lavc/aarch64: Fix addp overflow in ff_pred16x16_plane_neon_10

The mismatch between neon and C functions can be reproduced
using the following bitstream and command line on aarch64 devices.

wget https://streams.videolan.org/ffmpeg/incoming/replay_intra_pred_16x16.h264
 ./ffmpeg -cpuflags 0  -threads 1 -i replay_intra_pred_16x16.h264  -f framemd5 -y md5_ref
 ./ffmpeg              -threads 1 -i replay_intra_pred_16x16.h264 -f framemd5 -y md5_neon

Signed-off-by: Bin Peng <pengbin@visionular.com>
(cherry picked from commit 3115c0c0e6c27c689a02a7267dcf8e61fa2ac425)

diff --git a/libavcodec/aarch64/h264pred_neon.S b/libavcodec/aarch64/h264pred_neon.S
index d0999938efb3773ca840bb6c7352db5bbf1c11ad..795d2ce540b0cfdabaf55d9c49a70d4d629b20b2 100644 (file)
--- a/libavcodec/aarch64/h264pred_neon.S
+++ b/libavcodec/aarch64/h264pred_neon.S
@@ -489,10 +489,10 @@ function ff_pred16x16_plane_neon_10, export=1
         mul             v2.8h,  v2.8h,  v0.8h
         mul             v3.8h,  v3.8h,  v0.8h
         addp            v2.8h,  v2.8h,  v3.8h
-        addp            v2.8h,  v2.8h,  v2.8h
-        addp            v2.4h,  v2.4h,  v2.4h
-        sshll           v3.4s,  v2.4h,  #2
-        saddw           v2.4s,  v3.4s,  v2.4h
+        saddlp          v2.4s,  v2.8h
+        addp            v2.4s,  v2.4s,  v2.4s
+        shl             v3.4s,  v2.4s,  #2
+        add             v2.4s,  v3.4s,  v2.4s
         rshrn           v4.4h,  v2.4s,  #6
         trn2            v5.4h,  v4.4h,  v4.4h
         add             v2.4h,  v4.4h,  v5.4h
@@ -506,14 +506,13 @@ function ff_pred16x16_plane_neon_10, export=1
         sxtl            v6.4s,  v5.4h          // c
 
         mov             v0.h[0],  wzr
-        mul             v0.8h,  v0.8h,  v4.h[0]
         dup             v16.4s, v2.s[0]
         dup             v17.4s, v2.s[0]
         dup             v2.8h,  v4.h[0]        // b
         dup             v3.4s,  v6.s[0]        // c
         sshll           v2.4s,  v2.4h,  #3     // b * 8
-        saddw           v16.4s, v16.4s, v0.4h
-        saddw2          v17.4s, v17.4s, v0.8h
+        smlal           v16.4s, v0.4h, v4.h[0]
+        smlal2          v17.4s, v0.8h, v4.h[0]
         sub             v3.4s,  v3.4s,  v2.4s
 
         mov             w3,      #16