avcodec/arm64: fix inverted register order in transpose_4x4H

Fix related register order issue in ff_h264_idct_add_neon.

Found-by: zjh8890 <243186085@qq.com>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

diff --git a/libavcodec/aarch64/h264idct_neon.S b/libavcodec/aarch64/h264idct_neon.S
index 04b5a47f043db3512e981ecbd6ae1bd1d908ba29..91f1e773c419ae169c7d7f3b61fbf3563134e958 100644 (file)
--- a/libavcodec/aarch64/h264idct_neon.S
+++ b/libavcodec/aarch64/h264idct_neon.S
@@ -37,8 +37,8 @@ function ff_h264_idct_add_neon, export=1
         sub             v7.4H,  v16.4H, v3.4H
         add             v0.4H,  v4.4H,  v6.4H
         add             v1.4H,  v5.4H,  v7.4H
-        sub             v2.4H,  v4.4H,  v6.4H
-        sub             v3.4H,  v5.4H,  v7.4H
+        sub             v3.4H,  v4.4H,  v6.4H
+        sub             v2.4H,  v5.4H,  v7.4H
 
         transpose_4x4H  v0, v1, v2, v3, v4, v5, v6, v7
 

diff --git a/libavcodec/aarch64/neon.S b/libavcodec/aarch64/neon.S
index 619aec64269c27da7978be90cbbb1150273bc24e..a227cbd3f64b78c890cb05ba3a6effd2a99a9f51 100644 (file)
--- a/libavcodec/aarch64/neon.S
+++ b/libavcodec/aarch64/neon.S
@@ -107,8 +107,8 @@
 .macro  transpose_4x4H  r0, r1, r2, r3, r4, r5, r6, r7
         trn1            \r4\().4H,  \r0\().4H,  \r1\().4H
         trn2            \r5\().4H,  \r0\().4H,  \r1\().4H
-        trn1            \r7\().4H,  \r3\().4H,  \r2\().4H
-        trn2            \r6\().4H,  \r3\().4H,  \r2\().4H
+        trn1            \r7\().4H,  \r2\().4H,  \r3\().4H
+        trn2            \r6\().4H,  \r2\().4H,  \r3\().4H
         trn1            \r0\().2S,  \r4\().2S,  \r7\().2S
         trn2            \r3\().2S,  \r4\().2S,  \r7\().2S
         trn1            \r1\().2S,  \r5\().2S,  \r6\().2S