summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2014-02-19postproc.c: Cast away MSVC data loss warning.Tom Finegan
Change-Id: Ib80d4f394692a981e369dc5fecd5432cbec488d1
2014-02-18Merge "Enable sub-pixel motion search for rtc mode"Jingning Han
2014-02-18Merge "Initialize internal buffer pointers in rtc mode"Jingning Han
2014-02-18Merge "SSSE3 convolution optimization"Yunqing Wang
2014-02-18Merge "AVX2 SubPixel Variance Optimization"Yunqing Wang
2014-02-18Enable sub-pixel motion search for rtc modeJingning Han
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
2014-02-17Merge "Replace vqshrun by vqmovun if shift #0 bit"Johann
2014-02-17Merge "vp9_onyx_if.c resolve vs warnings"Yaowu Xu
2014-02-17Merge "Change post- to pre-increment."Adrian Grange
2014-02-15vp9_onyx_if.c resolve vs warningsJim Bankoski
Change-Id: I02cc50648b62768e20d2f465b5ad09648b1abe93
2014-02-15Merge "A couple more V.S. warnings silenced."James Zern
2014-02-15vp9_cx_iface vp9_dx_iface vpxdec vs warningsJim Bankoski
Change-Id: I747982e7d1157a8b45f4034ddf207306f9f957e0
2014-02-14vp9/encoder/vp9_onyx_if: Fix compute_qdelta_by_rate() warningsTom Finegan
- 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
2014-02-14Replace vqshrun by vqmovun if shift #0 bitJames Yu
Change-Id: Ifabb8c7ec0c327fea9d6739cab10addb060ff435 Signed-off-by: James Yu <james.yu@linaro.org>
2014-02-14A couple more V.S. warnings silenced.Paul Wilkins
Change-Id: Ica1b583d69810182f621de757d2543b2a3b35566
2014-02-14Merge "Remove redundant arm neon instructions."Johann
2014-02-14Change post- to pre-increment.Adrian Grange
Change-Id: I29e4d3a3c8cceb18825371bb78c83c0e7dd86e0f
2014-02-14Merge "Cleanup some comments."Adrian Grange
2014-02-14AVX2 SubPixel Variance Optimizationlevytamar82
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
2014-02-14Merge "Make cpi->speed always positive"Deb Mukherjee
2014-02-14Merge "Enforce max-intra-pct in one-pass cbr mode"Deb Mukherjee
2014-02-14Cleanup some comments.Adrian Grange
Change-Id: I568861ba1d43620865ad9a98a97eef37a51fd856
2014-02-14Merge "minor spelling cleanup in comments"Yaowu Xu
2014-02-14Make cpi->speed always positiveDeb Mukherjee
Minor fix to ensure that positive and negative cpu_used values produce the same output. Change-Id: I9157d05cb9a7c0bd57a4d8a9f268205a825b9b0b
2014-02-14Enforce max-intra-pct in one-pass cbr modeDeb Mukherjee
This was inadvertently left out in a previous refactoring step. Change-Id: Idf3350e95152f876a1a1a4591dd30c8981856c96
2014-02-14Merge "vp9_rdopt.c : Silence more V.S. compiler warnings."Jim Bankoski
2014-02-14Merge "vp9_bitstream.c resolve warnings in vs"Jim Bankoski
2014-02-14Merge "vp9_pickmode.c resolve vs issue"Jim Bankoski
2014-02-14Merge "vp9_vaq.c resolve vs warnings"Jim Bankoski
2014-02-14SSSE3 convolution optimizationlevytamar82
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
2014-02-14vp9_rdopt.c : Silence more V.S. compiler warnings.Paul Wilkins
Change-Id: I151c6c9396b8ea1ce2e05b80359f60f0d38af138
2014-02-14vp9_bitstream.c resolve warnings in vsJim Bankoski
Change-Id: I65677b7822204dc7344c67b8080e90633afc13dc
2014-02-14vp9_pickmode.c resolve vs issueJim Bankoski
Change-Id: Ibe4276fa9ffeb2ef30871d6db8ac75c4648f1e58
2014-02-14vp9_vaq.c resolve vs warningsJim Bankoski
Change-Id: I8f1107a33f0ec51010fb00eae3d28ee8b4d748c2
2014-02-14Remove some unused and non-persistant variables from VP9_COMP.Alex Converse
Change-Id: I4deb1b97eec6b1244e3460a1162b41fa5312654a
2014-02-14Merge "vp9_ratectrl - convert buffers to int64 to avoid casting"Jim Bankoski
2014-02-14Merge "vp9_write_bit_buffer.h add consts to suppress warnings in vs"Jim Bankoski
2014-02-14Merge "In realtime mode enforce one pass with 0 lag"Deb Mukherjee
2014-02-14Merge "vp9_ratectrl.h resolve visual studio warnings"Jim Bankoski
2014-02-14Merge "vp9_onyx_int.h resolve visual studio warning errors"Jim Bankoski
2014-02-14Merge "fast approximate model_rd_from_var_lapndz"Jim Bankoski
2014-02-14Merge "vp9_mcomp.c visual studio warnings resolved"Jim Bankoski
2014-02-14Merge "vp9_firstpass.c visual studio warnings addressed"Jim Bankoski
2014-02-14vp9_ratectrl - convert buffers to int64 to avoid castingJim Bankoski
Change-Id: Ifd6b2d36d91237b5f38853a3a8a529d8be38ba09
2014-02-14vp9_write_bit_buffer.h add consts to suppress warnings in vsJim Bankoski
Change-Id: Iacda473090ae84c798f1d93df8284f34bdf646a5
2014-02-14vp9_ratectrl.h resolve visual studio warningsJim Bankoski
Change-Id: If3a2edd744eb76337fa78f34d0e059cda2c6da54
2014-02-14vp9_onyx_int.h resolve visual studio warning errorsJim Bankoski
Change-Id: Iec8a51bdea6d6c916051d3bc5bbc6d00754d0cc8
2014-02-14vp9_mcomp.c visual studio warnings resolvedJim Bankoski
Change-Id: I7546cc8db4decbcd094ad76c64385b97666331b0
2014-02-14vp9_firstpass.c visual studio warnings addressedJim Bankoski
Change-Id: I6fe9ec50f937b12fd9c9321465270e289dbbc59d
2014-02-13Merge "Cleanup: removing "ptr" suffix from var names."Dmitry Kovalev
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-10 07:18:01 +0000