aarch64: Fix ff_hevc_put_hevc_epel_h48_8_neon_i8mm

The first 32 elements of each row were correct, while the
last 16 were scrambled.

This hasn't been noticed, because the checkasm test erroneously
only checked half of the output (for 8 bit functions), and
apparently none of the samples as part of "fate-hevc" seem to
trigger this specific function.

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

libavcodec/aarch64/hevcdsp_epel_neon.S

@@ -1572,6 +1572,7 @@ function ff_hevc_put_hevc_epel_h48_8_neon_i8mm, export=1
         xtn2            v22.8h, v26.4s
         xtn             v23.4h, v23.4s
         xtn2            v23.8h, v27.4s
+        add             x7, x0, #64
         st4             {v20.8h, v21.8h, v22.8h, v23.8h}, [x0], x10
         ext             v4.16b, v2.16b, v3.16b, #1
         ext             v5.16b, v2.16b, v3.16b, #2
@@ -1584,11 +1585,14 @@ function ff_hevc_put_hevc_epel_h48_8_neon_i8mm, export=1
         usdot           v21.4s, v4.16b, v30.16b
         usdot           v22.4s, v5.16b, v30.16b
         usdot           v23.4s, v6.16b, v30.16b
-        xtn             v20.4h, v20.4s
-        xtn2            v20.8h, v22.4s
-        xtn             v21.4h, v21.4s
-        xtn2            v21.8h, v23.4s
-        add             x7, x0, #64
+        zip1            v24.4s, v20.4s, v22.4s
+        zip2            v25.4s, v20.4s, v22.4s
+        zip1            v26.4s, v21.4s, v23.4s
+        zip2            v27.4s, v21.4s, v23.4s
+        xtn             v20.4h, v24.4s
+        xtn2            v20.8h, v25.4s
+        xtn             v21.4h, v26.4s
+        xtn2            v21.8h, v27.4s
         st2             {v20.8h, v21.8h}, [x7]
         b.ne            1b
         ret