1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
From 9744978dd7b9ca9dda0846fa82faf6fa264a52a7 Mon Sep 17 00:00:00 2001
From: conrad <conrad@9553f0bf-9b14-0410-a0b8-cfaf0461ba5b>
Date: Wed, 29 Apr 2009 11:31:43 +0000
Subject: [PATCH 06/27] ARM: NEON put_pixels_clamped
git-svn-id: file:///var/local/repositories/ffmpeg/trunk@18712 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b
---
libavcodec/arm/dsputil_neon.c | 2 ++
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 37425a3..9b95130 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 f16293d..a55e05f 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]!
--
1.6.3.3
|