diff options
| author | Martin Storsjö <martin@martin.st> | 2023-10-17 14:27:17 +0300 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2023-10-21 23:25:54 +0300 |
| commit | a76b409dd030a461b0c5dd1ead8b22d1be560afd (patch) | |
| tree | 76d2d19d10c17857f664a70d5c155def96ee440f /libavcodec/aarch64/opusdsp_neon.S | |
| parent | cada4597ca873b7636e145783dd3ae3725862005 (diff) | |
| download | ffmpeg-a76b409dd030a461b0c5dd1ead8b22d1be560afd.tar.gz | |
aarch64: Reindent all assembly to 8/24 column indentation
libavcodec/aarch64/vc1dsp_neon.S is skipped here, as it intentionally
uses a layered indentation style to visually show how different
unrolled/interleaved phases fit together.
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/aarch64/opusdsp_neon.S')
| -rw-r--r-- | libavcodec/aarch64/opusdsp_neon.S | 102 |
1 files changed, 51 insertions, 51 deletions
diff --git a/libavcodec/aarch64/opusdsp_neon.S b/libavcodec/aarch64/opusdsp_neon.S index 1c88d7d123..e933151ab4 100644 --- a/libavcodec/aarch64/opusdsp_neon.S +++ b/libavcodec/aarch64/opusdsp_neon.S @@ -33,81 +33,81 @@ const tab_x2, align=4 endconst function ff_opus_deemphasis_neon, export=1 - movrel x4, tab_st - ld1 {v4.4s}, [x4] - movrel x4, tab_x0 - ld1 {v5.4s}, [x4] - movrel x4, tab_x1 - ld1 {v6.4s}, [x4] - movrel x4, tab_x2 - ld1 {v7.4s}, [x4] + movrel x4, tab_st + ld1 {v4.4s}, [x4] + movrel x4, tab_x0 + ld1 {v5.4s}, [x4] + movrel x4, tab_x1 + ld1 {v6.4s}, [x4] + movrel x4, tab_x2 + ld1 {v7.4s}, [x4] - fmul v0.4s, v4.4s, v0.s[0] + fmul v0.4s, v4.4s, v0.s[0] -1: ld1 {v1.4s, v2.4s}, [x1], #32 +1: ld1 {v1.4s, v2.4s}, [x1], #32 - fmla v0.4s, v5.4s, v1.s[0] - fmul v3.4s, v7.4s, v2.s[2] + fmla v0.4s, v5.4s, v1.s[0] + fmul v3.4s, v7.4s, v2.s[2] - fmla v0.4s, v6.4s, v1.s[1] - fmla v3.4s, v6.4s, v2.s[1] + fmla v0.4s, v6.4s, v1.s[1] + fmla v3.4s, v6.4s, v2.s[1] - fmla v0.4s, v7.4s, v1.s[2] - fmla v3.4s, v5.4s, v2.s[0] + fmla v0.4s, v7.4s, v1.s[2] + fmla v3.4s, v5.4s, v2.s[0] - fadd v1.4s, v1.4s, v0.4s - fadd v2.4s, v2.4s, v3.4s + fadd v1.4s, v1.4s, v0.4s + fadd v2.4s, v2.4s, v3.4s - fmla v2.4s, v4.4s, v1.s[3] + fmla v2.4s, v4.4s, v1.s[3] - st1 {v1.4s, v2.4s}, [x0], #32 - fmul v0.4s, v4.4s, v2.s[3] + st1 {v1.4s, v2.4s}, [x0], #32 + fmul v0.4s, v4.4s, v2.s[3] - subs w2, w2, #8 - b.gt 1b + subs w2, w2, #8 + b.gt 1b - mov s0, v2.s[3] + mov s0, v2.s[3] ret endfunc function ff_opus_postfilter_neon, export=1 - ld1 {v0.4s}, [x2] - dup v1.4s, v0.s[1] - dup v2.4s, v0.s[2] - dup v0.4s, v0.s[0] + ld1 {v0.4s}, [x2] + dup v1.4s, v0.s[1] + dup v2.4s, v0.s[2] + dup v0.4s, v0.s[0] - add w1, w1, #2 - sub x1, x0, x1, lsl #2 + add w1, w1, #2 + sub x1, x0, x1, lsl #2 - ld1 {v3.4s}, [x1] - fmul v3.4s, v3.4s, v2.4s + ld1 {v3.4s}, [x1] + fmul v3.4s, v3.4s, v2.4s -1: add x1, x1, #4 - ld1 {v4.4s}, [x1] - add x1, x1, #4 - ld1 {v5.4s}, [x1] - add x1, x1, #4 - ld1 {v6.4s}, [x1] - add x1, x1, #4 - ld1 {v7.4s}, [x1] +1: add x1, x1, #4 + ld1 {v4.4s}, [x1] + add x1, x1, #4 + ld1 {v5.4s}, [x1] + add x1, x1, #4 + ld1 {v6.4s}, [x1] + add x1, x1, #4 + ld1 {v7.4s}, [x1] - fmla v3.4s, v7.4s, v2.4s - fadd v6.4s, v6.4s, v4.4s + fmla v3.4s, v7.4s, v2.4s + fadd v6.4s, v6.4s, v4.4s - ld1 {v4.4s}, [x0] - fmla v4.4s, v5.4s, v0.4s + ld1 {v4.4s}, [x0] + fmla v4.4s, v5.4s, v0.4s - fmul v6.4s, v6.4s, v1.4s - fadd v6.4s, v6.4s, v3.4s + fmul v6.4s, v6.4s, v1.4s + fadd v6.4s, v6.4s, v3.4s - fadd v4.4s, v4.4s, v6.4s - fmul v3.4s, v7.4s, v2.4s + fadd v4.4s, v4.4s, v6.4s + fmul v3.4s, v7.4s, v2.4s - st1 {v4.4s}, [x0], #16 + st1 {v4.4s}, [x0], #16 - subs w3, w3, #4 - b.gt 1b + subs w3, w3, #4 + b.gt 1b ret endfunc |