mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-18 03:19:31 +02:00
42c1cc35b7
The previous implementation targeted DTS Coherent Acoustics, which only
requires mdct_bits == 6. This relatively small size lent itself to
unrolling the loops a small number of times, and encoding offsets
calculated at assembly time within the load/store instructions of each
iteration.
In the more general case (codecs such as AAC and AC3) much larger arrays
are used - mdct_bits == [8, 9, 11]. The old method does not scale for
these cases, so more integer registers are used with non-unrolled versions
of the loops (and with some stack spillage). The postrotation filter loop
is still unrolled by a factor of 2 to permit the double-buffering of some
VFP registers to facilitate overlap of neighbouring iterations.
I benchmarked the result by measuring the number of gperftools samples
that hit anywhere in the AAC decoder (starting from aac_decode_frame())
or specifically in ff_imdct_half_c / ff_imdct_half_vfp, for the same
example AAC stream:
Before After
Mean StdDev Mean StdDev Confidence Change
aac_decode_frame 2368.1 35.8 2117.2 35.3 100.0% +11.8%
ff_imdct_half_* 457.5 22.4 251.2 16.2 100.0% +82.1%
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
|
||
|---|---|---|
| .. | ||
| aac.h | ||
| aacpsdsp_init_arm.c | ||
| aacpsdsp_neon.S | ||
| ac3dsp_arm.S | ||
| ac3dsp_armv6.S | ||
| ac3dsp_init_arm.c | ||
| ac3dsp_neon.S | ||
| asm-offsets.h | ||
| audiodsp_arm.h | ||
| audiodsp_init_arm.c | ||
| audiodsp_init_neon.c | ||
| audiodsp_neon.S | ||
| blockdsp_arm.h | ||
| blockdsp_init_arm.c | ||
| blockdsp_init_neon.c | ||
| blockdsp_neon.S | ||
| cabac.h | ||
| dca.h | ||
| dcadsp_init_arm.c | ||
| dcadsp_neon.S | ||
| dcadsp_vfp.S | ||
| dsputil_arm.h | ||
| dsputil_armv6.S | ||
| dsputil_init_arm.c | ||
| dsputil_init_armv6.c | ||
| fft_fixed_init_arm.c | ||
| fft_fixed_neon.S | ||
| fft_init_arm.c | ||
| fft_neon.S | ||
| fft_vfp.S | ||
| flacdsp_arm.S | ||
| flacdsp_init_arm.c | ||
| fmtconvert_init_arm.c | ||
| fmtconvert_neon.S | ||
| fmtconvert_vfp_armv6.S | ||
| fmtconvert_vfp.S | ||
| h264chroma_init_arm.c | ||
| h264cmc_neon.S | ||
| h264dsp_init_arm.c | ||
| h264dsp_neon.S | ||
| h264idct_neon.S | ||
| h264pred_init_arm.c | ||
| h264pred_neon.S | ||
| h264qpel_init_arm.c | ||
| h264qpel_neon.S | ||
| hpeldsp_arm.h | ||
| hpeldsp_arm.S | ||
| hpeldsp_armv6.S | ||
| hpeldsp_init_arm.c | ||
| hpeldsp_init_armv6.c | ||
| hpeldsp_init_neon.c | ||
| hpeldsp_neon.S | ||
| idctdsp_arm.h | ||
| idctdsp_arm.S | ||
| idctdsp_armv6.S | ||
| idctdsp_init_arm.c | ||
| idctdsp_init_armv5te.c | ||
| idctdsp_init_armv6.c | ||
| idctdsp_init_neon.c | ||
| idctdsp_neon.S | ||
| int_neon.S | ||
| jrevdct_arm.S | ||
| lossless_audiodsp_init_arm.c | ||
| lossless_audiodsp_neon.S | ||
| Makefile | ||
| mathops.h | ||
| mdct_fixed_neon.S | ||
| mdct_neon.S | ||
| mdct_vfp.S | ||
| mlpdsp_armv5te.S | ||
| mlpdsp_armv6.S | ||
| mlpdsp_init_arm.c | ||
| mpegaudiodsp_fixed_armv6.S | ||
| mpegaudiodsp_init_arm.c | ||
| mpegvideo_arm.c | ||
| mpegvideo_arm.h | ||
| mpegvideo_armv5te_s.S | ||
| mpegvideo_armv5te.c | ||
| mpegvideo_neon.S | ||
| mpegvideoencdsp_armv6.S | ||
| mpegvideoencdsp_init_arm.c | ||
| neon.S | ||
| neontest.c | ||
| pixblockdsp_armv6.S | ||
| pixblockdsp_init_arm.c | ||
| rdft_neon.S | ||
| rv34dsp_init_arm.c | ||
| rv34dsp_neon.S | ||
| rv40dsp_init_arm.c | ||
| rv40dsp_neon.S | ||
| sbrdsp_init_arm.c | ||
| sbrdsp_neon.S | ||
| simple_idct_arm.S | ||
| simple_idct_armv5te.S | ||
| simple_idct_armv6.S | ||
| simple_idct_neon.S | ||
| startcode_armv6.S | ||
| synth_filter_neon.S | ||
| synth_filter_vfp.S | ||
| vc1dsp_init_arm.c | ||
| vc1dsp_init_neon.c | ||
| vc1dsp_neon.S | ||
| vc1dsp.h | ||
| videodsp_arm.h | ||
| videodsp_armv5te.S | ||
| videodsp_init_arm.c | ||
| videodsp_init_armv5te.c | ||
| vorbisdsp_init_arm.c | ||
| vorbisdsp_neon.S | ||
| vp3dsp_init_arm.c | ||
| vp3dsp_neon.S | ||
| vp6dsp_init_arm.c | ||
| vp6dsp_neon.S | ||
| vp8_armv6.S | ||
| vp8.h | ||
| vp8dsp_armv6.S | ||
| vp8dsp_init_arm.c | ||
| vp8dsp_init_armv6.c | ||
| vp8dsp_init_neon.c | ||
| vp8dsp_neon.S | ||
| vp8dsp.h | ||
| vp56_arith.h | ||