Pascal Massimino bfd3fc02df ~2x faster SSE2 RGB24toY, BGR24toY, ARGBToY|UV ...

global effect is ~2% faster encoding from JPG source
and ~8% faster lossless-webp source decoding to PGM (e.g.)

Also revamped the YUVA case to first accumulate R/G/B value into 16b
temporary buffer, and then doing the UV conversion.
-> New function: WebPConvertRGBA32ToUV

Change-Id: I1d7d0c4003aa02966ad33490ce0fcdc7925cf9f5

2015-11-06 15:02:01 -08:00

..

alpha_processing_mips_dsp_r2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

alpha_processing_sse2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

alpha_processing_sse41.c

SSE4.1 implementation of some alpha-processing functions

2015-06-19 14:17:39 -07:00

alpha_processing.c

SSE4.1 implementation of some alpha-processing functions

2015-06-19 14:17:39 -07:00

argb_mips_dsp_r2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

argb_sse2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

argb.c

make the 'last_cpuinfo_used' variable names unique

2015-01-07 23:38:53 -08:00

cost_mips32.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

cost_mips_dsp_r2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

cost_sse2.c

speed-up SetResidualSSE2

2015-05-14 21:24:24 -07:00

cost.c

1-2% faster encoding by removing an indirection in GetResidualCost()

2015-02-19 08:44:35 +01:00

cpu.c

Android: limit use of cpufeatures

2015-08-19 18:44:33 -07:00

dec_clip_tables.c

WEBP_TSAN_IGNORE_FUNCTION: fix gcc compat warning

2014-10-16 18:06:43 +02:00

dec_mips32.c

dsp/mips: cosmetics: add whitespace around XSTR macro

2015-09-03 23:09:13 -07:00

dec_mips_dsp_r2.c

dsp/mips: cosmetics: add whitespace around XSTR macro

2015-09-03 23:09:13 -07:00

dec_neon.c

dec_neon: add whitespace around stringizing operator

2015-09-03 23:13:56 -07:00

dec_sse2.c

SSE2: minor cosmetrics on in-loop filter code

2015-06-28 11:59:22 +02:00

dec_sse41.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

dec.c

stub for SSE4.1 support.

2015-03-20 00:26:35 -07:00

dsp.h

~2x faster SSE2 RGB24toY, BGR24toY, ARGBToY|UV

2015-11-06 15:02:01 -08:00

enc_avx2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

enc_mips32.c

dsp/mips: cosmetics: add whitespace around XSTR macro

2015-09-03 23:09:13 -07:00

enc_mips_dsp_r2.c

dsp/mips: cosmetics: add whitespace around XSTR macro

2015-09-03 23:09:13 -07:00

enc_neon.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

enc_sse2.c

SSE2/SSE41: optimize SSE_16xN loops

2015-07-02 20:55:04 +02:00

enc_sse41.c

SSE2/SSE41: optimize SSE_16xN loops

2015-07-02 20:55:04 +02:00

enc.c

introduce FTransform2 to perform two transforms at a time.

2015-05-18 21:06:15 -07:00

filters_mips_dsp_r2.c

dsp/mips: add whitespace around stringizing operator

2015-09-02 23:21:13 -07:00

filters_sse2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

filters.c

add SSE2 variants for alpha filtering functions

2015-01-29 08:46:22 +01:00

lossless_enc_mips32.c

dsp/mips: add whitespace around stringizing operator

2015-09-02 23:21:13 -07:00

lossless_enc_mips_dsp_r2.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

lossless_enc_neon.c

lossless_enc_neon: add VP8LTransformColor

2015-08-05 00:15:13 -07:00

lossless_enc_sse2.c

dsp/lossless_*sse2: remove some unnecessary inlines

2015-06-25 21:02:01 -07:00

lossless_enc_sse41.c

SSE2: 53% faster TransformColor[Inverse]

2015-06-23 14:52:01 -07:00

lossless_enc.c

lossless: encoding, don't compute unnecessary histo

2015-07-07 20:24:26 -07:00

lossless_mips_dsp_r2.c

dsp/mips: add whitespace around stringizing operator

2015-09-02 23:21:13 -07:00

lossless_neon.c

lossless_neon: add VP8LTransformColorInverse

2015-08-04 23:22:36 -07:00

lossless_sse2.c

dsp/lossless_*sse2: remove some unnecessary inlines

2015-06-25 21:02:01 -07:00

lossless.c

remove unnecessary #include "yuv.h"

2015-10-27 01:27:36 -07:00

lossless.h

Add delta_palettization feature to WebP

2015-10-02 14:29:54 -07:00

Makefile.am

neon-implementation for rescaler code

2015-10-07 21:18:39 -07:00

mips_macro.h

dsp/mips: cosmetics: add whitespace around XSTR macro

2015-09-03 23:09:13 -07:00

neon.h

dsp: s/USE_INTRINSICS/WEBP_USE_INTRINSICS/

2015-01-12 14:27:36 -08:00

rescaler_mips32.c

MIPS: rescaler code synced with C implementation

2015-10-17 00:16:27 -07:00

rescaler_mips_dsp_r2.c

MIPS: rescaler code synced with C implementation

2015-10-17 00:16:27 -07:00

rescaler_neon.c

neon-implementation for rescaler code

2015-10-07 21:18:39 -07:00

rescaler_sse2.c

rescaler: ~20% faster SSE2 implementation for lossless ImportRowExpand

2015-10-14 07:32:12 +02:00

rescaler.c

neon-implementation for rescaler code

2015-10-07 21:18:39 -07:00

upsampling_mips_dsp_r2.c

dsp/mips: add whitespace around stringizing operator

2015-09-02 23:21:13 -07:00

upsampling_neon.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

upsampling_sse2.c

SSE2: add yuv444 converters, re-using yuv_sse2.c

2015-08-17 21:15:37 -07:00

upsampling.c

SSE2: add yuv444 converters, re-using yuv_sse2.c

2015-08-17 21:15:37 -07:00

yuv_mips32.c

dsp: add DSP_INIT_STUB

2015-04-02 23:55:35 -07:00

yuv_mips_dsp_r2.c

dsp/mips: add whitespace around stringizing operator

2015-09-02 23:21:13 -07:00

yuv_sse2.c

~2x faster SSE2 RGB24toY, BGR24toY, ARGBToY|UV

2015-11-06 15:02:01 -08:00

yuv_tables_sse2.h

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

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

yuv.c

~2x faster SSE2 RGB24toY, BGR24toY, ARGBToY|UV

2015-11-06 15:02:01 -08:00

yuv.h

SSE2: add yuv444 converters, re-using yuv_sse2.c

2015-08-17 21:15:37 -07:00