diff options
Diffstat (limited to 'libavcodec/aarch64')
| -rw-r--r-- | libavcodec/aarch64/h264idct_neon.S | 20 |
1 files changed, 12 insertions, 8 deletions
diff --git a/libavcodec/aarch64/h264idct_neon.S b/libavcodec/aarch64/h264idct_neon.S index 825ec49..7de4420 100644 --- a/libavcodec/aarch64/h264idct_neon.S +++ b/libavcodec/aarch64/h264idct_neon.S @@ -23,6 +23,7 @@ #include "neon.S" function ff_h264_idct_add_neon, export=1 +.L_ff_h264_idct_add_neon: ld1 {v0.4H, v1.4H, v2.4H, v3.4H}, [x1] sxtw x2, w2 movi v30.8H, #0 @@ -77,6 +78,7 @@ function ff_h264_idct_add_neon, export=1 endfunc function ff_h264_idct_dc_add_neon, export=1 +.L_ff_h264_idct_dc_add_neon: sxtw x2, w2 mov w3, #0 ld1r {v2.8H}, [x1] @@ -106,8 +108,8 @@ function ff_h264_idct_add16_neon, export=1 mov w9, w3 // stride movrel x7, scan8 mov x10, #16 - movrel x13, X(ff_h264_idct_dc_add_neon) - movrel x14, X(ff_h264_idct_add_neon) + movrel x13, .L_ff_h264_idct_dc_add_neon + movrel x14, .L_ff_h264_idct_add_neon 1: mov w2, w9 ldrb w3, [x7], #1 ldrsw x0, [x5], #4 @@ -133,8 +135,8 @@ function ff_h264_idct_add16intra_neon, export=1 mov w9, w3 // stride movrel x7, scan8 mov x10, #16 - movrel x13, X(ff_h264_idct_dc_add_neon) - movrel x14, X(ff_h264_idct_add_neon) + movrel x13, .L_ff_h264_idct_dc_add_neon + movrel x14, .L_ff_h264_idct_add_neon 1: mov w2, w9 ldrb w3, [x7], #1 ldrsw x0, [x5], #4 @@ -160,8 +162,8 @@ function ff_h264_idct_add8_neon, export=1 add x5, x1, #16*4 // block_offset add x9, x2, #16*32 // block mov w19, w3 // stride - movrel x13, X(ff_h264_idct_dc_add_neon) - movrel x14, X(ff_h264_idct_add_neon) + movrel x13, .L_ff_h264_idct_dc_add_neon + movrel x14, .L_ff_h264_idct_add_neon movrel x7, scan8, 16 mov x10, #0 mov x11, #16 @@ -263,6 +265,7 @@ endfunc .endm function ff_h264_idct8_add_neon, export=1 +.L_ff_h264_idct8_add_neon: movi v19.8H, #0 sxtw x2, w2 ld1 {v24.8H, v25.8H}, [x1] @@ -326,6 +329,7 @@ function ff_h264_idct8_add_neon, export=1 endfunc function ff_h264_idct8_dc_add_neon, export=1 +.L_ff_h264_idct8_dc_add_neon: mov w3, #0 sxtw x2, w2 ld1r {v31.8H}, [x1] @@ -375,8 +379,8 @@ function ff_h264_idct8_add4_neon, export=1 mov w2, w3 movrel x7, scan8 mov w10, #16 - movrel x13, X(ff_h264_idct8_dc_add_neon) - movrel x14, X(ff_h264_idct8_add_neon) + movrel x13, .L_ff_h264_idct8_dc_add_neon + movrel x14, .L_ff_h264_idct8_add_neon 1: ldrb w9, [x7], #4 ldrsw x0, [x5], #16 ldrb w9, [x4, w9, UXTW] |
