Christophe GISQUET 98f24ecd6c rv34: joint coefficient decoding and dequantization ...

Perform dequantization while decoding coefficients instead of performing it
on the entire coefficients buffer.

Since quantized coefficients are very sparse, this usually causes a small
speedup. Speedup of around 1% on Panda board compared to the removed here
neon code. Global speedup is probably around 3%.

Signed-off-by: Kostya Shishkov <kostya.shishkov@gmail.com>

2012-01-04 10:30:01 +01:00

..

aac.h

…

ac3dsp_arm.S

…

ac3dsp_armv6.S

…

ac3dsp_init_arm.c

…

ac3dsp_neon.S

…

asm-offsets.h

…

asm.S

rv40: NEON optimised loop filter strength selection

2011-12-14 11:26:30 +00:00

dca.h

ARM: dca: disable optimised decode_blockcodes() for old gcc

2011-12-15 01:02:58 +00:00

dcadsp_init_arm.c

…

dcadsp_neon.S

…

dsputil_arm.h

…

dsputil_arm.S

…

dsputil_armv6.S

…

dsputil_init_arm.c

…

dsputil_init_armv5te.c

…

dsputil_init_armv6.c

…

dsputil_init_neon.c

ARM: fix indentation in ff_dsputil_init_neon()

2011-12-01 19:41:36 +00:00

dsputil_init_vfp.c

…

dsputil_iwmmxt_rnd_template.c

…

dsputil_iwmmxt.c

…

dsputil_neon.S

ARM: NEON put/avg_pixels8/16 cosmetics

2011-12-01 19:41:36 +00:00

dsputil_vfp.S

…

fft_fixed_init_arm.c

…

fft_fixed_neon.S

…

fft_init_arm.c

…

fft_neon.S

…

fmtconvert_init_arm.c

…

fmtconvert_neon.S

…

fmtconvert_vfp.S

…

h264cmc_neon.S

rv40: NEON optimised chroma MC

2011-12-06 13:48:25 +00:00

h264dsp_init_arm.c

…

h264dsp_neon.S

ARM: move NEON H264 chroma mc to a separate file

2011-12-06 13:48:24 +00:00

h264idct_neon.S

…

h264pred_init_arm.c

…

h264pred_neon.S

…

int_neon.S

…

jrevdct_arm.S

…

Makefile

rv40: NEON optimised weighted prediction

2011-12-06 13:48:25 +00:00

mathops.h

…

mdct_fixed_neon.S

…

mdct_neon.S

…

mpegaudiodsp_fixed_armv6.S

…

mpegaudiodsp_init_arm.c

…

mpegvideo_arm.c

…

mpegvideo_arm.h

…

mpegvideo_armv5te_s.S

…

mpegvideo_armv5te.c

…

mpegvideo_iwmmxt.c

…

mpegvideo_neon.S

…

neon.S

ARM: make some NEON macros reusable

2011-12-02 19:59:18 +00:00

rdft_neon.S

…

rv34dsp_init_neon.c

rv34: joint coefficient decoding and dequantization

2012-01-04 10:30:01 +01:00

rv34dsp_neon.S

rv34: joint coefficient decoding and dequantization

2012-01-04 10:30:01 +01:00

rv40dsp_init_neon.c

rv40: NEON optimised weak loop filter

2011-12-16 14:36:01 +00:00

rv40dsp_neon.S

rv40: NEON optimised weak loop filter

2011-12-16 14:36:01 +00:00

simple_idct_arm.S

…

simple_idct_armv5te.S

…

simple_idct_armv6.S

…

simple_idct_neon.S

…

synth_filter_neon.S

…

vp3dsp_neon.S

…

vp8_armv6.S

…

vp8.h

…

vp8dsp_init_arm.c

…

vp8dsp_neon.S

ARM: make some NEON macros reusable

2011-12-02 19:59:18 +00:00

vp56_arith.h

…

vp56dsp_init_arm.c

…

vp56dsp_neon.S

…