diff options
| author | Mikhail Nitenko <mnitenko@gmail.com> | 2021-08-20 00:07:59 +0300 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2021-08-21 00:06:26 +0300 |
| commit | 756d2e087a73c1e1ebe9647e085a1f5c90fa87de (patch) | |
| tree | c29be92cd03fbbc46d146edd2813ba12d060e668 /libavcodec/aarch64 | |
| parent | 1698cd8422c8a363e25dd94beb61c0a6d68bd67c (diff) | |
lavc/aarch64: move transpose_4x8H to neon.S
transpose_4x8H was declared in vp9lpf_16bpp_neon, however this macro is
not unique to vp9 and could be used elsewhere.
Signed-off-by: Mikhail Nitenko <mnitenko@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/aarch64')
| -rw-r--r-- | libavcodec/aarch64/neon.S | 13 | ||||
| -rw-r--r-- | libavcodec/aarch64/vp9lpf_16bpp_neon.S | 12 |
2 files changed, 13 insertions, 12 deletions
diff --git a/libavcodec/aarch64/neon.S b/libavcodec/aarch64/neon.S index 0fddbecae3..1ad32c359d 100644 --- a/libavcodec/aarch64/neon.S +++ b/libavcodec/aarch64/neon.S @@ -109,12 +109,25 @@ trn2 \r5\().4H, \r0\().4H, \r1\().4H trn1 \r6\().4H, \r2\().4H, \r3\().4H trn2 \r7\().4H, \r2\().4H, \r3\().4H + trn1 \r0\().2S, \r4\().2S, \r6\().2S trn2 \r2\().2S, \r4\().2S, \r6\().2S trn1 \r1\().2S, \r5\().2S, \r7\().2S trn2 \r3\().2S, \r5\().2S, \r7\().2S .endm +.macro transpose_4x8H r0, r1, r2, r3, t4, t5, t6, t7 + trn1 \t4\().8H, \r0\().8H, \r1\().8H + trn2 \t5\().8H, \r0\().8H, \r1\().8H + trn1 \t6\().8H, \r2\().8H, \r3\().8H + trn2 \t7\().8H, \r2\().8H, \r3\().8H + + trn1 \r0\().4S, \t4\().4S, \t6\().4S + trn2 \r2\().4S, \t4\().4S, \t6\().4S + trn1 \r1\().4S, \t5\().4S, \t7\().4S + trn2 \r3\().4S, \t5\().4S, \t7\().4S +.endm + .macro transpose_8x8H r0, r1, r2, r3, r4, r5, r6, r7, r8, r9 trn1 \r8\().8H, \r0\().8H, \r1\().8H trn2 \r9\().8H, \r0\().8H, \r1\().8H diff --git a/libavcodec/aarch64/vp9lpf_16bpp_neon.S b/libavcodec/aarch64/vp9lpf_16bpp_neon.S index 9075f3d406..9869614a29 100644 --- a/libavcodec/aarch64/vp9lpf_16bpp_neon.S +++ b/libavcodec/aarch64/vp9lpf_16bpp_neon.S @@ -22,18 +22,6 @@ #include "neon.S" -.macro transpose_4x8H r0, r1, r2, r3, t4, t5, t6, t7 - trn1 \t4\().8h, \r0\().8h, \r1\().8h - trn2 \t5\().8h, \r0\().8h, \r1\().8h - trn1 \t6\().8h, \r2\().8h, \r3\().8h - trn2 \t7\().8h, \r2\().8h, \r3\().8h - - trn1 \r0\().4s, \t4\().4s, \t6\().4s - trn2 \r2\().4s, \t4\().4s, \t6\().4s - trn1 \r1\().4s, \t5\().4s, \t7\().4s - trn2 \r3\().4s, \t5\().4s, \t7\().4s -.endm - // The input to and output from this macro is in the registers v16-v31, // and v0-v7 are used as scratch registers. // p7 = v16 .. p3 = v20, p0 = v23, q0 = v24, q3 = v27, q7 = v31 |