Yi Luo 299c5fc202 HBD hybrid transform 8x8 SSE4.1 optimization ...

- Tx_type: DCT_DCT, DCT_ADST, ADST_DCT, ADST_ADST.
- Update bit-exact unit test against current C version.
- HBD encoder speed improves ~3.8%.

Change-Id: Ie13925ba11214eef2b5326814940638507bf68ec

2016-04-29 17:04:52 -07:00

..

arm

split vpx_lpf_horizontal_16 in two

2016-02-16 22:57:45 -08:00

mips

Merge changes I7a1c0cba,Ie02b5caf,I2cbd85d7,I644f35b0

2016-04-06 02:51:53 +00:00

x86

HBD hybrid transform 8x8 SSE4.1 optimization

2016-04-29 17:04:52 -07:00

avg.c

Merge branch 'master' into nextgenv2

2016-04-18 15:15:05 -07:00

bitreader_buffer.c

Merge branch 'master' into nextgenv2

2015-11-21 05:00:05 -08:00

bitreader_buffer.h

vp10: code sign bit before absolute value in non-arithcoded header.

2015-09-16 19:35:03 -04:00

bitreader.c

Include vpx_dsp_common.h when using VPXMIN/MAX

2015-08-31 14:36:35 -07:00

bitreader.h

bitreader/writer: Change shift to signed

2015-11-19 15:13:39 -08:00

bitwriter_buffer.c

Merge MISC_FIXES

2015-11-17 15:06:08 -08:00

bitwriter_buffer.h

vp10: code sign bit before absolute value in non-arithcoded header.

2015-09-16 19:35:03 -04:00

bitwriter.c

vpx_dsp/bitwriter.h: vp9_->vpx_

2015-07-20 18:13:05 -07:00

bitwriter.h

bitreader/writer: Change shift to signed

2015-11-19 15:13:39 -08:00

fastssim.c

Fix some compiler warnings.

2016-02-24 11:17:33 -08:00

fwd_txfm.c

vpx_fdct16x16_1_c/msa: fix accumulator overflow

2016-04-04 16:03:41 -07:00

fwd_txfm.h

Replace vp9_ prefix in 2D-DCT functions with vpx_

2015-07-28 16:06:44 -07:00

intrapred.c

Merge branch 'master' into nextgenv2

2016-02-17 07:23:58 -08:00

inv_txfm.c

Extends ext-tx to support 32x32 masked transforms

2016-02-17 09:31:34 -08:00

inv_txfm.h

Extends ext-tx to support 32x32 masked transforms

2016-02-17 09:31:34 -08:00

loopfilter.c

split vpx_highbd_lpf_horizontal_16 in two

2016-02-16 23:13:58 -08:00

prob.c

vpx_dsp/prob.h: vp9_ -> vpx_

2015-07-20 18:13:04 -07:00

prob.h

vpx_dsp_common: add VPX prefix to MIN/MAX

2015-08-26 20:11:32 -07:00

psnr.c

Cleanup psnr.h

2016-02-22 15:37:40 -08:00

psnr.h

Cleanup psnr.h

2016-02-22 15:37:40 -08:00

psnrhvs.c

Add shift stage for PSNRHVS computation

2016-02-22 10:22:42 -08:00

quantize.c

Change vp9_quantize to vpx_quantize

2015-08-04 15:31:49 -07:00

quantize.h

Change vp9_quantize to vpx_quantize

2015-08-04 15:31:49 -07:00

sad.c

Add 128 pixel variance and SAD functions

2016-03-03 10:24:29 +00:00

ssim.c

Fix compiler warnings

2016-02-26 13:52:49 -08:00

ssim.h

Extend vpxssim to handle more HBD combinations

2016-02-22 16:09:08 -08:00

subtract.c

Move subtract functions from vp9 to vpx_dsp

2015-07-06 12:22:47 -07:00

sum_squares.c

Add optimized vpx_sum_squares_2d_i16 for vp10.

2016-02-15 16:54:52 +00:00

txfm_common.h

Extends ext-tx to support 32x32 masked transforms

2016-02-17 09:31:34 -08:00

variance.c

Some cosmetic improvements since HBD variance 4x4 optimization

2016-04-08 10:32:13 -07:00

variance.h

Merge "Extend variance based partitioning to 128x128 superblocks" into nextgenv2

2016-04-12 19:42:35 +00:00

vpx_convolve.c

Extend superblock size fo 128x128 pixels.

2016-03-30 18:23:06 +01:00

vpx_convolve.h

Extend convolution functions to 128x128 for ext-partition.

2016-03-07 11:39:27 +00:00

vpx_dsp_common.h

Make superblock size variable at the frame level.

2016-04-07 10:34:25 +01:00

vpx_dsp_rtcd_defs.pl

Merge branch 'master' into nextgenv2

2016-04-18 15:15:05 -07:00

vpx_dsp_rtcd.c

Move shared SAD code to vpx_dsp

2015-05-06 16:58:20 -07:00

vpx_dsp.mk

Merge "Optimized HBD block subtraction for all block sizes" into nextgenv2

2016-04-12 21:22:32 +00:00

vpx_filter.h

Add 128 pixel variance and SAD functions

2016-03-03 10:24:29 +00:00