ARM: NEON put_pixels_clamped

Originally committed as revision 18712 to svn://svn.ffmpeg.org/ffmpeg/trunk

diff --git a/libavcodec/arm/dsputil_neon.c b/libavcodec/arm/dsputil_neon.c
index 37425a3..9b95130 100644 (file)
--- 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 f16293d..a55e05f 100644 (file)
--- 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]!