diff --git a/libavcodec/aarch64/h264idct_neon.S b/libavcodec/aarch64/h264idct_neon.S
index 99c2cb5030..78f780a632 100644
--- 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 f1072b73e5..767bc9d455 100644
--- 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