diff --git a/libavcodec/aarch64/simple_idct_neon.S b/libavcodec/aarch64/simple_idct_neon.S
index 52273420f9..92987985d2 100644
--- a/libavcodec/aarch64/simple_idct_neon.S
+++ b/libavcodec/aarch64/simple_idct_neon.S
@@ -61,37 +61,37 @@ endconst
         br              x10
 .endm
 
-.macro smull1 a b c
+.macro smull1 a, b, c
         smull           \a, \b, \c
 .endm
 
-.macro smlal1 a b c
+.macro smlal1 a, b, c
         smlal           \a, \b, \c
 .endm
 
-.macro smlsl1 a b c
+.macro smlsl1 a, b, c
         smlsl           \a, \b, \c
 .endm
 
-.macro idct_col4_top y1 y2 y3 y4 i l
-        smull\i         v7.4S,  \y3\().\l, z2
-        smull\i         v16.4S, \y3\().\l, z6
-        smull\i         v17.4S, \y2\().\l, z1
+.macro idct_col4_top y1, y2, y3, y4, i, l
+        smull\i         v7.4S,  \y3\l, z1
+        smull\i         v16.4S, \y3\l, z6
+        smull\i         v17.4S, \y2\l, z1
         add             v19.4S, v23.4S, v7.4S
-        smull\i         v18.4S, \y2\().\l, z3
+        smull\i         v18.4S, \y2\l, z3
         add             v20.4S, v23.4S, v16.4S
-        smull\i         v5.4S,  \y2\().\l, z5
+        smull\i         v5.4S,  \y2\l, z5
         sub             v21.4S, v23.4S, v16.4S
-        smull\i         v6.4S,  \y2\().\l, z7
+        smull\i         v6.4S,  \y2\l, z7
         sub             v22.4S, v23.4S, v7.4S
 
-        smlal\i         v17.4S, \y4\().\l, z3
-        smlsl\i         v18.4S, \y4\().\l, z7
-        smlsl\i         v5.4S,  \y4\().\l, z1
-        smlsl\i         v6.4S,  \y4\().\l, z5
+        smlal\i         v17.4S, \y4\l, z3
+        smlsl\i         v18.4S, \y4\l, z7
+        smlsl\i         v5.4S,  \y4\l, z1
+        smlsl\i         v6.4S,  \y4\l, z5
 .endm
 
-.macro idct_row4_neon y1 y2 y3 y4 pass
+.macro idct_row4_neon y1, y2, y3, y4, pass
         ld1             {\y1\().2D-\y2\().2D}, [x2], #32
         movi            v23.4S, #1<<2, lsl #8
         orr             v5.16B, \y1\().16B, \y2\().16B
@@ -101,7 +101,7 @@ endconst
         mov             x3, v5.D[1]
         smlal           v23.4S, \y1\().4H, z4
 
-        idct_col4_top   \y1 \y2 \y3 \y4 1 4H
+        idct_col4_top   \y1, \y2, \y3, \y4, 1, .4H
 
         cmp             x3, #0
         beq             \pass\()f
@@ -153,7 +153,7 @@ endconst
         trn2            \y4\().4S, v17.4S, v19.4S
 .endm
 
-.macro declare_idct_col4_neon i l
+.macro declare_idct_col4_neon i, l
 function idct_col4_neon\i
         dup             v23.4H, z4c
 .if \i == 1
@@ -164,14 +164,14 @@ function idct_col4_neon\i
 .endif
         smull           v23.4S, v23.4H, z4
 
-        idct_col4_top   v24 v25 v26 v27 \i \l
+        idct_col4_top   v24, v25, v26, v27, \i, \l
 
         mov             x4, v28.D[\i - 1]
         mov             x5, v29.D[\i - 1]
         cmp             x4, #0
         beq             1f
 
-        smull\i         v7.4S,  v28.\l, z4
+        smull\i         v7.4S,  v28\l,  z4
         add             v19.4S, v19.4S, v7.4S
         sub             v20.4S, v20.4S, v7.4S
         sub             v21.4S, v21.4S, v7.4S
@@ -181,17 +181,17 @@ function idct_col4_neon\i
         cmp             x5, #0
         beq             2f
 
-        smlal\i         v17.4S, v29.\l, z5
-        smlsl\i         v18.4S, v29.\l, z1
-        smlal\i         v5.4S,  v29.\l, z7
-        smlal\i         v6.4S,  v29.\l, z3
+        smlal\i         v17.4S, v29\l, z5
+        smlsl\i         v18.4S, v29\l, z1
+        smlal\i         v5.4S,  v29\l, z7
+        smlal\i         v6.4S,  v29\l, z3
 
 2:      mov             x5, v31.D[\i - 1]
         cmp             x4, #0
         beq             3f
 
-        smull\i         v7.4S,  v30.\l, z6
-        smull\i         v16.4S, v30.\l, z2
+        smull\i         v7.4S,  v30\l, z6
+        smull\i         v16.4S, v30\l, z2
         add             v19.4S, v19.4S, v7.4S
         sub             v22.4S, v22.4S, v7.4S
         sub             v20.4S, v20.4S, v16.4S
@@ -200,10 +200,10 @@ function idct_col4_neon\i
 3:      cmp             x5, #0
         beq             4f
 
-        smlal\i         v17.4S, v31.\l, z7
-        smlsl\i         v18.4S, v31.\l, z5
-        smlal\i         v5.4S,  v31.\l, z3
-        smlsl\i         v6.4S,  v31.\l, z1
+        smlal\i         v17.4S, v31\l, z7
+        smlsl\i         v18.4S, v31\l, z5
+        smlal\i         v5.4S,  v31\l, z3
+        smlsl\i         v6.4S,  v31\l, z1
 
 4:      addhn           v7.4H, v19.4S, v17.4S
         addhn2          v7.8H, v20.4S, v18.4S
@@ -219,14 +219,14 @@ function idct_col4_neon\i
 endfunc
 .endm
 
-declare_idct_col4_neon 1 4H
-declare_idct_col4_neon 2 8H
+declare_idct_col4_neon 1, .4H
+declare_idct_col4_neon 2, .8H
 
 function ff_simple_idct_put_neon, export=1
         idct_start      x2
 
-        idct_row4_neon  v24 v25 v26 v27 1
-        idct_row4_neon  v28 v29 v30 v31 2
+        idct_row4_neon  v24, v25, v26, v27, 1
+        idct_row4_neon  v28, v29, v30, v31, 2
         bl              idct_col4_neon1
 
         sqshrun         v1.8B,  v7.8H, #COL_SHIFT-16
@@ -263,8 +263,8 @@ endfunc
 function ff_simple_idct_add_neon, export=1
         idct_start      x2
 
-        idct_row4_neon  v24 v25 v26 v27 1
-        idct_row4_neon  v28 v29 v30 v31 2
+        idct_row4_neon  v24, v25, v26, v27, 1
+        idct_row4_neon  v28, v29, v30, v31, 2
         bl              idct_col4_neon1
 
         sshr            v1.8H, V7.8H, #COL_SHIFT-16
@@ -328,8 +328,8 @@ function ff_simple_idct_neon, export=1
         idct_start      x0
 
         mov             x2,  x0
-        idct_row4_neon  v24 v25 v26 v27 1
-        idct_row4_neon  v28 v29 v30 v31 2
+        idct_row4_neon  v24, v25, v26, v27, 1
+        idct_row4_neon  v28, v29, v30, v31, 2
         add             x2, x2, #-128
         bl              idct_col4_neon1