[FFmpeg-cvslog] lavc/aarch64: add clip N macro

[J. Dekker]

ffmpeg | branch: master | J. Dekker <jdek at itanimul.li> | Wed Mar 22 00:57:00 2023 +0100| [37cde570bc2dcd64a15c5d9a37b9fa0d78d84f9f] | committer: J. Dekker

lavc/aarch64: add clip N macro

Signed-off-by: J. Dekker <jdek at itanimul.li>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=37cde570bc2dcd64a15c5d9a37b9fa0d78d84f9f
---

 libavcodec/aarch64/hevcdsp_idct_neon.S | 19 +++++--------------
 libavcodec/aarch64/neon.S              | 11 +++++++++++
 2 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/libavcodec/aarch64/hevcdsp_idct_neon.S b/libavcodec/aarch64/hevcdsp_idct_neon.S
index 467cb0f48a..3e59dd20bb 100644
--- a/libavcodec/aarch64/hevcdsp_idct_neon.S
+++ b/libavcodec/aarch64/hevcdsp_idct_neon.S
@@ -5,7 +5,7 @@
  *
  * Ported from arm/hevcdsp_idct_neon.S by
  * Copyright (c) 2020 Reimar Döffinger
- * Copyright (c) 2020 J. Dekker
+ * Copyright (c) 2023 J. Dekker <jdek at itanimul.li>
  *
  * This file is part of FFmpeg.
  *
@@ -38,13 +38,6 @@ const trans, align=4
         .short          31, 22, 13, 4
 endconst
 
-.macro clip2 in1, in2, min, max
-        smax            \in1, \in1, \min
-        smax            \in2, \in2, \min
-        smin            \in1, \in1, \max
-        smin            \in2, \in2, \max
-.endm
-
 function ff_hevc_add_residual_4x4_8_neon, export=1
         ld1             {v0.8h-v1.8h}, [x1]
         ld1             {v2.s}[0], [x0], x2
@@ -182,7 +175,7 @@ function hevc_add_residual_4x4_16_neon, export=0
         ld1             {v3.d}[1], [x12], x2
         movi            v4.8h, #0
         sqadd           v1.8h, v1.8h, v3.8h
-        clip2           v0.8h, v1.8h, v4.8h, v21.8h
+        clip            v4.8h, v21.8h, v0.8h, v1.8h
         st1             {v0.d}[0], [x0],  x2
         st1             {v0.d}[1], [x0],  x2
         st1             {v1.d}[0], [x0],  x2
@@ -201,7 +194,7 @@ function hevc_add_residual_8x8_16_neon, export=0
         sqadd           v0.8h, v0.8h, v2.8h
         ld1             {v3.8h}, [x12]
         sqadd           v1.8h, v1.8h, v3.8h
-        clip2           v0.8h, v1.8h, v4.8h, v21.8h
+        clip            v4.8h, v21.8h, v0.8h, v1.8h
         st1             {v0.8h}, [x0],  x2
         st1             {v1.8h}, [x12], x2
         bne             1b
@@ -221,8 +214,7 @@ function hevc_add_residual_16x16_16_neon, export=0
         sqadd           v1.8h, v1.8h, v17.8h
         sqadd           v2.8h, v2.8h, v18.8h
         sqadd           v3.8h, v3.8h, v19.8h
-        clip2           v0.8h, v1.8h, v20.8h, v21.8h
-        clip2           v2.8h, v3.8h, v20.8h, v21.8h
+        clip            v20.8h, v21.8h, v0.8h, v1.8h, v2.8h, v3.8h
         st1             {v0.8h-v1.8h}, [x0],  x2
         st1             {v2.8h-v3.8h}, [x12], x2
         bne             1b
@@ -239,8 +231,7 @@ function hevc_add_residual_32x32_16_neon, export=0
         sqadd           v1.8h, v1.8h, v17.8h
         sqadd           v2.8h, v2.8h, v18.8h
         sqadd           v3.8h, v3.8h, v19.8h
-        clip2           v0.8h, v1.8h, v20.8h, v21.8h
-        clip2           v2.8h, v3.8h, v20.8h, v21.8h
+        clip            v20.8h, v21.8h, v0.8h, v1.8h, v2.8h, v3.8h
         st1             {v0.8h-v3.8h}, [x0], x2
         bne             1b
         ret
diff --git a/libavcodec/aarch64/neon.S b/libavcodec/aarch64/neon.S
index 1ad32c359d..bc105e4861 100644
--- a/libavcodec/aarch64/neon.S
+++ b/libavcodec/aarch64/neon.S
@@ -1,6 +1,8 @@
 /*
  * This file is part of FFmpeg.
  *
+ * Copyright (c) 2023 J. Dekker <jdek at itanimul.li>
+ *
  * FFmpeg is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Lesser General Public
  * License as published by the Free Software Foundation; either
@@ -16,6 +18,15 @@
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
+.macro clip min, max, regs:vararg
+.irp x, \regs
+        smax            \x, \x, \min
+.endr
+.irp x, \regs
+        smin            \x, \x, \max
+.endr
+.endm
+
 .macro  transpose_8x8B  r0, r1, r2, r3, r4, r5, r6, r7, r8, r9
         trn1            \r8\().8B,  \r0\().8B,  \r1\().8B
         trn2            \r9\().8B,  \r0\().8B,  \r1\().8B