- 18 Feb, 2014 - 6 commits
-
-
Jingning Han authored
-
Jingning Han authored
-
Yunqing Wang authored
-
Yunqing Wang authored
-
Jingning Han authored
Run sub-pixel motion search when NEWMV gives lower rate-distortion cost. This improves coding performance of derf set by 8%, std-hd by 2.2%. Change-Id: Ife50f7fda8463927784fe59a41cc439c833e941a
-
Johann authored
-
- 17 Feb, 2014 - 2 commits
-
-
Yaowu Xu authored
-
Adrian Grange authored
-
- 16 Feb, 2014 - 1 commit
-
-
Jim Bankoski authored
Change-Id: I02cc50648b62768e20d2f465b5ad09648b1abe93
-
- 15 Feb, 2014 - 8 commits
-
-
James Zern authored
-
Jim Bankoski authored
Change-Id: I747982e7d1157a8b45f4034ddf207306f9f957e0
-
Tom Finegan authored
- Rename and make static s/vp9_compute_qdelta_by_rate/compute_qdelta_by_rate/ - Make base_q_index an integer. - Add a cast. Change-Id: Iea8d1397fd2717e7373b182ec51f5db960ef2cca
-
James Yu authored
Change-Id: Ifabb8c7ec0c327fea9d6739cab10addb060ff435 Signed-off-by:
James Yu <james.yu@linaro.org>
-
Paul Wilkins authored
Change-Id: Ica1b583d69810182f621de757d2543b2a3b35566
-
Johann authored
-
Adrian Grange authored
Change-Id: I29e4d3a3c8cceb18825371bb78c83c0e7dd86e0f
-
Adrian Grange authored
-
- 14 Feb, 2014 - 23 commits
-
-
levytamar82 authored
Optimizing 2 functions to process 32 elements in parallel instead of 16: 1. vp9_sub_pixel_variance64x64 2. vp9_sub_pixel_variance32x32 both of those function were calling vp9_sub_pixel_variance16xh_ssse3 instead of calling that function, it calls vp9_sub_pixel_variance32xh_avx2 that is written in avx2 and process 32 elements in parallel. This Optimization gave 70% function level gain and 2% user level gain Change-Id: I4f5cb386b346ff6c878a094e1c3b37e418e50bde
-
Deb Mukherjee authored
-
Deb Mukherjee authored
-
Adrian Grange authored
Change-Id: I568861ba1d43620865ad9a98a97eef37a51fd856
-
Yaowu Xu authored
-
Deb Mukherjee authored
Minor fix to ensure that positive and negative cpu_used values produce the same output. Change-Id: I9157d05cb9a7c0bd57a4d8a9f268205a825b9b0b
-
Deb Mukherjee authored
This was inadvertently left out in a previous refactoring step. Change-Id: Idf3350e95152f876a1a1a4591dd30c8981856c96
-
Jim Bankoski authored
-
Jim Bankoski authored
-
Jim Bankoski authored
-
Jim Bankoski authored
-
levytamar82 authored
Optimizing all SSSE3 assembly for convolution: 1. vp9_filter_block1d4_h8_sse2 2. vp9_filter_block1d8_h8_sse2 3. vp9_filter_block1d16_h8_sse2 4. vp9_filter_block1d4_v8_sse2 5. vp9_filter_block1d8_v8_sse2 6. vp9_filter_block1d16_v8_sse2 my optimization include: -processing 2x8 elements in one 128 bit register instead of processing 8 elements in one 128 bit register. -removing unecessary loads. This optimization gives between 2.4% user level gain for 480p input and 1.6% user level gain for 720p. This Optimization is done only for 64 bit Change-Id: Ic07fce2f9360329b4f2d956efda1480ae958766b
-
Paul Wilkins authored
Change-Id: I151c6c9396b8ea1ce2e05b80359f60f0d38af138
-
Jim Bankoski authored
Change-Id: I65677b7822204dc7344c67b8080e90633afc13dc
-
Jim Bankoski authored
Change-Id: Ibe4276fa9ffeb2ef30871d6db8ac75c4648f1e58
-
Jim Bankoski authored
Change-Id: I8f1107a33f0ec51010fb00eae3d28ee8b4d748c2
-
Alex Converse authored
Change-Id: I4deb1b97eec6b1244e3460a1162b41fa5312654a
-
Jim Bankoski authored
-
Jim Bankoski authored
-
Deb Mukherjee authored
-
Jim Bankoski authored
-
Jim Bankoski authored
-
Jim Bankoski authored
-