diff options
| author | Diego Biurrun <diego@biurrun.de> | 2014-02-03 11:13:59 -0800 |
|---|---|---|
| committer | Diego Biurrun <diego@biurrun.de> | 2014-07-06 14:48:50 -0700 |
| commit | 3c650efb81aaa3b395ba4606ee68a47ee4efb57b (patch) | |
| tree | 1f72694cf002091051d5f13bf25ec212dbbc5a01 /libavcodec/x86/mpegvideoencdsp_init.c | |
| parent | c166148409fe8f0dbccef2fe684286a40ba1e37d (diff) | |
| download | ffmpeg-3c650efb81aaa3b395ba4606ee68a47ee4efb57b.tar.gz | |
dsputil: Move draw_edges() to mpegvideoencdsp
Diffstat (limited to 'libavcodec/x86/mpegvideoencdsp_init.c')
| -rw-r--r-- | libavcodec/x86/mpegvideoencdsp_init.c | 99 |
1 files changed, 99 insertions, 0 deletions
diff --git a/libavcodec/x86/mpegvideoencdsp_init.c b/libavcodec/x86/mpegvideoencdsp_init.c index 4ef2f34961..7732e7307f 100644 --- a/libavcodec/x86/mpegvideoencdsp_init.c +++ b/libavcodec/x86/mpegvideoencdsp_init.c @@ -93,6 +93,101 @@ int ff_pix_norm1_mmx(uint8_t *pix, int line_size); #undef PHADDD #endif /* HAVE_SSSE3_INLINE */ +/* 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, int h, int sides) +{ + 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" ((x86_reg) wrap), "r" ((x86_reg) 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" ((x86_reg) wrap), "r" ((x86_reg) width), + "r" (ptr + wrap * height)); + } + + /* top and bottom (and hopefully also the corners) */ + if (sides & EDGE_TOP) { + for (i = 0; i < h; i += 4) { + 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" ((x86_reg) buf - (x86_reg) ptr - w), + "r" ((x86_reg) - wrap), "r" ((x86_reg) - wrap * 3), + "r" (ptr + width + 2 * w)); + } + } + + if (sides & EDGE_BOTTOM) { + for (i = 0; i < h; i += 4) { + 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" ((x86_reg) last_line - (x86_reg) ptr - w), + "r" ((x86_reg) wrap), "r" ((x86_reg) wrap * 3), + "r" (ptr + width + 2 * w)); + } + } +} + #endif /* HAVE_INLINE_ASM */ av_cold void ff_mpegvideoencdsp_init_x86(MpegvideoEncDSPContext *c, @@ -112,6 +207,10 @@ av_cold void ff_mpegvideoencdsp_init_x86(MpegvideoEncDSPContext *c, c->try_8x8basis = try_8x8basis_mmx; } c->add_8x8basis = add_8x8basis_mmx; + + if (avctx->bits_per_raw_sample <= 8) { + c->draw_edges = draw_edges_mmx; + } } if (INLINE_AMD3DNOW(cpu_flags)) { |