Ronald S. Bultje 1ff94fea56 Inline vp9_quantize() in xform_quant(). ...

Cycle times:
4x4:    151 to  131 cycles (15% faster)
8x8:    334 to  306 cycles (9% faster)
16x16: 1401 to 1368 cycles (2.5% faster)
32x32: 7403 to 7367 cycles (0.5% faster)

Total encode time of first 50 frames of bus @ 1500kbps (speed 0)
goes from 1min39.2 to 1min38.6, i.e. a 0.67% overall speedup.

Change-Id: I799a49460e5e3fcab01725564dd49c629bfe935f

2013-07-15 17:30:57 -07:00

..

common

Merge "Neon: Update mbfilter if all vectors follow one branch."

2013-07-15 17:11:55 -07:00

decoder

Code cleanup inside vp9_decodeframe.c.

2013-07-15 14:47:25 -07:00

encoder

Inline vp9_quantize() in xform_quant().

2013-07-15 17:30:57 -07:00

exports_dec

support building vp8 and vp9 into a single lib

2012-11-15 10:46:17 -08:00

exports_enc

support building vp8 and vp9 into a single lib

2012-11-15 10:46:17 -08:00

vp9_common.mk

convolve8 optimizations for neon

2013-07-11 11:08:19 -07:00

vp9_cx_iface.c

Bug fix: set frame_parallel_decoding_mode

2013-07-03 10:25:29 -04:00

vp9_dx_iface.c

vp9_dx_iface: s/vp8/vp9/ where possible

2013-07-12 11:05:39 -07:00

vp9_iface_common.h

Using mi_cols instead of mb_cols.

2013-07-08 14:54:04 -07:00

vp9cx.mk

Remove unused fwalsh/fdct x86 SIMD implementations.

2013-07-10 18:22:51 -07:00

vp9dx.mk

Remove all asm offset files from VP9

2013-07-09 14:26:53 -07:00