Yang Zhang ab70794ddb rewrite Disto4x4 in enc_neon.c with intrinsic ...

Performance test:
Platform: A9
Input data: bryce.yuv  11158x2156
performance of assembly is the base. Less ratio is better.
|toolchain |assembly |intrinsic |
|gcc4.6    |100%     |97.15%    |
|gcc4.8    |100%     |95.51     |

Change-Id: Idc2446685acdeb58a4dbdcdae533c68a83a1b879

2014-09-23 18:28:36 -07:00

..

alpha_processing_mips_dsp_r2.c

MIPS: dspr2: added optimization for EmitAlphaRGB

2014-08-21 20:39:35 -07:00

alpha_processing_sse2.c

Add a WebPExtractAlpha function to dsp

2014-09-15 08:12:03 +02:00

alpha_processing.c

Add a WebPExtractAlpha function to dsp

2014-09-15 08:12:03 +02:00

cpu.c

cpu: check for _MSC_VER before using msvc inline asm

2014-08-15 15:11:40 -07:00

dec_clip_tables.c

add missing file

2014-02-13 21:56:19 -08:00

dec_mips32.c

MIPS: mips32: code rebase

2014-08-19 15:13:16 +02:00

dec_mips_dsp_r2.c

MIPS: dspr2: added optimization for function FilterLoop24

2014-09-23 10:32:55 +02:00

dec_neon.c

dec_neon/TransformAC3: initialize vector w/vcreate

2014-07-11 15:56:53 -07:00

dec_sse2.c

strong filtering speed-up (~2-3% x86, ~1-2% for NEON)

2014-06-03 07:14:23 +02:00

dec.c

MIPS: dspr2: added optimization for TransformDC

2014-09-09 14:15:04 +02:00

dsp.h

Add a WebPExtractAlpha function to dsp

2014-09-15 08:12:03 +02:00

enc_avx2.c

add stub dsp/enc_avx2.c

2014-05-22 00:31:46 -07:00

enc_mips32.c

introduce VP8EncQuantize2Blocks to quantize two blocks at a time

2014-08-25 20:21:42 -07:00

enc_neon.c

rewrite Disto4x4 in enc_neon.c with intrinsic

2014-09-23 18:28:36 -07:00

enc_sse2.c

introduce VP8EncQuantize2Blocks to quantize two blocks at a time

2014-08-25 20:21:42 -07:00

enc.c

introduce VP8EncQuantize2Blocks to quantize two blocks at a time

2014-08-25 20:21:42 -07:00

filters_mips_dsp_r2.c

MIPS: dspr2: added optimization for (un)filters

2014-08-14 11:55:19 -07:00

lossless_mips32.c

MIPS: MIPS32r1: Added optimization for HistogramAdd.

2014-04-29 08:36:51 -07:00

lossless_mips_dsp_r2.c

MIPS: dspr2: added optimization for ColorIndexInverseTransforms

2014-09-08 17:22:59 +02:00

lossless_neon.c

neon: add INIT_VECTOR4

2014-07-01 00:18:23 -07:00

lossless_sse2.c

Added SSE2 variants for Average2/3/4

2014-04-28 14:47:30 -07:00

lossless.c

MIPS: dspr2: added optimization for ColorIndexInverseTransforms

2014-09-08 17:22:59 +02:00

lossless.h

MIPS: dspr2: added optimization for ColorIndexInverseTransforms

2014-09-08 17:22:59 +02:00

Makefile.am

MIPS: dspr2: added optimization for TransformDC

2014-09-09 14:15:04 +02:00

neon.h

neon: add INIT_VECTOR4

2014-07-01 00:18:23 -07:00

upsampling_mips_dsp_r2.c

move static initialization of WebPYUV444Converters[] to the Init function.

2014-08-27 11:36:37 -07:00

upsampling_neon.c

neon: normalize vdup_n_* usage

2014-07-01 00:55:05 -07:00

upsampling_sse2.c

lossy decoding: correct alpha-rescaling for YUVA format

2014-05-27 15:27:13 -07:00

upsampling.c

move static initialization of WebPYUV444Converters[] to the Init function.

2014-08-27 11:36:37 -07:00

yuv_mips32.c

rename upsampling_mips32.c to yuv_mips32.c

2014-06-07 12:35:47 -07:00

yuv_mips_dsp_r2.c

MIPS: dspr2: Optimization of some simple point-sampling functions

2014-08-13 17:18:49 +02:00

yuv_sse2.c

dsp/yuv: move sse2 functions to yuv_sse2.c

2014-06-05 23:52:54 -07:00

yuv_tables_sse2.h

SSE2: yuv->rgb speed-up for point-sampling

2014-05-22 09:56:47 +02:00

yuv.c

MIPS: dspr2: Optimization of some simple point-sampling functions

2014-08-13 17:18:49 +02:00

yuv.h

SSE2: yuv->rgb speed-up for point-sampling

2014-05-22 09:56:47 +02:00