diff options
| author | David Conrad <lessen42@gmail.com> | 2009-04-29 11:31:43 +0000 |
|---|---|---|
| committer | David Conrad <lessen42@gmail.com> | 2009-04-29 11:31:43 +0000 |
| commit | 428bf2ac88d6f75482d9fec999b3b9fcfca19e5e (patch) | |
| tree | 3b5a9b6bb2a1596dfcbf308a9b06050ee5b302f1 | |
| parent | 4b11e833b886045d89d4435fac5cf0b2275dc7e9 (diff) | |
| download | ffmpeg-428bf2ac88d6f75482d9fec999b3b9fcfca19e5e.tar.gz | |
ARM: NEON put_pixels_clamped
Originally committed as revision 18712 to svn://svn.ffmpeg.org/ffmpeg/trunk
| -rw-r--r-- | libavcodec/arm/dsputil_neon.c | 2 | ||||
| -rw-r--r-- | libavcodec/arm/dsputil_neon_s.S | 24 |
2 files changed, 26 insertions, 0 deletions
diff --git a/libavcodec/arm/dsputil_neon.c b/libavcodec/arm/dsputil_neon.c index 37425a31f9..9b9513001a 100644 --- a/libavcodec/arm/dsputil_neon.c +++ b/libavcodec/arm/dsputil_neon.c @@ -42,6 +42,7 @@ void ff_put_pixels8_xy2_no_rnd_neon(uint8_t *, const uint8_t *, int, int); void ff_avg_pixels16_neon(uint8_t *, const uint8_t *, int, int); void ff_add_pixels_clamped_neon(const DCTELEM *, uint8_t *, int); +void ff_put_pixels_clamped_neon(const DCTELEM *, uint8_t *, int); void ff_put_signed_pixels_clamped_neon(const DCTELEM *, uint8_t *, int); void ff_put_h264_qpel16_mc00_neon(uint8_t *, uint8_t *, int); @@ -180,6 +181,7 @@ void ff_dsputil_init_neon(DSPContext *c, AVCodecContext *avctx) c->avg_pixels_tab[0][0] = ff_avg_pixels16_neon; c->add_pixels_clamped = ff_add_pixels_clamped_neon; + c->put_pixels_clamped = ff_put_pixels_clamped_neon; c->put_signed_pixels_clamped = ff_put_signed_pixels_clamped_neon; c->put_h264_chroma_pixels_tab[0] = ff_put_h264_chroma_mc8_neon; diff --git a/libavcodec/arm/dsputil_neon_s.S b/libavcodec/arm/dsputil_neon_s.S index f16293db03..a55e05f3dc 100644 --- a/libavcodec/arm/dsputil_neon_s.S +++ b/libavcodec/arm/dsputil_neon_s.S @@ -273,6 +273,30 @@ function ff_put_h264_qpel8_mc00_neon, export=1 pixfunc2 put_ pixels8_y2, _no_rnd, vhadd.u8 pixfunc2 put_ pixels8_xy2, _no_rnd, vshrn.u16, 1 +function ff_put_pixels_clamped_neon, export=1 + vld1.64 {d16-d19}, [r0,:128]! + vqmovun.s16 d0, q8 + vld1.64 {d20-d23}, [r0,:128]! + vqmovun.s16 d1, q9 + vld1.64 {d24-d27}, [r0,:128]! + vqmovun.s16 d2, q10 + vld1.64 {d28-d31}, [r0,:128]! + vqmovun.s16 d3, q11 + vst1.64 {d0}, [r1,:64], r2 + vqmovun.s16 d4, q12 + vst1.64 {d1}, [r1,:64], r2 + vqmovun.s16 d5, q13 + vst1.64 {d2}, [r1,:64], r2 + vqmovun.s16 d6, q14 + vst1.64 {d3}, [r1,:64], r2 + vqmovun.s16 d7, q15 + vst1.64 {d4}, [r1,:64], r2 + vst1.64 {d5}, [r1,:64], r2 + vst1.64 {d6}, [r1,:64], r2 + vst1.64 {d7}, [r1,:64], r2 + bx lr + .endfunc + function ff_put_signed_pixels_clamped_neon, export=1 vmov.u8 d31, #128 vld1.64 {d16-d17}, [r0,:128]! |