diff options
-rw-r--r-- | libavcodec/aarch64/simple_idct_neon.S | 28 |
1 files changed, 14 insertions, 14 deletions
diff --git a/libavcodec/aarch64/simple_idct_neon.S b/libavcodec/aarch64/simple_idct_neon.S index 5bd31e5be9..5e4d021a97 100644 --- a/libavcodec/aarch64/simple_idct_neon.S +++ b/libavcodec/aarch64/simple_idct_neon.S @@ -92,10 +92,10 @@ endconst .endm .macro idct_row4_neon y1, y2, y3, y4, pass - ld1 {\y1\().2D-\y2\().2D}, [x2], #32 + ld1 {\y1\().2D,\y2\().2D}, [x2], #32 movi v23.4S, #1<<2, lsl #8 orr v5.16B, \y1\().16B, \y2\().16B - ld1 {\y3\().2D, \y4\().2D}, [x2], #32 + ld1 {\y3\().2D,\y4\().2D}, [x2], #32 orr v6.16B, \y3\().16B, \y4\().16B orr v5.16B, v5.16B, v6.16B mov x3, v5.D[1] @@ -104,7 +104,7 @@ endconst idct_col4_top \y1, \y2, \y3, \y4, 1, .4H cmp x3, #0 - beq \pass\()f + b.eq \pass\()f smull2 v7.4S, \y1\().8H, z4 smlal2 v17.4S, \y2\().8H, z5 @@ -169,7 +169,7 @@ function idct_col4_neon\i mov x4, v28.D[\i - 1] mov x5, v29.D[\i - 1] cmp x4, #0 - beq 1f + b.eq 1f smull\i v7.4S, v28\l, z4 add v19.4S, v19.4S, v7.4S @@ -179,7 +179,7 @@ function idct_col4_neon\i 1: mov x4, v30.D[\i - 1] cmp x5, #0 - beq 2f + b.eq 2f smlal\i v17.4S, v29\l, z5 smlsl\i v18.4S, v29\l, z1 @@ -188,7 +188,7 @@ function idct_col4_neon\i 2: mov x5, v31.D[\i - 1] cmp x4, #0 - beq 3f + b.eq 3f smull\i v7.4S, v30\l, z6 smull\i v16.4S, v30\l, z2 @@ -198,7 +198,7 @@ function idct_col4_neon\i add v21.4S, v21.4S, v16.4S 3: cmp x5, #0 - beq 4f + b.eq 4f smlal\i v17.4S, v31\l, z7 smlsl\i v18.4S, v31\l, z5 @@ -267,14 +267,14 @@ function ff_simple_idct_add_neon, export=1 idct_row4_neon v28, v29, v30, v31, 2 bl idct_col4_neon1 - sshr v1.8H, V7.8H, #COL_SHIFT-16 + sshr v1.8H, v7.8H, #COL_SHIFT-16 sshr v2.8H, v16.8H, #COL_SHIFT-16 sshr v3.8H, v17.8H, #COL_SHIFT-16 sshr v4.8H, v18.8H, #COL_SHIFT-16 bl idct_col4_neon2 - sshr v7.8H, V7.8H, #COL_SHIFT-16 + sshr v7.8H, v7.8H, #COL_SHIFT-16 sshr v16.8H, v16.8H, #COL_SHIFT-16 sshr v17.8H, v17.8H, #COL_SHIFT-16 sshr v18.8H, v18.8H, #COL_SHIFT-16 @@ -330,7 +330,7 @@ function ff_simple_idct_neon, export=1 mov x2, x0 idct_row4_neon v24, v25, v26, v27, 1 idct_row4_neon v28, v29, v30, v31, 2 - add x2, x2, #-128 + sub x2, x2, #128 bl idct_col4_neon1 sshr v1.8H, v7.8H, #COL_SHIFT-16 @@ -347,16 +347,16 @@ function ff_simple_idct_neon, export=1 zip1 v23.2D, v1.2D, v7.2D zip2 v24.2D, v1.2D, v7.2D - st1 {v23.2D,V24.2D}, [x2], #32 + st1 {v23.2D,v24.2D}, [x2], #32 zip1 v25.2D, v2.2D, v16.2D zip2 v26.2D, v2.2D, v16.2D - st1 {v25.2D,V26.2D}, [x2], #32 + st1 {v25.2D,v26.2D}, [x2], #32 zip1 v27.2D, v3.2D, v17.2D zip2 v28.2D, v3.2D, v17.2D - st1 {v27.2D,V28.2D}, [x2], #32 + st1 {v27.2D,v28.2D}, [x2], #32 zip1 v29.2D, v4.2D, v18.2D zip2 v30.2D, v4.2D, v18.2D - st1 {v29.2D,V30.2D}, [x2], #32 + st1 {v29.2D,v30.2D}, [x2], #32 idct_end endfunc |