptr= buf - (i + 1) * wrap - w; + asm volatile( + "1: \n\t" + "movq (%1, %0), %%mm0 \n\t" + "movq %%mm0, (%0) \n\t" + "movq %%mm0, (%0, %2) \n\t" + "movq %%mm0, (%0, %2, 2) \n\t" + "movq %%mm0, (%0, %3) \n\t" + "add $8, %0 \n\t" + "cmp %4, %0 \n\t" + " jb 1b \n\t" + : "+r" (ptr) + : "r" ((long)buf - (long)ptr - w), "r" ((long)-wrap), "r" ((long)-wrap*3), "r" (ptr+width+2*w) + ); + ptr= last_line + (i + 1) * wrap - w; + asm volatile( + "1: \n\t" + "movq (%1, %0), %%mm0 \n\t" + "movq %%mm0, (%0) \n\t" + "movq %%mm0, (%0, %2) \n\t" + "movq %%mm0, (%0, %2, 2) \n\t" + "movq %%mm0, (%0, %3) \n\t" + "add $8, %0 \n\t" + "cmp %4, %0 \n\t" + " jb 1b \n\t" + : "+r" (ptr) + : "r" ((long)last_line - (long)ptr - w), "r" ((long)wrap), "r" ((long)wrap*3), "r" (ptr+width+2*w) + ); + } +} + #define PAETH(cpu, abs3)\ void add_png_paeth_prediction_##cpu(uint8_t *dst, uint8_t *src, uint8_t *top, int w, int bpp)\ {\ @@ -2075,6 +2163,8 @@ void dsputil_init_mmx(DSPContext* c, AVCodecContext *avctx) c->add_bytes= add_bytes_mmx; c->add_bytes_l2= add_bytes_l2_mmx; + c->draw_edges = draw_edges_mmx; + if (ENABLE_ANY_H263) { c->h263_v_loop_filter= h263_v_loop_filter_mmx; c->h263_h_loop_filter= h263_h_loop_filter_mmx; |