diff options
| author | Michael Niedermayer <michaelni@gmx.at> | 2012-03-08 02:28:40 +0100 |
|---|---|---|
| committer | Michael Niedermayer <michaelni@gmx.at> | 2012-03-08 02:51:45 +0100 |
| commit | bf807a5e874442aa3fe1b475459cdd509e34bff4 (patch) | |
| tree | f8067bfb5e99b8b8e2716a7ea8519a4aaa8ac60f /libavcodec/arm/int_neon.S | |
| parent | 4cda8aa1c5bc58f8a7f53a21a19b03e7379bbcdc (diff) | |
| parent | 6eda85e15b38863a627fd0602098aa3250174698 (diff) | |
Merge remote-tracking branch 'qatar/master'
* qatar/master: (29 commits)
sbrdsp.asm: convert all instructions to float/SSE ones.
dv: cosmetics.
dv: check buffer size before reading profile.
Revert "AAC SBR: group some writes."
udp: Print an error message if bind fails
cook: extend channel uncoupling tables so the full bit range is covered.
roqvideo: cosmetics.
roqvideo: convert to bytestream2 API.
dca: don't use av_clip_uintp2().
wmall: fix build with -DDEBUG enabled.
smc: port to bytestream2 API.
AAC SBR: group some writes.
dsputil: remove shift parameter from scalarproduct_int16
SBR DSP: unroll sum_square
rv34: remove dead code in intra availability check
rv34: clean a bit availability checks.
v4l2: update documentation
tgq: convert to bytestream2 API.
parser: remove forward declaration of MpegEncContext
dca: prevent accessing static arrays with invalid indexes.
...
Conflicts:
doc/indevs.texi
libavcodec/Makefile
libavcodec/dca.c
libavcodec/dvdata.c
libavcodec/eatgq.c
libavcodec/mmvideo.c
libavcodec/roqvideodec.c
libavcodec/smc.c
libswscale/output.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
Diffstat (limited to 'libavcodec/arm/int_neon.S')
| -rw-r--r-- | libavcodec/arm/int_neon.S | 28 |
1 files changed, 2 insertions, 26 deletions
diff --git a/libavcodec/arm/int_neon.S b/libavcodec/arm/int_neon.S index e1353982d0..311c99d95e 100644 --- a/libavcodec/arm/int_neon.S +++ b/libavcodec/arm/int_neon.S @@ -29,32 +29,8 @@ function ff_scalarproduct_int16_neon, export=1 vmov.i16 q1, #0 vmov.i16 q2, #0 vmov.i16 q3, #0 - negs r3, r3 - beq 2f - - vdup.s32 q12, r3 1: vld1.16 {d16-d17}, [r0]! vld1.16 {d20-d21}, [r1,:128]! - vmull.s16 q12, d16, d20 - vld1.16 {d18-d19}, [r0]! - vmull.s16 q13, d17, d21 - vld1.16 {d22-d23}, [r1,:128]! - vmull.s16 q14, d18, d22 - vmull.s16 q15, d19, d23 - vshl.s32 q8, q12, q12 - vshl.s32 q9, q13, q12 - vadd.s32 q0, q0, q8 - vshl.s32 q10, q14, q12 - vadd.s32 q1, q1, q9 - vshl.s32 q11, q15, q12 - vadd.s32 q2, q2, q10 - vadd.s32 q3, q3, q11 - subs r2, r2, #16 - bne 1b - b 3f - -2: vld1.16 {d16-d17}, [r0]! - vld1.16 {d20-d21}, [r1,:128]! vmlal.s16 q0, d16, d20 vld1.16 {d18-d19}, [r0]! vmlal.s16 q1, d17, d21 @@ -62,9 +38,9 @@ function ff_scalarproduct_int16_neon, export=1 vmlal.s16 q2, d18, d22 vmlal.s16 q3, d19, d23 subs r2, r2, #16 - bne 2b + bne 1b -3: vpadd.s32 d16, d0, d1 + vpadd.s32 d16, d0, d1 vpadd.s32 d17, d2, d3 vpadd.s32 d10, d4, d5 vpadd.s32 d11, d6, d7 |